Anupama Jha, PhD

Dr. Anupama Jha's research is focused on developing predictive machine-learning methods to understand three-dimensional genome architecture and downstream gene regulation in healthy tissues and cancers. By building computational models that connect DNA sequence, chromatin organization, and functional readouts, her work aims to uncover the principles governing genome regulation across biological contexts and to translate large-scale genomic data into interpretable models of cellular function.

Dr. Jha received a B.Tech. in Information Technology from GGSIPU, an M.S. in Informatics from the Technical University of Munich, and a Ph.D. in Computer and Information Science from the University of Pennsylvania, where she worked in the BioCiphers Lab under the mentorship of Dr. Yoseph Barash. During her doctoral training, she developed interpretable deep learning methods to study tissue-specific alternative splicing and RNA-binding protein regulatory networks, including the development of enhanced integrated gradients as a framework for improving the interpretability of deep learning models in genomics. She then completed postdoctoral training at the University of Washington in the Noble Lab, under the supervision of Dr. William Stafford Noble, prior to joining Yale in 2026.

Among her notable contributions, Dr. Jha developed TwinC, a sequence-to-function model for predicting and functionally interpreting inter-chromosomal genome architecture from DNA sequence, published in Nature Communications. She also co-developed Fibertools, a tool for DNA m6A calling and integrated long-read epigenetic and genetic analysis, published in Genome Research. Her earlier work on applying deep learning to identify common transcriptome signatures of cancer, published in Genome Biology, demonstrated the power of interpretable neural network models for uncovering disease-relevant regulatory programs. She is a collaborating member of the ENCODE, DNA Zoo, and 4D Nucleome Consortia, and is a co-author on a generalizable Hi-C foundation model for chromatin architecture published in Nature Methods.

Dr. Jha is the recipient of an NHGRI K99/R00 Pathway to Independence Award, an NVIDIA Academic Grant, and a UW Data Science Fellowship from the eScience Institute at the University of Washington. She has received travel fellowships from ISMB/ECCB and multiple best poster awards, including at the RNA Biology & Cancer Symposium. She serves on the Joint Steering Committee of the Yale-BI Biomedical Data Science Fellowship and is an active reviewer for journals including Genome Biology, Nature Communications, and PLOS Computational Biology, as well as conferences including RECOMB and ISMB.