Tanmayee Narendra’s research focuses on the intersection of machine learning and biological systems, with a particular emphasis on causal reasoning and epigenomic modeling. Their early indexed work centers on explaining deep learning models using causal inference, a framework that has received 28 citations for its approach to model interpretability. This interest in causality extends to the application of counterfactual reasoning for process optimization using structural causal models, which explores how algorithmic interventions can improve complex workflows. More recently, Narendra’s lead-author research has transitioned into high-resolution genomics, specifically focusing on learning shared chromatin landscapes and joint de-noising of histone modification assays to advance personalized epigenomics. The researcher’s broader contributions include collaborative efforts to refine precision medicine through computational tools. Publicly indexed outputs suggest a significant role in developing individual-specific epigenomic imputation with machine learning, a study published in Nature Communications that addresses the challenges of data sparsity in epigenetic profiling. Narendra has also contributed to the technical toolkit of the field through the development of multi-histone ChIP-Seq analysis with DecoDen, a method designed to enhance the clarity of genomic signals. Collectively, these works represent a research arc that moves from foundational causal theory toward the practical application of deep learning for understanding individual-specific regulatory biology.