Machine Learning Links T-cell Function and Spatial Localization to Neoadjuvant Immunotherapy and Clinical Outcome in Pancreatic Cancer.

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.

PI3Kγ inhibition circumvents inflammation and vascular leak in SARS-CoV-2 and other infections.

Virulent infectious agents such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and methicillin-resistant Staphylococcus aureus (MRSA) induce tissue damage that recruits neutrophils, monocyte, and macrophages, leading to T cell exhaustion, fibrosis, vascular leak, epithelial cell depletion, and fatal organ damage. Neutrophils, monocytes, and macrophages recruited to pathogen-infected lungs, including SARS-CoV-2-infected lungs, express phosphatidylinositol 3-kinase gamma (PI3Kγ), a signaling protein that coordinates both granulocyte and monocyte trafficking to diseased tissues and immune-suppressive, profibrotic transcription in myeloid cells. PI3Kγ deletion and inhibition with the clinical PI3Kγ inhibitor eganelisib promoted survival in models of infectious diseases, including SARS-CoV-2 and MRSA, by suppressing inflammation, vascular leak, organ damage, and cytokine storm. These results demonstrate essential roles for PI3Kγ in inflammatory lung disease and support the potential use of PI3Kγ inhibitors to suppress inflammation in severe infectious diseases.

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

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.

MYC Deregulation and PTEN Loss Model Tumor and Stromal Heterogeneity of Aggressive Triple-Negative Breast Cancer.

Triple-negative breast cancer (TNBC) patients have a poor prognosis and few treatment options. Mouse models of TNBC are important for development of new therapies, however, few mouse models represent the complexity of TNBC. Here, we develop a female TNBC murine model by mimicking two common TNBC mutations with high co-occurrence: amplification of the oncogene MYC and deletion of the tumor suppressor PTEN. This Myc;Ptenfl model develops heterogeneous triple-negative mammary tumors that display histological and molecular features commonly found in human TNBC. Our research involves deep molecular and spatial analyses on Myc;Ptenfl tumors including bulk and single-cell RNA-sequencing, and multiplex tissue-imaging. Through comparison with human TNBC, we demonstrate that this genetic mouse model develops mammary tumors with differential survival and therapeutic responses that closely resemble the inter- and intra-tumoral and microenvironmental heterogeneity of human TNBC, providing a pre-clinical tool for assessing the spectrum of patient TNBC biology and drug response.

The MEMIC is an ex vivo system to model the complexity of the tumor microenvironment.

There is an urgent need for accurate, scalable and cost-efficient models of the tumor microenvironment. Here, we detail how to fabricate and use the metabolic microenvironment chamber (MEMIC) - a 3D-printed ex vivo model of intratumoral heterogeneity. A major driver of the cellular and molecular diversity in tumors is accessibility to the blood stream. Whereas perivascular tumor cells have direct access to oxygen and nutrients, cells further from the vasculature must survive under progressively more ischemic environments. The MEMIC simulates this differential access to nutrients, allow co-culturing any number of cell types, and it is optimized for live imaging and other microscopy-based analyses. Owing to a modular design and full experimental control, the MEMIC provides insights into the tumor microenvironment that would be difficult to obtain via other methods. As proof of principle, we show that cells sense gradual changes in metabolite concentration leading to predictable molecular and cellular spatial patterns. We propose the MEMIC as a complement to standard in vitro and in vivo experiments, diversifying the tools available to accurately model, perturb and monitor the tumor microenvironment.

Geospatial Resolution of Human and Bacterial Diversity with City-Scale Metagenomics.

The panoply of microorganisms and other species present in our environment influence human health and disease, especially in cities, but have not been profiled with metagenomics at a city-wide scale. We sequenced DNA from surfaces across the entire New York City (NYC) subway system, the Gowanus Canal, and public parks. Nearly half of the DNA (48%) does not match any known organism; identified organisms spanned 1,688 bacterial, viral, archaeal, and eukaryotic taxa, which were enriched for harmless genera associated with skin (e.g., Acinetobacter). Predicted ancestry of human DNA left on subway surfaces can recapitulate U.S. Census demographic data, and bacterial signatures can reveal a station's history, such as marine-associated bacteria in a hurricane-flooded station. Some evidence of pathogens was found (Bacillus anthracis), but a lack of reported cases in NYC suggests that the pathogens represent a normal, urban microbiome. This baseline metagenomic map of NYC could help long-term disease surveillance, bioterrorism threat mitigation, and health management in the built environment of cities.