I'm a PhD student at the Stanford AI Lab (SAIL), advised by Ron Dror, where I develop ML methods for molecular biology applications. Previously, I graduated from the University of California, Berkeley, where I earned my Bachelor's and Master's degrees in EECS.
At Berkeley, I was a member of the Yosef Lab, where I developed VAE models for single-cell genomics data as part of the scvi-tools team. Previously, I built RNA design algorithms and benchmarks in Rhiju Das's Lab. I've also interned at Microsoft Research (advised by Eric Horvitz and Bruce Wittmann), Google, and Atomic AI.
A Graph Completion Method that Jointly Predicts Geometry and Topology Enables Effective Molecule Assembly
Rohan V Koodli, Alexander S Powers, Ayush Pandit, Chiho Im, Ron O Dror
MLSB 2025
Paper
MedSAGE: Bridging Generative AI and Medicinal Chemistry for Structure-Based Design of Small Molecule Drugs
Alexander S Powers, Tianyu Lu, Rohan V Koodli, Minkai Xu, Siyi Gu, Masha Karelina, Ron O Dror
bioRxiv, May 2025
Paper
Redesigning the Eterna100 for the Vienna 2 folding engine
Rohan V Koodli*, Boris Rudolfs*, Jonathan Romano*, Hannah K Wayment-Steele, William A Dunlap IV, Eterna Participants, Rhiju Das
bioRxiv, March 2025
Paper
Code
Geometric deep learning for structure-based ligand design
Alexander S Powers, Helen H Yu, Patricia Suriana, Rohan V Koodli, Tianyu Lu, Joseph M Paggi, and Ron O Dror
ACS Central Science, November 2023
Paper
MultiVI: deep generative model for the integration of multimodal data
Tal Ashuach*, Mariano I Gabitto*, Rohan V Koodli, Giuseppe-Antonio Saldi, Michael I Jordan, Nir Yosef
Nature Methods, June 2023
Paper
PolyVI: Deep Generative Models for Gene Expression, Chromatin Accessibility, and Surface Protein Expression Data
Rohan V Koodli
Master's Thesis, May 2022
Thesis
EternaBrain: Automated RNA design through move sets and strategies from an Internet-scale RNA videogame
Rohan V Koodli, Benjamin Keep, Katherine R Coppess, Fernando Portela, Eterna participants, Rhiju Das
PLOS Computational Biology, June 2019
Paper
Code
Cover art