About

Hi, I'm Ishan. I'm a second-year PhD student at Berkeley AI Research, advised by Jennifer Listgarten. I work on generative models and agents for scientific discovery.

I spent part of my gap year at Aviv Regev's group at Genentech, working on multimodal language models with Yongju Lee. Before that, I was an undergrad at Stanford. During my time there, I studied computer systems, was active in the startup community, and was fortunate to have worked with Emma Lundberg on vision models for mapping dynamic changes in the human proteome. I also had a blast working with new hardware accelerators, with Kunle Olukotun and Muhammad Shahbaz.

Links: Twitter Email Scholar GitHub

What's New?

• [4/27] Released ProteinGenProteinGen is a package for leveraging wet-lab data in ML-based library design. It provides a simple interface for conditioning, finetuning, and sampling from all common sequence design models: ESM3, ProteinMPNN, ProGen3, etc. It provides several tools for effectively using coding agents for assembling and testing your library design pipeline. during Jenn's talk at the Broad.
• [4/11] Put out a little AF3 Fast API server. It's intended to be used on SLURM machines and shared across users in a lab. That way one machine running one instance of AF3 can be used by everyone.
• [2/23] Bear Xiong and I gave a talk on ProteinGuide at Profluent

Research

Guide your favorite protein sequence generative model

arXiv preprint arXiv:2505.04823, May 7, 2025
Junhao Xiong^*, Ishan Gaur^*, Hunter Nisonoff^*, Maria Lukarska^*, Luke M Oltrogge, David F Savage, Jennifer Listgarten
Paper | Blog Posts | Code | Dataset

Multimodal cell maps as a foundation for structural and functional genomics

Nature, April 9, 2025
Leah V Schaffer, Mengzhou Hu, Gege Qian, Kyung-Mee Moon, Abantika Pal, Neelesh Soni, Andrew P Latham, Laura Pontano Vaites, Dorothy Tsai, Nicole M Mattson, Katherine Licon, Robin Bachelder, Anthony Cesnik, Ishan Gaur, Trang Le, William Leineweber, Aji Palar, Ernst Pulido, Yue Qin, Xiaoyu Zhao, Christopher Churas, Joanna Lenkiewicz, Jing Chen, Keiichiro Ono, Dexter Pratt, Peter Zage, Ignacia Echeverria, Andrej Sali, J Wade Harper, Steven P Gygi, Leonard J Foster, Edward L Huttlin, Emma Lundberg, Trey Ideker
Paper | Website | Code

ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation

ACL, Aug 6, 2024
Jirayu Burapacheep, Ishan Gaur, Agam Bhatia, Tristan Thrush
Paper | Code | Dataset

Mapping the Multiscale Proteomic Organization of Cellular and Disease Phenotypes

Annual Review of Biomedical Data Science, May 15, 2024
Anthony Cesnik^*, Leah V Schaffer^*, Ishan Gaur, Mayank Jain, Trey Ideker, Emma Lundberg
Paper

A Cell-Cycle Resolved Multi-Scale Map of the Cell

Poster at Pacific Symposium on Biocomputing, January 3, 2024
Ishan Gaur, Trang Le, Emma Lundberg
Poster | Code

Taurus: A Data Plane Architecture for Per-Packet ML

ASPLOS, Feb 28, 2022 (IETF Applied Networking Research Prize)
Tushar Swamy, Alexander Rucker, Muhammad Shahbaz, Ishan Gaur, Kunle Olukotun
Paper | Code