Format

Send to

Choose Destination
PLoS One. 2018 Dec 31;13(12):e0208422. doi: 10.1371/journal.pone.0208422. eCollection 2018.

A multifactorial model of T cell expansion and durable clinical benefit in response to a PD-L1 inhibitor.

Author information

1
Microsoft Research New England, Cambridge, MA, United States of America.
2
University of Maryland, College Park, Department of Computer Science, College Park, MD, United States of America.
3
Microsoft Research New York, New York, NY, United States of America.
4
Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY, United States of America.
5
Department of Medicine, Weill Cornell Medical College, New York, NY, United States of America.
6
Adaptive Biotechnologies, Seattle, WA, United States of America.

Abstract

Checkpoint inhibitor immunotherapies have had major success in treating patients with late-stage cancers, yet the minority of patients benefit. Mutation load and PD-L1 staining are leading biomarkers associated with response, but each is an imperfect predictor. A key challenge to predicting response is modeling the interaction between the tumor and immune system. We begin to address this challenge with a multifactorial model for response to anti-PD-L1 therapy. We train a model to predict immune response in patients after treatment based on 36 clinical, tumor, and circulating features collected prior to treatment. We analyze data from 21 bladder cancer patients using the elastic net high-dimensional regression procedure and, as training set error is a biased and overly optimistic measure of prediction error, we use leave-one-out cross-validation to obtain unbiased estimates of accuracy on held-out patients. In held-out patients, the model explains 79% of the variance in T cell clonal expansion. This predicted immune response is multifactorial, as the variance explained is at most 23% if clinical, tumor, or circulating features are excluded. Moreover, if patients are triaged according to predicted expansion, only 38% of non-durable clinical benefit (DCB) patients need be treated to ensure that 100% of DCB patients are treated. In contrast, using mutation load or PD-L1 staining alone, one must treat at least 77% of non-DCB patients to ensure that all DCB patients receive treatment. Thus, integrative models of immune response may improve our ability to anticipate clinical benefit of immunotherapy.

Conflict of interest statement

ML is a former employee of and is currently a paid consultant for Microsoft. AG is a former employee of Microsoft. DJ was a paid consultant for Merck within the last 12 months and was a paid consultant for Genentech within the last 24 months. JER is a paid consultant of Roche and Genentech. SAF owns stock in Urogen and receives research funding from AstroZeneca and Genentech. AS is a current employee of and owns stock in Merck, received prior research funding from Bristol Myers Squibb, is a former employee of Adaptive Biotechnologies, and is a prior paid consultant of Genentech. JR has consulted for AstraZeneca, Roche/Genentech, Astellas, Seattle Genetics, EMD Serono, Merck, BMS, Eli Lilly, Sanofi, Adicet Bio, Sensei Biotherapeutics, Oncogenex, Inovio, Gritstone, Pharmacyclics, Western Oncolytics, Bayer, Mirati, Bioclin Therapeutics, QED Therapeutics, and Fortress Biotech. Additionally, JR has received honoraria, royalties, stock, or research funding from the following organizations: Chugai, BMS, Merck, AstraZeneca, Medscape, Uptodate, Genentech/Roche, Oncogenex, Agensys/Astellas, Seattle Genetics, Novartis, Mirati, Incyte, Bayer, Viralytics Memorial Sloan Kettering Cancer Center core grant P30 CA008748. DFB has consulted for Shionogi, Astellas, Bristol Myers Squibb, Celgene, Merck, Genentech, Vertex, Roche, Hoffman-LaRoche, Fidia Farmaceutici, Pfizer, Esai, Eli-Lilly, AstraZeneca, Urogen. DFB has also received honoraria, grants or research funding from the following: Novartis, Genentech, Merck, Bristol Myers Squibb, Dendreon, Genentech, Merck, McKesson, and the Memorial Sloan Kettering Cancer Center core grant P30 CA008748. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center