I am a professor of Computer Engineering at the Middle East Technical University (METU), Ankara, Turkey. I have obtained “Diplôme de Docteur dans la spécialité Informatique” (Ph.D in computer science) from Université Paris Descartes, Paris, France. During sabbatical leave, I spent a year (2004) at Virginia Bioinformatics Institute, Virginia Tech, VA, USA. From 2010 to 2016, I was the Vice President for research of METU and Chairman of Board of Directors of ODTU TEKNOKENT (METU Technopolis). My main responsibilities included strategies and policies for research and for university-industry partnership, relations with both public and private institutions, and corporate strategy management.

My research interest lies in the area of machine learning in bioinformatics. I am also involved in activities related to technology based innovation, technology based entrepreneurship, technology management, and research policies and strategies.

I am currently member of International Technical Advisory Board of Arcelik (Research and Development Directorate) and member of Technology Advisory Board of Turkish Aerospace Industries (TAI).



Diplôme de Docteur dans la spécialité Informatique (Ph.D in Computer Science), 1993, Université Paris Descartes (Paris V), Paris, France
Diplôme d’Etudes Approfondies en Informatique, 1991, Université Paris Descartes (Paris V), Paris, France
Master of Science in Electrical and Electronics Engineering, 1990, METU, Ankara, Turkey
Bachelor of Science in Electrical and Electronics Engineering, 1987, METU, Ankara, Turkey

Professional Positions

Professor, METU, Ankara, Turkey, 2005-present
Associate Professor, METU, Ankara, Turkey, 1998-2005
Research Associate Professor, Virginia Bioinformatics Institute, Virginia Tech, VA, USA, Jan. 2004-Jan. 2005
Assistant Professor, METU, Ankara, Turkey, 1993-1998
Instructor, Université Paris Descartes (Paris V), Paris, France, 1993
Visiting Scholar, New Jersey Institute of Technology, NJ, USA, 1991-1992
Development Engineer, Aselsan Electronics Company, Ankara, Turkey, 1987-1988

Major Administrational Positions

Vice President for research, METU, 2010-2016
Chairman of Board, ODTÜ TEKNOKENT (METU Technopolis), 2010-2016
Member of University Senate, METU, 2010-2016
Assistant to President, METU, 2008-2010
Board Member, Informatics Association of Turkey, 2009-2011
Department Chairperson, METU Dep. of Computer Eng., 2007-2008

Recent Selected Publications

  1. S Genç, M Baştan, U Güdükbay, V Atalay, Ö Ulusoy, “HandVR: a hand-gesture-based interface to a video retrieval system”, Signal, Image and Video Processing, 9 (7), 1717-1726, 2015, doi:10.1007/s11760-014-0631-x.
  2. T. Ersahin, L. Carkacioglu, T. Can, O. Konu, V. Atalay, R. Cetin-Atalay, “Identification of novel reference genes based on MeSH categories”, PLoS ONE, Public Library of Science (PLoS), 9(3): e93341, 2014, doi:10.1371/journal.pone.0093341.
  3. Z. Isik, T. Ersahin, V. Atalay, C. Aykanat, R. Cetin-Atalay, “A signal transduction score flow algorithm for cyclic cellular pathway analysis, which combines transcriptome and ChIP-seq data”, Molecular BioSystems, 8, p.3224-3231, 2012, doi:10.1039/C2MB25215E.
  4. O.S. Sarac, V. Atalay, R. Çetin-Atalay, “GOPred: GO Molecular Function Prediction by Combined Classifiers”, PLoS ONE, Public Library of Science (PLoS), 5(8): e12382, 2010, doi:10.1371/journal.pone.0012382.

list of all publications


In the last 10 years, I am involved in machine learning for bioinformatics. My research efforts are focused on developing and applying computational techniques for the analysis of biological data and modeling of biological processes at the molecular level. The broad aim is to provide computational tools to assist researchers to understand, explain and predict the behavior of complex biological systems.

Our major activity is focused on developing tools for genome annotation based on sequence analysis. Automated classification of proteins is indispensable for further in vivo investigation of excessive number of unknown sequences generated by large scale molecular biology techniques. We have developed a discriminative system based on feature space mapping, called subsequence profile map (SPMap) for functional classification of protein sequences. Instead of focusing on function specific motifs, SPMap considers all of the subsequences as a distribution over a quantized space by discretizing and reducing the dimension of an otherwise huge space of all possible subsequences. We formulated the function annotation problem as a classification problem defined on 300 different Gene Ontology (GO) terms from molecular function aspect. We presented a method to form positive and negative training examples while taking into account the directed acyclic graph (DAG) structure and evidence codes of GO. In addition to SPMap, we have devised and implemented BLAST k-nearest neighbor (BLAST-kNN) and peptide statistics combined with SVMs (PEPSTATS-SVM). We applied these two methods and their combinations for the same problem. Results show that combining different methods improves prediction accuracy in most cases. We are currently extending the application of GOPred to large scale protein databases.

As an alternative to already existing functional enrichment methods aimed at identifying significant biological processes/pathways on the basis of experimental data, we have proposed and developed an approach to assess the activity of cellular pathways on the basis of experimental data. The approach is based on a conversion of the pathway to a directed graph and on a score flow algorithm that initializes scores of pathway nodes relying on experimental data and then iteratively updates scores until convergence is reached. The algorithm has been implemented as a Cytoscape plug-in and tested by relying on different sets of paired transcriptome/Chip-seq data and relying on KEGG pathways. The algorithm has been further tested as an in silico gene knockout tool by relying on a manually constructed pathway. Our current effort is on developing a probabilistic computational method for this approach.

Even the most frequently used reference genes are subject to differential regulation under specific treatments or between different cell lines or tissues. We have devised a method that provides alternative reference gene lists for global and cell-type specific normalization of transcriptome data. Gene lists are scored based on their expression stability, and classified according to the Medical Subject Headings (MeSH) associated with the transcriptome study that was published and indexed by National Library of Medicine.

Although force-directed layout algorithm could be used to draw biological graphs, modification is required when we would like to embed domain-specific knowledge. We proposed a modified and improved (Kamada-Kawaii) force-directed layout algorithm, EClerize, to generate more readable layouts for biological graphs that represent pathways in which the vertices are identified with EC (Enzyme Commission) numbers. While the vertices with the same EC class numbers are treated as members of the same cluster, positions of vertices in clusters are affected by the biological similarity of each vertex in the same cluster and the theoretical length between the vertices.


I enjoy teaching. The best part of teaching is to be in interaction with young people and to learn while you teach as well. I am currently teaching