Predrag Radivojac

[Teaching] [Research] [People] [Publications] [Software] [FAQ]


Pedja Radivojac, Indiana University, 2013

Professor of Computer Science and Informatics

Adjunct Professor of Statistics


Department of Computer Science and Informatics

Indiana University

150 South Woodlawn Avenue

Bloomington, IN 47405

Office:  Lindley Hall 301F

Phone:  (812) 856-1851


Download my curriculum vitae in pdf format (last updated on 07/13/2016). Google Scholar profile.


Post-doctoral fellow, Bioinformatics, Indiana University School of Medicine, Indianapolis, Indiana, 2004

Ph.D., Computer and Information Sciences, Temple University, Philadelphia, Pennsylvania, 2003

M.S., Electrical Engineering, University of Belgrade, Serbia, 1997

B.S., Electrical Engineering, University of Novi Sad, Serbia, 1994

Professional Activities:

Board of Directors Member, International Society for Computational Biology (ISCB), 2012-

Associate Editor, PLoS Computational Biology, 2014-

Editorial Board Member, Bioinformatics, Oxford University Press, 2010-

Evolution of Molecular Function at PSB 2017

Yana Bromberg, Matt Hahn and I are organizing a session on the evolution of molecular function at PSB 2017. Details here.

Recent Updates:

  1. (September 2016) Sujun's paper accepted to the Journal of Proteome Research; available here.

  2. (September 2016) CAFA2 paper officially published, with Yuxiang being the first author; available here.

  3. (September 2016) We have pre-computed MutPred scores for about 80 million possible human variants; available here.

  4. (August 2016) Shantanu's paper accepted to NIPS 2016; pre-print available on arXiv.

  5. (August 2016) Jose's paper on the functional significance of disease mutations accepted to PLoS Computational Biology.

  6. (July 2016) Krishna Reddy's paper (U South Florida) with Vikas and me as coauthors accepted to Journal of Biomolecular Structure and Dynamics.

  7. (July 2016) Our review paper, with Burkhard Rost (TUM) and Yana Bromberg (Rutgers) on protein function, machine learning and precision medicine accepted to FEBS Letters.

  8. (July 2016) Kym gave a talk at ISMB's VarI-SIG in Orlando, Florida. Jose, Vikas, Ruiyu and Yuxiang all attended ISMB.

  9. (June 2016) Vikas's paper in top-10 most cited papers in Protein Science among all papers published in 2014-2015.

  10. (May 2016) I will be chairing a session at the Gordon Research Conference about Variant Effects in the Era of Genome Sequencing. The conference takes place in June 2016. Abstract and poster submission until May 15, 2016.

  11. (May 2016) I am visiting Technical University of Munich in Germany as an August-Wilhelm Scheer Visiting Professor.

  12. (April 2016) Chao's paper on identification of cross-linked peptides accepted in the Journal of Proteome Research. Manuscript available here.

  13. (April 2016) Chao defends Ph.D. dissertation on April 11. Congratulations!

  14. (March 2016) Our session of the evolution of molecular function accepted for Pacific Symposium on Biocomputing 2017. The session is co-organized with Yana Bromberg and Matt Hahn. Consider submitting a paper!

  15. (March 2016) Ruiyu's pre-print on new distance metrics on sets, ontologies and functions is now available on arXiv. The paper also introduces functional phylogenies.

  16. (February 2016) Vikas receives eScience Moore/Sloan Data Science and Washington Research Foundation Innovation in Data Science Postdoctoral Fellowship, at the University of Washington.

  17. (January 2016) Shantanu's pre-print on estimating class priors from positive and unlabeled data is now available on arXiv.

Research Interests:

Bioinformatics and Computational Biology

 Protein structure and function; method development and evaluation for function prediction.

 Post-translational modifications (PTMs)

 Mass spectrometry (MS) and MS/MS proteomics.


Biomedical Informatics and Applications to Human Health

 Development of computational models for understanding and predicting molecular mechanisms of disease.

 Candidate gene prioritization and biomarker discovery.

 Genome interpretation.


Machine Learning

 Supervised and semi-supervised learning: learning from positive and unlabeled data; learning from biased data.

 Structured-output learning and evaluation; extreme classification.

 Kernel-based inference on sequences, time-series, and graphs.


Last modified: September 16, 2016