Μαθήματα
- Τεχνολογίες Ανάπτυξης Εφαρμογών ΔιαδικτύουHY220Δ΄ εξάμηνο · Κορμού
- Ανάλυση Κοινωνικών ΔικτύωνME140ΣΤ΄ εξάμηνο · Επιλογής κατεύθυνσης ΨΜΑΔ
- Πλατφόρμες και Αρχιτεκτονικές ΝέφουςMO180ΣΤ΄ εξάμηνο · Υποχρεωτικό κατεύθυνσης ΨΜΑΔ
- Διαχείριση Έργων ΠληροφορικήςME230Η΄ εξάμηνο · Επιλογής κατεύθυνσης ΨΜΑΔ
Δημοσιεύσεις
Άρθρα σε Περιοδικά
Panagiotopoulos, A., Karyotis, V., Dimitrakopoulos, G. N., Choleva-Tsiringkaki, V., & Kourouthanassis, P. E. (2026). Demystifying the Digital Transformation of Humanitarian Supply Chains Through AidTech. Logistics, 10(5), 110. https://doi.org/10.3390/logistics10050110
@article{panagiotopoulos2026demystifying,
title = {Demystifying the Digital Transformation of Humanitarian Supply Chains Through AidTech},
author = {Apostolos Panagiotopoulos and Vasileios Karyotis and Georgios N. Dimitrakopoulos and Vassiliki Choleva-Tsiringkaki and Panos E. Kourouthanassis},
url = {https://doi.org/10.3390/logistics10050110},
doi = {10.3390/logistics10050110},
year = {2026},
date = {2026-01-01},
journal = {Logistics},
volume = {10},
number = {5},
pages = {110},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Background: Humanitarian campaigns are more popular with more initiatives organized than ever by public and private bodies. Simultaneously, more peculiar challenges, such as zero-waste and transparency, are required compared to traditional supply chains. This work investigates the current technological landscape for shaping the next generation of humanitarian aid management systems, focusing on algorithmic and operational aspects, matching them to a new architecture for a target-platform, called AidTech. Methods: The methodology follows a systematic literature coverage, identifying cross-disciplinary trends from operations research, computer science and sustainable logistics. We examine the convergence of optimization, artificial intelligence, and blockchain-enabled traceability toward efficient and transparent humanitarian logistics. The employed methods include adaptive scheduling, resource allocation algorithms and privacy–preserving collaboration for meeting special constraints imposed by the humanitarian scope. Results: The findings focus on the architectural perspective of humanitarian supply chains and highlight that modern humanitarian infrastructures will increasingly rely on hybrid optimization methods integrating graph theory, dynamic routing under stochastic demand, multi-criteria decision analysis and distributed ledger technologies. Conclusions: We conclude that these paradigms, when combined under a unified cyber–physical architecture, e.g., AidTech, can substantially improve responsiveness, equity and sustainability in crisis management, further shaping future humanitarian logistics.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background: Humanitarian campaigns are more popular with more initiatives organized than ever by public and private bodies. Simultaneously, more peculiar challenges, such as zero-waste and transparency, are required compared to traditional supply chains. This work investigates the current technological landscape for shaping the next generation of humanitarian aid management systems, focusing on algorithmic and operational aspects, matching them to a new architecture for a target-platform, called AidTech. Methods: The methodology follows a systematic literature coverage, identifying cross-disciplinary trends from operations research, computer science and sustainable logistics. We examine the convergence of optimization, artificial intelligence, and blockchain-enabled traceability toward efficient and transparent humanitarian logistics. The employed methods include adaptive scheduling, resource allocation algorithms and privacy–preserving collaboration for meeting special constraints imposed by the humanitarian scope. Results: The findings focus on the architectural perspective of humanitarian supply chains and highlight that modern humanitarian infrastructures will increasingly rely on hybrid optimization methods integrating graph theory, dynamic routing under stochastic demand, multi-criteria decision analysis and distributed ledger technologies. Conclusions: We conclude that these paradigms, when combined under a unified cyber–physical architecture, e.g., AidTech, can substantially improve responsiveness, equity and sustainability in crisis management, further shaping future humanitarian logistics.
Koumadorakis, D. E., Dimitrakopoulos, G. N., Exarchos, T. P., Vlamos, P., & Vrahatis, A. G. (2025). Integrating Machine Learning and Biological Context for Single-Cell Gene Regulatory Network Inference. International Journal of Artificial Intelligence Tools, 35(01), 250–260. https://doi.org/10.1142/s0218213025400147
@article{koumadorakis2025integrating,
title = {Integrating Machine Learning and Biological Context for Single-Cell Gene Regulatory Network Inference},
author = {Dimitrios E. Koumadorakis and Georgios N. Dimitrakopoulos and Themis P. Exarchos and Panagiotis Vlamos and Aristidis G. Vrahatis},
url = {https://doi.org/10.1142/s0218213025400147},
doi = {10.1142/s0218213025400147},
year = {2025},
date = {2025-01-01},
journal = {International Journal of Artificial Intelligence Tools},
volume = {35},
number = {01},
pages = {250–260},
publisher = {World Scientific},
abstract = {Single-cell RNA Sequencing (scRNA-seq) data is a powerful approach for aiding in the uncovering of intricate regulatory networks that drive cellular processes. These Gene Regulatory Networks (GRNs) play a pivotal role in understanding how Transcription Factors (TFs) and target genes interact to control gene expression in diverse biological contexts. However, existing methods for GRN inference often rely heavily on mathematical models, frequently neglecting biological knowledge. Alternatively, some approaches incorporate biological knowledge with strict constraints, limiting their ability to predict novel interactions, resulting in reduced biological interpretability and the inclusion of false-positive regulatory interactions. To address these limitations, we propose a novel framework that integrates dataset-specific information with GO term annotations to enhance GRN inference. By combining mathematical modeling with biologically informed criteria, our approach prioritizes genes based on functional relevance and improves network interpretability. Using scRNA-seq data from donors with Type 2 Diabetes (T2D), we demonstrate that our method significantly reduces false positives and can identify biologically relevant TFs that other approaches may miss. This integration of biological knowledge with computational models not only enhances the precision of GRN predictions but also provides a deeper understanding of the regulatory mechanisms underlying complex cellular processes and disease pathogenesis.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Single-cell RNA Sequencing (scRNA-seq) data is a powerful approach for aiding in the uncovering of intricate regulatory networks that drive cellular processes. These Gene Regulatory Networks (GRNs) play a pivotal role in understanding how Transcription Factors (TFs) and target genes interact to control gene expression in diverse biological contexts. However, existing methods for GRN inference often rely heavily on mathematical models, frequently neglecting biological knowledge. Alternatively, some approaches incorporate biological knowledge with strict constraints, limiting their ability to predict novel interactions, resulting in reduced biological interpretability and the inclusion of false-positive regulatory interactions. To address these limitations, we propose a novel framework that integrates dataset-specific information with GO term annotations to enhance GRN inference. By combining mathematical modeling with biologically informed criteria, our approach prioritizes genes based on functional relevance and improves network interpretability. Using scRNA-seq data from donors with Type 2 Diabetes (T2D), we demonstrate that our method significantly reduces false positives and can identify biologically relevant TFs that other approaches may miss. This integration of biological knowledge with computational models not only enhances the precision of GRN predictions but also provides a deeper understanding of the regulatory mechanisms underlying complex cellular processes and disease pathogenesis.
Lekati, E., Dimitrakopoulos, G. N., Lazaros, K., Giannopoulou, P., Vrahatis, A. G., Krokidis, M. G., Vlamos, P., & Doukakis, S. (2025). Wearable EEG Sensor Analysis for Cognitive Profiling in Educational Contexts. Sensors, 25(20), 6446. https://doi.org/10.3390/s25206446
@article{lekati2025wearable,
title = {Wearable EEG Sensor Analysis for Cognitive Profiling in Educational Contexts},
author = {Eleni Lekati and Georgios N. Dimitrakopoulos and Konstantinos Lazaros and Panagiota Giannopoulou and Aristidis G. Vrahatis and Marios G. Krokidis and Panagiotis Vlamos and Spyridon Doukakis},
url = {https://doi.org/10.3390/s25206446},
doi = {10.3390/s25206446},
year = {2025},
date = {2025-01-01},
journal = {Sensors},
volume = {25},
number = {20},
pages = {6446},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Electroencephalography (EEG) provides a powerful means of capturing real-time neural activity, enabling the study of cognitive processes during complex learning tasks. This study explores the application of wearable EEG and advanced signal analysis to examine cognitive profiles of 30 sixth-grade students engaged in fraction learning. Using validated estimations alongside interactive digital tools such as Fraction Lab and the Diamond Paper task, EEG recordings were processed to evaluate spectral dynamics across delta, theta, alpha, and beta bands. Results revealed that lower-performing students exhibited elevated delta and theta power under cognitive load, whereas higher-performing students showed more stable beta activity linked to cognitive control. These findings highlight the utility of EEG-based signal analysis for identifying neurocognitive markers associated with conceptual and procedural knowledge (PK) in mathematics. The integration of such methodologies supports the development of precision-oriented educational strategies grounded in objective neural data. Clustering further revealed three learner profiles: Core Support Needed, Developing, and Advanced, while classification analyses confirmed that EEG features, especially gamma and beta oscillations, reliably distinguished among them, underscoring the potential of neurocognitive markers to guide adaptive instruction.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Electroencephalography (EEG) provides a powerful means of capturing real-time neural activity, enabling the study of cognitive processes during complex learning tasks. This study explores the application of wearable EEG and advanced signal analysis to examine cognitive profiles of 30 sixth-grade students engaged in fraction learning. Using validated estimations alongside interactive digital tools such as Fraction Lab and the Diamond Paper task, EEG recordings were processed to evaluate spectral dynamics across delta, theta, alpha, and beta bands. Results revealed that lower-performing students exhibited elevated delta and theta power under cognitive load, whereas higher-performing students showed more stable beta activity linked to cognitive control. These findings highlight the utility of EEG-based signal analysis for identifying neurocognitive markers associated with conceptual and procedural knowledge (PK) in mathematics. The integration of such methodologies supports the development of precision-oriented educational strategies grounded in objective neural data. Clustering further revealed three learner profiles: Core Support Needed, Developing, and Advanced, while classification analyses confirmed that EEG features, especially gamma and beta oscillations, reliably distinguished among them, underscoring the potential of neurocognitive markers to guide adaptive instruction.
Krokidis, M. G., Dimitrakopoulos, G. N., Vrahatis, A. G., Exarchos, T. P., & Vlamos, P. (2024). Challenges and limitations in computational prediction of protein misfolding in neurodegenerative diseases. Frontiers in Computational Neuroscience, 17, 1323182. https://doi.org/10.3389/fncom.2023.1323182
@article{krokidis2024challenges,
title = {Challenges and limitations in computational prediction of protein misfolding in neurodegenerative diseases},
author = {Marios G. Krokidis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Themis P. Exarchos and Panagiotis Vlamos},
url = {https://doi.org/10.3389/fncom.2023.1323182},
doi = {10.3389/fncom.2023.1323182},
year = {2024},
date = {2024-01-01},
journal = {Frontiers in Computational Neuroscience},
volume = {17},
pages = {1323182},
publisher = {Frontiers Media},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Paplomatas, P., Lazaros, K., Dimitrakopoulos, G. N., & Vrahatis, A. G. (2024). Feature selection in single-cell RNA sequencing data: a comprehensive evaluation. Academia Biology, 2(3). https://doi.org/10.20935/acadbiol7324
@article{paplomatas2024feature,
title = {Feature selection in single-cell RNA sequencing data: a comprehensive evaluation},
author = {Petros Paplomatas and Konstantinos Lazaros and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis},
url = {https://doi.org/10.20935/acadbiol7324},
doi = {10.20935/acadbiol7324},
year = {2024},
date = {2024-01-01},
journal = {Academia Biology},
volume = {2},
number = {3},
publisher = {Academia.edu Journals},
abstract = {Single-cell RNA sequencing (scRNA-seq) has revolutionized biological and medical research, providing unique insights into the intricate cell-type compositions within various tissues. Unlike bulk RNA sequencing, scRNA-seq allows for examining gene expression at the individual cell level, revealing cellular heterogeneity and identifying rare cell types. However, the high dimensionality and inherent noise in scRNA-seq data pose significant analytical challenges. This study focuses on dimensionality reduction and cell-type identification in scRNA-seq data analysis. We developed the GenesRanking package, which offers 20 techniques for dimensionality reduction, including filter-based and embedding machine learning–based methods. By integrating feature selection methods from both statistics and machine learning, we provide a robust framework for improving data interpretation. Our comprehensive evaluation across five diverse scRNA-seq datasets demonstrates that although some methods show consistent performance, the technique should be chosen according to specific datasets for obtaining optimal results. Our findings underscore the enduring necessity for further refinement and continuous innovation in the field of scRNA-seq analysis, aiming to enhance the accuracy of cell-type identification and improve overall data interpretation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Single-cell RNA sequencing (scRNA-seq) has revolutionized biological and medical research, providing unique insights into the intricate cell-type compositions within various tissues. Unlike bulk RNA sequencing, scRNA-seq allows for examining gene expression at the individual cell level, revealing cellular heterogeneity and identifying rare cell types. However, the high dimensionality and inherent noise in scRNA-seq data pose significant analytical challenges. This study focuses on dimensionality reduction and cell-type identification in scRNA-seq data analysis. We developed the GenesRanking package, which offers 20 techniques for dimensionality reduction, including filter-based and embedding machine learning–based methods. By integrating feature selection methods from both statistics and machine learning, we provide a robust framework for improving data interpretation. Our comprehensive evaluation across five diverse scRNA-seq datasets demonstrates that although some methods show consistent performance, the technique should be chosen according to specific datasets for obtaining optimal results. Our findings underscore the enduring necessity for further refinement and continuous innovation in the field of scRNA-seq analysis, aiming to enhance the accuracy of cell-type identification and improve overall data interpretation.
Giannakopoulou, O., Kakkos, I., Dimitrakopoulos, G. N., Tarousi, M., Sun, Y., Bezerianos, A., Koutsouris, D., & Matsopoulos, G. K. (2024). Individual Variability in Brain Connectivity Patterns and Driving-Fatigue Dynamics. Sensors, 24(12), 3894. https://doi.org/10.3390/s24123894
@article{giannakopoulou2024individual,
title = {Individual Variability in Brain Connectivity Patterns and Driving-Fatigue Dynamics},
author = {Olympia Giannakopoulou and Ioannis Kakkos and Georgios N. Dimitrakopoulos and Marilena Tarousi and Yu Sun and Anastasios Bezerianos and Dimitris Koutsouris and George K. Matsopoulos},
url = {https://doi.org/10.3390/s24123894},
doi = {10.3390/s24123894},
year = {2024},
date = {2024-01-01},
journal = {Sensors},
volume = {24},
number = {12},
pages = {3894},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Mental fatigue during driving poses significant risks to road safety, necessitating accurate assessment methods to mitigate potential hazards. This study explores the impact of individual variability in brain networks on driving fatigue assessment, hypothesizing that subject-specific connectivity patterns play a pivotal role in understanding fatigue dynamics. By conducting a linear regression analysis of subject-specific brain networks in different frequency bands, this research aims to elucidate the relationships between frequency-specific connectivity patterns and driving fatigue. As such, an EEG sustained driving simulation experiment was carried out, estimating individuals' brain networks using the Phase Lag Index (PLI) to capture shared connectivity patterns. The results unveiled notable variability in connectivity patterns across frequency bands, with the alpha band exhibiting heightened sensitivity to driving fatigue. Individualized connectivity analysis underscored the complexity of fatigue assessment and the potential for personalized approaches. These findings emphasize the importance of subject-specific brain networks in comprehending fatigue dynamics, while providing sensor space minimization, advocating for the development of efficient mobile sensor applications for real-time fatigue detection in driving scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mental fatigue during driving poses significant risks to road safety, necessitating accurate assessment methods to mitigate potential hazards. This study explores the impact of individual variability in brain networks on driving fatigue assessment, hypothesizing that subject-specific connectivity patterns play a pivotal role in understanding fatigue dynamics. By conducting a linear regression analysis of subject-specific brain networks in different frequency bands, this research aims to elucidate the relationships between frequency-specific connectivity patterns and driving fatigue. As such, an EEG sustained driving simulation experiment was carried out, estimating individuals' brain networks using the Phase Lag Index (PLI) to capture shared connectivity patterns. The results unveiled notable variability in connectivity patterns across frequency bands, with the alpha band exhibiting heightened sensitivity to driving fatigue. Individualized connectivity analysis underscored the complexity of fatigue assessment and the potential for personalized approaches. These findings emphasize the importance of subject-specific brain networks in comprehending fatigue dynamics, while providing sensor space minimization, advocating for the development of efficient mobile sensor applications for real-time fatigue detection in driving scenarios.
Exarchos, T. P., Dimitrakopoulos, G. N., Vrahatis, A. G., Chrysovitsiotis, G., Zachou, Z., & Kyrodimos, E. (2024). Lip-Reading Advancements: A 3D Convolutional Neural Network/Long Short-Term Memory Fusion for Precise Word Recognition. BioMedInformatics, 4(1), 410–422. https://doi.org/10.3390/biomedinformatics4010023
@article{exarchos2024lip,
title = {Lip-Reading Advancements: A 3D Convolutional Neural Network/Long Short-Term Memory Fusion for Precise Word Recognition},
author = {Themis P. Exarchos and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Georgios Chrysovitsiotis and Zoi Zachou and Efthymios Kyrodimos},
url = {https://doi.org/10.3390/biomedinformatics4010023},
doi = {10.3390/biomedinformatics4010023},
year = {2024},
date = {2024-01-01},
journal = {BioMedInformatics},
volume = {4},
number = {1},
pages = {410–422},
publisher = {MDPI AG},
abstract = {Lip reading, the art of deciphering spoken words from the visual cues of lip movements, has garnered significant interest for its potential applications in diverse fields, including assistive technologies, human–computer interaction, and security systems. With the rapid advancements in technology and the increasing emphasis on non-verbal communication methods, the significance of lip reading has expanded beyond its traditional boundaries. These technological advancements have led to the generation of large-scale and complex datasets, necessitating the use of cutting-edge deep learning tools that are adept at handling such intricacies. In this study, we propose an innovative approach combining 3D Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to tackle the challenging task of word recognition from lip movements. Our research leverages a meticulously curated dataset, named MobLip, encompassing various speech patterns, speakers, and environmental conditions. The synergy between the spatial information extracted by 3D CNNs and the temporal dynamics captured by LSTMs yields impressive results, achieving an accuracy rate of up to 87.5%, showcasing robustness to lighting variations and speaker diversity. Comparative experiments demonstrate our model’s superiority over existing lip-reading approaches, underlining its potential for real-world deployment. Furthermore, we discuss ethical considerations and propose avenues for future research, such as multimodal integration with audio data and expanded language support. In conclusion, our 3D CNN-LSTM architecture presents a promising solution to the complex problem of word recognition from lip movements, contributing to the advancement of communication technology and opening doors to innovative applications in an increasingly visual world.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lip reading, the art of deciphering spoken words from the visual cues of lip movements, has garnered significant interest for its potential applications in diverse fields, including assistive technologies, human–computer interaction, and security systems. With the rapid advancements in technology and the increasing emphasis on non-verbal communication methods, the significance of lip reading has expanded beyond its traditional boundaries. These technological advancements have led to the generation of large-scale and complex datasets, necessitating the use of cutting-edge deep learning tools that are adept at handling such intricacies. In this study, we propose an innovative approach combining 3D Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to tackle the challenging task of word recognition from lip movements. Our research leverages a meticulously curated dataset, named MobLip, encompassing various speech patterns, speakers, and environmental conditions. The synergy between the spatial information extracted by 3D CNNs and the temporal dynamics captured by LSTMs yields impressive results, achieving an accuracy rate of up to 87.5%, showcasing robustness to lighting variations and speaker diversity. Comparative experiments demonstrate our model’s superiority over existing lip-reading approaches, underlining its potential for real-world deployment. Furthermore, we discuss ethical considerations and propose avenues for future research, such as multimodal integration with audio data and expanded language support. In conclusion, our 3D CNN-LSTM architecture presents a promising solution to the complex problem of word recognition from lip movements, contributing to the advancement of communication technology and opening doors to innovative applications in an increasingly visual world.
Dimitrakopoulos, G. N., Kakkos, I., Anastasiou, A., Bezerianos, A., Sun, Y., & Matsopoulos, G. K. (2023). Cognitive Reorganization Due to Mental Workload: A Functional Connectivity Analysis Based on Working Memory Paradigms. Applied Sciences, 13(4), 2129. https://doi.org/10.3390/app13042129
@article{dimitrakopoulos2023cognitive,
title = {Cognitive Reorganization Due to Mental Workload: A Functional Connectivity Analysis Based on Working Memory Paradigms},
author = {Georgios N. Dimitrakopoulos and Ioannis Kakkos and Athanasios Anastasiou and Anastasios Bezerianos and Yu Sun and George K. Matsopoulos},
url = {https://doi.org/10.3390/app13042129},
doi = {10.3390/app13042129},
year = {2023},
date = {2023-01-01},
journal = {Applied Sciences},
volume = {13},
number = {4},
pages = {2129},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Mental workload has a major effect on the individual’s performance in most real-world tasks, which can lead to significant errors in critical operations. On this premise, the analysis and assessment of mental workload attain high research interest in both the fields of Neuroergonomics and Neuroscience. In this work, we implemented an EEG experimental design consisting of two distinct mental tasks (mental arithmetic task, n-back task), each with two conditions of complexity (low and high) to investigate the task-related and task-unrelated workload effects. Since mental workload is an intricate phenomenon involving multiple brain areas, we performed a graph theoretical analysis estimating the Phase Locking Index (PLI) in four frequency bands (delta, theta, alpha, beta). The brainwave-dependent network results show statistically significant reductions in clustering coefficient, characteristic path length, and small-worldness metrics with higher workload in both tasks across several bands. Moreover, functional connectivity analysis indicates a task-independent fashion of the brain topological re-organization with increasing mental load. These results revealed how the brain network is re-organized with increasing mental workload in a task-independent way. Finally, the network metrics were used as classification features, leading to high performance in workload level discrimination.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mental workload has a major effect on the individual’s performance in most real-world tasks, which can lead to significant errors in critical operations. On this premise, the analysis and assessment of mental workload attain high research interest in both the fields of Neuroergonomics and Neuroscience. In this work, we implemented an EEG experimental design consisting of two distinct mental tasks (mental arithmetic task, n-back task), each with two conditions of complexity (low and high) to investigate the task-related and task-unrelated workload effects. Since mental workload is an intricate phenomenon involving multiple brain areas, we performed a graph theoretical analysis estimating the Phase Locking Index (PLI) in four frequency bands (delta, theta, alpha, beta). The brainwave-dependent network results show statistically significant reductions in clustering coefficient, characteristic path length, and small-worldness metrics with higher workload in both tasks across several bands. Moreover, functional connectivity analysis indicates a task-independent fashion of the brain topological re-organization with increasing mental load. These results revealed how the brain network is re-organized with increasing mental workload in a task-independent way. Finally, the network metrics were used as classification features, leading to high performance in workload level discrimination.
Dimitrakopoulos, G. N., Vrahatis, A. G., Exarchos, T. P., Krokidis, M. G., & Vlamos, P. (2023). Drug and Protein Interaction Network Construction for Drug Repurposing in Alzheimer’s Disease. Future Pharmacology, 3(4), 731–741. https://doi.org/10.3390/futurepharmacol3040045
@article{dimitrakopoulos2023drug,
title = {Drug and Protein Interaction Network Construction for Drug Repurposing in Alzheimer’s Disease},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Themis P. Exarchos and Marios G. Krokidis and Panagiotis Vlamos},
url = {https://doi.org/10.3390/futurepharmacol3040045},
doi = {10.3390/futurepharmacol3040045},
year = {2023},
date = {2023-01-01},
journal = {Future Pharmacology},
volume = {3},
number = {4},
pages = {731–741},
publisher = {MDPI AG},
abstract = {Alzheimer’s disease is one of the leading causes of death globally, significantly impacting countless families and communities. In parallel, recent advancements in molecular biology and network approaches, guided by the Network Medicine perspective, offer promising outcomes for Alzheimer’s disease research and treatment. In this study, we aim to discover candidate therapies for AD through drug repurposing. We combined a protein-protein interaction (PPI) network with drug-target interactions. Experimentally validated PPI data were collected from the PICKLE meta-database, while drugs and their protein targets were sourced from the DrugBank database. Then, based on RNA-Seq data, we first assigned weights to edges to indicate co-expression, and secondly, estimated differential gene expression to select a subset of genes potentially related to the disease. Finally, small subgraphs (modules) were extracted from the graph, centered on the genes of interest. The analysis revealed that even if there is no drug targeting several genes of interest directly, an existing drug might target a neighboring node, thus indirectly affecting the aforementioned genes. Our approach offers a promising method for treating various diseases by repurposing existing drugs, thereby reducing the cost and time of experimental procedures and paving the way for more precise Network Medicine strategies.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Alzheimer’s disease is one of the leading causes of death globally, significantly impacting countless families and communities. In parallel, recent advancements in molecular biology and network approaches, guided by the Network Medicine perspective, offer promising outcomes for Alzheimer’s disease research and treatment. In this study, we aim to discover candidate therapies for AD through drug repurposing. We combined a protein-protein interaction (PPI) network with drug-target interactions. Experimentally validated PPI data were collected from the PICKLE meta-database, while drugs and their protein targets were sourced from the DrugBank database. Then, based on RNA-Seq data, we first assigned weights to edges to indicate co-expression, and secondly, estimated differential gene expression to select a subset of genes potentially related to the disease. Finally, small subgraphs (modules) were extracted from the graph, centered on the genes of interest. The analysis revealed that even if there is no drug targeting several genes of interest directly, an existing drug might target a neighboring node, thus indirectly affecting the aforementioned genes. Our approach offers a promising method for treating various diseases by repurposing existing drugs, thereby reducing the cost and time of experimental procedures and paving the way for more precise Network Medicine strategies.
Krokidis, M. G., Dimitrakopoulos, G. N., Vrahatis, A. G., Tzouvelekis, C., Drakoulis, D., Papavassileiou, F., Exarchos, T. P., & Vlamos, P. (2022). A Sensor-Based Perspective in Early-Stage Parkinson’s Disease: Current State and the Need for Machine Learning Processes. Sensors, 22(2), 409. https://doi.org/10.3390/s22020409
@article{krokidis2022sensor,
title = {A Sensor-Based Perspective in Early-Stage Parkinson’s Disease: Current State and the Need for Machine Learning Processes},
author = {Marios G. Krokidis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Christos Tzouvelekis and Dimitrios Drakoulis and Foteini Papavassileiou and Themis P. Exarchos and Panagiotis Vlamos},
url = {https://doi.org/10.3390/s22020409},
doi = {10.3390/s22020409},
year = {2022},
date = {2022-01-01},
journal = {Sensors},
volume = {22},
number = {2},
pages = {409},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {Parkinson's disease (PD) is a progressive neurodegenerative disorder associated with dysfunction of dopaminergic neurons in the brain, lack of dopamine and the formation of abnormal Lewy body protein particles. PD is an idiopathic disease of the nervous system, characterized by motor and nonmotor manifestations without a discrete onset of symptoms until a substantial loss of neurons has already occurred, enabling early diagnosis very challenging. Sensor-based platforms have gained much attention in clinical practice screening various biological signals simultaneously and allowing researchers to quickly receive a huge number of biomarkers for diagnostic and prognostic purposes. The integration of machine learning into medical systems provides the potential for optimization of data collection, disease prediction through classification of symptoms and can strongly support data-driven clinical decisions. This work attempts to examine some of the facts and current situation of sensor-based approaches in PD diagnosis and discusses ensemble techniques using sensor-based data for developing machine learning models for personalized risk prediction. Additionally, a biosensing platform combined with clinical data processing and appropriate software is proposed in order to implement a complete diagnostic system for PD monitoring.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Parkinson's disease (PD) is a progressive neurodegenerative disorder associated with dysfunction of dopaminergic neurons in the brain, lack of dopamine and the formation of abnormal Lewy body protein particles. PD is an idiopathic disease of the nervous system, characterized by motor and nonmotor manifestations without a discrete onset of symptoms until a substantial loss of neurons has already occurred, enabling early diagnosis very challenging. Sensor-based platforms have gained much attention in clinical practice screening various biological signals simultaneously and allowing researchers to quickly receive a huge number of biomarkers for diagnostic and prognostic purposes. The integration of machine learning into medical systems provides the potential for optimization of data collection, disease prediction through classification of symptoms and can strongly support data-driven clinical decisions. This work attempts to examine some of the facts and current situation of sensor-based approaches in PD diagnosis and discusses ensemble techniques using sensor-based data for developing machine learning models for personalized risk prediction. Additionally, a biosensing platform combined with clinical data processing and appropriate software is proposed in order to implement a complete diagnostic system for PD monitoring.
Dimitrakopoulos, G. N., Klapa, M. I., & Moschonas, N. K. (2022). How Far Are We from the Completion of the Human Protein Interactome Reconstruction?. Biomolecules, 12(1), 140. https://doi.org/10.3390/biom12010140
@article{dimitrakopoulos2022far,
title = {How Far Are We from the Completion of the Human Protein Interactome Reconstruction?},
author = {Georgios N. Dimitrakopoulos and Maria I. Klapa and Nicholas K. Moschonas},
url = {https://doi.org/10.3390/biom12010140},
doi = {10.3390/biom12010140},
year = {2022},
date = {2022-01-01},
journal = {Biomolecules},
volume = {12},
number = {1},
pages = {140},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {After more than fifteen years from the first high-throughput experiments for human protein-protein interaction (PPI) detection, we are still wondering how close the completion of the genome-scale human PPI network reconstruction is, what needs to be further explored and whether the biological insights gained from the holistic investigation of the current network are valid and useful. The unique structure of PICKLE, a meta-database of the human experimentally determined direct PPI network developed by our group, presently covering ~80% of the UniProtKB/Swiss-Prot reviewed human complete proteome, enables the evaluation of the interactome expansion by comparing the successive PICKLE releases since 2013. We observe a gradual overall increase of 39%, 182%, and 67% in protein nodes, PPIs, and supporting references, respectively. Our results indicate that, in recent years, (a) the PPI addition rate has decreased, (b) the new PPIs are largely determined by high-throughput experiments and mainly concern existing protein nodes and (c), as we had predicted earlier, most of the newly added protein nodes have a low degree. These observations, combined with a largely overlapping k-core between PICKLE releases and a network density increase, imply that an almost complete picture of a structurally defined network has been reached. The comparative unsupervised application of two clustering algorithms indicated that exploring the full interactome topology can reveal the protein neighborhoods involved in closely related biological processes as transcriptional regulation, cell signaling and multiprotein complexes such as the connexon complex associated with cancers. A well-reconstructed human protein interactome is a powerful tool in network biology and medicine research forming the basis for multi-omic and dynamic analyses.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
After more than fifteen years from the first high-throughput experiments for human protein-protein interaction (PPI) detection, we are still wondering how close the completion of the genome-scale human PPI network reconstruction is, what needs to be further explored and whether the biological insights gained from the holistic investigation of the current network are valid and useful. The unique structure of PICKLE, a meta-database of the human experimentally determined direct PPI network developed by our group, presently covering ~80% of the UniProtKB/Swiss-Prot reviewed human complete proteome, enables the evaluation of the interactome expansion by comparing the successive PICKLE releases since 2013. We observe a gradual overall increase of 39%, 182%, and 67% in protein nodes, PPIs, and supporting references, respectively. Our results indicate that, in recent years, (a) the PPI addition rate has decreased, (b) the new PPIs are largely determined by high-throughput experiments and mainly concern existing protein nodes and (c), as we had predicted earlier, most of the newly added protein nodes have a low degree. These observations, combined with a largely overlapping k-core between PICKLE releases and a network density increase, imply that an almost complete picture of a structurally defined network has been reached. The comparative unsupervised application of two clustering algorithms indicated that exploring the full interactome topology can reveal the protein neighborhoods involved in closely related biological processes as transcriptional regulation, cell signaling and multiprotein complexes such as the connexon complex associated with cancers. A well-reconstructed human protein interactome is a powerful tool in network biology and medicine research forming the basis for multi-omic and dynamic analyses.
Kakkos, I., Dimitrakopoulos, G. N., Sun, Y., Yuan, J., Matsopoulos, G. K., Bezerianos, A., & Sun, Y. (2021). EEG Fingerprints of Task-Independent Mental Workload Discrimination. IEEE Journal of Biomedical and Health Informatics, 25(10), 3824–3833. https://doi.org/10.1109/jbhi.2021.3085131
@article{kakkos2021eeg,
title = {EEG Fingerprints of Task-Independent Mental Workload Discrimination},
author = {Ioannis Kakkos and Georgios N. Dimitrakopoulos and Yi Sun and Jingjia Yuan and George K. Matsopoulos and Anastasios Bezerianos and Yu Sun},
url = {https://doi.org/10.1109/jbhi.2021.3085131},
doi = {10.1109/jbhi.2021.3085131},
year = {2021},
date = {2021-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
volume = {25},
number = {10},
pages = {3824–3833},
publisher = {Institute of Electrical and Electronics Engineers},
abstract = {In the nascent field of neuroergonomics, mental workload assessment is one of the most important issues and has an apparent significance in real-world applications. Although prior research has achieved efficient single-task classification, scatted studies on cross-task mental workload assessment usually result in unsatisfactory performance. Here, we introduce a data-driven analysis framework to overcome the challenges regarding task-independent workload assessment using a fusion of EEG spectral characteristics and unveil the common neural mechanisms underlying mental workload. Specifically, multi-frequency power spectrum and functional connectivity (FC) were estimated for two workload levels in two working-memory tasks performed by 40 healthy participants, subsequently being fed into a machine learning approach to obtain the importance of each feature vector and evaluate classification performance in a cross-task fashion. Our framework achieved a classification accuracy of 0.94 for task-independent mental workload discrimination. Further investigation of the designated features in terms of their spectral and localization properties revealed task-independent common patterns in the neural mechanisms governing workload. In particular, increased workload was associated with elevated frontal delta and theta power but reduced parietal alpha power, whereas FC exhibited complex frequency- and region-dependent alterations. By implication, the employment of the EEG feature fusion emphasized their utility in serving as promising indicators for different workload conditions applications.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In the nascent field of neuroergonomics, mental workload assessment is one of the most important issues and has an apparent significance in real-world applications. Although prior research has achieved efficient single-task classification, scatted studies on cross-task mental workload assessment usually result in unsatisfactory performance. Here, we introduce a data-driven analysis framework to overcome the challenges regarding task-independent workload assessment using a fusion of EEG spectral characteristics and unveil the common neural mechanisms underlying mental workload. Specifically, multi-frequency power spectrum and functional connectivity (FC) were estimated for two workload levels in two working-memory tasks performed by 40 healthy participants, subsequently being fed into a machine learning approach to obtain the importance of each feature vector and evaluate classification performance in a cross-task fashion. Our framework achieved a classification accuracy of 0.94 for task-independent mental workload discrimination. Further investigation of the designated features in terms of their spectral and localization properties revealed task-independent common patterns in the neural mechanisms governing workload. In particular, increased workload was associated with elevated frontal delta and theta power but reduced parietal alpha power, whereas FC exhibited complex frequency- and region-dependent alterations. By implication, the employment of the EEG feature fusion emphasized their utility in serving as promising indicators for different workload conditions applications.
Dimitrakopoulos, G. N. (2021). XGRN: Reconstruction of Biological Networks Based on Boosted Trees Regression. Computation, 9(4), 48. https://doi.org/10.3390/computation9040048
@article{dimitrakopoulos2021xgrn,
title = {XGRN: Reconstruction of Biological Networks Based on Boosted Trees Regression},
author = {Georgios N. Dimitrakopoulos},
url = {https://doi.org/10.3390/computation9040048},
doi = {10.3390/computation9040048},
year = {2021},
date = {2021-01-01},
journal = {Computation},
volume = {9},
number = {4},
pages = {48},
publisher = {Multidisciplinary Digital Publishing Institute},
abstract = {In Systems Biology, the complex relationships between different entities in the cells are modeled and analyzed using networks. Towards this aim, a rich variety of gene regulatory network (GRN) inference algorithms has been developed in recent years. However, most algorithms rely solely on gene expression data to reconstruct the network. Due to possible expression profile similarity, predictions can contain connections between biologically unrelated genes. Therefore, previously known biological information should also be considered by computational methods to obtain more consistent results, such as experimentally validated interactions between transcription factors and target genes. In this work, we propose XGBoost for gene regulatory networks (XGRN), a supervised algorithm, which combines gene expression data with previously known interactions for GRN inference. The key idea of our method is to train a regression model for each known interaction of the network and then utilize this model to predict new interactions. The regression is performed by XGBoost, a state-of-the-art algorithm using an ensemble of decision trees. In detail, XGRN learns a regression model based on gene expression of the two interactors and then provides predictions using as input the gene expression of other candidate interactors. Application on benchmark datasets and a real large single-cell RNA-Seq experiment resulted in high performance compared to other unsupervised and supervised methods, demonstrating the ability of XGRN to provide reliable predictions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In Systems Biology, the complex relationships between different entities in the cells are modeled and analyzed using networks. Towards this aim, a rich variety of gene regulatory network (GRN) inference algorithms has been developed in recent years. However, most algorithms rely solely on gene expression data to reconstruct the network. Due to possible expression profile similarity, predictions can contain connections between biologically unrelated genes. Therefore, previously known biological information should also be considered by computational methods to obtain more consistent results, such as experimentally validated interactions between transcription factors and target genes. In this work, we propose XGBoost for gene regulatory networks (XGRN), a supervised algorithm, which combines gene expression data with previously known interactions for GRN inference. The key idea of our method is to train a regression model for each known interaction of the network and then utilize this model to predict new interactions. The regression is performed by XGBoost, a state-of-the-art algorithm using an ensemble of decision trees. In detail, XGRN learns a regression model based on gene expression of the two interactors and then provides predictions using as input the gene expression of other candidate interactors. Application on benchmark datasets and a real large single-cell RNA-Seq experiment resulted in high performance compared to other unsupervised and supervised methods, demonstrating the ability of XGRN to provide reliable predictions.
Dimitrakopoulos, G. N., Klapa, M. I., & Moschonas, N. K. (2020). PICKLE 3.0: enriching the human meta-database with the mouse protein interactome extended via mouse–human orthology. Bioinformatics, 37(1), 145–146. https://doi.org/10.1093/bioinformatics/btaa1070
@article{dimitrakopoulos2020pickle,
title = {PICKLE 3.0: enriching the human meta-database with the mouse protein interactome extended via mouse–human orthology},
author = {Georgios N. Dimitrakopoulos and Maria I. Klapa and Nicholas K Moschonas},
url = {https://doi.org/10.1093/bioinformatics/btaa1070},
doi = {10.1093/bioinformatics/btaa1070},
year = {2020},
date = {2020-01-01},
journal = {Bioinformatics},
volume = {37},
number = {1},
pages = {145–146},
publisher = {Oxford University Press},
abstract = {SUMMARY: The PICKLE 3.0 upgrade refers to the enrichment of this human protein-protein interaction (PPI) meta-database with the mouse protein interactome. Experimental PPI data between mouse genetic entities are rather limited; however, they are substantially complemented by PPIs between mouse and human genetic entities. The relational scheme of PICKLE 3.0 has been amended to exploit the Mouse Genome Informatics mouse-human ortholog gene pair collection, enabling (i) the extension through orthology of the mouse interactome with potentially valid PPIs between mouse entities based on the experimental PPIs between mouse and human entities and (ii) the comparison between mouse and human PPI networks. Interestingly, 43.5% of the experimental mouse PPIs lacks a corresponding by orthology PPI in human, an inconsistency in need of further investigation. Overall, as primary mouse PPI datasets show a considerably limited overlap, PICKLE 3.0 provides a unique comprehensive representation of the mouse protein interactome. AVAILABILITY AND IMPLEMENTATION: PICKLE can be queried and downloaded at http://www.pickle.gr. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
SUMMARY: The PICKLE 3.0 upgrade refers to the enrichment of this human protein-protein interaction (PPI) meta-database with the mouse protein interactome. Experimental PPI data between mouse genetic entities are rather limited; however, they are substantially complemented by PPIs between mouse and human genetic entities. The relational scheme of PICKLE 3.0 has been amended to exploit the Mouse Genome Informatics mouse-human ortholog gene pair collection, enabling (i) the extension through orthology of the mouse interactome with potentially valid PPIs between mouse entities based on the experimental PPIs between mouse and human entities and (ii) the comparison between mouse and human PPI networks. Interestingly, 43.5% of the experimental mouse PPIs lacks a corresponding by orthology PPI in human, an inconsistency in need of further investigation. Overall, as primary mouse PPI datasets show a considerably limited overlap, PICKLE 3.0 provides a unique comprehensive representation of the mouse protein interactome. AVAILABILITY AND IMPLEMENTATION: PICKLE can be queried and downloaded at http://www.pickle.gr. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Kakkos, I., Dimitrakopoulos, G. N., Gao, L., Zhang, Y., Qi, P., Matsopoulos, G. K., Thakor, N. V., Bezerianos, A., & Sun, Y. (2019). Mental Workload Drives Different Reorganizations of Functional Cortical Connectivity Between 2D and 3D Simulated Flight Experiments. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(9), 1704–1713. https://doi.org/10.1109/tnsre.2019.2930082
@article{kakkos2019mental,
title = {Mental Workload Drives Different Reorganizations of Functional Cortical Connectivity Between 2D and 3D Simulated Flight Experiments},
author = {Ioannis Kakkos and Georgios N. Dimitrakopoulos and Lingyun Gao and Yuan Zhang and Peng Qi and George K. Matsopoulos and Nitish V. Thakor and Anastasios Bezerianos and Yu Sun},
url = {https://doi.org/10.1109/tnsre.2019.2930082},
doi = {10.1109/tnsre.2019.2930082},
year = {2019},
date = {2019-01-01},
journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
volume = {27},
number = {9},
pages = {1704–1713},
publisher = {Institute of Electrical and Electronics Engineers},
abstract = {Despite the apparent usefulness of efficient mental workload assessment in various real-world situations, the underlying neural mechanism remains largely unknown, and studies of the mental workload are limited to well-controlled cognitive tasks using a 2D computer screen. In this paper, we investigated functional brain network alterations in a simulated flight experiment with three mental workload levels and compared the reorganization pattern between computer screen (2D) and virtual reality (3D) interfaces. We constructed multiband functional networks in electroencephalogram (EEG) source space, which were further assessed in terms of network efficiency and workload classification performances. We found that increased alpha band efficiencies and beta band local efficiency were associated with elevated mental workload levels, while beta band global efficiency exhibited distinct development trends between 2D and 3D interfaces. Furthermore, using a small subset of connectivity features, we achieved a satisfactory multi-level workload classification accuracy in both interfaces (82% for both 2D and 3D). Further inspection of these discriminative connectivity subsets, we found predominant alpha band connectivity features followed by beta and theta band features with different topological patterns between 2D and 3D interfaces. These findings allow for a more comprehensive interpretation of the neural mechanisms of mental workload in relation to real-world assessment.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Despite the apparent usefulness of efficient mental workload assessment in various real-world situations, the underlying neural mechanism remains largely unknown, and studies of the mental workload are limited to well-controlled cognitive tasks using a 2D computer screen. In this paper, we investigated functional brain network alterations in a simulated flight experiment with three mental workload levels and compared the reorganization pattern between computer screen (2D) and virtual reality (3D) interfaces. We constructed multiband functional networks in electroencephalogram (EEG) source space, which were further assessed in terms of network efficiency and workload classification performances. We found that increased alpha band efficiencies and beta band local efficiency were associated with elevated mental workload levels, while beta band global efficiency exhibited distinct development trends between 2D and 3D interfaces. Furthermore, using a small subset of connectivity features, we achieved a satisfactory multi-level workload classification accuracy in both interfaces (82% for both 2D and 3D). Further inspection of these discriminative connectivity subsets, we found predominant alpha band connectivity features followed by beta and theta band features with different topological patterns between 2D and 3D interfaces. These findings allow for a more comprehensive interpretation of the neural mechanisms of mental workload in relation to real-world assessment.
Li, J., Dimitrakopoulos, G. N., Thangavel, P., Gong, C., Sun, Y., Guo, Z., Yu, H., Thakor, N. V., & Bezerianos, A. (2019). What Are Spectral and Spatial Distributions of EEG-EMG Correlations in Overground Walking? An Exploratory Study. IEEE Access, 7, 143935–143946. https://doi.org/10.1109/access.2019.2945602
@article{li2019spectral,
title = {What Are Spectral and Spatial Distributions of EEG-EMG Correlations in Overground Walking? An Exploratory Study},
author = {Junhua Li and Georgios N. Dimitrakopoulos and Pavithra Thangavel and Chen Gong and Yu Sun and Zhao Guo and Haoyong Yu and Nitish V. Thakor and Anastasios Bezerianos},
url = {https://doi.org/10.1109/access.2019.2945602},
doi = {10.1109/access.2019.2945602},
year = {2019},
date = {2019-01-01},
journal = {IEEE Access},
volume = {7},
pages = {143935–143946},
publisher = {Institute of Electrical and Electronics Engineers},
abstract = {You probably believe that a latent relationship between the brain and lower limbs exists and it varies across different walking conditions (e.g., walking with or without an exoskeleton). Have you ever thought what the distributions of measured signals are? To address this question, we simultaneously collected electroencephalogram (EEG) and electromyogram (EMG) signals while healthy participants were conducting four overground walking conditions without any constraints (e.g., specific speed). The EEG results demonstrated that a wide range of frequencies from delta band to gamma band were involved in walking. The EEG power spectral density (PSD) was significantly different in sensorimotor and posterior parietal areas between exoskeleton-assisted walking and non-exoskeleton walking. The EMG PSD difference was predominantly observed in the theta band and the gastrocnemius lateralis muscle. EEG-EMG PSD correlations differed among walking conditions. The alpha and beta bands were primarily involved in consistently increasing EEG-EMG PSD correlations across the walking conditions, while the theta band was primarily involved in consistently decreasing correlations as observed in the EEG involvement. However, there is no dominant frequency band as observed in the EMG involvement. Channels located over the sensorimotor area were primarily involved in consistently decreasing EEG-EMG PSD correlations and the outer-ring channels were involved in the increasing EEG-EMG PSD correlations. Our study revealed the spectral and spatial distributions relevant to overground walking and deepened the understanding of EEG and EMG representations during locomotion, which may inform the development of a more human-compatible exoskeleton and its usage in motor rehabilitation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
You probably believe that a latent relationship between the brain and lower limbs exists and it varies across different walking conditions (e.g., walking with or without an exoskeleton). Have you ever thought what the distributions of measured signals are? To address this question, we simultaneously collected electroencephalogram (EEG) and electromyogram (EMG) signals while healthy participants were conducting four overground walking conditions without any constraints (e.g., specific speed). The EEG results demonstrated that a wide range of frequencies from delta band to gamma band were involved in walking. The EEG power spectral density (PSD) was significantly different in sensorimotor and posterior parietal areas between exoskeleton-assisted walking and non-exoskeleton walking. The EMG PSD difference was predominantly observed in the theta band and the gastrocnemius lateralis muscle. EEG-EMG PSD correlations differed among walking conditions. The alpha and beta bands were primarily involved in consistently increasing EEG-EMG PSD correlations across the walking conditions, while the theta band was primarily involved in consistently decreasing correlations as observed in the EEG involvement. However, there is no dominant frequency band as observed in the EMG involvement. Channels located over the sensorimotor area were primarily involved in consistently decreasing EEG-EMG PSD correlations and the outer-ring channels were involved in the increasing EEG-EMG PSD correlations. Our study revealed the spectral and spatial distributions relevant to overground walking and deepened the understanding of EEG and EMG representations during locomotion, which may inform the development of a more human-compatible exoskeleton and its usage in motor rehabilitation.
Dimitrakopoulos, G. N., Kakkos, I., Dai, Z., Wang, H., Sgarbas, K., Thakor, N. V., Bezerianos, A., & Sun, Y. (2018). Functional Connectivity Analysis of Mental Fatigue Reveals Different Network Topological Alterations Between Driving and Vigilance Tasks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4), 740–749. https://doi.org/10.1109/tnsre.2018.2791936
@article{dimitrakopoulos2018functional,
title = {Functional Connectivity Analysis of Mental Fatigue Reveals Different Network Topological Alterations Between Driving and Vigilance Tasks},
author = {Georgios N. Dimitrakopoulos and Ioannis Kakkos and Zhongxiang Dai and Hongtao Wang and Kyriakos Sgarbas and Nitish V. Thakor and Anastasios Bezerianos and Yu Sun},
url = {https://doi.org/10.1109/tnsre.2018.2791936},
doi = {10.1109/tnsre.2018.2791936},
year = {2018},
date = {2018-01-01},
journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
volume = {26},
number = {4},
pages = {740–749},
publisher = {Institute of Electrical and Electronics Engineers},
abstract = {Despite the apparent importance of mental fatigue detection, a reliable application is hindered due to the incomprehensive understanding of the neural mechanisms of mental fatigue. In this paper, we investigated the topological alterations of functional brain networks in the theta band (4 - 7 Hz) of electroencephalography (EEG) data from 40 male subjects undergoing two distinct fatigue-inducing tasks: a low-intensity one-hour simulated driving and a high-demanding half-hour sustained attention task [psychomotor vigilance task (PVT)]. Behaviorally, subjects demonstrated a robust mental fatigue effect, as reflected by significantly declined performances in cognitive tasks prior and post these two tasks. Furthermore, characteristic path length presented a positive correlation with task duration, which led to a significant increase between the first and the last five minutes of both tasks, indicating a fatigue-related disruption in information processing efficiency. However, significantly increased clustering coefficient was revealed only in the driving task, suggesting distinct network reorganizations between the two fatigue-inducing tasks. Moreover, high accuracy (92% for driving; 97% for PVT) was achieved for fatigue classification with apparently different discriminative functional connectivity features. These findings augment our understanding of the complex nature of fatigue-related neural mechanisms and demonstrate the feasibility of using functional connectivity as neural biomarkers for applicable fatigue monitoring.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Despite the apparent importance of mental fatigue detection, a reliable application is hindered due to the incomprehensive understanding of the neural mechanisms of mental fatigue. In this paper, we investigated the topological alterations of functional brain networks in the theta band (4 - 7 Hz) of electroencephalography (EEG) data from 40 male subjects undergoing two distinct fatigue-inducing tasks: a low-intensity one-hour simulated driving and a high-demanding half-hour sustained attention task [psychomotor vigilance task (PVT)]. Behaviorally, subjects demonstrated a robust mental fatigue effect, as reflected by significantly declined performances in cognitive tasks prior and post these two tasks. Furthermore, characteristic path length presented a positive correlation with task duration, which led to a significant increase between the first and the last five minutes of both tasks, indicating a fatigue-related disruption in information processing efficiency. However, significantly increased clustering coefficient was revealed only in the driving task, suggesting distinct network reorganizations between the two fatigue-inducing tasks. Moreover, high accuracy (92% for driving; 97% for PVT) was achieved for fatigue classification with apparently different discriminative functional connectivity features. These findings augment our understanding of the complex nature of fatigue-related neural mechanisms and demonstrate the feasibility of using functional connectivity as neural biomarkers for applicable fatigue monitoring.
Dimitrakopoulos, G. N., Kakkos, I., Dai, Z., Lim, J., Souza, J., Bezerianos, A., & Sun, Y. (2017). Task-Independent Mental Workload Classification Based Upon Common Multiband EEG Cortical Connectivity. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11), 1940–1949. https://doi.org/10.1109/tnsre.2017.2701002
@article{dimitrakopoulos2017task,
title = {Task-Independent Mental Workload Classification Based Upon Common Multiband EEG Cortical Connectivity},
author = {Georgios N. Dimitrakopoulos and Ioannis Kakkos and Zhongxiang Dai and Julian Lim and Joshua Souza and Anastasios Bezerianos and Yu Sun},
url = {https://doi.org/10.1109/tnsre.2017.2701002},
doi = {10.1109/tnsre.2017.2701002},
year = {2017},
date = {2017-01-01},
journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
volume = {25},
number = {11},
pages = {1940–1949},
publisher = {Institute of Electrical and Electronics Engineers},
abstract = {Efficient classification of mental workload, an important issue in neuroscience, is limited, so far to single task, while cross-task classification remains a challenge. Furthermore, network approaches have emerged as a promising direction for studying the complex organization of the brain, enabling easier interpretation of various mental states. In this paper, using two mental tasks (N-back and mental arithmetic), we present a framework for cross- as well as within-task workload discrimination by utilizing multiband electroencephalography (EEG) cortical brain connectivity. In detail, we constructed functional networks in EEG source space in different frequency bands and considering the individual functional connections as classification features, we identified salient feature subsets based on a sequential feature selection algorithm. These connectivity subsets were able to provide accuracy of 87% for cross-task, 88% for N-back task, and 86% for mental arithmetic task. In conclusion, our method achieved to detect a small number of discriminative interactions among brain areas, leading to high accuracy in both within-task and cross-task classifications. In addition, the identified functional connectivity features, the majority of which were detected in frontal areas in theta and beta frequency bands, helped delineate the shared as well as the distinct neural mechanisms of the two mental tasks.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Efficient classification of mental workload, an important issue in neuroscience, is limited, so far to single task, while cross-task classification remains a challenge. Furthermore, network approaches have emerged as a promising direction for studying the complex organization of the brain, enabling easier interpretation of various mental states. In this paper, using two mental tasks (N-back and mental arithmetic), we present a framework for cross- as well as within-task workload discrimination by utilizing multiband electroencephalography (EEG) cortical brain connectivity. In detail, we constructed functional networks in EEG source space in different frequency bands and considering the individual functional connections as classification features, we identified salient feature subsets based on a sequential feature selection algorithm. These connectivity subsets were able to provide accuracy of 87% for cross-task, 88% for N-back task, and 86% for mental arithmetic task. In conclusion, our method achieved to detect a small number of discriminative interactions among brain areas, leading to high accuracy in both within-task and cross-task classifications. In addition, the identified functional connectivity features, the majority of which were detected in frontal areas in theta and beta frequency bands, helped delineate the shared as well as the distinct neural mechanisms of the two mental tasks.
Dimitrakopoulos, G. N., Sun, Y., Ardian, K., Nitish, T., & Bezerianos, A. (2016). A method for cross-task mental workload classification based on brain connectivity. Frontiers in Human Neuroscience, 10. https://doi.org/10.3389/conf.fnhum.2016.220.00002
@article{dimitrakopoulos2016method,
title = {A method for cross-task mental workload classification based on brain connectivity},
author = {Georgios N. Dimitrakopoulos and Yu Sun and Kevin Ardian and Thakor Nitish and Anastasios Bezerianos},
url = {https://doi.org/10.3389/conf.fnhum.2016.220.00002},
doi = {10.3389/conf.fnhum.2016.220.00002},
year = {2016},
date = {2016-01-01},
journal = {Frontiers in Human Neuroscience},
volume = {10},
publisher = {Frontiers Media},
abstract = {Frontiers Events is a rapidly growing calendar management system dedicated to the scheduling of academic events. This includes announcements and invitations, participant listings and search functionality, abstract handling and publication, related events and post-event exchanges. Whether an organizer or participant, make your event a Frontiers Event!},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Frontiers Events is a rapidly growing calendar management system dedicated to the scheduling of academic events. This includes announcements and invitations, participant listings and search functionality, abstract handling and publication, related events and post-event exchanges. Whether an organizer or participant, make your event a Frontiers Event!
Dimitrakopoulou, K., Dimitrakopoulos, G. N., Wilk, E., Tsimpouris, C., Sgarbas, K., Schughart, K., & Bezerianos, A. (2014). Influenza A Immunomics and Public Health Omics: The Dynamic Pathway Interplay in Host Response to H1N1 Infection. OMICS A Journal of Integrative Biology, 18(3), 167–183. https://doi.org/10.1089/omi.2013.0062
@article{dimitrakopoulou2014influenza,
title = {Influenza A Immunomics and Public Health Omics: The Dynamic Pathway Interplay in Host Response to H1N1 Infection},
author = {Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and Esther Wilk and Charalampos Tsimpouris and Kyriakos Sgarbas and Klaus Schughart and Anastasios Bezerianos},
url = {https://doi.org/10.1089/omi.2013.0062},
doi = {10.1089/omi.2013.0062},
year = {2014},
date = {2014-01-01},
journal = {OMICS A Journal of Integrative Biology},
volume = {18},
number = {3},
pages = {167–183},
publisher = {Mary Ann Liebert, Inc.},
abstract = {Towards unraveling the influenza A (H1N1) immunome, this work aims at constructing the murine host response pathway interactome. To accomplish that, an ensemble of dynamic and time-varying Gene Regulatory Network Inference methodologies was recruited to set a confident interactome based on mouse time series transcriptome data (day 1-day 60). The proposed H1N1 interactome demonstrated significant transformations among activated and suppressed pathways in time. Enhanced interplay was observed at day 1, while the maximal network complexity was reached at day 8 (correlated with viral clearance and iBALT tissue formation) and one interaction was present at day 40. Next, we searched for common interactivity features between the murine-adapted PR8 strain and other influenza A subtypes/strains. For this, two other interactomes, describing the murine host response against H5N1 and H1N1pdm, were constructed, which in turn validated many of the observed interactions (in the period day 1-day 7). The H1N1 interactome revealed the role of cell cycle both in innate and adaptive immunity (day 1-day 14). Also, pathogen sensory pathways (e.g., RIG-I) displayed long-lasting association with cytokine/chemokine signaling (until day 8). Interestingly, the above observations were also supported by the H5N1 and H1N1pdm models. It also elucidated the enhanced coupling of the activated innate pathways with the suppressed PPAR signaling to keep low inflammation until viral clearance (until day 14). Further, it showed that interactions reflecting phagocytosis processes continued long after the viral clearance and the establishment of adaptive immunity (day 8-day 40). Additionally, interactions involving B cell receptor pathway were evident since day 1. These results collectively inform the emerging field of public health omics and future clinical studies aimed at deciphering dynamic host responses to infectious agents.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Towards unraveling the influenza A (H1N1) immunome, this work aims at constructing the murine host response pathway interactome. To accomplish that, an ensemble of dynamic and time-varying Gene Regulatory Network Inference methodologies was recruited to set a confident interactome based on mouse time series transcriptome data (day 1-day 60). The proposed H1N1 interactome demonstrated significant transformations among activated and suppressed pathways in time. Enhanced interplay was observed at day 1, while the maximal network complexity was reached at day 8 (correlated with viral clearance and iBALT tissue formation) and one interaction was present at day 40. Next, we searched for common interactivity features between the murine-adapted PR8 strain and other influenza A subtypes/strains. For this, two other interactomes, describing the murine host response against H5N1 and H1N1pdm, were constructed, which in turn validated many of the observed interactions (in the period day 1-day 7). The H1N1 interactome revealed the role of cell cycle both in innate and adaptive immunity (day 1-day 14). Also, pathogen sensory pathways (e.g., RIG-I) displayed long-lasting association with cytokine/chemokine signaling (until day 8). Interestingly, the above observations were also supported by the H5N1 and H1N1pdm models. It also elucidated the enhanced coupling of the activated innate pathways with the suppressed PPAR signaling to keep low inflammation until viral clearance (until day 14). Further, it showed that interactions reflecting phagocytosis processes continued long after the viral clearance and the establishment of adaptive immunity (day 8-day 40). Additionally, interactions involving B cell receptor pathway were evident since day 1. These results collectively inform the emerging field of public health omics and future clinical studies aimed at deciphering dynamic host responses to infectious agents.
Dimitrakopoulos, G. N., Vrahatis, A. G., Dimitrakopoulou, K., Tsakalidis, A., Sgarbas, K., & Bezerianos, A. (2013). Module-Based Cross-Tissue Pathway Identification in Aging. Transactions of Japanese Society for Medical and Biological Engineering, 51. https://doi.org/10.11239/jsmbe.51.r-170
@article{dimitrakopoulos2013module,
title = {Module-Based Cross-Tissue Pathway Identification in Aging},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Konstantina Dimitrakopoulou and Athanasios Tsakalidis and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.11239/jsmbe.51.r-170},
doi = {10.11239/jsmbe.51.r-170},
year = {2013},
date = {2013-01-01},
journal = {Transactions of Japanese Society for Medical and Biological Engineering},
volume = {51},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Dimitrakopoulou, K., Dimitrakopoulos, G. N., Sgarbas, K., & Bezerianos, A. (2013). Revealing Aging Mechanisms from Ensemble Gene Network Inference Methods. Transactions of Japanese Society for Medical and Biological Engineering, 51. https://doi.org/10.11239/jsmbe.51.r-161
@article{dimitrakopoulou2013revealing,
title = {Revealing Aging Mechanisms from Ensemble Gene Network Inference Methods},
author = {Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.11239/jsmbe.51.r-161},
doi = {10.11239/jsmbe.51.r-161},
year = {2013},
date = {2013-01-01},
journal = {Transactions of Japanese Society for Medical and Biological Engineering},
volume = {51},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Dimitrakopoulou, K., Dimitrakopoulos, G. N., Sgarbas, K., & Bezerianos, A. (2013). Tamoxifen Integromics and Personalized Medicine: Dynamic Modular Transformations Underpinning Response to Tamoxifen in Breast Cancer Treatment. OMICS A Journal of Integrative Biology, 18(1), 15–33. https://doi.org/10.1089/omi.2013.0055
@article{dimitrakopoulou2013tamoxifen,
title = {Tamoxifen Integromics and Personalized Medicine: Dynamic Modular Transformations Underpinning Response to Tamoxifen in Breast Cancer Treatment},
author = {Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1089/omi.2013.0055},
doi = {10.1089/omi.2013.0055},
year = {2013},
date = {2013-01-01},
journal = {OMICS A Journal of Integrative Biology},
volume = {18},
number = {1},
pages = {15–33},
publisher = {Mary Ann Liebert, Inc.},
abstract = {Recent advances in pharmacogenomics technologies allow bold steps to be taken towards personalized medicine, more accurate health planning, and personalized drug development. In this framework, systems pharmacology network-based approaches offer an appealing way for integrating multi-omics data and set the basis for defining systems-level drug response biomarkers. On the road to individualized tamoxifen treatment in estrogen receptor-positive breast cancer patients, we examine the dynamics of the attendant pharmacological response mechanisms. By means of an "integromics" network approach, we assessed the tamoxifen effect through the way the high-order organization of interactome (i.e., the modules) is perturbed. To accomplish that, first we integrated the time series transcriptome data with the human protein interaction data, and second, an efficient module-detecting algorithm was applied onto the composite graphs. Our findings show that tamoxifen induces severe modular transformations on specific areas of the interactome. Our modular biomarkers in response to tamoxifen attest to the immunomodulatory role of tamoxifen, and further reveal that it deregulates cell cycle and apoptosis pathways, while coordinating the proteasome and basal transcription factors. To the best of our knowledge, this is the first report that informs the fields of personalized medicine and clinical pharmacology about the actual dynamic interactome response to tamoxifen administration.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Recent advances in pharmacogenomics technologies allow bold steps to be taken towards personalized medicine, more accurate health planning, and personalized drug development. In this framework, systems pharmacology network-based approaches offer an appealing way for integrating multi-omics data and set the basis for defining systems-level drug response biomarkers. On the road to individualized tamoxifen treatment in estrogen receptor-positive breast cancer patients, we examine the dynamics of the attendant pharmacological response mechanisms. By means of an "integromics" network approach, we assessed the tamoxifen effect through the way the high-order organization of interactome (i.e., the modules) is perturbed. To accomplish that, first we integrated the time series transcriptome data with the human protein interaction data, and second, an efficient module-detecting algorithm was applied onto the composite graphs. Our findings show that tamoxifen induces severe modular transformations on specific areas of the interactome. Our modular biomarkers in response to tamoxifen attest to the immunomodulatory role of tamoxifen, and further reveal that it deregulates cell cycle and apoptosis pathways, while coordinating the proteasome and basal transcription factors. To the best of our knowledge, this is the first report that informs the fields of personalized medicine and clinical pharmacology about the actual dynamic interactome response to tamoxifen administration.
Βιβλία
Vrahatis, A., Dimitrakopoulos, G. N., & Vlamos, P. (2024). Modeling and Analysis of Complex Networks in Molecular Biology and Neuroscience: Using R and Python. Athens: Kallipos, Open Academic Editions. https://doi.org/10.57713/kallipos-1055
@book{vrahatis2024modeling,
title = {Modeling and Analysis of Complex Networks in Molecular Biology and Neuroscience: Using R and Python},
author = {Aristidis Vrahatis and Georgios N. Dimitrakopoulos and Panagiotis Vlamos},
url = {https://doi.org/10.57713/kallipos-1055},
doi = {10.57713/kallipos-1055},
isbn = {978-618-228-305-9},
year = {2024},
date = {2024-01-01},
publisher = {Kallipos, Open Academic Editions},
address = {Athens},
abstract = {A complex system consists of many components, which may interact with each other in several ways. Graph/Network-based modelling is a suitable approach for understanding such complex systems. Also, machine learning techniques now play an important role in analysing large volumes of data. Two such systems in the wider area of Biology, which are still not fully understood, are the cell and the brain. Bioinformatics is an interdisciplinary scientific field that develops methodologies and software tools for understanding biological data, which can focus on the genomic, transcriptomic, proteomic or metabolomic level. Today, with the recent techniques of Molecular Biology, a huge amount of data is produced; thus, adapted algorithmic techniques are required for their efficient processing. In the field of Computational Neuroscience, we focus on electroencephalography (EEG), which captures signals from multiple areas of the brain. These data require careful pre-processing to be analysed and provide useful information. The most advanced analysis techniques include the generation of networks in time and frequency domains. Therefore, in this book, we present in detail the most recent and widely used methods in the literature for graph analysis of distinct types of data in Molecular Biology and Neurosciences.},
note = {Greek-language textbook: Μοντελοποίηση και Ανάλυση Πολύπλοκων Δικτύων της Μοριακής Βιολογίας και των Νευροεπιστημών. Με τη χρήση των R και Python},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
A complex system consists of many components, which may interact with each other in several ways. Graph/Network-based modelling is a suitable approach for understanding such complex systems. Also, machine learning techniques now play an important role in analysing large volumes of data. Two such systems in the wider area of Biology, which are still not fully understood, are the cell and the brain. Bioinformatics is an interdisciplinary scientific field that develops methodologies and software tools for understanding biological data, which can focus on the genomic, transcriptomic, proteomic or metabolomic level. Today, with the recent techniques of Molecular Biology, a huge amount of data is produced; thus, adapted algorithmic techniques are required for their efficient processing. In the field of Computational Neuroscience, we focus on electroencephalography (EEG), which captures signals from multiple areas of the brain. These data require careful pre-processing to be analysed and provide useful information. The most advanced analysis techniques include the generation of networks in time and frequency domains. Therefore, in this book, we present in detail the most recent and widely used methods in the literature for graph analysis of distinct types of data in Molecular Biology and Neurosciences.
Κεφάλαια σε Συλλογικούς Τόμους
Dimitrakopoulos, G. N. (2023). From Raw EEG Signals to Brain Networks: An EEGLAB Tutorial. In Handbook of Computational Neurodegeneration (pp. 1–16). Springer International Publishing. https://doi.org/10.1007/978-3-319-75479-6_26-1
@incollection{dimitrakopoulos2023raw,
title = {From Raw EEG Signals to Brain Networks: An EEGLAB Tutorial},
author = {Georgios N. Dimitrakopoulos},
url = {https://doi.org/10.1007/978-3-319-75479-6_26-1},
doi = {10.1007/978-3-319-75479-6_26-1},
isbn = {9783319754796},
year = {2023},
date = {2023-01-01},
booktitle = {Handbook of Computational Neurodegeneration},
pages = {1–16},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Koumadorakis, D. E., Dimitrakopoulos, G. N., Krokidis, M. G., & Vrahatis, A. G. (2022). Gene Regulatory Network Reconstruction Using Single-Cell RNA-Sequencing. In Handbook of Computational Neurodegeneration (pp. 1–15). Springer International Publishing. https://doi.org/10.1007/978-3-319-75479-6_18-1
@incollection{koumadorakis2022gene,
title = {Gene Regulatory Network Reconstruction Using Single-Cell RNA-Sequencing},
author = {Dimitrios E. Koumadorakis and Georgios N. Dimitrakopoulos and Marios G. Krokidis and Aristidis G. Vrahatis},
url = {https://doi.org/10.1007/978-3-319-75479-6_18-1},
doi = {10.1007/978-3-319-75479-6_18-1},
isbn = {9783319754796},
year = {2022},
date = {2022-01-01},
booktitle = {Handbook of Computational Neurodegeneration},
pages = {1–15},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Kakkos, I., Miloulis, S.-T., Gkiatis, K., Dimitrakopoulos, G. N., & Matsopoulos, G. K. (2020). Human–Machine Interfaces for Motor Rehabilitation. In Studies in Computational Intelligence (pp. 1–16). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-662-61114-2_1
@incollection{kakkos2020humanmachine,
title = {Human–Machine Interfaces for Motor Rehabilitation},
author = {Ioannis Kakkos and Stavros-Theofanis Miloulis and Kostakis Gkiatis and Georgios N. Dimitrakopoulos and George K. Matsopoulos},
url = {https://doi.org/10.1007/978-3-662-61114-2_1},
doi = {10.1007/978-3-662-61114-2_1},
isbn = {9783662611128},
year = {2020},
date = {2020-01-01},
booktitle = {Studies in Computational Intelligence},
pages = {1–16},
publisher = {Springer Berlin Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Άρθρα σε Πρακτικά Συνεδρίων
Dimitrakopoulos, G. N., Vrahatis, A. G., Choleva, V., Korfiatis, N., Karyotis, V., & Kourouthanassis, P. E. (2025). AutoGluon and TabPFN for Supply Chain Optimization. In 2025 IEEE International Conference on Big Data (BigData). Macau, China: IEEE.
@inproceedings{dimitrakopoulos2025autogluon,
title = {AutoGluon and TabPFN for Supply Chain Optimization},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and V. Choleva and Nikolaos Korfiatis and Vasileios Karyotis and Panos E. Kourouthanassis},
year = {2025},
date = {2025-01-01},
booktitle = {2025 IEEE International Conference on Big Data (BigData)},
publisher = {IEEE},
address = {Macau, China},
note = {IEEE BigData 2025, December 8-11, 2025, Macau, China},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Vrahatis, A. G., Panagiotopoulos, A., Korfiatis, N., Karyotis, V., & Kourouthanassis, P. E. (2025). Decision Support and Predictive Intelligence in Humanitarian Logistics: An Updated Overview. In 2025 IEEE International Conference on Big Data (BigData). Macau, China: IEEE.
@inproceedings{dimitrakopoulos2025decision,
title = {Decision Support and Predictive Intelligence in Humanitarian Logistics: An Updated Overview},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and A. Panagiotopoulos and Nikolaos Korfiatis and Vasileios Karyotis and Panos E. Kourouthanassis},
year = {2025},
date = {2025-01-01},
booktitle = {2025 IEEE International Conference on Big Data (BigData)},
publisher = {IEEE},
address = {Macau, China},
note = {IEEE BigData 2025, December 8-11, 2025, Macau, China},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Miloulis, S.-T., Kakkos, I., Kaliampakou, C., Zorzos, I., Dimitrakopoulos, G. N., Vezakis, I., Kouris, I., Anastasiou, A., & Matsopoulos, G. K. (2025). Feature-Level Explainability in EEG-Based Fatigue Detection Using LASSO and Functional Connectivity. In 2025 IEEE International Conference on Big Data (BigData) (pp. 6545–6551). IEEE. https://doi.org/10.1109/bigdata66926.2025.11401674
@inproceedings{miloulis2025feature,
title = {Feature-Level Explainability in EEG-Based Fatigue Detection Using LASSO and Functional Connectivity},
author = {Stavros-Theofanis Miloulis and Ioannis Kakkos and Christina Kaliampakou and Ioannis Zorzos and Georgios N. Dimitrakopoulos and Ioannis Vezakis and Ioannis Kouris and Athanasios Anastasiou and George K. Matsopoulos},
url = {https://doi.org/10.1109/bigdata66926.2025.11401674},
doi = {10.1109/bigdata66926.2025.11401674},
year = {2025},
date = {2025-01-01},
booktitle = {2025 IEEE International Conference on Big Data (BigData)},
pages = {6545–6551},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Karakatsoulis, D., Dimitrakopoulos, G. N., Vrahatis, A. G., Matzakos, N., & Doukakis, S. (2025). Learning Management System (LMS) Design Toward Precision Education Using Brain Data. In Advances in Experimental Medicine and Biology (pp. 519–527). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-03394-9_51
@inproceedings{karakatsoulis2025learning,
title = {Learning Management System (LMS) Design Toward Precision Education Using Brain Data},
author = {Dimosthenis Karakatsoulis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Nikolaos Matzakos and Spyridon Doukakis},
url = {https://doi.org/10.1007/978-3-032-03394-9_51},
doi = {10.1007/978-3-032-03394-9_51},
isbn = {9783032033932},
year = {2025},
date = {2025-01-01},
booktitle = {Advances in Experimental Medicine and Biology},
volume = {1489},
pages = {519–527},
publisher = {Springer Nature Switzerland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gasparinatou, M. M., Dimitrakopoulos, G. N., Vrahatis, A. G., & Vlamos, P. (2025). Minimum Redundancy Maximum Relevance Feature Selection–Application on Single-Cell RNA Sequencing Dataset. In Advances in Experimental Medicine and Biology (pp. 213–221). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-03398-7_22
@inproceedings{gasparinatou2025minimum,
title = {Minimum Redundancy Maximum Relevance Feature Selection–Application on Single-Cell RNA Sequencing Dataset},
author = {Mirto M. Gasparinatou and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Panagiotis Vlamos},
url = {https://doi.org/10.1007/978-3-032-03398-7_22},
doi = {10.1007/978-3-032-03398-7_22},
isbn = {9783032033970},
year = {2025},
date = {2025-01-01},
booktitle = {Advances in Experimental Medicine and Biology},
volume = {1487},
pages = {213–221},
publisher = {Springer Nature Switzerland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Koumadorakis, D. E., Krokidis, M. G., Dimitrakopoulos, G. N., & Vrahatis, A. G. (2023). A Consensus Gene Regulatory Network for Neurodegenerative Diseases Using Single-Cell RNA-Seq Data. In Advances in Experimental Medicine and Biology (pp. 215–224). Springer International Publishing. https://doi.org/10.1007/978-3-031-31978-5_20
@inproceedings{koumadorakis2023consensus,
title = {A Consensus Gene Regulatory Network for Neurodegenerative Diseases Using Single-Cell RNA-Seq Data},
author = {Dimitrios E. Koumadorakis and Marios G. Krokidis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis},
url = {https://doi.org/10.1007/978-3-031-31978-5_20},
doi = {10.1007/978-3-031-31978-5_20},
isbn = {9783031319778},
year = {2023},
date = {2023-01-01},
booktitle = {Advances in Experimental Medicine and Biology},
volume = {1423},
pages = {215–224},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lazaros, K., Dimitrakopoulos, G. N., Vlamos, P., & Vrahatis, A. G. (2023). A Gene Selection Strategy for Enhancing Single-Cell RNA-Seq Data Integration. In Advances in Biomedical Sciences, Engineering and Technology (ABSET) Conference (pp. 12). MDPI. https://doi.org/10.3390/engproc2023050012
@inproceedings{lazaros2023gene,
title = {A Gene Selection Strategy for Enhancing Single-Cell RNA-Seq Data Integration},
author = {Konstantinos Lazaros and Georgios N. Dimitrakopoulos and Panagiotis Vlamos and Aristidis G. Vrahatis},
url = {https://doi.org/10.3390/engproc2023050012},
doi = {10.3390/engproc2023050012},
year = {2023},
date = {2023-01-01},
booktitle = {Advances in Biomedical Sciences, Engineering and Technology (ABSET) Conference},
pages = {12},
publisher = {MDPI},
abstract = {Cancer remains a pervasive and formidable disease within modern societies, necessitating the utilization of advanced techniques in both diagnosis and therapy. Molecular biology has emerged as a crucial tool in deciphering the underlying biological mechanisms that contribute to various types of cancer. Notably, single-cell sequencing has garnered significant attention as a state-of-the-art method for profiling gene expression in individual cells, unveiling previously concealed mechanisms and biological phenomena. With the abundance of single-cell datasets available, there is a pressing need to integrate related datasets into larger ones to enhance our understanding of biological processes and augment predictive capabilities. In this study, we investigated the impact of gene selection, achieved through the implementation of feature selection techniques, on the integration of single-cell datasets. By systematically exploring the effects of gene selection, we aim to enhance the integration process, leading to improved biological insights and enhanced predictive power. The proposed method aims to enhance two cutting-edge data integration methodologies for single-cell RNA sequencing (scRNA-seq). The method utilizes a strategy that combines two key components: a statistical approach to isolate the high variability in gene expression across cells or samples and a feature selection strategy based on XgBoost to keep genes that are important for distinguishing among healthy and cancerous cells.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Cancer remains a pervasive and formidable disease within modern societies, necessitating the utilization of advanced techniques in both diagnosis and therapy. Molecular biology has emerged as a crucial tool in deciphering the underlying biological mechanisms that contribute to various types of cancer. Notably, single-cell sequencing has garnered significant attention as a state-of-the-art method for profiling gene expression in individual cells, unveiling previously concealed mechanisms and biological phenomena. With the abundance of single-cell datasets available, there is a pressing need to integrate related datasets into larger ones to enhance our understanding of biological processes and augment predictive capabilities. In this study, we investigated the impact of gene selection, achieved through the implementation of feature selection techniques, on the integration of single-cell datasets. By systematically exploring the effects of gene selection, we aim to enhance the integration process, leading to improved biological insights and enhanced predictive power. The proposed method aims to enhance two cutting-edge data integration methodologies for single-cell RNA sequencing (scRNA-seq). The method utilizes a strategy that combines two key components: a statistical approach to isolate the high variability in gene expression across cells or samples and a feature selection strategy based on XgBoost to keep genes that are important for distinguishing among healthy and cancerous cells.
Dimitrakopoulos, G. N., Lazaros, K., Krokidis, M. G., Exarchos, T., Vrahatis, A. G., & Vlamos, P. (2023). A Graph-Based Approach to Integrate Large-Scale Drug and Protein Data for Alzheimer’s Disease Drug Repurposing. In 2023 IEEE International Conference on Big Data (BigData) (pp. 4584–4587). IEEE. https://doi.org/10.1109/bigdata59044.2023.10386766
@inproceedings{dimitrakopoulos2023graph,
title = {A Graph-Based Approach to Integrate Large-Scale Drug and Protein Data for Alzheimer’s Disease Drug Repurposing},
author = {Georgios N. Dimitrakopoulos and Konstantinos Lazaros and Marios G. Krokidis and Themis Exarchos and Aristidis G. Vrahatis and Panagiotis Vlamos},
url = {https://doi.org/10.1109/bigdata59044.2023.10386766},
doi = {10.1109/bigdata59044.2023.10386766},
year = {2023},
date = {2023-01-01},
booktitle = {2023 IEEE International Conference on Big Data (BigData)},
pages = {4584–4587},
publisher = {IEEE},
abstract = {Alzheimer’s Disease (AD) remains a formidable challenge in neurodegenerative research, necessitating innovative approaches to uncover novel therapeutic strategies. This study presents a graph-based approach to integrate large-scale drug and protein data, aiming to identify potential drug repurposing candidates for AD. Our methodology constructs a comprehensive graph incorporating protein-protein interactions and drug-protein relations, providing a multifaceted view of the intricate relationships within the biological and pharmacological landscape. By leveraging this graph, we conduct an in-depth analysis to explore various drug repurposing possibilities, focusing on the alignment of AD-related single-cell transcriptomic data. Our approach enables the identification of promising drug candidates by examining the connectivity and interaction patterns within the graph, revealing potential therapeutic targets and drug synergies that may be beneficial for AD treatment. The integration of diverse data types allows for a more holistic understanding of the underlying molecular mechanisms and drug interactions. Through this graph-based analysis, we uncover several promising drug repurposing candidates, providing a foundation for further experimental validation and clinical investigation. This study underscores the potential of leveraging large-scale data and graph-based methodologies in drug repurposing efforts for neurodegenerative diseases, contributing to the advancement of therapeutic research in AD. Our findings illuminate the importance of integrative data analysis in biomedical research, paving the way for the development of more effective and targeted therapeutic interventions for AD.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Alzheimer’s Disease (AD) remains a formidable challenge in neurodegenerative research, necessitating innovative approaches to uncover novel therapeutic strategies. This study presents a graph-based approach to integrate large-scale drug and protein data, aiming to identify potential drug repurposing candidates for AD. Our methodology constructs a comprehensive graph incorporating protein-protein interactions and drug-protein relations, providing a multifaceted view of the intricate relationships within the biological and pharmacological landscape. By leveraging this graph, we conduct an in-depth analysis to explore various drug repurposing possibilities, focusing on the alignment of AD-related single-cell transcriptomic data. Our approach enables the identification of promising drug candidates by examining the connectivity and interaction patterns within the graph, revealing potential therapeutic targets and drug synergies that may be beneficial for AD treatment. The integration of diverse data types allows for a more holistic understanding of the underlying molecular mechanisms and drug interactions. Through this graph-based analysis, we uncover several promising drug repurposing candidates, providing a foundation for further experimental validation and clinical investigation. This study underscores the potential of leveraging large-scale data and graph-based methodologies in drug repurposing efforts for neurodegenerative diseases, contributing to the advancement of therapeutic research in AD. Our findings illuminate the importance of integrative data analysis in biomedical research, paving the way for the development of more effective and targeted therapeutic interventions for AD.
Dimitrakopoulos, G. N., Lazaros, K., Vrahatis, A. G., Krokidis, M. G., Skolariki, K., Vlamos, P., & Exarchos, T. (2023). A Machine Learning approach combining omics data for Alzheimer’s Disease analysis. In Book of Proceedings (pp. 342–345). Institute for Information Technologies, University of Kragujevac. https://doi.org/10.46793/iccbi23.342d
@inproceedings{dimitrakopoulos2023machine,
title = {A Machine Learning approach combining omics data for Alzheimer’s Disease analysis},
author = {Georgios N. Dimitrakopoulos and Konstantinos Lazaros and Aristidis G. Vrahatis and Marios G. Krokidis and Konstantina Skolariki and Panagiotis Vlamos and Themis Exarchos},
url = {https://doi.org/10.46793/iccbi23.342d},
doi = {10.46793/iccbi23.342d},
year = {2023},
date = {2023-01-01},
booktitle = {Book of Proceedings},
pages = {342–345},
publisher = {Institute for Information Technologies, University of Kragujevac},
abstract = {Alzheimer’s disease (AD) is a complex neurological disorder whose underlying mechanisms remain elusive to this day. Molecular biology methodologies, especially techniques like single-cell RNA sequencing (scRNA-seq), offer unparalleled granularity in deciphering the disease’s cellular intricacies. However, despite the potential of scRNA-seq, comprehensive machine-learning analyses are yet to be fully harnessed. Emphasizing the multi-omics machine-learning-based approaches, which integrate diverse single-cell omics datasets, could highlight novel therapeutic targets and deepen our understanding of AD’s intricate nature. In this work, we propose a machine-learning-based method to embed gene expression into a protein interaction graph. Specifically, we model each interaction with a regression model on the participating genes and we use the R2 score as edge weight. Our aim is to detect parts of the PPI graph that differentiate between control and disease conditions. Application on a scRNA-seq AD dataset managed to identify interactions forming small subgraphs, which consisted of genes involved with biological processes related to neurons.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Alzheimer’s disease (AD) is a complex neurological disorder whose underlying mechanisms remain elusive to this day. Molecular biology methodologies, especially techniques like single-cell RNA sequencing (scRNA-seq), offer unparalleled granularity in deciphering the disease’s cellular intricacies. However, despite the potential of scRNA-seq, comprehensive machine-learning analyses are yet to be fully harnessed. Emphasizing the multi-omics machine-learning-based approaches, which integrate diverse single-cell omics datasets, could highlight novel therapeutic targets and deepen our understanding of AD’s intricate nature. In this work, we propose a machine-learning-based method to embed gene expression into a protein interaction graph. Specifically, we model each interaction with a regression model on the participating genes and we use the R2 score as edge weight. Our aim is to detect parts of the PPI graph that differentiate between control and disease conditions. Application on a scRNA-seq AD dataset managed to identify interactions forming small subgraphs, which consisted of genes involved with biological processes related to neurons.
Krokidis, M. G., Dimitrakopoulos, G. N., Exarchos, T. P., Vrahatis, A. G., & Vlamos, P. (2023). Advanced Big Data Analysis for Deciphering the Role of Protein Misfolding and Interactions in the Pathogenesis of Alzheimer’s Disease. In 2023 IEEE International Conference on Big Data (BigData) (pp. 4614–4617). IEEE. https://doi.org/10.1109/bigdata59044.2023.10386706
@inproceedings{krokidis2023advanced,
title = {Advanced Big Data Analysis for Deciphering the Role of Protein Misfolding and Interactions in the Pathogenesis of Alzheimer’s Disease},
author = {Marios G. Krokidis and Georgios N. Dimitrakopoulos and Themis P. Exarchos and Aristidis G. Vrahatis and Panagiotis Vlamos},
url = {https://doi.org/10.1109/bigdata59044.2023.10386706},
doi = {10.1109/bigdata59044.2023.10386706},
year = {2023},
date = {2023-01-01},
booktitle = {2023 IEEE International Conference on Big Data (BigData)},
pages = {4614–4617},
publisher = {IEEE},
abstract = {Predicting the three-dimensional structure of proteins directly from their sequence of amino acids remains a challenge in biomedical research. Protein functionality depends not only on its sequence but also on the precise folding that occurs during the process of developing their tertiary structure. Misfolded proteins may lead to the generation of entities that are inherently toxic to the organism, such as the formation of amyloid fibrils in the context of Alzheimer’s disease. Herein, the structural conformation of specific missense mutations in proteins involved in Alzheimer’s disease was performed through computational analysis and prediction of the binding mode and multiplicity of them was further assessed. Our findings reveal direct sequence-to-structure motifs from single polypeptides and the received domains with the proper fold. Nevertheless, the positions with the particular deviations are most commonly accompanied by limited downward spikes in pLDDT value, suggesting lower prediction confidence and potential disorder.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Predicting the three-dimensional structure of proteins directly from their sequence of amino acids remains a challenge in biomedical research. Protein functionality depends not only on its sequence but also on the precise folding that occurs during the process of developing their tertiary structure. Misfolded proteins may lead to the generation of entities that are inherently toxic to the organism, such as the formation of amyloid fibrils in the context of Alzheimer’s disease. Herein, the structural conformation of specific missense mutations in proteins involved in Alzheimer’s disease was performed through computational analysis and prediction of the binding mode and multiplicity of them was further assessed. Our findings reveal direct sequence-to-structure motifs from single polypeptides and the received domains with the proper fold. Nevertheless, the positions with the particular deviations are most commonly accompanied by limited downward spikes in pLDDT value, suggesting lower prediction confidence and potential disorder.
Aslanis, I., Krokidis, M. G., Dimitrakopoulos, G. N., & Vrahatis, A. G. (2023). Identifying Network Biomarkers for Alzheimer’s Disease Using Single-Cell RNA Sequencing Data. In Advances in Experimental Medicine and Biology (pp. 207–214). Springer International Publishing. https://doi.org/10.1007/978-3-031-31978-5_19
@inproceedings{aslanis2023identifying,
title = {Identifying Network Biomarkers for Alzheimer’s Disease Using Single-Cell RNA Sequencing Data},
author = {Ioannis Aslanis and Marios G. Krokidis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis},
url = {https://doi.org/10.1007/978-3-031-31978-5_19},
doi = {10.1007/978-3-031-31978-5_19},
isbn = {9783031319778},
year = {2023},
date = {2023-01-01},
booktitle = {Advances in Experimental Medicine and Biology},
volume = {1423},
pages = {207–214},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mantellos, G., Exarchos, T. P., Dimitrakopoulos, G. N., Vlamos, P., Papastamatiou, N., Karaiskos, K., Minos, P., Alexandridis, T., Axiotopoulos, S., Tsakiridis, D., Avramoudis, V., Vasiliadis, A., & Stagakis, S. (2023). Integrating Wearable Sensors and Machine Learning for the Detection of Critical Events in Industry Workers. In Advances in Experimental Medicine and Biology (pp. 213–222). Springer International Publishing. https://doi.org/10.1007/978-3-031-31982-2_23
@inproceedings{mantellos2023integrating,
title = {Integrating Wearable Sensors and Machine Learning for the Detection of Critical Events in Industry Workers},
author = {George Mantellos and Themis P. Exarchos and Georgios N. Dimitrakopoulos and Panagiotis Vlamos and Nikolaos Papastamatiou and Konstantinos Karaiskos and Panagiotis Minos and Theofanis Alexandridis and Stelios Axiotopoulos and Dimitrios Tsakiridis and Vasilios Avramoudis and Anastasios Vasiliadis and Stylianos Stagakis},
url = {https://doi.org/10.1007/978-3-031-31982-2_23},
doi = {10.1007/978-3-031-31982-2_23},
isbn = {9783031319815},
year = {2023},
date = {2023-01-01},
booktitle = {Advances in Experimental Medicine and Biology},
volume = {1424},
pages = {213–222},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Krokidis, M. G., Vrahatis, A. G., Dimitrakopoulos, G. N., Skolariki, K., Vlamos, P., & Exarchos, T. P. (2023). Structural simulations predicting protein folding in Alzheimer's disease. In 2nd International Conference on Chemo and Bioinformatics (ICCBIKG 2023). Kragujevac, Serbia.
@inproceedings{krokidis2023structural,
title = {Structural simulations predicting protein folding in Alzheimer's disease},
author = {Marios G. Krokidis and Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Konstantina Skolariki and Panagiotis Vlamos and Themis P. Exarchos},
year = {2023},
date = {2023-01-01},
booktitle = {2nd International Conference on Chemo and Bioinformatics (ICCBIKG 2023)},
address = {Kragujevac, Serbia},
note = {September 28-29, 2023},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Giannakopoulou, O., Kakkos, I., Dimitrakopoulos, G. N., Sun, Y., Matsopoulos, G. K., & Koutsouris, D. (2023). Time-Dependent Adaptations of Brain Networks in Driving Fatigue. In ABSET 2023 (pp. 6). MDPI. https://doi.org/10.3390/engproc2023050006
@inproceedings{giannakopoulou2023time,
title = {Time-Dependent Adaptations of Brain Networks in Driving Fatigue},
author = {Olympia Giannakopoulou and Ioannis Kakkos and Georgios N. Dimitrakopoulos and Yu Sun and George K. Matsopoulos and Dimitris Koutsouris},
url = {https://doi.org/10.3390/engproc2023050006},
doi = {10.3390/engproc2023050006},
year = {2023},
date = {2023-01-01},
booktitle = {ABSET 2023},
pages = {6},
publisher = {MDPI},
abstract = {Driving with fatigue is a major contributor to traffic accidents and is closely linked to central nervous system functions. To investigate the evolution of brain dynamics during simulated driving under different EEG rhythms, we conducted an experiment in which participants performed a 1 h driving task while their EEG signals were recorded. We used the complex network theory to analyze data derived from the driving stimulation and found that as fatigue deepened, small-world metrics, namely the path lengths, clustering coefficients, and measures of efficiency (global, local, nodal), showed alterations against the driving time. Additionally, a major correlation (corr = 0.98) was observed between the cluster coefficient with local efficiency in all frequency bands (theta, alpha, beta). Our findings suggest that driving fatigue can cause significant trends in brain network characteristics, such as path length (m = −103 to −93), (m = 98) for specific rhythms (beta, alpha, theta band, respectively) and their related brain functions, which could serve as objective indicators when evaluating the fatigue level and in the future, preventing driving fatigue and its consequences.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Driving with fatigue is a major contributor to traffic accidents and is closely linked to central nervous system functions. To investigate the evolution of brain dynamics during simulated driving under different EEG rhythms, we conducted an experiment in which participants performed a 1 h driving task while their EEG signals were recorded. We used the complex network theory to analyze data derived from the driving stimulation and found that as fatigue deepened, small-world metrics, namely the path lengths, clustering coefficients, and measures of efficiency (global, local, nodal), showed alterations against the driving time. Additionally, a major correlation (corr = 0.98) was observed between the cluster coefficient with local efficiency in all frequency bands (theta, alpha, beta). Our findings suggest that driving fatigue can cause significant trends in brain network characteristics, such as path length (m = −103 to −93), (m = 98) for specific rhythms (beta, alpha, theta band, respectively) and their related brain functions, which could serve as objective indicators when evaluating the fatigue level and in the future, preventing driving fatigue and its consequences.
Miloulis, S.-T., Kakkos, I., Dimitrakopoulos, G. N., Sun, Y., Karanasiou, I. S., Asvestas, P. A., Ventouras, E.-C., & Matsopoulos, G. K. (2021). Evaluating Memory and Cognition via a Wearable EEG System: A Preliminary Study. In Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (pp. 52–66). Springer International Publishing. https://doi.org/10.1007/978-3-030-70569-5_4
@inproceedings{miloulis2021evaluating,
title = {Evaluating Memory and Cognition via a Wearable EEG System: A Preliminary Study},
author = {Stavros-Theofanis Miloulis and Ioannis Kakkos and Georgios N. Dimitrakopoulos and Yu Sun and Irene S. Karanasiou and Pantelis A. Asvestas and Errikos-Chaim Ventouras and George K. Matsopoulos},
url = {https://doi.org/10.1007/978-3-030-70569-5_4},
doi = {10.1007/978-3-030-70569-5_4},
isbn = {9783030705688},
year = {2021},
date = {2021-01-01},
booktitle = {Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering},
pages = {52–66},
publisher = {Springer International Publishing},
abstract = {Human memory comprises one of the most complex brain functions, attracting researchers to unveil the neural mechanisms governing its effective operation. In this respect, the current study examines the application of a wearable single-channel EEG to the interpretation of cognitive operations reflecting memory processes. For this purpose, we implemented a set of tasks for evaluating the participants’ processing skills and memory efficiency, in order to examine potential outcomes derived from a specialized cognitive training routine. The employed training method targeted the distinction of automatic and controlled processing and its effects on memory, while we also investigated transfer effects to untrained tasks. Based on the electrophysiological data recorded during the cognitive tasks, we computed measures of induced EEG activity for each frequency band to examine the influence of cognitive training on both task performance and brain activity, as well as whether the EEG metrics could provide insight into the underlying brain processes and augment the interpretation of behavioral outcomes. Ultimately, statistical analysis showed an apparent contribution of EEG in understanding the observed behavioral differences, while our training program had a clear impact on the participants’ performance and brain activity. Moreover, we observed the reported distinction between automatic and controlled memory processes which play an integral part in both ageing and cognitive impairments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Human memory comprises one of the most complex brain functions, attracting researchers to unveil the neural mechanisms governing its effective operation. In this respect, the current study examines the application of a wearable single-channel EEG to the interpretation of cognitive operations reflecting memory processes. For this purpose, we implemented a set of tasks for evaluating the participants’ processing skills and memory efficiency, in order to examine potential outcomes derived from a specialized cognitive training routine. The employed training method targeted the distinction of automatic and controlled processing and its effects on memory, while we also investigated transfer effects to untrained tasks. Based on the electrophysiological data recorded during the cognitive tasks, we computed measures of induced EEG activity for each frequency band to examine the influence of cognitive training on both task performance and brain activity, as well as whether the EEG metrics could provide insight into the underlying brain processes and augment the interpretation of behavioral outcomes. Ultimately, statistical analysis showed an apparent contribution of EEG in understanding the observed behavioral differences, while our training program had a clear impact on the participants’ performance and brain activity. Moreover, we observed the reported distinction between automatic and controlled memory processes which play an integral part in both ageing and cognitive impairments.
Krokidis, M. G., Dimitrakopoulos, G. N., Vrahatis, A. G., Exarchos, T. P., & Vlamos, P. (2021). Recent Dimensionality Reduction Techniques for Visualizing High-Dimensional Parkinson’s Disease Omics Data. In 2021 IEEE International Conference on Big Data (Big Data) (pp. 4460–4463). IEEE. https://doi.org/10.1109/bigdata52589.2021.9671736
@inproceedings{krokidis2021recent,
title = {Recent Dimensionality Reduction Techniques for Visualizing High-Dimensional Parkinson’s Disease Omics Data},
author = {Marios G. Krokidis and Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Themis P. Exarchos and Panagiotis Vlamos},
url = {https://doi.org/10.1109/bigdata52589.2021.9671736},
doi = {10.1109/bigdata52589.2021.9671736},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Conference on Big Data (Big Data)},
volume = {10},
pages = {4460–4463},
publisher = {IEEE},
abstract = {One challenge facing Systems Biology is the conversion of vast amounts of data into systematic and organized knowledge through automated processes. Improvements in experimental technologies have created an enormous pool of heterogeneous omics data such as genomics, proteomics and metabolomics. Exporting insights of these datasets can lead to important discoveries for complex pathologies such as age-related neurodegenerative disorders and specifically Parkinson's disease (PD). However, such data are characterized by huge dimensionality which increases their complexity for various data analyses as well for data mining processes such as clustering and classification. In this perspective, we implemented state-of-the-art Dimensionality Reduction Techniques for Visualizing Omics High-Dimensional Parkinson’s Disease Data. Our study highlights the cutting-edge dimensionality reduction techniques for 2D data visualization and their contribution the deeper interpretation of PD data. Approaches in this direction can provide a deeper understanding of biological dynamics and enable integrative multilayered diagnostic assessment of complex disorders such as neurodegenerative diseases.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
One challenge facing Systems Biology is the conversion of vast amounts of data into systematic and organized knowledge through automated processes. Improvements in experimental technologies have created an enormous pool of heterogeneous omics data such as genomics, proteomics and metabolomics. Exporting insights of these datasets can lead to important discoveries for complex pathologies such as age-related neurodegenerative disorders and specifically Parkinson's disease (PD). However, such data are characterized by huge dimensionality which increases their complexity for various data analyses as well for data mining processes such as clustering and classification. In this perspective, we implemented state-of-the-art Dimensionality Reduction Techniques for Visualizing Omics High-Dimensional Parkinson’s Disease Data. Our study highlights the cutting-edge dimensionality reduction techniques for 2D data visualization and their contribution the deeper interpretation of PD data. Approaches in this direction can provide a deeper understanding of biological dynamics and enable integrative multilayered diagnostic assessment of complex disorders such as neurodegenerative diseases.
Karampasi, A., Kakkos, I., Miloulis, S.-T., Zorzos, I., Dimitrakopoulos, G. N., Gkiatis, K., Asvestas, P., & Matsopoulos, G. K. (2020). A Machine Learning fMRI Approach in the Diagnosis of Autism. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 3628–3631). IEEE. https://doi.org/10.1109/bigdata50022.2020.9378453
@inproceedings{karampasi2020machine,
title = {A Machine Learning fMRI Approach in the Diagnosis of Autism},
author = {Aikaterini Karampasi and Ioannis Kakkos and Stavros-Theofanis Miloulis and Ioannis Zorzos and Georgios N. Dimitrakopoulos and Kostakis Gkiatis and Panteleimon Asvestas and George K. Matsopoulos},
url = {https://doi.org/10.1109/bigdata50022.2020.9378453},
doi = {10.1109/bigdata50022.2020.9378453},
year = {2020},
date = {2020-01-01},
booktitle = {2020 IEEE International Conference on Big Data (Big Data)},
pages = {3628–3631},
publisher = {IEEE},
abstract = {Diagnosis of Autism Spectrum Disorder (ASD) is a complex task that typically relies on the expertise of the clinician due to the lack of specific quantitative biomarkers. As a consequence, automatic categorization of an individual within the ASD taxonomy poses many challenges, usually with controversial results. The implementation of Machine Learning approaches as a diagnostic tool for ASD classification is rapidly growing in the field of neuroscience, holding the potential to enhance discrimination validity among ASD and Typically Developed (TD) individuals, while providing indications in regard to ASD differentiating factors. In this study, various feature selection and classification techniques were employed in order to successfully discern between ASD and TD, using data from large resting-state functional Magnetic Resonance Imaging (rs-fMRI) database. Moreover, we adopt novel features, namely the Haralick texture features and the Kullback-Leibler divergence, combined with already established ones (i.e. static Functional Connectivity and demographics), assessing the most informative global attributes. Our framework succeeded in the identification of a small number of discriminative features, leading to high performance relative to previous works with optimal classification accuracy of 0.725.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Diagnosis of Autism Spectrum Disorder (ASD) is a complex task that typically relies on the expertise of the clinician due to the lack of specific quantitative biomarkers. As a consequence, automatic categorization of an individual within the ASD taxonomy poses many challenges, usually with controversial results. The implementation of Machine Learning approaches as a diagnostic tool for ASD classification is rapidly growing in the field of neuroscience, holding the potential to enhance discrimination validity among ASD and Typically Developed (TD) individuals, while providing indications in regard to ASD differentiating factors. In this study, various feature selection and classification techniques were employed in order to successfully discern between ASD and TD, using data from large resting-state functional Magnetic Resonance Imaging (rs-fMRI) database. Moreover, we adopt novel features, namely the Haralick texture features and the Kullback-Leibler divergence, combined with already established ones (i.e. static Functional Connectivity and demographics), assessing the most informative global attributes. Our framework succeeded in the identification of a small number of discriminative features, leading to high performance relative to previous works with optimal classification accuracy of 0.725.
Dimitrakopoulos, G. N., Klapa, M. I., & Moschonas, N. K. (2020). Enriching PICKLE meta-database with the mouse protein interactome. In ELIXIR-GR All Hands Meeting 2020. Virtual.
@inproceedings{dimitrakopoulos2020enriching,
title = {Enriching PICKLE meta-database with the mouse protein interactome},
author = {Georgios N. Dimitrakopoulos and Maria I. Klapa and Nicholas K. Moschonas},
year = {2020},
date = {2020-01-01},
booktitle = {ELIXIR-GR All Hands Meeting 2020},
address = {Virtual},
note = {Conference abstract. Short paper or abstract, 22 September 2020},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vrahatis, A. G., Dimitrakopoulos, G. N., Tasoulis, S. K., & Plagianakos, V. P. (2019). A single-cell Systems Biology approach for disease-specific subpathway extraction. In 2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (pp. 1–7). IEEE. https://doi.org/10.1109/cibcb.2019.8791460
@inproceedings{vrahatis2019single,
title = {A single-cell Systems Biology approach for disease-specific subpathway extraction},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Sotiris K. Tasoulis and Vassilis P. Plagianakos},
url = {https://doi.org/10.1109/cibcb.2019.8791460},
doi = {10.1109/cibcb.2019.8791460},
year = {2019},
date = {2019-01-01},
booktitle = {2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)},
pages = {1–7},
publisher = {IEEE},
abstract = {Single-cell sequencing technologies offer a platform to explore deeper the complex diseases and biological processes. On parallel, Systems Biology approaches can tackle part of this complexity, since they are based on biological networks elucidating genotype to phenotype relationships in a more comprehensive framework. Hence, research community is shifting towards singlecell systems biology approaches to identify and validate disease-specific biomarkers. Under this perspective, we propose a methodological framework aimed to infer disease-specific subpathway activities, using cell signaling pathway topology and transcriptomics data derived from single-cell RNA-seq technologies. More specifically, we concatenated and integrated pathway network refining with single-cell expression profiles. Linear subpathways were extracted and a subpathway profile score was calculated taking into account the pathway information flow. The core of our method is XGBoost supervised classification based on the aforementioned score in order to identify important subpathways that control the rest of the network and cause major changes from a control to a disease state under study. The proposed methodology was applied to a real experimental study with single-cell RNA-seq expression profiles revealing changes in type 2 diabetes. Exported subpathways showed promising results, suggesting that the proposed approach can reliably identify subpathways, acting as potential disease-specific biomarkers.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Single-cell sequencing technologies offer a platform to explore deeper the complex diseases and biological processes. On parallel, Systems Biology approaches can tackle part of this complexity, since they are based on biological networks elucidating genotype to phenotype relationships in a more comprehensive framework. Hence, research community is shifting towards singlecell systems biology approaches to identify and validate disease-specific biomarkers. Under this perspective, we propose a methodological framework aimed to infer disease-specific subpathway activities, using cell signaling pathway topology and transcriptomics data derived from single-cell RNA-seq technologies. More specifically, we concatenated and integrated pathway network refining with single-cell expression profiles. Linear subpathways were extracted and a subpathway profile score was calculated taking into account the pathway information flow. The core of our method is XGBoost supervised classification based on the aforementioned score in order to identify important subpathways that control the rest of the network and cause major changes from a control to a disease state under study. The proposed methodology was applied to a real experimental study with single-cell RNA-seq expression profiles revealing changes in type 2 diabetes. Exported subpathways showed promising results, suggesting that the proposed approach can reliably identify subpathways, acting as potential disease-specific biomarkers.
Vrahatis, A. G., Dimitrakopoulos, G. N., Tasoulis, S. K., & Plagianakos, V. P. (2019). Enhancing Clustering of Single-Cell RNA-Seq Data by Proximity Learning on Random Projected Spaces. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 846–849). IEEE. https://doi.org/10.1109/bibe.2019.00157
@inproceedings{vrahatis2019enhancing,
title = {Enhancing Clustering of Single-Cell RNA-Seq Data by Proximity Learning on Random Projected Spaces},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Sotiris K. Tasoulis and Vassilis P. Plagianakos},
url = {https://doi.org/10.1109/bibe.2019.00157},
doi = {10.1109/bibe.2019.00157},
year = {2019},
date = {2019-01-01},
booktitle = {2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)},
volume = {3},
pages = {846–849},
publisher = {IEEE},
abstract = {We are in the era of single-cell RNA sequencing technology, which offers a great potential for uncovering cellular differences with a higher resolution, shedding light in various complex biological processes and complex human diseases. However, such studies create extremely high dimensional data isolating expression profiles for thousands or even millions of cells. Consequently, dealing with single-cell RNA-seq (scRNA-seq) data is considered the main challenge for unsupervised clustering, which can be used in order to identify grouped cell types. Towards this direction, we present a framework that enhances hierarchical clustering utilizing Proximity Learning on Random Projected spaces (PLRP). The proposed method's efficiency lies in the fact that we exploit the distances from multiple significantly lower dimension spaces defined by Random Projections using ensembles of k-nearest neighbor searches. In the transformed data we applied hierarchical agglomerative clustering (HAC) improving significantly its performance when compared against using the original space. The performance of the proposed PLRP was evaluated in a publicly available experimental dataset with scRNA-seq expression profiles, against three well-established clustering tools. The results showed that our approach greatly enhances clustering performance exposing its applicability in ultra-high dimensions and imposing further development towards this direction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We are in the era of single-cell RNA sequencing technology, which offers a great potential for uncovering cellular differences with a higher resolution, shedding light in various complex biological processes and complex human diseases. However, such studies create extremely high dimensional data isolating expression profiles for thousands or even millions of cells. Consequently, dealing with single-cell RNA-seq (scRNA-seq) data is considered the main challenge for unsupervised clustering, which can be used in order to identify grouped cell types. Towards this direction, we present a framework that enhances hierarchical clustering utilizing Proximity Learning on Random Projected spaces (PLRP). The proposed method's efficiency lies in the fact that we exploit the distances from multiple significantly lower dimension spaces defined by Random Projections using ensembles of k-nearest neighbor searches. In the transformed data we applied hierarchical agglomerative clustering (HAC) improving significantly its performance when compared against using the original space. The performance of the proposed PLRP was evaluated in a publicly available experimental dataset with scRNA-seq expression profiles, against three well-established clustering tools. The results showed that our approach greatly enhances clustering performance exposing its applicability in ultra-high dimensions and imposing further development towards this direction.
Dimitrakopoulos, G. N., Gioutlakis, A., Klapa, M. I., & Moschonas, N. K. (2019). Evaluating the expansion of the experimentally determined human protein interactome using the PICKLE meta-database. In 12th Panhellenic Scientific Conference in Chemical Engineering. Athens, Greece.
@inproceedings{dimitrakopoulos2019evaluating,
title = {Evaluating the expansion of the experimentally determined human protein interactome using the PICKLE meta-database},
author = {Georgios N. Dimitrakopoulos and A. Gioutlakis and Maria I. Klapa and Nicholas K. Moschonas},
year = {2019},
date = {2019-01-01},
booktitle = {12th Panhellenic Scientific Conference in Chemical Engineering},
address = {Athens, Greece},
note = {May 29-31, 2019},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vrahatis, A. G., Dimitrakopoulos, G. N., Tasoulis, S. K., Georgakopoulos, S. V., & Plagianakos, V. P. (2019). Single-cell regulatory network inference and clustering from high-dimensional sequencing data. In 2019 IEEE International Conference on Big Data (Big Data) (pp. 2782–2789). IEEE. https://doi.org/10.1109/bigdata47090.2019.9006016
@inproceedings{vrahatis2019singlea,
title = {Single-cell regulatory network inference and clustering from high-dimensional sequencing data},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Sotiris K. Tasoulis and Spiros V. Georgakopoulos and Vassilis P. Plagianakos},
url = {https://doi.org/10.1109/bigdata47090.2019.9006016},
doi = {10.1109/bigdata47090.2019.9006016},
year = {2019},
date = {2019-01-01},
booktitle = {2019 IEEE International Conference on Big Data (Big Data)},
pages = {2782–2789},
publisher = {IEEE},
abstract = {We are in the big data era which has affected several domains including biomedicine and healthcare. This revolution driven by the explosion of biomedical data offers the potential for better understanding of biology and human diseases. An illustrative example is the emerging single-cell sequencing technologies, which isolate and measure each cell individually, taking a step beyond the traditional techniques where consider their measurements from a bulk of cell. Although big single-cell RNA sequencing (scRNA-seq) data promises valuable insights into the cellular level, their volume poses several challenges related to the ultra-high dimensionality. Furthermore, to further elucidate the potential of these data, more insight into gene regulatory networks (GRN) is required. Network-based approaches can tackle part of the inherent complexity of human diseases, however, the challenges related to the ultra-high dimensionality are increased. Towards this direction, we propose the NIRP, an algorithm that copes with the high dimensionality of scRNA-data using a workflow based on fast multiple random projections and a radius-based nearest neighbors search. NIRP infers a gene regulatory network (GRN) from big scRNA-seq data by transforming the original data space to a lower dimensions space and capturing the similarities among gene expressions. The network is further analyzed using a random walk approach in order to achieve dense subgraphs, active to the case under study. The performance of NIRP is evaluated in a real single-cell experimental study among three well-established GRN tools. Our results make NIRP a reliable tool, able to handle big single-cell data with ultra-high dimensionality and complexity. he main advantage of this method is that it is not affected by the volume, as much as it increases, since it transforms the data space to a specific low dimensional space.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We are in the big data era which has affected several domains including biomedicine and healthcare. This revolution driven by the explosion of biomedical data offers the potential for better understanding of biology and human diseases. An illustrative example is the emerging single-cell sequencing technologies, which isolate and measure each cell individually, taking a step beyond the traditional techniques where consider their measurements from a bulk of cell. Although big single-cell RNA sequencing (scRNA-seq) data promises valuable insights into the cellular level, their volume poses several challenges related to the ultra-high dimensionality. Furthermore, to further elucidate the potential of these data, more insight into gene regulatory networks (GRN) is required. Network-based approaches can tackle part of the inherent complexity of human diseases, however, the challenges related to the ultra-high dimensionality are increased. Towards this direction, we propose the NIRP, an algorithm that copes with the high dimensionality of scRNA-data using a workflow based on fast multiple random projections and a radius-based nearest neighbors search. NIRP infers a gene regulatory network (GRN) from big scRNA-seq data by transforming the original data space to a lower dimensions space and capturing the similarities among gene expressions. The network is further analyzed using a random walk approach in order to achieve dense subgraphs, active to the case under study. The performance of NIRP is evaluated in a real single-cell experimental study among three well-established GRN tools. Our results make NIRP a reliable tool, able to handle big single-cell data with ultra-high dimensionality and complexity. he main advantage of this method is that it is not affected by the volume, as much as it increases, since it transforms the data space to a specific low dimensional space.
Dimitrakopoulos, G. N., Gioutlakis, A., Klapa, M. I., & Moschonas, N. K. (2019). Unraveling the way of expansion of the experimentally supported human protein interactome using the PICKLE meta-database. In Conference of the Hellenic Society for Computational Biology and Bioinformatics (HSCBB19). Patras, Greece.
@inproceedings{dimitrakopoulos2019unraveling,
title = {Unraveling the way of expansion of the experimentally supported human protein interactome using the PICKLE meta-database},
author = {Georgios N. Dimitrakopoulos and A. Gioutlakis and Maria I. Klapa and Nicholas K. Moschonas},
year = {2019},
date = {2019-01-01},
booktitle = {Conference of the Hellenic Society for Computational Biology and Bioinformatics (HSCBB19)},
address = {Patras, Greece},
note = {Conference abstract. Short paper or abstract, 8-10 December 2019},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vrahatis, A. G., Tasoulis, S. K., Dimitrakopoulos, G. N., & Plagianakos, V. P. (2019). Visualizing High-Dimensional Single-Cell RNA-seq Data via Random Projections and Geodesic Distances. In 2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (pp. 1–6). IEEE. https://doi.org/10.1109/cibcb.2019.8791482
@inproceedings{vrahatis2019visualizing,
title = {Visualizing High-Dimensional Single-Cell RNA-seq Data via Random Projections and Geodesic Distances},
author = {Aristidis G. Vrahatis and Sotiris K. Tasoulis and Georgios N. Dimitrakopoulos and Vassilis P. Plagianakos},
url = {https://doi.org/10.1109/cibcb.2019.8791482},
doi = {10.1109/cibcb.2019.8791482},
year = {2019},
date = {2019-01-01},
booktitle = {2019 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)},
pages = {1–6},
publisher = {IEEE},
abstract = {The recent advent in Next Generation Sequencing has created a huge data source which offers a great potential for elucidating complex disease mechanisms and biological processes. A recent technology is the single-cell RNA sequencing, which allows transcriptomics measurements in individual cells, having promising results. However, such studies measure the entire genome for thousands of cells, creating datasets with extremely high dimensionality and complexity. Following this perspective, we propose a dimensionality reduction approach, called RGt-SNE, which visualizes single-cell RNA-seq data in two dimensions. Initially, RGt-SNE defines a cell-cell distance matrix based on Random Projections and Geodesic Distances. The first is used to define the pairwise cells distances in a low dimensional projected space avoiding the difficulties that exist in data with ultra-high dimensionality. The latter is used to better define the large pairwise cells distances. Subsequently, the t-SNE method is applied in the customized distance matrix for two dimensional visualization. RGt-SNE was evaluated in two real experimental single-cell RNA-seq data against three well-known methods, such as t-SNE, Multidimensional scaling, and ISOMAP. Outcomes provide the superiority of RGt-SNE suggesting it as a reliable tool for single-cell RNA-seq data analysis and visualization.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The recent advent in Next Generation Sequencing has created a huge data source which offers a great potential for elucidating complex disease mechanisms and biological processes. A recent technology is the single-cell RNA sequencing, which allows transcriptomics measurements in individual cells, having promising results. However, such studies measure the entire genome for thousands of cells, creating datasets with extremely high dimensionality and complexity. Following this perspective, we propose a dimensionality reduction approach, called RGt-SNE, which visualizes single-cell RNA-seq data in two dimensions. Initially, RGt-SNE defines a cell-cell distance matrix based on Random Projections and Geodesic Distances. The first is used to define the pairwise cells distances in a low dimensional projected space avoiding the difficulties that exist in data with ultra-high dimensionality. The latter is used to better define the large pairwise cells distances. Subsequently, the t-SNE method is applied in the customized distance matrix for two dimensional visualization. RGt-SNE was evaluated in two real experimental single-cell RNA-seq data against three well-known methods, such as t-SNE, Multidimensional scaling, and ISOMAP. Outcomes provide the superiority of RGt-SNE suggesting it as a reliable tool for single-cell RNA-seq data analysis and visualization.
Dimitrakopoulos, G. N., Vrahatis, A. G., Plagianakos, V. P., & Sgarbas, K. (2018). Pathway analysis using XGBoost classification in Biomedical Data. In Proceedings of the 10th Hellenic Conference on Artificial Intelligence (pp. 1–6). ACM. https://doi.org/10.1145/3200947.3201029
@inproceedings{dimitrakopoulos2018pathway,
title = {Pathway analysis using XGBoost classification in Biomedical Data},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Vassilis P. Plagianakos and Kyriakos Sgarbas},
url = {https://doi.org/10.1145/3200947.3201029},
doi = {10.1145/3200947.3201029},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 10th Hellenic Conference on Artificial Intelligence},
pages = {1–6},
publisher = {ACM},
abstract = {Given the fact that our biological existence is rooted in a complex system within our cells with thousands of interactions among genes and metabolites, research community in biological and medical fields have shifted their interest to network-based approaches. This complexity is imprinted in networks which encode the relationships among system's components. This evolution has also led to the generation a new research fields, the Network Medicine, a combination of Network Science and Systems Biology applied to human diseases. Meanwhile, cutting-edge approaches towards this direction are the subpathway-based methods, identifying "active subpathways" - in the form of local sub-structures within pathways - related with a case under study.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Given the fact that our biological existence is rooted in a complex system within our cells with thousands of interactions among genes and metabolites, research community in biological and medical fields have shifted their interest to network-based approaches. This complexity is imprinted in networks which encode the relationships among system's components. This evolution has also led to the generation a new research fields, the Network Medicine, a combination of Network Science and Systems Biology applied to human diseases. Meanwhile, cutting-edge approaches towards this direction are the subpathway-based methods, identifying "active subpathways" - in the form of local sub-structures within pathways - related with a case under study.
Dimitrakopoulos, G. N., Kakkos, I., Thakor, N. V., Bezerianos, A., & Sun, Y. (2017). A mental fatigue index based on regression using mulitband EEG features with application in simulated driving. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3220–3223). IEEE. https://doi.org/10.1109/embc.2017.8037542
@inproceedings{dimitrakopoulos2017mental,
title = {A mental fatigue index based on regression using mulitband EEG features with application in simulated driving},
author = {Georgios N. Dimitrakopoulos and Ioannis Kakkos and Nitish V. Thakor and Anastasios Bezerianos and Yu Sun},
url = {https://doi.org/10.1109/embc.2017.8037542},
doi = {10.1109/embc.2017.8037542},
year = {2017},
date = {2017-01-01},
booktitle = {2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
volume = {2017},
pages = {3220–3223},
publisher = {IEEE},
abstract = {Development of accurate fatigue level prediction models is of great importance for driving safety. In parallel, a limited number of sensors is a prerequisite for development of applicable wearable devices. Several EEG-based studies so far have performed classification in two or few levels, while others have proposed indices based on power ratios. Here, we utilized a regression Random Forest model in order to provide more accurate continuous fatigue level prediction. In detail, multiband power features were extracted from EEG data recorded from one hour simulated driving task. Next, cross-subject regression was performed to obtain common fatigue-related discriminative features. We achieved satisfactory prediction accuracy and simultaneously we minimized required electrodes, proposing to use a set of 3 electrodes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Development of accurate fatigue level prediction models is of great importance for driving safety. In parallel, a limited number of sensors is a prerequisite for development of applicable wearable devices. Several EEG-based studies so far have performed classification in two or few levels, while others have proposed indices based on power ratios. Here, we utilized a regression Random Forest model in order to provide more accurate continuous fatigue level prediction. In detail, multiband power features were extracted from EEG data recorded from one hour simulated driving task. Next, cross-subject regression was performed to obtain common fatigue-related discriminative features. We achieved satisfactory prediction accuracy and simultaneously we minimized required electrodes, proposing to use a set of 3 electrodes.
Dimitrakopoulos, G. N., Kakkos, I., Vrahatis, A. G., Sgarbas, K., Li, J., Sun, Y., & Bezerianos, A. (2017). Driving Mental Fatigue Classification Based on Brain Functional Connectivity. In Communications in Computer and Information Science (pp. 465–474). Springer International Publishing. https://doi.org/10.1007/978-3-319-65172-9_39
@inproceedings{dimitrakopoulos2017driving,
title = {Driving Mental Fatigue Classification Based on Brain Functional Connectivity},
author = {Georgios N. Dimitrakopoulos and Ioannis Kakkos and Aristidis G. Vrahatis and Kyriakos Sgarbas and Junhua Li and Yu Sun and Anastasios Bezerianos},
url = {https://doi.org/10.1007/978-3-319-65172-9_39},
doi = {10.1007/978-3-319-65172-9_39},
isbn = {9783319651712},
year = {2017},
date = {2017-01-01},
booktitle = {Communications in Computer and Information Science},
pages = {465–474},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chai, J., Gong, C., Thangavel, P., Dimitrakopoulos, G. N., Kakkos, I., Sun, Y., Dai, Z., Yu, H., Thakor, N. V., Bezerianos, A., & Li, J. (2017). Identification of gait-related brain activity using electroencephalographic signals. In 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER) (pp. 548–551). IEEE. https://doi.org/10.1109/ner.2017.8008410
@inproceedings{chai2017identification,
title = {Identification of gait-related brain activity using electroencephalographic signals},
author = {Jingwen Chai and Chen Gong and Pavithra Thangavel and Georgios N. Dimitrakopoulos and Ioannis Kakkos and Yu Sun and Zhongxiang Dai and Haoyong Yu and Nitish V. Thakor and Anastasios Bezerianos and Junhua Li},
url = {https://doi.org/10.1109/ner.2017.8008410},
doi = {10.1109/ner.2017.8008410},
year = {2017},
date = {2017-01-01},
booktitle = {2017 8th International IEEE/EMBS Conference on Neural Engineering (NER)},
pages = {548–551},
publisher = {IEEE},
abstract = {Restoring normal walking abilities following the loss of them is a challenge. Importantly, there is a growing need for a better understanding of brain plasticity and the neural involvements for the initiation and control of these abilities so as to develop better rehabilitation programmes and external support devices. In this paper, we attempt to identify gait-related neural activities by decoding neural signals obtained from electroencephalography (EEG) measurements while subjects performed three types of walking: without exoskeleton (free walking), and with exoskeleton support (zero force and assisting force). An average classification accuracy of 92.0% for training and 73.8% for testing sets was achieved using features extracted from mu and beta frequency bands. Furthermore, we found that mu band features contributed significantly to the classification accuracy and were localized mainly in sensorimotor regions that are associated with the control of the exoskeleton. These findings contribute meaningful insight on the neural dynamics associated with lower limb movements and provide useful information for future developments of orthotic devices and rehabilitation programs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Restoring normal walking abilities following the loss of them is a challenge. Importantly, there is a growing need for a better understanding of brain plasticity and the neural involvements for the initiation and control of these abilities so as to develop better rehabilitation programmes and external support devices. In this paper, we attempt to identify gait-related neural activities by decoding neural signals obtained from electroencephalography (EEG) measurements while subjects performed three types of walking: without exoskeleton (free walking), and with exoskeleton support (zero force and assisting force). An average classification accuracy of 92.0% for training and 73.8% for testing sets was achieved using features extracted from mu and beta frequency bands. Furthermore, we found that mu band features contributed significantly to the classification accuracy and were localized mainly in sensorimotor regions that are associated with the control of the exoskeleton. These findings contribute meaningful insight on the neural dynamics associated with lower limb movements and provide useful information for future developments of orthotic devices and rehabilitation programs.
Bezerianos, A., Vrahatis, A. G., Balomenos, P., & Dimitrakopoulos, G. N. (2016). Deciphering the Complexity of Human Diseases via Network Medicine. In Advanced Health Informatics, Gordon Research Conference. Hong Kong, China.
@inproceedings{bezerianos2016deciphering,
title = {Deciphering the Complexity of Human Diseases via Network Medicine},
author = {Anastasios Bezerianos and Aristidis G. Vrahatis and Panos Balomenos and Georgios N. Dimitrakopoulos},
year = {2016},
date = {2016-01-01},
booktitle = {Advanced Health Informatics, Gordon Research Conference},
address = {Hong Kong, China},
note = {Conference abstract. Short paper or abstract, July 17-22, 2016},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Balomenos, P., Vrahatis, A. G., Sgarbas, K., & Bezerianos, A. (2016). Identifying disease network perturbations through regression on gene expression and pathway topology analysis. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 5969–5972). IEEE. https://doi.org/10.1109/embc.2016.7592088
@inproceedings{dimitrakopoulos2016identifying,
title = {Identifying disease network perturbations through regression on gene expression and pathway topology analysis},
author = {Georgios N. Dimitrakopoulos and Panos Balomenos and Aristidis G. Vrahatis and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1109/embc.2016.7592088},
doi = {10.1109/embc.2016.7592088},
year = {2016},
date = {2016-01-01},
booktitle = {2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
volume = {5},
pages = {5969–5972},
publisher = {IEEE},
abstract = {In Systems Biology, network-based approaches have been extensively used to effectively study complex diseases. An important challenge is the detection of network perturbations which disrupt regular biological functions as a result of a disease. In this regard, we introduce a network based pathway analysis method which isolates casual interactions with significant regulatory roles within diseased-perturbed pathways. Specifically, we use gene expression data with Random Forest regression models to assess the interactivity strengths of genes within disease-perturbed networks, using KEGG pathway maps as a source of prior-knowledge pertaining to pathway topology. We deliver as output a network with imprinted perturbations corresponding to the biological phenomena arising in a disease-oriented experiment. The efficacy of our approach is demonstrated on a serous papillary ovarian cancer experiment and results highlight the functional roles of high impact interactions and key gene regulators which cause strong perturbations on pathway networks, in accordance with experimentally validated knowledge from recent literature.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In Systems Biology, network-based approaches have been extensively used to effectively study complex diseases. An important challenge is the detection of network perturbations which disrupt regular biological functions as a result of a disease. In this regard, we introduce a network based pathway analysis method which isolates casual interactions with significant regulatory roles within diseased-perturbed pathways. Specifically, we use gene expression data with Random Forest regression models to assess the interactivity strengths of genes within disease-perturbed networks, using KEGG pathway maps as a source of prior-knowledge pertaining to pathway topology. We deliver as output a network with imprinted perturbations corresponding to the biological phenomena arising in a disease-oriented experiment. The efficacy of our approach is demonstrated on a serous papillary ovarian cancer experiment and results highlight the functional roles of high impact interactions and key gene regulators which cause strong perturbations on pathway networks, in accordance with experimentally validated knowledge from recent literature.
Dimitrakopoulos, G. N., Vrahatis, A. G., Balomenos, P., Sgarbas, K., & Bezerianos, A. (2015). Age-related subpathway detection through meta-analysis of multiple gene expression datasets. In 2015 IEEE International Conference on Digital Signal Processing (DSP) (pp. 539–542). IEEE. https://doi.org/10.1109/icdsp.2015.7251931
@inproceedings{dimitrakopoulos2015age,
title = {Age-related subpathway detection through meta-analysis of multiple gene expression datasets},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Panos Balomenos and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1109/icdsp.2015.7251931},
doi = {10.1109/icdsp.2015.7251931},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE International Conference on Digital Signal Processing (DSP)},
volume = {6},
pages = {539–542},
publisher = {IEEE},
abstract = {A novel perspective of systems biology is the incorporation of pathway structure data along with transcriptomics studies. In parallel, the plethora of high-throughput experimental studies necessitates employment of meta-analysis approaches in order to obtain more biologically consistent results. Towards this orientation we developed a subpathway-based meta-analysis method that integrates human pathway maps along with multiple human mRNA expression experiments. Our method succeeded to identify known age-related subpathways as differentially expressed exploiting several independent muscle-specific aging studies. Finally, our method is applicable in several complex biological problems where massive amount of time series expression data is available.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A novel perspective of systems biology is the incorporation of pathway structure data along with transcriptomics studies. In parallel, the plethora of high-throughput experimental studies necessitates employment of meta-analysis approaches in order to obtain more biologically consistent results. Towards this orientation we developed a subpathway-based meta-analysis method that integrates human pathway maps along with multiple human mRNA expression experiments. Our method succeeded to identify known age-related subpathways as differentially expressed exploiting several independent muscle-specific aging studies. Finally, our method is applicable in several complex biological problems where massive amount of time series expression data is available.
Vrahatis, A. G., Dimitrakopoulos, G. N., Tsakalidis, A. K., & Bezerianos, A. (2015). Cardiac aging signatures in the form of network communities. In Biology of Ageing Conference. Singapore.
@inproceedings{vrahatis2015cardiac,
title = {Cardiac aging signatures in the form of network communities},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Athanasios K. Tsakalidis and Anastasios Bezerianos},
year = {2015},
date = {2015-01-01},
booktitle = {Biology of Ageing Conference},
address = {Singapore},
note = {Conference abstract. Short paper or abstract, October 22-24, 2015},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Vrahatis, A. G., Sgarbas, K., & Bezerianos, A. (2015). Gene Expression Trend Analysis in Aging. In 6th Panhellenic Conference on Biomedical Technology. Athens, Greece.
@inproceedings{dimitrakopoulos2015gene,
title = {Gene Expression Trend Analysis in Aging},
author = {Georgios N. Dimitrakopoulos and Aristidis G. Vrahatis and Kyriakos Sgarbas and Anastasios Bezerianos},
year = {2015},
date = {2015-01-01},
booktitle = {6th Panhellenic Conference on Biomedical Technology},
address = {Athens, Greece},
note = {Conference abstract. Short paper or abstract, May 6-8, 2015},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vrahatis, A. G., Dimitrakopoulos, G. N., Tsakalidis, A. K., & Bezerianos, A. (2015). Identifying miRNA-mediated signaling subpathways by integrating paired miRNA/mRNA expression data with pathway topology. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3997–4000). IEEE. https://doi.org/10.1109/embc.2015.7319270
@inproceedings{vrahatis2015identifying,
title = {Identifying miRNA-mediated signaling subpathways by integrating paired miRNA/mRNA expression data with pathway topology},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Athanasios K. Tsakalidis and Anastasios Bezerianos},
url = {https://doi.org/10.1109/embc.2015.7319270},
doi = {10.1109/embc.2015.7319270},
year = {2015},
date = {2015-01-01},
booktitle = {2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
volume = {8},
pages = {3997–4000},
publisher = {IEEE},
abstract = {In the road for network medicine the newly emerged systems-level subpathway-based analysis methods offer new disease genes, drug targets and network-based biomarkers. In parallel, paired miRNA/mRNA expression data enable simultaneously monitoring of the micronome effect upon the signaling pathways. Towards this orientation, we present a methodological pipeline for the identification of differentially expressed subpathways along with their miRNA regulators by using KEGG signaling pathway maps, miRNA-target interactions and expression profiles from paired miRNA/mRNA experiments. Our pipeline offered new biological insights on a real application of paired miRNA/mRNA expression profiles with respect to the dynamic changes from colostrum to mature milk whey; several literature supported genes and miRNAs were recontextualized through miRNA-mediated differentially expressed subpathways.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In the road for network medicine the newly emerged systems-level subpathway-based analysis methods offer new disease genes, drug targets and network-based biomarkers. In parallel, paired miRNA/mRNA expression data enable simultaneously monitoring of the micronome effect upon the signaling pathways. Towards this orientation, we present a methodological pipeline for the identification of differentially expressed subpathways along with their miRNA regulators by using KEGG signaling pathway maps, miRNA-target interactions and expression profiles from paired miRNA/mRNA experiments. Our pipeline offered new biological insights on a real application of paired miRNA/mRNA expression profiles with respect to the dynamic changes from colostrum to mature milk whey; several literature supported genes and miRNAs were recontextualized through miRNA-mediated differentially expressed subpathways.
Vrahatis, A. G., Dimitrakopoulos, G. N., Tsakalidis, A. K., & Bezerianos, A. (2015). Structural and Functional Communities of Longevity-associated Genes in Signalling Pathways. In 6th Panhellenic Conference on Biomedical Technology. Athens, Greece.
@inproceedings{vrahatis2015structural,
title = {Structural and Functional Communities of Longevity-associated Genes in Signalling Pathways},
author = {Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Athanasios K. Tsakalidis and Anastasios Bezerianos},
year = {2015},
date = {2015-01-01},
booktitle = {6th Panhellenic Conference on Biomedical Technology},
address = {Athens, Greece},
note = {Conference abstract. Short paper or abstract, May 6-8, 2015},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Maraziotis, I. A., Sgarbas, K., & Bezerianos, A. (2014). A Clustering based Method Accelerating Gene Regulatory Network Reconstruction. In Procedia Computer Science (pp. 1993–2002). Elsevier BV. https://doi.org/10.1016/j.procs.2014.05.183
@inproceedings{dimitrakopoulos2014clustering,
title = {A Clustering based Method Accelerating Gene Regulatory Network Reconstruction},
author = {Georgios N. Dimitrakopoulos and Ioannis A. Maraziotis and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1016/j.procs.2014.05.183},
doi = {10.1016/j.procs.2014.05.183},
year = {2014},
date = {2014-01-01},
booktitle = {Procedia Computer Science},
volume = {29},
pages = {1993–2002},
publisher = {Elsevier BV},
abstract = {One important direction of Systems Biology is to infer Gene Regulatory Networks and many methods have been developed recently, but they cannot be applied effectively in full scale data. In this work we propose a framework based on clustering to handle the large dimensionality of the data, aiming to improve accuracy of inferred network while reducing time complexity. We explored the efficiency of this framework employing the newly proposed metric Maximal Information Coefficient (MIC), which showed superior performance in comparison to other well established methods. Utilizing both benchmark and real life datasets, we showed that our method is able to deliver accurate results in fractions of time required by other state of the art methods. Our method provides as output interactions among groups of highly correlated genes, which in an application on an aging experiment were able to reveal aging related pathways.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
One important direction of Systems Biology is to infer Gene Regulatory Networks and many methods have been developed recently, but they cannot be applied effectively in full scale data. In this work we propose a framework based on clustering to handle the large dimensionality of the data, aiming to improve accuracy of inferred network while reducing time complexity. We explored the efficiency of this framework employing the newly proposed metric Maximal Information Coefficient (MIC), which showed superior performance in comparison to other well established methods. Utilizing both benchmark and real life datasets, we showed that our method is able to deliver accurate results in fractions of time required by other state of the art methods. Our method provides as output interactions among groups of highly correlated genes, which in an application on an aging experiment were able to reveal aging related pathways.
Dimitrakopoulos, G. N., Dimitrakopoulou, K., Maraziotis, I. A., Sgarbas, K., & Bezerianos, A. (2014). Supervised method for construction of microRNA-mRNA networks: Application in cardiac tissue aging dataset. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 318–321). IEEE. https://doi.org/10.1109/embc.2014.6943593
@inproceedings{dimitrakopoulos2014supervised,
title = {Supervised method for construction of microRNA-mRNA networks: Application in cardiac tissue aging dataset},
author = {Georgios N. Dimitrakopoulos and Konstantina Dimitrakopoulou and Ioannis A. Maraziotis and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1109/embc.2014.6943593},
doi = {10.1109/embc.2014.6943593},
year = {2014},
date = {2014-01-01},
booktitle = {2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
volume = {7},
pages = {318–321},
publisher = {IEEE},
abstract = {MicroRNAs play an important role in regulation of gene expression, but still detection of their targets remains a challenge. In this work we present a supervised regulatory network inference method with aim to identify potential target genes (mRNAs) of microRNAs. Briefly, the proposed method exploiting mRNA and microRNA expression trains Random Forests on known interactions and subsequently it is able to predict novel ones. In parallel, we incorporate different available data sources, such as Gene Ontology and ProteinProtein Interactions, to deliver biologically consistent results. Application in both benchmark data and an experiment studying aging showed robust performance.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
MicroRNAs play an important role in regulation of gene expression, but still detection of their targets remains a challenge. In this work we present a supervised regulatory network inference method with aim to identify potential target genes (mRNAs) of microRNAs. Briefly, the proposed method exploiting mRNA and microRNA expression trains Random Forests on known interactions and subsequently it is able to predict novel ones. In parallel, we incorporate different available data sources, such as Gene Ontology and ProteinProtein Interactions, to deliver biologically consistent results. Application in both benchmark data and an experiment studying aging showed robust performance.
Dimitrakopoulou, K., Vrahatis, A. G., Dimitrakopoulos, G. N., & Bezerianos, A. (2013). Aging Integromics: Module-Based Markers of Heart Aging from Multi-omics Data. In IFMBE Proceedings (pp. 104–107). Springer International Publishing. https://doi.org/10.1007/978-3-319-02913-9_27
@inproceedings{dimitrakopoulou2013aging,
title = {Aging Integromics: Module-Based Markers of Heart Aging from Multi-omics Data},
author = {Konstantina Dimitrakopoulou and Aristidis G. Vrahatis and Georgios N. Dimitrakopoulos and Anastasios Bezerianos},
url = {https://doi.org/10.1007/978-3-319-02913-9_27},
doi = {10.1007/978-3-319-02913-9_27},
isbn = {9783319029122},
year = {2013},
date = {2013-01-01},
booktitle = {IFMBE Proceedings},
pages = {104–107},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Dimitrakopoulou, K., Vrahatis, A. G., Sgarbas, K. N., & Bezerianos, A. (2013). An integrative meta-analysis method to reveal age-related cross-tissue pathways. In 27th International Mammalian Genome Conference. Salamanca, Spain.
@inproceedings{dimitrakopoulos2013integrative,
title = {An integrative meta-analysis method to reveal age-related cross-tissue pathways},
author = {Georgios N. Dimitrakopoulos and Konstantina Dimitrakopoulou and Aristidis G. Vrahatis and Kyriakos N. Sgarbas and Anastasios Bezerianos},
year = {2013},
date = {2013-01-01},
booktitle = {27th International Mammalian Genome Conference},
address = {Salamanca, Spain},
note = {Conference abstract. Short paper or abstract, September 15-18, 2013},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Icay, K., Dimitrakopoulou, K., Hovatta, I., & Bezerianos, A. (2013). Deciphering anxiety mechanisms through an ensemble of gene network inference methods. In Annual Conference of the German Genetics Society (GfG). Braunschweig, Germany.
@inproceedings{dimitrakopoulos2013deciphering,
title = {Deciphering anxiety mechanisms through an ensemble of gene network inference methods},
author = {Georgios N. Dimitrakopoulos and K. Icay and Konstantina Dimitrakopoulou and Iiris Hovatta and Anastasios Bezerianos},
year = {2013},
date = {2013-01-01},
booktitle = {Annual Conference of the German Genetics Society (GfG)},
address = {Braunschweig, Germany},
note = {Conference abstract. Short paper or abstract, September 23-25, 2013},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vrahatis, A. G., Dimitrakopoulou, K., Dimitrakopoulos, G. N., Sgarbas, K., Tsakalidis, A. K., & Bezerianos, A. (2013). Network-Based Modular Markers of Aging across Different Tissues. In IFMBE Proceedings (pp. 1849–1852). Springer International Publishing. https://doi.org/10.1007/978-3-319-00846-2_456
@inproceedings{vrahatis2013network,
title = {Network-Based Modular Markers of Aging across Different Tissues},
author = {Aristidis G. Vrahatis and Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and Kyriakos Sgarbas and Athanasios K. Tsakalidis and Anastasios Bezerianos},
url = {https://doi.org/10.1007/978-3-319-00846-2_456},
doi = {10.1007/978-3-319-00846-2_456},
isbn = {9783319008455},
year = {2013},
date = {2013-01-01},
booktitle = {IFMBE Proceedings},
pages = {1849–1852},
publisher = {Springer International Publishing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Maraziotis, I. A., Dimitrakopoulos, G. N., & Bezerianos, A. (2012). Gene Ontology Semi-supervised Possibilistic Clustering of Gene Expression Data. In Lecture Notes in Computer Science (pp. 262–269). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-30448-4_33
@inproceedings{maraziotis2012gene,
title = {Gene Ontology Semi-supervised Possibilistic Clustering of Gene Expression Data},
author = {Ioannis A. Maraziotis and Georgios N. Dimitrakopoulos and Anastasios Bezerianos},
url = {https://doi.org/10.1007/978-3-642-30448-4_33},
doi = {10.1007/978-3-642-30448-4_33},
isbn = {9783642304477},
year = {2012},
date = {2012-01-01},
booktitle = {Lecture Notes in Computer Science},
pages = {262–269},
publisher = {Springer Berlin Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Dimitrakopoulos, G. N., Sgarbas, K., Dimitrakopoulou, K., Dragomir, A., Bezerianos, A., & Maraziotis, I. A. (2012). Multi-scale modeling of gene regulatory networks via integration of temporal and topological biological data. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 1242–1245). IEEE. https://doi.org/10.1109/embc.2012.6346162
@inproceedings{dimitrakopoulos2012multi,
title = {Multi-scale modeling of gene regulatory networks via integration of temporal and topological biological data},
author = {Georgios N. Dimitrakopoulos and Kyriakos Sgarbas and Konstantina Dimitrakopoulou and Andrei Dragomir and Anastasios Bezerianos and Ioannis A. Maraziotis},
url = {https://doi.org/10.1109/embc.2012.6346162},
doi = {10.1109/embc.2012.6346162},
year = {2012},
date = {2012-01-01},
booktitle = {2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
volume = {2012},
pages = {1242–1245},
publisher = {IEEE},
abstract = {Regulome is the dynamic network representation of the regulatory interplay among genes, proteins and other cellular components that control cellular processes. Reconstruction of gene regulatory networks (GRN) delineates one of the main objectives of Systems Biology towards understanding the organization of regulome. Significant progress has been reported the last years regarding GRN reconstruction methods, but the majority of them either consider information originating solely from gene expression data or/and are applied on a small fraction of the experimental dataset. In this paper, we will describe an integrative method, utilizing both temporal information arriving from time-series gene expression profiles, as well as topological properties of protein networks. The proposed methodology detects relations among either groups of genes or specific genes depending on the level of abstraction or resolution requested. Application on real data proved the ability of the method to extract relations in accordance with current biological knowledge as well as discriminate between different experimental conditions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Regulome is the dynamic network representation of the regulatory interplay among genes, proteins and other cellular components that control cellular processes. Reconstruction of gene regulatory networks (GRN) delineates one of the main objectives of Systems Biology towards understanding the organization of regulome. Significant progress has been reported the last years regarding GRN reconstruction methods, but the majority of them either consider information originating solely from gene expression data or/and are applied on a small fraction of the experimental dataset. In this paper, we will describe an integrative method, utilizing both temporal information arriving from time-series gene expression profiles, as well as topological properties of protein networks. The proposed methodology detects relations among either groups of genes or specific genes depending on the level of abstraction or resolution requested. Application on real data proved the ability of the method to extract relations in accordance with current biological knowledge as well as discriminate between different experimental conditions.
Dimitrakopoulou, K., Dimitrakopoulos, G. N., Zacharaki, E. I., Maraziotis, I. A., Sgarbas, K., & Bezerianos, A. (2012). Revealing the dynamic modularity of composite biological networks in breast cancer treatment. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 5432–5436). IEEE. https://doi.org/10.1109/embc.2012.6347223
@inproceedings{dimitrakopoulou2012revealing,
title = {Revealing the dynamic modularity of composite biological networks in breast cancer treatment},
author = {Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and Evangelia I. Zacharaki and Ioannis A. Maraziotis and Kyriakos Sgarbas and Anastasios Bezerianos},
url = {https://doi.org/10.1109/embc.2012.6347223},
doi = {10.1109/embc.2012.6347223},
year = {2012},
date = {2012-01-01},
booktitle = {2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
volume = {107},
pages = {5432–5436},
publisher = {IEEE},
abstract = {A major challenge in modern breast cancer treatment is to unravel the effect of drug activity through the systematic rewiring of cellular networks over time. Here, we illustrate the efficacy and discriminative power of our integrative approach in detecting modules that represent the regulatory effect of tamoxifen, widely used in anti-estrogen treatment, on transcriptome and proteome and serve as dynamic sub-network signatures. Initially, composite networks, after integrating protein interaction and time series gene expression data between two conditions (estradiol and estradiol plus tamoxifen), were constructed. Further, the Detect Module from Seed Protein (DMSP) algorithm elaborated on the graphs and constructed modules, with specific 'seed' proteins used as starting points. Our findings provide evidence about the way drugs perturb and rewire the high-order organization of interactome in time.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A major challenge in modern breast cancer treatment is to unravel the effect of drug activity through the systematic rewiring of cellular networks over time. Here, we illustrate the efficacy and discriminative power of our integrative approach in detecting modules that represent the regulatory effect of tamoxifen, widely used in anti-estrogen treatment, on transcriptome and proteome and serve as dynamic sub-network signatures. Initially, composite networks, after integrating protein interaction and time series gene expression data between two conditions (estradiol and estradiol plus tamoxifen), were constructed. Further, the Detect Module from Seed Protein (DMSP) algorithm elaborated on the graphs and constructed modules, with specific 'seed' proteins used as starting points. Our findings provide evidence about the way drugs perturb and rewire the high-order organization of interactome in time.
Dimitrakopoulou, K., Dimitrakopoulos, G. N., Tsimpouris, C., Sgarbas, K., & Bezerianos, A. (2011). Exploring the temporal dynamics of immune system in response to Influenza A (H1N1) virus through dynamic gene network reconstruction methods. In Proceedings of the 6th Conference of the Hellenic Society for Computational Biology and Bioinformatics (HSCBB11). Patras, Greece.
@inproceedings{dimitrakopoulou2011exploring,
title = {Exploring the temporal dynamics of immune system in response to Influenza A (H1N1) virus through dynamic gene network reconstruction methods},
author = {Konstantina Dimitrakopoulou and Georgios N. Dimitrakopoulos and C. Tsimpouris and Kyriakos Sgarbas and Anastasios Bezerianos},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the 6th Conference of the Hellenic Society for Computational Biology and Bioinformatics (HSCBB11)},
address = {Patras, Greece},
note = {Conference abstract. Short paper or abstract, October 7-9, 2011},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}