Yusuf Roohani

About:

I design new machine learning approaches for modeling biological systems, with a particular interest in how artificial intelligence can enhance experiment design for biological discovery. My recent work centers on building closed-loop experimental systems, with a focus on computationally guiding the engineering of cell state.

Most recently, I led the first dedicated machine learning group at the Arc Institute, which I built from scratch and scaled to over 10 people. There we developed an AI model of cell state by pairing model development with AI-guided data generation. I completed my PhD at Stanford Unsversity under the guidance of Jure Leskovec and Stephen Quake. Prior to that, I worked for four years in early stage drug discovery at GSK.

I'm currently building a new approach for closing the loop in biological discovery. It's time to move past scaling data to scaling AI-guided experiments.

yroohani@alumni.stanford.edu

Curriculum Vitae:

[CV]

Featured Publications:

For complete list: Google Scholar

Journal Publications

Cell [2026] scBaseCount: An AI agent-curated, uniformly processed, and continually expanding single cell data repository
Youngblut, N., Carpenter, C., ... , Goodarzi, H.* and Roohani, Y.*.

Cell [2026] Predicting cellular responses to perturbation across diverse contexts with STATE
Adduri, A., Gautam, D., Bevilacqua B., ... and Roohani, Y..
     [Media coverage] Century of Biology, GEN
     [GitHub 600+ Stars]

Nature [2026] Universal Cell Embeddings: A Foundation Model for Cell Biology
Rosen Y.*, Roohani Y.*, Agrawal A., Samotorcan L., Quake S., Leskovec J..
     [Media coverage] New York Times

Cell [2025] Virtual Cell Challenge: Toward a Turing test for the virtual cell
Roohani, Y., Hua, T., ... Goodarzi, H., Burke D..
     [Media coverage] GEN, Nature

Cell [2024] How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities
Bunne, C.*, Roohani, Y.*, Rosen, Y.*, ... Regev, A., Lundberg, E., Lekovec, J., Quake S..
     [Media coverage] The Atlantic

Nature Biotechnology [2023] GEARS: Predicting transcriptional outcomes of novel multi-gene perturbations
Roohani, Y., Huang, K., Leskovec J.
     [Best Poster] Intelligent Systems For Molecular Biology (ISMB 2022)
     [Innovation Award] Society for Lab Automation and Screening (SLAS 2023)
     [GitHub 350+ Stars]

Nature Methods [2023] Towards Universal Cell Embeddings: Integrating Single-cell RNA-seq Datasets across Species with SATURN
Rosen Y.*, Brbic M.*, Roohani, Y.*, Swanson K., Li Z., Leskovec, J..

(* = equal contribution)

Preprints

bioRxiv [2026] Stack: In-Context Learning of Single-Cell Biology
Dong M., Adduri A., Gautam D., ... and Roohani, Y..

bioRxiv [2024] PreciCE: Precision engineering of cell fates via data-driven multi-gene control of transcriptional networks
Magnusson, J.*, Roohani, Y.*, Stauber, D., ... Sandberg, R., Lekovec, J., Lei, S. Qi.

Conference Papers

ICLR [2025] BioDiscoveryAgent: An AI agent for designing genetic perturbation experiments
Roohani Y.*, Vora J.*, Huang Q.*, Steinhart Z., Marson A., Liang P., Leskovec J..
[Best Poster] ICLR 2024 MLGenX Workshop

NeurIPS [2023] Zero-shot causal learning
Nilforoshan H.*, Moor M.*, Roohani Y., Chen Y., Surina A., Yasunaga M., Oblak S., Leskovec J..
[Spotlight Presentation]

Past Research Group Members

Abhinav Adduri (Arc ML Research Scientist)
Arshia Nayebnazar (UC Berkeley EECS undergrad student)
Basak Eraslan (Arc ML, Bioinformatics Senior Scientist)
Beatrice Bevilacqua (Arc ML Research Scientist)
Chris Carpenter (Arc Senior Research Assistant)
Leon Hafner (Arc ML Research Fellow)
Rishi Verma (Arc ML Engineer)
Apratim Dey (Stanford Statistics Postdoc)
Dhruv Gautam (UC Berkeley EECS MS student, now at Engram)
Yangyi Shen (Stanford CS MS student, now Stanford CS PhD student)
Mingze Dong (Yale Comp Bio PhD student, now at Stanford)
Francis Chalissery (Arc ML Research Fellow, now at OpenAI)
Rohan Shah (UPenn Math undergraduate)
Alishba Imran (UC Berkeley EECS undergraduate, now at OpenAI)
Andrew Lee (Stanford CS MS student, now at Need AI)
Sanjay Nagaraj (Stanford CS MS student, now at Stealth Startup)