The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Biomedical Data Science and Bioinformatics Unit was founded and it is supported by the project “InTechThrace: Integrated Technologies in biomedical research: multilevel biomarker analysis in Thrace”. The aim of the Unit is to offer data analytic services in a wide range of research areas in Faculty of Health Science (DUTh), as well as to set up infrastructure (hardware) to support the computational needs of bioscientists in DUTh.

The main aim of the unit is on developing new methods, tools and databases for handling and organizing and analyzing a wide range of data types such as large-scale omics data, clinical data, Electronic Health Records (EHRs) and others. The development and analysis is preformed using the most up-to-date technologies and framework, such as Python, R, Java, Tensorflow, PHP/Laravel, Typescript/Angular, SQL/PostgreSQL, NoSQL/MongoDB.

The unit offers:

• Analyses incorporating various Artificial Intelligence elements, Machine Learning and Deep Learning algorithms (Descriptive, predictive and prescriptive analytics)
• Database, ontology and web application development

• Next Generation Sequencing Omics data preprocessing and analysis (Quality check, adapter inference and removal, quantification, pathway analysis)

• Search, retrieval, storage and analysis of data from open data repositories and databases (NCBI-SRA, TCGA, GTEx, ArrayExpress, GEO)