Projects

Projects

About

The Multidimensional Data Analysis and Knowledge Management Laboratory in the Department of Computer Engineering and Informatics of the University of Patras is a laboratory devoted to research and educational activities related to the development of methodologies, algorithms and software tools for the efficient analysis and management of multidimensional data. The lab focuses on the development of similarity metrics for various types of data, techniques for data preprocessing and representation, feature extraction, dimensionality reduction, pattern detection, classification, clustering, association discovery, data modeling and simulation, and on the application of these methodologies to critical sectors such as medicine, biology, the environment, etc. The lab members are engaged in the analysis of various spatiotemporal data obtained from a wide range of modalities. The laboratory collaborates with other research units at the University of Patras including the Medical Image Processing and Analysis Group and the Neurophysiology Lab of the University of Patras, School of Medicine and other institutes in Greece such as the Biomedical Research Foundation, Academy of Athens, the Hellenic Open University, etc. The Laboratory also has active collaboration with international researchers at several foreign institutions including Carnegie Mellon University, MD Anderson Cancer Center, Univ. of Pennsylvania, Temple Univ., Univ. of California Riverside, Univ. of Maryland, Indiana Univ., Yale, and University of California, Los Angeles (UCLA), Rutgers University, Kings College London (KCL), Karlsruhe Institute of Technology (KIT), Ecole Centrale de Paris, institutes such as the National Institutes of Health in the US as well as industrial partners in US and Europe.

Members

Director
Vasilis Megalooikonomou

Prof. Vasilis Megalooikonomou, received his B.E. in Computer Engineering and Informatics from the Univ. of Patras (UoP), Greece, in 1991, and his M.S. and Ph.D. in Computer Science from the Univ. of Maryland, Baltimore County in 1995 and 1997, respectively. He is currently a Professor in the Computer Engineering and Informatics Department (CEID) of UoP, Greece. Prior to his appointment at UoP, he held faculty positions at Temple University, Dartmouth College and Johns Hopkins University, School of Medicine. His research interests include medical informatics and bioinformatics, data mining, data compression, pattern recognition, intelligent information systems, medical image analysis, and multimedia database systems. He has co-authored over 200 refereed articles in journals and conference proceedings and six book chapters. He has been on the program committees of a number of premier conferences and he is regularly serving as a referee for a number of premier journals in his areas of research. He received a CAREER award from the National Science Foundation in 2003 to work on developing data mining methods for extracting patterns from medical image databases. His research has been supported in the United States by the National Science Foundation, the National Institutes of Health, the Pennsylvania Department of Health and the Lockheed Martin Corporation. During the last 8 years he has served as the scientific coordinator of the FP7 ARMOR project and of the BIOMEDMINE project co-financed by the European Social Fund and Greek national funds. He is currently the coordinator of the H2020 FRAILSAFE project. Prof. Megalooikonomou is a member of IEEE, IEEE CS, ACM, SIAM and OHBM.

Research

Research areas

1. Data Management Systems
In addition to the design and development of databases we focus on providing extensions to existing DBMS technology to support the organization of complex data including the support of efficient storage and retrieval capabilities such as multidimensional indexing and content-based queries for multimedia. We investigate data compression issues and study how properties/characteristics of data can be used to improve their management. We also focus on providing extensions to geographic information systems (GIS) and enhance their analytical capabilities. Other areas of interest include development of data management tools for streaming data (DSMS), taking into account computational cost constraints, while highlighting further requirements such as data summarization and caching, in order to serve rapid transaction requests. A recent research focus includes NoSQL databases.

2. Biomedical Data Analysis
2.1 Biomedical Image Analysis
Our focus on Biomedical Image Analysis is on the development of computer-based approaches and decision-support tools applicable to clinical practice. In our lab, image analysis methodologies focus on medical image segmentation and registration, high dimensional feature extraction and pattern classification, texture, tree structure and morphological variability analysis. Clinical research studies span a variety of clinical areas, such as brain tumors, brain lesions or breast cancer. Brain and breast imaging modalities for which we have expertise analyzing data from include: conventional Magnetic Resonance Imaging (MRI), Computerized Tomography (CT), functional MRI (fMRI), ultrasound (US), digital subtraction angiography (DSA), galactography and mammography. These modalities are commonly utilized in clinical practice and provide noninvasive images of anatomy and function of living tissues.

2.2 Health informatics and data analytics
The health informatics and data analytics group aims to apply new data management, knowledge discovery and data mining technologies in complicated multi-dimensional, multi-scale, multi-modal health data to develop effective decision support systems that improve health care. Our group, recognizing human beings as the ultimate users of biomedical information, focuses on bridging the gap between clinical research and practice; thus, we develop effective health data management systems for the storage, retrieval, usage and sharing of biomedical knowledge.

3 Bioinformatics
Our work in bioinformatics is centered around two main axis: analysis of gene expression maps and analysis of protein molecular surfaces. Voxelation is a relatively new method for obtaining gene expression patterns in the brain. It employs high-throughput analysis of spatially registered voxels to produce 3-D maps of gene expression. Gene expression in the mammalian brain holds the key for understanding neural development and neurological disease. Our lab has done extensive work on large scale data analysis for identifying the relation between gene expression maps obtained by voxelation and gene functions. Moreover, in the areas of drug design, pharmacology and 3D molecular modeling and in order to speed up the drug discovery process, considering the rapid increase in genomic and structural database sizes, we are developing novel strategies to perform effective and efficient similarity searches and molecular docking experiments using protein molecular surfaces.

4. Big Data pattern analysis and modeling
The large amount of digital information in society is inherently connected to advances in technology, the WWW, the rise of smart phones, cloud services, the Internet of Things. This big data phenomenon is unstructured and transient. Motivated by this reality, the Big Data pattern analysis and modeling group aims at converting raw data into valuable knowledge by uncovering hidden patterns and unknown correlations in order to stimulate scientific discoveries and optimize processes within the society through the understanding of social and collective behavior. Our research, applied to a broad range of applications, spans from data management and advanced data analysis to service platforms. More specifically, our research interests include:

• Multi-dimensional data analysis (preprocessing, feature extraction, dimensionality reduction, knowledge discovery)
• Spatial, temporal (including multi-dimensional time series), spatio-temporal data mining
• Computational frameworks and modeling (data driven, statistical, probabilistic, graph (time-evolving and static))
• Data representation, integration, fusion and high-order analysis
• Data compression
• Streaming data analysis and decision making
• Applications of interest: energy management, economics, environment, human activity, social behavior, seismology, neuroinformatics.

5. Natural language processing
The NLP group of the MDAKM laboratory of the University of Patras, constitutes an integrated research environment for the design and development of language technology products and solutions. In continuous interaction with the academic community, the national and European informatics industry, the international scientific community and the public sector, NLP group has evolved to an internationally renowned institution in Computer Science and Technology. NLP group is involved in both theoretical and applied research in the general field of databases, natural language processing and information retrieval, pattern recognition and software engineering. The NLP group has the expertise for carrying out large scale IT projects and collaborates with senior researchers who are capable of conducting cutting edge research in the fields of Natural Language Processing, Very large Databases and Hypermedia.

Projects

General Description of projects

Current Projects

MilkSafe

Project code: Milksafeimage

Project Title: An innovative research project to unravel the special features of human breast milk and enrich formula milk using omics technologies

Website: http://darkdna.gr/milksafe/index.html

Description: We aim to perform an extensive comparative analysis of human breastmilk with three locally traded animal milks (domestic sheep, goats and cattle from different regions of Greece ). In particular, a high-quality, quantitative and qualitative study will be conducted for the analysis of the membrane and intracellular composition of the major classes of secreted extracellular vesicles and other transported microparticles. The long term aim is to establish topological networks of phylogenetic distance across human biopolymers. The proposed multidimensional bioinformatics analysis will show which animal milk has the highest phylogenetic affinity for human milk based on specific nucleotide and amino acid sequences, and thus the highest nutritional value for neonates. Application of high-throughput techniques in combination with comparative genomic analysis of mRNAs, non-coding RNAs, proteins, and small molecules that bind or are encapsulated in secreted lipid membranes (exosomes) will be included.

Duration: 29/10/2020 – 30/9/2023

Role: Subcontractor

Consortium: Agricultural University of Athens (team from the Genetics Laboratory), Research University Institute of Maternal and Child Health, and Precision Medicine, ELGO Demeter, Gene Expression Laboratory, Molecular Diagnostics & Modern Therapeutic Means of the Democritus University of Thrace, GIOTIS S.A., EVROPHARM A.E., STAMOU A.E., and the Association of Greek Food Industries (SEVT)

Funding: Co-financed by the European Union’s European Regional Development Fund (ERDF) and national resources through the Operational Programme Competitiveness, Entrepreneurship, and Innovation (EPAnEK). Intervention II ‘Collaborations of Businesses with Research Organizations’ of the 2nd cycle of the Single Action for State Aid for Research, Technological Development & Innovation ‘RESEARCH – CREATE – INNOVATE.’ EPAnEK 2014-2020 Operational Programme Competitiveness, Entrepreneurship, Innovation.

Budget: 878,135.00 €

Bridging big omical, genetic and medical data for the wide application of Precision Medicine in Greece

Project code: TAEDR-0539180image

Project Title: Bridging big omical, genetic and medical data for the wide application of Precision Medicine in Greece

Website: http://gomedprecision.gr/

Description: The main objective of the project is the utilization of modern high-resolution molecular data (genetics, metabolomics etc. ) in order to integrate them (consolidation) in patient registries, so that in combination with clinical and epidemiological data to contribute to an integrated environment of innovative Smart-Electronic Health Record (E-EFY) with integrated clinical decision / prediction support subsystems for the support of the doctor and the personalized therapeutic approach. Utilizing state-of-the-art technologies for the management of large volumes of data and the construction of new algorithmic methods, the project focuses on improving the prognosis and clinical management of diseases, through understanding the genetic background of the disease in each patient individually, in order to determine the risk of developing both rare and common diseases such as cardiovascular diseases, metabolic diseases, various cancers etc.

Duration: 8/2023-12/2025

Role: Development of Machine Learning Models for Knowledge Mining and Patient Categorization

Consortium: University of Thessaly, BIOMEDICAL SCIENCES RESEARCH CENTER “ALEXANDROS FLEMING”, University of Patras, Hellenic Pasteur Institute

Funding: GENERAL SECRETARIAT FOR RESEARCH AND TECHNOLOGY

Budget: 2,392,436€ €
Budget Work Package: 165,921€

(Greek)
Κωδικός έργου: TAEDR-0539180

Τίτλος έργου: Γεφυρώνοντας μεγάλα ομικά, γενετικά και ιατρικά δεδομένα για την ευρεία εφαρμογή της Ιατρικής Ακρίβειας στην Ελλάδα

Ιστοσελίδα: http://gomedprecision.gr/

Περιγραφή: Βασικό αντικείμενο του έργου είναι η αξιοποίηση των σύγχρονων μοριακών δεδομένων υψηλής ευκρίνειας (γενετική, μεταβολομική, κα. ) με σκοπό την ένταξη τους (ενοποίηση) στα μητρώα ασθενών, ώστε σε συνδυασμό με τα κλινικά και επιδημιολογικά δεδομένα να συντελέσουν ένα ολοκληρωμένο περιβάλλον καινοτόμου Έξυπνου-Ηλεκτρονικού Φακέλου Υγείας (Ε-ΗΦΥ) με ενσωματωμένα υποσυστήματα υποστήριξης κλινικής απόφασης/πρόβλεψης για την υποστήριξη του ιατρού και την εξατομικευμένη θεραπευτική προσέγγιση. Αξιοποιώντας σύγχρονες τεχνολογίες για την διαχείριση δεδομένων μεγάλου όγκου και με την κατασκευή νέων αλγοριθμικών μεθόδων το έργο εστιάζει στη βελτίωση την πρόγνωση και κλινική διαχείριση νοσημάτων, μέσω της κατανόησης του γενετικού υποβάθρου της νόσου σε κάθε ασθενή εξατομικευμένα, ώστε να προσδιοριστεί ο κίνδυνος εμφάνισης τόσο σπάνιων όσο και κοινών νοσημάτων όπως τα καρδιαγγειακά νοσήματα, μεταβολικά νοσήματα, διάφοροι καρκίνοι κα.

Διάρκεια:8/2023-12/2025

Ενότητα εργασίας: Ανάπτυξη Μοντέλων Μηχανικής Μάθησης για Εξόρυξη Γνώσης και Κατηγοριοποίησης Ασθενών

Εταίροι: Πανεπιστήμιο Θεσσαλίας, ΕΡΕΥΝΗΤΙΚΟ ΚΕΝΤΡΟ ΒΙΟΙΑΤΡΙΚΩΝ ΕΠΙΣΤΗΜΩΝ «ΑΛΕΞΑΝΔΡΟΣ ΦΛΕΜΙΓΚ», Πανεπιστήμιο Πατρών, Ελληνικό Ινστιτούτο Παστέρ

Χρηματοδότηση: ΓΕΝΙΚΗ ΓΡΑΜΜΑΤΕΙΑ ΕΡΕΥΝΑΣ ΚΑΙ ΤΕΧΝΟΛΟΓΙΑΣ

Προϋπολογισμός: 2,392,436€ €
Προϋπολογισμός Ενότητα Εργασίας ΕΕ6: 165,921€

FrailSafe

Project code: FrailSafe

Project Title: Sensing and predictive treatment of frailty and associated co-morbidities using advanced personalized models and advanced interventions

Website: http://frailsafe-project.eu

Description: Ageing population is steeply increasing worldwide. A consequence of age related decline is the clinical condition of frailty. Frailty is a biological syndrome of decreased reserve and resistance to stressors, resulting from cumulative declines across multiple physiologic systems and causing vulnerability to adverse outcomes. Susceptibility to stressors is influenced by biological, behavioral, environmental, and social risk factors, with the main consequence being an increased risk for multiple adverse health outcomes, including disability, morbidity, falls, hospitalization, institutionalization, and death. However, frailty is a dynamic and not an irreversible process; it seems preventable, may be delayed, or reversed. Our understanding of frailty has markedly improved over the last five years, yet there are many issues yet to be resolved. FrailSafe aims to better understand frailty and its relation to co-morbidities; to identify quantitative and qualitative measures of frailty through advanced data mining approaches on multiparametric data and use them to predict short and long-term outcome and risk of frailty; to develop real life sensing (physical, cognitive, psychological, social ) and intervention (guidelines, real-time feedback, Augmented Reality serious games) platform offering physiological reserve and external challenges; to provide a digital patient model of frailty sensitive to several dynamic parameters, including physiological, behavioural and contextual; this model being the key for developing and testing pharmaceutical and non-pharmaceutical interventions; to create “prevent-frailty” evidence-based recommendations for the elderly; to strengthen the motor, cognitive, and other “anti-frailty” activities through the delivery of personalised treatment programmes, monitoring alerts, guidance and education; and to achieve all with a safe, unobtrusive and acceptable system for the ageing population while reducing the cost of health care systems.

Duration: 01/2016 – 06/2019

Role: Coordinator

Consortium: University of Patras (Greece), Brainstorm Multimedia (Spain), Smartex (Italy), AGE Platform Europe (Belgium), Center for Research and Technology Hellas/Information Technologies Institute (Greece), Materia Group (Cyprus), Gruppo SIGLA (Italy), Hypertech (Greece), University Hospital of Nancy and INSERM U1116 Nancy (France)

Funding: H2020-PHC-21-2015

Budget: 3,820,896.25 €

Past Projects

SCH: EXP: Cost Efficient Osteoporosis Analysis using Dental Data

ARMOR – Advanced multi-paramertic monitoring and analysis for diagnosis and optimal management of epilepsy and related brain disorders

BIOMEDMINE: Mining Biomedical Data and Images: Development of Algorithms and Applications

Herakleitus II. - Data Mining from Tree and Network Topologies represented in Medical Images

Program C. Carathéodory - Shape analysis based on subsequence similarity methods

Small: Collaborative Research: Modeling, Detection, and Analysis of Branching Structures in Medical Imaging

Collaborative Research: Mining Biomedical and Network Data Using Tensors

CA­REER: Extracting Patterns from Medical Image Databases

Large Scale Data Analysis for Brain Images

Mining Human Brain Data: Analysis, Classification, and Visualization of Probabilistic 3D Objects

High Performance Network Connection for Knowledge Discovery Research

Visualization and Analysis of Commercial Flight Data

Mining 3-D Medical Image Data

Spatially Oriented Database for Digital Brain Images

Other Grants

ANGIO

Τεχνόηση: Τεχνητή Νοημοσύνη και Εφαρμογές

Supplemental award

Supplemental award

Supplemental award

Supplemental award

Tools

Tools generated in MDAKM

NOTCH3

Description:
We created an information system to provide access to an organized data set of all genetic replacement mutations that can be found in the NOTCH3 protein, arranged in a database that facilitates their study.
The main goal is understanding the CADASIL syndrome at the genetic level, since mutations in the NOTCH3 protein have been linked with the syndrome, so as to discover useful information that could be applied in the development of pharmaceutical solutions directed against it.

Link:
NOTCH3 tool

Manual:
NOTCH3 manual

Drugster Suite

Description:
Drugster is a de novo Drug Design platform, which through the versatility of the elite software that it incorporates can efficiently exploit single or multiple processor workstations and achieve high performance through novel and faster custom-made routines. Drugster is a freeware platform aimed to assist scientists in the field of Computer Aided Drug Design (CADD). It facilitates the use of other freeware applications (PDB2PQR, Gromacs, Ligbuilder, Dock) in order to create a pipeline for producing high quality results.

Link:
https://drive.google.com/file/d/0B3M_yvYLwDcpRDBIUzdCQnBoYjg/view

Citation:
Vlachakis D, Tsagkrasoulis D, Megalooikonomou V, Kossida S. (2012 ) Introducing Drugster: a comprehensive drug design, lead and structure optimization toolkit. Bioinformatics, 2013, 29(1):126-128. [doi: 10.1093/bioinformatics/bts637]

DrugOn Suite

Description:
During the past few years, pharmacophore modeling has become one of the key components in computer-aided drug design and in modern drug discovery. DrugOn is a fully interactive pipeline designed to exploit the advantages of modern programming and overcome the command line barrier with two friendly environments for the user (either novice or experienced in the field of Computer Aided Drug Design) to perform pharmacophore modeling through an efficient combination of the PharmACOphore, Gromacs, Ligbuilder and PDB2PQR suites. Our platform features a novel workflow that guides the user through each logical step of the iterative 3D structural optimization setup and drug design process. For the pharmacophore modeling we are focusing on either the characteristics of the receptor or the full molecular system, including a set of selected ligands.

Link:
https://drive.google.com/file/d/0B3M_yvYLwDcpS1U0dlBFdDJDdlE/view

Citation:
Vlachakis D, Fakourelis P, Megalooikonomou V, Makris C, Kossida S. (2015 ) DrugOn: a fully integrated pharmacophore modeling and structure optimization toolkit. PeerJ, 2015; 13;3:e725. . [doi: 10.7717/peerj.725]

Education

Undergraduate Courses

• Databases Ι
• Databases ΙΙ
• Databases Laboratory
• Data Mining and Algorithms for Machine Learning

Postgraduate Courses

MSc in Computer Science and Engineering

• Special Topics in Spatial and Temporal Databases and Knowledge Discovery (graduate level)

MSc in Informatics for Life Sciences

• Medical Informatics I
• Medical Informatics II
• Basic Methods of Machine Learning and Data Mining

MSc in Biomedical Engineering

• Biostatistics & Data Analytics

MSc in Mathematics of Computation and Decision Making

• Knowledge Discovery in Databases

Publications

Refereed Publications in International Journals (in reverse chronological order)

M. Tsivgoulis, T. Papastergiou and V. Megalooikonomou, “An Improved SqueezeNet Model for the Diagnosis of Lung Cancer in CT Scans”, Machine Learning with Applications, Vol. 10, 2022
100399, ISSN 2666-8270, https://doi.org/10.1016/j.mlwa.2022.100399.
F.-I. Dimitrakopoulos, G. Mountzios, P. Christopoulos, T. Papastergiou, M. Elshiaty, L.Daniello, E. Zervas, S. Agelaki, E. Samantas, A. Nikolaidi, I. Athanasiadis, S. Baka, K. Syrigos, A.Christopoulou, E. Lianos, K. Samitas, N. Tsoukalas, E.-I. Perdikouri, G. Oikonomopoulos, A. Kottorou, F. Kalofonou, T. Makatsoris, A. Koutras, V. Megalooikonomou, H. Kalofonos, “Validation of PIOS (Patras Immunotherapy Score ) Model for Prediction and Prognosis of Patients with Advanced NSCLC Treated with Nivolumab or Pembrolizumab: Results from a European Multicenter Study”, Therapeutic
Advances in Medical Oncology, 2022;14. doi:10.1177/17588359221122728.
I.M. Grypari, Ι. Pappa, T. Papastergiou, V. Zolota, I. Bravou, M. Melachrinou, V.Megalooikonomou, V. Tzelepi, “Elucidating the role of PRMTs in prostate cancer using open access databases and patient cohort dataset”, Histology and Histopathology, 2022.
G. I. Smani, V. Megalooikonomou, “Maximization Influence in Dynamic Social Networks and Graphs”, Array, 15, 2022, https://doi.org/10.1016/j.array.2022.100226.
Papakonstantinou E, Mitsis T, Dragoumani K, Bacopoulou F, Megalooikonomou V, Chrousos GP, Vlachakis D. “The medical cyborg concept”. EMBnet J. 2022 Apr;27:e1005. doi: 10.14806/ej.27.0.1005. Epub 2022 Apr 21. PMID: 35464258; PMCID: PMC9022891.
Papakonstantinou E, Io Diakou K, Mitsis T, Dragoumani K, Bacopoulou F, Megalooikonomou V, Kossida S, Chrousos GP, Vlachakis D. “Molecular fusion events in carcinogenic organisms: a bioinformatics study for the detection of fused proteins between viruses, bacteria and eukaryotes”. EMBnet J. 2022 Apr;27:e1004. doi: 10.14806/ej.27.0.1004. Epub 2022 Apr 4. PMID: 35464257; PMCID: PMC9029568.
Kalamaras, K. Glykos, V. Megalooikonomou, K. Votis, D. Tzovaras, “Graph-based visualization of sensitive medical data”, Multimedia Tools and Applications, pp. 1-28, Springer, https://doi.org/10.1007/s11042-021-10990-1, 2021.
Papadimitriou K, Koumoulidis D, Papalamprou L, Kasimatis C, Sparangis P, Katsenios N, Megalooikonomou V, Vlachakis D, Triantakonstantis D, Efthimiadou A. Environmental impacts of wars-Social consequences. Case Study: Aleppo Governorate Syria, EMBnet Journal 2021, Accepted. In Press.
F.-I. D. Dimitrakopoulos, G. S. Mountzios, P. Christopoulos, T. Papastergiou, E. Zervas, S. Agelaki,