TISMO: syngeneic mouse tumor database to model tumor immunity and immunotherapy response.

Syngeneic mouse models are tumors derived from murine cancer cells engrafted on genetically identical mouse strains. They are widely used tools for studying tumor immunity and immunotherapy response in the context of a fully functional murine immune system. Large volumes of syngeneic mouse tumor expression profiles under different immunotherapy treatments have been generated, although a lack of systematic collection and analysis makes data reuse challenging. We present Tumor Immune Syngeneic MOuse (TISMO), a database with an extensive collection of syngeneic mouse model profiles with interactive visualization features. TISMO contains 605 in vitro RNA-seq samples from 49 syngeneic cancer cell lines across 23 cancer types, of which 195 underwent cytokine treatment. TISMO also includes 1518 in vivo RNA-seq samples from 68 syngeneic mouse tumor models across 19 cancer types, of which 832 were from immune checkpoint blockade (ICB) studies. We manually annotated the sample metadata, such as cell line, mouse strain, transplantation site, treatment, and response status, and uniformly processed and quality-controlled the RNA-seq data. Besides data download, TISMO provides interactive web interfaces to investigate whether specific gene expression, pathway enrichment, or immune infiltration level is associated with differential immunotherapy response. TISMO is available at http://tismo.cistrome.org.

A validation of models for prediction of pathogenic variants in mismatch repair genes.

PURPOSE: Models used to predict the probability of an individual having a pathogenic homozygous or heterozygous variant in a mismatch repair gene, such as MMRpro, are widely used. Recently, MMRpro was updated with new colorectal cancer penetrance estimates. The purpose of this study was to evaluate the predictive performance of MMRpro and other models for individuals with a family history of colorectal cancer. METHODS: We performed a validation study of 4 models, Leiden, MMRpredict, PREMM5, and MMRpro, using 784 members of clinic-based families from the United States. Predicted probabilities were compared with germline testing results and evaluated for discrimination, calibration, and predictive accuracy. We analyzed several strategies to combine models and improve predictive performance. RESULTS: MMRpro with additional tumor information (MMRpro+) and PREMM5 outperformed the other models in discrimination and predictive accuracy. MMRpro+ was the best calibrated with an observed to expected ratio of 0.98 (95% CI = 0.89-1.08). The combination models showed improvement over PREMM5 and performed similar to MMRpro+. CONCLUSION: MMRpro+ and PREMM5 performed well in predicting the probability of having a pathogenic homozygous or heterozygous variant in a mismatch repair gene. They serve as useful clinical decision tools for identifying individuals who would benefit greatly from screening and prevention strategies.

Machine learning on syngeneic mouse tumor profiles to model clinical immunotherapy response.

Most patients with cancer are refractory to immune checkpoint blockade (ICB) therapy, and proper patient stratification remains an open question. Primary patient data suffer from high heterogeneity, low accessibility, and lack of proper controls. In contrast, syngeneic mouse tumor models enable controlled experiments with ICB treatments. Using transcriptomic and experimental variables from >700 ICB-treated/control syngeneic mouse tumors, we developed a machine learning framework to model tumor immunity and identify factors influencing ICB response. Projected on human immunotherapy trial data, we found that the model can predict clinical ICB response. We further applied the model to predicting ICB-responsive/resistant cancer types in The Cancer Genome Atlas, which agreed well with existing clinical reports. Last, feature analysis implicated factors associated with ICB response. In summary, our computational framework based on mouse tumor data reliably stratified patients regarding ICB response, informed resistance mechanisms, and has the potential for wide applications in disease treatment studies.

Hippo Signaling Pathway Regulates Cancer Cell-Intrinsic MHC-II Expression.

MHC-II is known to be mainly expressed on the surface of antigen-presenting cells. Evidence suggests MHC-II is also expressed by cancer cells and may be associated with better immunotherapy responses. However, the role and regulation of MHC-II in cancer cells remain unclear. In this study, we leveraged data mining and experimental validation to elucidate the regulation of MHC-II in cancer cells and its role in modulating the response to immunotherapy. We collated an extensive collection of omics data to examine cancer cell-intrinsic MHC-II expression and its association with immunotherapy outcomes. We then tested the functional relevance of cancer cell-intrinsic MHC-II expression using a syngeneic transplantation model. Finally, we performed data mining to identify pathways potentially involved in the regulation of MHC-II expression, and experimentally validated candidate regulators. Analyses of preimmunotherapy clinical samples in the CheckMate 064 trial revealed that cancer cell-intrinsic MHC-II protein was positively correlated with more favorable immunotherapy outcomes. Comprehensive meta-analyses of multiomics data from an exhaustive collection of data revealed that MHC-II is heterogeneously expressed in various solid tumors, and its expression is particularly high in melanoma. Using a syngeneic transplantation model, we further established that melanoma cells with high MHC-II responded better to anti-PD-1 treatment. Data mining followed by experimental validation revealed the Hippo signaling pathway as a potential regulator of melanoma MHC-II expression. In summary, we identified the Hippo signaling pathway as a novel regulator of cancer cell-intrinsic MHC-II expression. These findings suggest modulation of MHC-II in melanoma could potentially improve immunotherapy response.

Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes.

PURPOSE: The medical literature relevant to germline genetics is growing exponentially. Clinicians need tools that help to monitor and prioritize the literature to understand the clinical implications of pathogenic genetic variants. We developed and evaluated two machine learning models to classify abstracts as relevant to the penetrance-risk of cancer for germline mutation carriers-or prevalence of germline genetic mutations. MATERIALS AND METHODS: We conducted literature searches in PubMed and retrieved paper titles and abstracts to create an annotated data set for training and evaluating the two machine learning classification models. Our first model is a support vector machine (SVM) which learns a linear decision rule on the basis of the bag-of-ngrams representation of each title and abstract. Our second model is a convolutional neural network (CNN) which learns a complex nonlinear decision rule on the basis of the raw title and abstract. We evaluated the performance of the two models on the classification of papers as relevant to penetrance or prevalence. RESULTS: For penetrance classification, we annotated 3,740 paper titles and abstracts and evaluated the two models using 10-fold cross-validation. The SVM model achieved 88.93% accuracy-percentage of papers that were correctly classified-whereas the CNN model achieved 88.53% accuracy. For prevalence classification, we annotated 3,753 paper titles and abstracts. The SVM model achieved 88.92% accuracy and the CNN model achieved 88.52% accuracy. CONCLUSION: Our models achieve high accuracy in classifying abstracts as relevant to penetrance or prevalence. By facilitating literature review, this tool could help clinicians and researchers keep abreast of the burgeoning knowledge of gene-cancer associations and keep the knowledge bases for clinical decision support tools up to date.