Shantanu Jain is a research scientist at the Institute for Experiential AI. Previously, he was an associate research scientist at the Radivojac bioinformatics lab in the Khoury College of Computer Sciences. His research focuses on developing novel machine learning methods to address issues, such as absence of labeled data from one or more classes, detection and correction of selection bias, model calibration, querying expensive features and labels for model improvement, prediction, and evaluation. His work has been applied to problems in bioinformatics and clinical genetics, such as training models for variant effect prediction, estimating the proportion of pathogenic variants, prioritizing genes and variants to generate functional evidence for improved classification, and false discovery rate estimation in mass spectrometry-based proteomics.

He has been an active member of the Impact of Genomic Variation on Function (IGVF) consortium, where he regularly communicates with biologists and experimental scientists to understand and solve computational problems with AI. He has been an active member and assessor for the Critical Assessment of Genome Interpretation (CAGI) consortium. He has served as an organizer of the MLD bootcamp to teach machine learning to undergraduate students from diverse backgrounds and help them build pathogenicity predictors for metachromatic leukodystrophy. Shantanu graduated with doctoral and master’s degrees in computer science and statistics from Indiana University.