Assistant Professor
Address:
901 East 10th Street
Bloomington, IN 47408
Telephone: (812) 856-1851
Fax: (812) 856-1995
Office: Informatics 219
Email:..predrag@indiana.edu..
Education:
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
Recent updates:
▪ PSB 2009
"Molecular Bioinformatics for Diseases" is a session I am co-chairing at the 14th Pacific Symposium on Biocomputing, PSB 2009. This session is organized with Atul Butte (Stanford U.), Maricel Kann (UMBC), Yves Lusier (U. Chicago), and Yanay Ofran (Bar-Ilan U.). This is an extension of the sessions we organized from 2006 till 2008.
▪ AMIA Summit
on Translational Bioinformatics 2009
Summit on Translational Bioinformatics is a meeting dedicated to bioinformatics research and applications in the fields encompassing medical and clinical domains. This symposium will be held March 15-17, 2009 and is sponsored by AMIA and ISCB. See call for participation here.
Research Interests:
▪ Protein Bioinformatics
Methods for characterization and prediction of protein's structural and functional properties, both on a whole sequence and residue level. This includes automated inference of GO or EC protein annotation from its sequence/structure/interactions, as well as understanding post-translational modifications, protein-partner binding sites, extracting knowledge from literature etc. We are also interested in understanding the relationship between protein molecular function and its involvement in disease.
▪ Computational Proteomics
Methods for peptide identification, protein identification and protein quantification from tandem mass spectrometry data. Each peptide in a mixture of digested proteins can be viewed through its probability to be detected (identified) by a mass spectrometry instrument and corresponding software package. We hypothesized that this property, called peptide detectabiltiy, can be successfully inferred from amino acid sequence of a peptide and its parent protein. We use peptide detectability to build algorithms for protein inference and showed a correlation between peptide detectability and protein amount in a sample, which can be used for label-free quantification.
▪ Machine Learning/Data Mining
Classification methods: prediction from biased, noisy, high-dimensional, class-imbalanced, and heterogeneous data. These methods include feature selection algorithms, estimation, exploiting unlabeled data, etc.
Last modified: July 27, 2008