Machine learning links T cell function and spatial localization to neoadjuvant immunotherapy and clinical outcome in pancreatic cancer.

Autor:	Blise KE; Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR USA.; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA., Sivagnanam S; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA., Betts CB; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA.; Current affiliation: Akoya Biosciences, 100 Campus Drive, 6th Floor, Marlborough, MA USA., Betre K; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA., Kirchberger N; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA., Tate B; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Immune Monitoring and Cancer Omics Services, Oregon Health & Science University, Portland, OR USA., Furth EE; Department of Pathology and Laboratory Medicine, Hospital of the University of Pennsylvania, Philadelphia, PA USA.; Abramson Cancer Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA., Dias Costa A; Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA USA., Nowak JA; Department of Pathology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA USA., Wolpin BM; Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA USA., Vonderheide RH; Abramson Cancer Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA.; Parker Institute for Cancer Immunotherapy, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA., Goecks J; Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR USA.; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Current affiliation: Department of Machine Learning, H. Lee Moffitt Cancer Center, Tampa, FL USA.; Current affiliation: Department of Biostatistics and Bioinformatics, H. Lee Moffitt Cancer Center, Tampa, FL USA., Coussens LM; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA., Byrne KT; The Knight Cancer Institute, Oregon Health & Science University, Portland, OR USA.; Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR USA.; Lead contact.
Jazyk:	angličtina
Zdroj:	BioRxiv : the preprint server for biology [bioRxiv] 2023 Oct 23. Date of Electronic Publication: 2023 Oct 23.
DOI:	10.1101/2023.10.20.563335
Abstrakt:	Tumor molecular datasets are becoming increasingly complex, making it nearly impossible for humans alone to effectively analyze them. Here, we demonstrate the power of using machine learning to analyze a single-cell, spatial, and highly multiplexed proteomic dataset from human pancreatic cancer and reveal underlying biological mechanisms that may contribute to clinical outcome. A novel multiplex immunohistochemistry antibody panel was used to audit T cell functionality and spatial localization in resected tumors from treatment-naive patients with localized pancreatic ductal adenocarcinoma (PDAC) compared to a second cohort of patients treated with neoadjuvant agonistic CD40 (αCD40) monoclonal antibody therapy. In total, nearly 2.5 million cells from 306 tissue regions collected from 29 patients across both treatment cohorts were assayed, and more than 1,000 tumor microenvironment (TME) features were quantified. We then trained machine learning models to accurately predict αCD40 treatment status and disease-free survival (DFS) following αCD40 therapy based upon TME features. Through downstream interpretation of the machine learning models' predictions, we found αCD40 therapy to reduce canonical aspects of T cell exhaustion within the TME, as compared to treatment-naive TMEs. Using automated clustering approaches, we found improved DFS following αCD40 therapy to correlate with the increased presence of CD44 + CD4 + Th1 cells located specifically within cellular spatial neighborhoods characterized by increased T cell proliferation, antigen-experience, and cytotoxicity in immune aggregates. Overall, our results demonstrate the utility of machine learning in molecular cancer immunology applications, highlight the impact of αCD40 therapy on T cells within the TME, and identify potential candidate biomarkers of DFS for αCD40-treated patients with PDAC. Competing Interests: R.H.V. is an inventor on licensed patents relating to cancer cellular immunotherapy and cancer vaccines, and mutant Kras specific T cell receptors; has received consulting fees from BMS; and receives royalties from Children’s Hospital Boston for a licensed research-only monoclonal antibody and from the University of Pennsylvania for licensed research cell lines. J.A.N. receives consulting fees from Leica Biosystems and research support from Natera. B.M.W. receives research funding from AstraZeneca, Celgene/BMS, Eli Lilly, Novartis, and Revolution Medicines, and consulting for Celgene, GRAIL, Ipsen, Mirati, Third Rock Ventures unrelated to the current work. C.B.B. is an employee of, and holds equity in, Akoya Biosciences, Inc. K.T.B. receives royalties from the University of Pennsylvania for licensed research cell lines and has received consulting fees from Guidepoint. L.M.C. has received reagent support from Cell Signaling Technologies, Syndax Pharmaceuticals, Inc., ZielBio, Inc., and Hibercell, Inc.; holds sponsored research agreements with Syndax Pharmaceuticals, Hibercell, Inc., Prospect Creek Foundation, Lustgarten Foundation for Pancreatic Cancer Research, Susan G. Komen Foundation, and the National Foundation for Cancer Research; is on the Advisory Board for Carisma Therapeutics, Inc., CytomX Therapeutics, Inc., Kineta, Inc., Hibercell, Inc., Cell Signaling Technologies, Inc., Alkermes, Inc., Raska Pharma, Inc., NextCure, Guardian Bio, AstraZeneca Partner of Choice Network (OHSU Site Leader), Genenta Sciences, Pio Therapeutics Pty Ltd., and Lustgarten Foundation for Pancreatic Cancer Research Therapeutics Working Group, Inc.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu