Rohan Subramanian

I'm a second-year PhD student at NYU Courant advised by Prof. Romain Lopez in the BioML Group and CILVR Lab. My interests lie at the intersection of machine learning and biology. I'm grateful to be supported by the NSF GRFP.

I graduated in 2025 from Harvey Mudd College in Claremont, where I studied computer science with a humanities concentration in music.

I spent a summer at Memorial Sloan Kettering Cancer Center working with Wesley Tansey in Computational Oncology. At Harvey Mudd, I've had the privilege to work with Gabriel Hope on deep generative models and Danae Schulz on parasite gene regulation. Previously, I worked with Debashis Sahoo at UC San Diego, where I investigated Boolean network models of biological systems.

Email  /  CV  /  Scholar  /  Linkedin  /  Github

profile photo

Research Interests

My research sits at the intersection of machine learning and biology, where I seek to develop robust and interpretable methods for understanding complex biological systems using representation learning and generative modeling. Currently, I am interested in applications to single-cell and perturbation biology, particularly immune cells in health, cancer, and inflammatory diseases.

My Work

Publications, presentations, and other research projects.

Probabilistic time series modeling of tumor growth in patient-derived xenografts
Rohan Subramanian, Wesley Tansey
Computational Biology Summer Program Final Symposium, 2024
Poster / Abstract

Semi-supervised learning with constrained deep generative models
Rohan Subramanian, Sahil Rane, Saheli Patel, Gabriel Hope
January 2024-present
Code
Boolean implication analysis of single-cell data predicts retinal cell type markers
Rohan Subramanian, Debashis Sahoo
BMC Bioinformatics, 2022
Paper


Miscellanea

Hacks

MuddBots: talk to your textbooks (Track Winner, LAHacks 2023)
Breeezy: connect with outdoor enthusiasts (Finalist, HackTech 2024)

Teaching

Academic Excellence Tutor (2023-present): Introduction to Biology, Molecular Genetics
Teaching Assistant: Principles of CS (FA23), Algorithms (FA24), Neural Networks (SP25)

Inspired by a template from Jon Barron.