Dr. Subrata Saha received his PhD in applied algorithms from University of Connecticut, Storrs in 2017. Dr. Saha mainly focuses on designing and developing novel algorithms and data structures in the fields of computational genomics, data mining, and machine learning. He worked on a varied domain of problems in data mining and bioinformatics including closest pair detection, clustering, feature selection, haplotype phasing, metagenomics, biological data compression, error correction for short reads, spliced reads mapping, and sequence assembly. Dr. Saha’s research works have been published in top notch venues including Bioinformatics, BMC Bioinformatics, BMC Genomics, APBC, ACM BCB, IEEE BIBM, IEEE AINA, ADMA, IEEE ICDM, and ACM CIKM.
Dr. Saha’s current role include novel ensemble learning algorithms development, most discriminating variations selection from GWAS case-control study by employing machine learning algorithms, pathway and protein-protein interaction network analysis using novel graph theoretic approach, and AD-active genes prediction and analysis.