RESUMO
Multiplex tissue imaging are a collection of increasingly popular single-cell spatial proteomics and transcriptomics assays for characterizing biological tissues both compositionally and spatially. However, several technical issues limit the utility of multiplex tissue imaging, including the limited number of molecules (proteins and RNAs) that can be assayed, tissue loss, and protein probe failure. In this work, we demonstrate how machine learning methods can address these limitations by imputing protein abundance at the single-cell level using multiplex tissue imaging datasets from a breast cancer cohort. We first compared machine learning methods' strengths and weaknesses for imputing single-cell protein abundance. Machine learning methods used in this work include regularized linear regression, gradient-boosted regression trees, and deep learning autoencoders. We also incorporated cellular spatial information to improve imputation performance. Using machine learning, single-cell protein expression can be imputed with mean absolute error ranging between 0.05-0.3 on a [0,1] scale. Finally, we used imputed data to predict whether single cells were more likely to come from pre-treatment or post-treatment biopsies. Our results demonstrate (1) the feasibility of imputing single-cell abundance levels for many proteins using machine learning; (2) how including cellular spatial information can substantially enhance imputation results; and (3) the use of single-cell protein abundance levels in a use case to demonstrate biological relevance.
RESUMO
Tumor molecular data sets are becoming increasingly complex, making it nearly impossible for humans alone to effectively analyze them. Here, we demonstrate the power of using machine learning (ML) to analyze a single-cell, spatial, and highly multiplexed proteomic data set from human pancreatic cancer and reveal underlying biological mechanisms that may contribute to clinical outcomes. We designed a multiplex immunohistochemistry antibody panel to compare T-cell functionality and spatial localization in resected tumors from treatment-naïve patients with localized pancreatic ductal adenocarcinoma (PDAC) with resected tumors from a second cohort of patients treated with neoadjuvant agonistic CD40 (anti-CD40) monoclonal antibody therapy. In total, nearly 2.5 million cells from 306 tissue regions collected from 29 patients across both cohorts were assayed, and over 1,000 tumor microenvironment (TME) features were quantified. We then trained ML models to accurately predict anti-CD40 treatment status and disease-free survival (DFS) following anti-CD40 therapy based on TME features. Through downstream interpretation of the ML models' predictions, we found anti-CD40 therapy reduced canonical aspects of T-cell exhaustion within the TME, as compared with treatment-naïve TMEs. Using automated clustering approaches, we found improved DFS following anti-CD40 therapy correlated with an increased presence of CD44+CD4+ Th1 cells located specifically within cellular neighborhoods characterized by increased T-cell proliferation, antigen experience, and cytotoxicity in immune aggregates. Overall, our results demonstrate the utility of ML in molecular cancer immunology applications, highlight the impact of anti-CD40 therapy on T cells within the TME, and identify potential candidate biomarkers of DFS for anti-CD40-treated patients with PDAC.