Ramana Davuluri, PhD

Ramana Davuluri is a world leader in Molecular Data Science, with research focus on computational analysis of non-coding genomic regions and isoform-level gene regulation. Davuluri is well-known for his pioneering efforts to use artificial intelligence (AI) methods in biomedical applications, for example, algorithms for gene promoter prediction and molecular subtyping assays for glioblastoma and ovarian cancers, deep-learning algorithm for multi-omics data analyses, and informatics methods for analysis of cancer drug-target interactions affected by alternative splicing. Davuluri group has developed novel genomic foundation models for understanding the DNA language, and how genetic and epigenetic changes in the non-coding genome alter the DNA linguistics. Working at the interface of AI and Bioinformatics, Davuluri is one of the first groups to develop genomic foundation, called “DNABERT”. Released in 2021, DNABERT is widely used in understanding and decoding genomic and epigenomic languages. DNABERT based predictive models can prioritize candidate genomic variants and associated gene regulatory regions that are sensitive to variants at genome-scale. Building on DNABERT’s success, his group is developing informatics methods to calculate genome-wide mutational scores, based on whole genome sequence data, and integrate other biomedical data, such as histology, gene expression and microbiome metagenomics to improve diagnosis and patient outcome prediction.