Research
Learning from patients to understand mechanisms of resistance and unlock more effective T cell therapy designs.
Our overarching goal is to lay the foundations for a clinically informed T cell design through machine learning algorithms, eventually enabling artificial intelligence (AI) systems to nominate specific genetic edits for improved clinical outcomes in a given disease. We leverage innovation in machine learning and clinical multi-omic T cell therapy datasets to build AI systems at scale to enable broad generalization. We collaborate with physicians and scientists in the Cancer Cell Therapy Program, Cellular Immune Tolerance Program, computer
science labs, experimental T cell therapy labs, and teams beyond Stanford on the analysis of primary clinical and preclinical multi-omic datasets. This work serves as the basis for training T cell therapy AI models at scale, which in turn inform our preclinical T cell designs. We integrate insights from the literature with insights from the data and models to build and test advanced T cell designs in the lab leveraging preclinical models that recapitulate resistance mechanisms observed in patients.
Selected Publications
Stiber A, Quach B, Ogunlade B, Georgiadis A, Chang K, Li Y, Quinn P, Wang H, Ang C, Sotillo E, Mackall CL§, Good Z§, Dionne JA§. Dynamic, single-cell monitoring of CAR T cell identity and activation with Raman spectroscopy. Nature – In Revision. bioRxiv (2026). DOI: 10.64898/2026.02.22.707331.
Tsui KY*, Rodrigues KB*, Zhan X*, Chen Y, Mo KC, Mackall CL, Miklos DB, Gevaert O§, Good Z§. (2025). Patient-level prediction from single-cell data using attention-based multiple instance learning with regulatory priors. Proceedings to the 39th Conference on Neural Information Processing Systems, AI4D3: 16.
Rodrigues KB, Eggenhuizen PJ, Bacchetta R, Good Z. Regulatory T cell therapies: From patient data to biological insights. Frontiers in Immunology, 16: 1675114. PMID: 41246323.
Kadaba SE*, Eapen AK*, Tsui KCY, Pang K, Roth TL§, Good Z§. (2025). Conditional normalizing flows for the design of T cell therapies. Proceedings of the 42nd International Conference on Machine Learning, FM4LS: 43.
Good Z*, Spiegel JY*, Sahaf B, Malipatlolla MB, Ehlinger ZJ, Kurra S, Desai MH, Reynolds WD, Wong Lin A, Vandris P, Wu F, Prabhu S, Hamilton MP, Tamaresis JS, Hanson PJ, Patel S, Feldman SA, Frank MJ, Baird JH, Muffly L, Claire GK, Craig J, Kong KA, Wagh D, Coller J, Bendall SC, Tibshirani RJ, Plevritis SK, Miklos DB§, Mackall CL§. (2022). Post-infusion CAR TReg cells identify patients resistant to CD19-CAR therapy. Nature Medicine, 28(9): 1860-1871. PMID: 36097223.
Good Z, Borges L, Vivanco Gonzalez N, Sahaf B, Samusik N, Tibshirani R, Nolan GP§, Bendall SC§. (2019). Proliferative tracing with single-cell mass cytometry optimizes generation of stem cell memory-like T cells. Nature Biotechnology, 37(3): 259-66. PMID: 30742126.
Lab members highlighted; *co-first; §co-senior
Good Z, Glanville G, Gee MH, Davis MM, Khatri P. (2019). Computational and systems immunology: a students’ perspective. Trends in Immunology, 40(8): 665-8. PMID: 31288986.
Good Z*, Sarno J*, Jager A, Samusik N, Aghaeepour N, Simonds EF, While L, Lacayo NJ, Fantl WJ, Fazio G, Gaipa G, Biondi A, Tibshirani R, Bendall SC, Nolan GP§, Davis KL§. (2018). Single-cell developmental classification of B cell precursor acute lymphoblastic leukemia at diagnosis reveals predictors of relapse. Nature Medicine, 24(4): 474-83. PMID: 29505032.