BioMedMine

BioMedMine
Nowadays, the continuous development of improved imaging techniques, greater computational capabilities and improved analysis techniques of biological sequences, images and biosignals, have led to the creation of large biomedical databases. More advances are yet to come as scientists have efficient computational tools that take full advantage of the available data. Towards this direction, the “BIOMEDMINE” project is a collaborative effort aiming at addressing the great need for efficient informatics tools for the analysis and management of large collections of biomedical data types such as biological images and sequences, medical images and biosignals. After developing a general framework and specialized methods for each type of biomedical data, we will attempt to integrate the extracted patterns, features and associations in order to build a unified platform of biomedical analysis and knowledge discovery tools. We propose to develop automatic quantitative characterization of regions of interest, new approaches to address database queries including queries by content, large scale association detection techniques in images, sequences, and in general, efficient management and analysis of heterogeneous biomedical data including new ways to combine information from various levels and test clinical and biological hypotheses to produce new knowledge. An array of informatics tools will be developed combining information from gene and protein level up to the level of organism and behavior, allowing the generation and testing of new clinical and biological hypotheses. The system we select to apply the proposed methodologies is the nervous system because of its complexity, the availability of data types being derived from it and the related expertise of almost all project investigators. The data mining concepts and techniques to be implemented will assist the interpretation of biomedical data automating the process of extraction of new knowledge in medicine and biology.

 

Motivation

Among the most important objectives of biology and medicine today is the detection of associations between phenotype and genotype using multilevel analysis. Also, the discovery of patterns and associations between morphology and function (normal or pathological) of different organs and the effect of genes and proteins is an ongoing research issue. The biomedical variables that are analyzed by researchers nowadays, originate from various levels beginning from the level of the cell and the molecule and going up to the level of organism. As a result, processes such as medical diagnosis, prognosis and treatment have started to be based on a combination of such variables. Taking into account the main types of biomedical data such as biological images, biosequences, medical images and biosignals, this project intends to develop innovative algorithmic methodologies aiming at the discovery of new biomedical knowledge. The collaboration of experts from the field of informatics, medicine and biology will contribute to the effective design and implementation of new methods for approaching interesting open problems in the biomedical data mining field.

 

Objectives
The array of biomedical informatics open source tools that we propose to develop will combine information from the gene and protein level up to the level of the organism and behavior, facilitating the efficient management and analysis of biomedical data of various types. More specifically, the main objectives of the proposed research are:

  • The development of a general methodological framework for image and data mining which includes algorithms for feature extraction, dimensionality reduction, clustering, classification, indexing, as well as the similarity metrics for images, sequences and biosignals.
  • The application of the general methodological framework with suitable parameterizations to more specialized types of data that will result in the development of (a) Methodologies for biological image analysis. This aim includes the development of tools for proteomic analysis, discovery of associations in images of proteomic analysis, visualization of results of proteomic analysis, feature extraction from gene expression maps, and clustering, classification and indexing of biological images. (b) Analysis techniques for Regions Of Interest (ROIs) in medical images. This part focuses on medical image segmentation and registration, feature extraction from ROIs, classification, and analysis of morphological variability. (c) Analysis techniques for biological sequences, sequence representation techniques using motifs, similarity metrics, clustering and indexing of biosequences. (d) Methodologies for the analysis of biosignals and more specifically mass spectrometry and MR spectroscopy measurements.
  • Integration of information from biomedical images, biosequences, biosignals and other clinical data using probabilistic models. Association and correlation analysis of multidimensional data. Unification of data mining techniques with morphological variability analysis techniques.
  • Development of ontologies specific for the description of protein structures, biomedical images and signals and semantic unification of these ontologies. Integration of biomedical data and images in a database and demonstration of the applicability of the proposed methodologies for data mining and information fusion.

Evaluation and validation of the proposed methodologies using simulated and real data sets obtained from a large number of biomedical studies.The system that we select to apply the proposed data mining and knowledge discovery techniques is the nervous system because of its complexity, the availability of data at various levels and the prior related work from almost all members of the research team. The development of innovative algorithms for knowledge extraction from biological and medical data aims at the discovery of new rules that govern the operation of the nervous system on which this research project is focused. The understanding of development mechanisms of various neurodegenerative diseases, such as multiple sclerosis, Alzheimer”s and Parkinson”s disease and the discovery of potential markers for diagnosis, prognosis and treatment of various diseases and disorders of the nervous system constitute a necessary step not only for the early diagnosis but also for the development of drugs for these diseases.

Project Coordinator

Prof Vasileios Megaloikonomou

Department of Computer Engineering & Informatics
University of Patras, Greece

 

Research Team 1: Data Mining and Biomedical Informatics Team

  • Dr. Vasileios Megalooikonomou, Professor in the Computer Engineering and Informatics Department, University of Patras.
  • Dr. Christos Makris, Assistant Professor in the Computer Engineering and Informatics Department, University of Patras.
  • Dr. Achilleas Kameas, Assistant Professor in the School of Science and Technology, Hellenic Open University, and Faculty Research Coordinator of the Daisy Research Unit, Computer Technology Institute, Patras.
  • Invited Researcher Dr. Nikolaos Paragyios, Professor in the Department of Applied Mathematics, Ecole Centrale de Paris and head of the Galen Group, INRIA Saclay Ile-de-France, the French Research Institute in Informatics and Control, Ecole Centrale de Paris

 

Research Team 2: Medical Image Processing and Analysis Team

  • Dr. Dimitrios Karnampatidis, Associate Professor in the Department of Radiology, School of Medicine, University of Patras.
  • Dr. Dimitrios Siamplis, Professor in the Department of Radiology, School of Medicine, University of Patras.
  • Dr. Georgios Kagadis , Associate Professor of Medical Physics and Medical Informatics, Department of Medical Physics, School of Medicine, University of Patras, and Member of Biosignal Processing Group, University of Patras.
  • Dr. Panagiotis Polychronopoulos, Associate Professor, Department of Neurology, School of Medicine, University of Patras.

 

Research Team 3: Bioinformatics and Medical Informatics Team

C. Makris, Wavelet Trees: A survey, Computer Science and Information Systems Journal, 9(2), 585-625 (2012).
P. Antonellis, C. Makris and G. Pispirigos, Parallelized structural and value XML filtering on multicore processors, 8th International Conference on Web Information Systems and Technologies (WebIST 2012),pp. 5-12.
E. I. Zacharaki, A. Skoura, D. J. Smith, S. Faro, L. An, V.Megalooikonomou: Combining gene expression and function in a spatially localized approach. BIBM 2012: 1-8
E. I. Zacharaki, A. Skoura, L. An, D. J. Smith, V. Megalooikonomou: Using an Atlas-Based Approach in the Analysis of Gene Expression Maps Obtained by Voxelation. AIAI (2) 2012: 566-575
D. Vlachakis, G. Tsiliki, D. Tsagkrasoulis, C.S. Carvalho, V.Megalooikonomou, S. Kossida. Speeding up the drug discovery process: structural similarity searches using molecular surfaces. EMBnet Journal. 2012, 18(1):6-9
K. Mandelias, S. Tsantis, D. Karnabatidis, P. Katsakiori, D.Mihailidis, G.C. Nikiforidis, G.C. Kagadis. Fast and robust algorithm toward vessel lumen and stent strut detection in optical coherence tomography. Presented at the AAPM 2012 annual conference, Charlotte,NC
2013

  1. Makris, Wavelet Trees: A survey, Computer Science and Information Systems Journal, 9(2), 585-625 (2012).
  2. Antonellis, C. Makris and G. Pispirigos, Parallelized structural and value XML filtering on multicore processors, 8th International Conference on Web Information Systems and Technologies (WebIST 2012), pp. 5-12.
  3. I. Zacharaki, A. Skoura, D. J. Smith, S. Faro, L. An, V. Megalooikonomou: Combining gene expression and function in a spatially localized approach. BIBM 2012: 1-8
  4. E I. Zacharaki, A. Skoura, An, D. J. Smith, V. Megalooikonomou: Using an Atlas-Based Approach in the Analysis of Gene Expression Maps Obtained by Voxelation. AIAI (2) 2012: 566-575
  5. Vlachakis, G. Tsiliki, D. Tsagkrasoulis, C.S. Carvalho, V. Megalooikonomou, S. Kossida. Speeding up the drug discovery process: structural similarity searches using molecular surfaces. EMBnet Journal. 2012, 18(1):6-9
  6. Mandelias, S. Tsantis, D. Karnabatidis, P. Katsakiori, D. Mihailidis, G.C. Nikiforidis, G.C. Kagadis. Fast and robust algorithm toward vessel lumen and stent strut detection in optical coherence tomography. Presented at the AAPM 2012 annual conference, Charlotte, NC
  7. Vlachakis D, Tsagkrasoulis D, Megalooikonomou V, Kossida S. Introducing Drugster: a comprehensive drug design, lead and structure optimization toolkit. 2013, 29(1):126-128
  8. Vlachakis D, Feidakis C, Megalooikonomou V, Kossida S. IMGT/Collier-de-Perles: A two-dimensional visualization tool for amino acid domain sequences. Theor Biol Med Model.2013, 21;10(1):14.[doi:10.1186/1742-4682-10-14, MS id:1016205819051801]
  9. Vlachakis D, Tsiliki G, Roumbelakis MG, Pavlopoulou A, Champeris Tsaniras , S, Kossida S. Antiviral stratagems against HIV using RNA interference (RNAi) Evolutionary Bioinformatics.2013, 9:203-213.[doi:10.4137/EBO.S11412,  MS id:6005155668041401]
  10. I. Zacharaki, E. Pippa, A. Koupparis, G.K. Kostopoulos, V. Megalooikonomou, “Classification of EEG waveforms by spectral clustering,” 5th Pan-Hellenic Conference on Biomedical Technology, Athens, April 4-6, 2013.
  11. Antonellis, P., Kontopoulos, S., Makris, C., Plegas, Y. and Tsirakis, N. (2013). Semantic XML Filtering on Peer-to-Peer Networks Using Distributed Bloom Filter. On the Proceedings of the 9th International Conference on Web Information Systems and Technology (WEBIST 2013).
  12. Makris, C. and Plegas, Y. (2013). Exploiting Progressions for Improving Inverted Index Compression. On the Proceedings of the 9th International Conference on Web Information Systems and Technology (WEBIST 2013).
  13. Makris, Y. Plegas, G. Tzimas, Ε. Viennas: SerfSIN: Search Engines Results’ Refinement using a Sense-driven Inference Network. WEBIST 2013: 222-232
  14. Mandelias, S. Tsantis, S. Spiliopoulos, P.F. Katsakiori, D. Karnabatidis, G.C. Nikiforidis, G.C. Kagadis, “Automatic quantitative analysis of in-stent restenosis using FD-OCT in vivo intra-arterial imaging”, Med. Phys., Vol. 40 (6), June 2013.
  15. Skoura, P. R. Bakic, T. Nuznaya, and V. Megalooikonomou, “Detecting and localizing tree nodes in anatomic structures of branching topology”, 10th International Conference on Image Analysis and Recognition, Póvoa de Varzim, Portugal, Jun. 2013, Proceedings. Springer 2013 Lecture Notes in Computer Science, pp. 485-493.
  1. Kanavos, C. Makris, Y. Plegas and E. Theodoridis, Extracting Knowledge from Web Search Engine using Wikipedia, 2nd Humanistic Data Mining Workhop, 2013 in EANN 2013, (full paper) invited for a special issue of Neurocomputing.
  2. I. Zacharaki, E. Pippa, A. Koupparis, V. Kokkinos, G. Kostopoulos, V. Megalooikonomou, “One-class classification of temporal EEG patterns for K-complex extraction,” 35th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC ’13), July 3-7, 2013, Osaka, Japan.
  3. Papadimitroulas, G. Loudos, A.Le Maitre, M. Hatt, F. Tixier, N. Efthimiou, D. Visvikis, G.C. Nikiforidis, G.C. Kagadis “Investigation of realistic PET simulations incorporating tumor patient’s specificity using anthropomorphic models: Creation of an oncology database”, Med. Phys., Vol. 40 (11), November 2013.
  4. C. Kagadis, C. Kloukinas, K. Moore, J. Philbin, P. Papadimitroulas, C. Alexakos, P.G. Nagy, D. Visvikis, W.R. Hendee “Cloud Computing in medical Imaging”, Med. Phys., Vol. 40 (7), July 2013.
  5. Tsantis, P. Katsakiori, D. Karnabatidis, A. Skouroliakou, D. Mihailidis, G.C. Kagadis, “An edge-Preserving Markov-Random-Fields Model for Speckle Removal in Ultrasound Images”,55th Annual Meeting & Exhibition, August 4-8, 2013, Indianapolis, ΙΝ.
  6. Carvalho CS, Vlachakis D, Tsiliki G, Megalooikonomou V, Kossida S. Protein signatures using electrostatic molecular surfaces in harmonic space. PeerJ. 2013, 1:e185. [doi:10.7717/peerj.185] Featured Article / Cover Page
  7. Skoura, P. R. Bakic, and V. Megalooikonomou, “Analyzing tree-shape anatomical structures using topological descriptors of branching and ensemble of classifiers“, Journal of Theoretical and Applied Computer Science, vol. 7, no. 1, pp. 3-19, 2013
  8. Α. Skoura, T. Nuznaya, P. R. Bakic, and V. Megalooikonomou Classifying Ductal Trees Using Geometrical Features and Ensemble Learning Techniques, 14th Conference on Engineering Applications of Neural Networks (EANN), 13-16 Sept, 2013, Greece
  9. Papangelopoulos N, Vlachakis D, Filntisi A, Fakourelis P, Papageorgiou L, Megalooikonomou V, Kossida S. State of the art GPGPU applications in bioinformatics. International Journal of Systems Biology and Biomedical Technologies (IJSBBT). 2013, 2(4):24-48.

 

2014

  1. Efstathios Lempesis, Christos Makris, Combining Learning-to-Rank with Clustering, WEBIST 2014, short paper 286-295.
  2. Klev Diamanti, Andreas Kanavos, Christos Makris and Thodoris Tokis, Handling Weighted  Sequences employing Inverted Files and Suffix Trees, WEBIST 2014, short paper 231-238.
  3. Vlachakis D, Champeris Tsaniras S, Tsiliki G, Megalooikonomou V, Kossida S. 3D structural analysis of proteins using electrostatic surfaces based on image segmentation. J Mol Biochem. 2014, 3(1):27-33.
  4. Vlachakis D, Bencurova E, Papangelopoulos N, Kossida S. Current state of the art molecular dynamics methods and applications. Advances in Protein Chemistry and Structural Biology. 2014, 94:269–313.
  5. Loukatou S, Papageorgiou L, Fakourelis P, Filntisi A, Polychronidou E, Bassis I, Megalooikonomou V, Makałowski W, Vlachakis D, Kossida S. Molecular dynamics simulations through GPU video games technologies. J Mol Biochem. 2014, 3(2):In Press.
  6. Skoura and V. Megalooikonomou, “Analyzing Anatomical Structures of Branching Topology Through Elastic Matching  of Tree Encodings”, 10th IEEE International Symposium on Biomedical Imaging (ISBI), Beijing, China, May 2014.
  7. I. Zacharaki, K. Garganis, I. Mporas, V. Megalooikonomou, “Spike detection in EEG by LPP and SVM “, IEEE EMBS Int. Conf. on Biomedical and Health Informatics (BHI’2014).
  8. Mporas, V. Tsirka, E.I. Zacharaki, M. Koutroumanidis, V. Megalooikonomou, “Evaluation of Time and Frequency Domain Features for Seizure Detection from Combined EEG and ECG signals,” 7th Int. Conf. on PErvasive Technologies Related to Assistive Environments (PETRA 2014).
  9. C. Kagadis, “Cloud Computing in Medical Imaging”, 56th AAPM annual meeting, July 20-24, Austin TX, 2014
  10. Papadimitroulas, G. Loudos, G.C. Kagadis, “Evaluation of a new methodology for paediatric dosimetry: optimization of SPECT protocols, based on Monte Carlo simulations with high-resolution anthropomorphic phantoms”, 8th ECMP, September 11-13, Athens, 2014
  11. C. Kagadis, C. Alexakos, P. Papadimitroulas, N. Papanikolaou, V. Megalooikonomou, D. Karnabatidis, “Cloud Computing Application for Brain Tumor Detection”, ECR, March 4-8, Vienna, 2015
  12. Vlachakis D, Fakourelis P, Makris C, Kossida S. DrugOn: a fully integrated pharmacophore modelling and structure optimization toolkit. PeerJ. 2014, In Press.
  13. Papageorgiou L, Loukatou S, Koumandou VL, Makałowski W, Megalooikonomou V, Vlachakis D, Kossida S. Structural models for the design of novel antiviral agents against Greek Goat Encephalitis. PeerJ. 2014, 2:e664.
  14. Vlachakis D, Champeris Tsaniras S, Ioannidou K, Papageorgiou L, Baumann M, Kossida S. A series of Notch3 mutations in CADASIL; insights from 3D molecular modelling and evolutionary analyses. J Mol Biochem. 2014, 3(3):97-105.
  15. Loukatou S, Fakourelis P, Papageorgiou L, Megalooikonomou V, Kossida S, Vlachakis D. Ebola virus epidemic: a deliberate accident? J Mol Biochem. 2014, 3(3):72-76.
  16. Vlachakis D, Armaos A, Kasampalidis I, Filntisi A, Kossida S. ASSP; the Antibody Secondary Structure Profile search tool. Proceedings of the 2nd International Conference on Algorithms for Big Data; 01/2014 (properly peer-reviewed, to be included in MCS journal)
  17. Christos Makris, Michael Angelos Simos: Novel Techniques for Text Annotation with Wikipedia Entities,  Artificial Intelligence Applications and Innovations – 10th IFIP WG 12.5 International Conference, AIAI 2014, 508-518
  18. Seremeti, A. Kameas. Biomedical engineering through ontologies. Proceedings of the 6th International Conference on Knowledge Engineering and Ontology Development (KEOD), Rome, Italy, 21-24 October, 2014, pp 240-247.
  19. Pippa, E. I. Zacharaki, I. Mporas,V. Tsirka, M. Richardson, M. Koutroumanidis, V. Megalooikonomou, “Classification of Epileptic and Non-Epileptic EEG Events”, 4th Int. Conf. on Wireless Mobile Communication and Healthcare (MOBIHEALTH 2014).

All rights reserved, MDAKM 2017