Analysis of 3D pathology samples using weakly supervised AI.

Human tissue, which is inherently three-dimensional (3D), is traditionally examined through standard-of-care histopathology as limited two-dimensional (2D) cross-sections that can insufficiently represent the tissue due to sampling bias. To holistically characterize histomorphology, 3D imaging modalities have been developed, but clinical translation is hampered by complex manual evaluation and lack of computational platforms to distill clinical insights from large, high-resolution datasets. We present TriPath, a deep-learning platform for processing tissue volumes and efficiently predicting clinical outcomes based on 3D morphological features. Recurrence risk-stratification models were trained on prostate cancer specimens imaged with open-top light-sheet microscopy or microcomputed tomography. By comprehensively capturing 3D morphologies, 3D volume-based prognostication achieves superior performance to traditional 2D slice-based approaches, including clinical/histopathological baselines from six certified genitourinary pathologists. Incorporating greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, further emphasizing the value of capturing larger extents of heterogeneous morphology.

FOXO1 inactivation induces cisplatin resistance in bladder cancer.

We found that FOXO1-shRNA sublines or FOXO1-positive cells co-treated with a FOXO1 inhibitor were significantly more resistant to cisplatin treatment at pharmacological concentrations, compared with respective control sublines or those with mock treatment. Western blot demonstrated considerable increases in the expression levels of a phosphorylated inactive form of FOXO1 (p-FOXO1) in cisplatin-resistant sublines established by long-term culture with low/increasing doses of cisplatin, compared with respective controls. Immunohistochemistry in surgical specimens from patients with muscle-invasive bladder cancer undergoing cisplatin-based neoadjuvant therapy further showed a strong trend to associate between p-FOXO1 positivity and unfavorable response to chemotherapy.

Toward the human cellular microRNAome.

MicroRNAs are short RNAs that serve as regulators of gene expression and are essential components of normal development as well as modulators of disease. MicroRNAs generally act cell-autonomously, and thus their localization to specific cell types is needed to guide our understanding of microRNA activity. Current tissue-level data have caused considerable confusion, and comprehensive cell-level data do not yet exist. Here, we establish the landscape of human cell-specific microRNA expression. This project evaluated 8 billion small RNA-seq reads from 46 primary cell types, 42 cancer or immortalized cell lines, and 26 tissues. It identified both specific and ubiquitous patterns of expression that strongly correlate with adjacent superenhancer activity. Analysis of unaligned RNA reads uncovered 207 unknown minor strand (passenger) microRNAs of known microRNA loci and 495 novel putative microRNA loci. Although cancer cell lines generally recapitulated the expression patterns of matched primary cells, their isomiR sequence families exhibited increased disorder, suggesting DROSHA- and DICER1-dependent microRNA processing variability. Cell-specific patterns of microRNA expression were used to de-convolute variable cellular composition of colon and adipose tissue samples, highlighting one use of these cell-specific microRNA expression data. Characterization of cellular microRNA expression across a wide variety of cell types provides a new understanding of this critical regulatory RNA species.

miRge 2.0 for comprehensive analysis of microRNA sequencing data.

BACKGROUND: miRNAs play important roles in the regulation of gene expression. The rapidly developing field of microRNA sequencing (miRNA-seq; small RNA-seq) needs comprehensive, robust, user-friendly and standardized bioinformatics tools to analyze these large datasets. We present miRge 2.0, in which multiple enhancements were made towards these goals. RESULTS: miRge 2.0 has become more comprehensive with increased functionality including a novel miRNA detection method, A-to-I editing analysis, integrated standardized GFF3 isomiR reporting, and improved alignment to miRNAs. The novel miRNA detection method uniquely uses both miRNA hairpin sequence structure and composition of isomiRs resulting in higher specificity for potential miRNA identification. Using known miRNA data, our support vector machine (SVM) model predicted miRNAs with an average Matthews correlation coefficient (MCC) of 0.939 over 32 human cell datasets and outperformed miRDeep2 and miRAnalyzer regarding phylogenetic conservation. The A-to-I editing detection strongly correlated with a reference dataset with adjusted R2 = 0.96. miRge 2.0 is the most up-to-date aligner with custom libraries to both miRBase v22 and MirGeneDB v2.0 for 6 species: human, mouse, rat, fruit fly, nematode and zebrafish; and has a tool to create custom libraries. For user-friendliness, miRge 2.0 is incorporated into bcbio-nextgen and implementable through Bioconda. CONCLUSIONS: miRge 2.0 is a redesigned, leading miRNA RNA-seq aligner with several improvements and novel utilities. miRge 2.0 is freely available at: https://github.com/mhalushka/miRge .

Prostaglandin receptors induce urothelial tumourigenesis as well as bladder cancer progression and cisplatin resistance presumably via modulating PTEN expression.

BACKGROUND: We investigated the role of prostaglandin receptors (e.g. prostaglandin E2 receptor 2 (EP2), EP4) and the efficacy of celecoxib in urothelial tumourigenesis and cancer progression. METHODS: We performed immunohistochemistry in bladder cancer (BC) tissue microarrays, in vitro transformation assay in a normal urothelial SVHUC line, and western blot/reverse transcription-polymerase chain reaction/cell growth assays in BC lines. RESULTS: EP2/EP4 expression was elevated in BCs compared with non-neoplastic urothelial tissues and in BCs from those who were resistant to cisplatin-based neoadjuvant chemotherapy. Strong positivity of EP2/EP4 in non-muscle-invasive tumours or positivity of EP2/EP4 in muscle-invasive tumours strongly correlated with disease progression or disease-specific mortality, respectively. In SVHUC cells, exposure to a chemical carcinogen 3-methylcholanthrene considerably increased and decreased the expression of EP2/EP4 and phosphatase and tensin homologue (PTEN), respectively. Treatment with selective EP2/EP4 antagonist or celecoxib also resulted in prevention in 3-methylcholanthrene-induced neoplastic transformation of SVHUC cells. In BC lines, EP2/EP4 antagonists and celecoxib effectively inhibited cell viability and migration, as well as augmented PTEN expression. Furthermore, these drugs enhanced the cytotoxic activity of cisplatin in BC cells. EP2/EP4 and PTEN were also elevated and reduced, respectively, in cisplatin-resistant BC sublines. CONCLUSIONS: EP2/EP4 activation correlates with induction of urothelial cancer initiation and outgrowth, as well as chemoresistance, presumably via downregulating PTEN expression.

Implications of the tumor immune microenvironment for staging and therapeutics.

Characterizing the tumor immune microenvironment enables the identification of new prognostic and predictive biomarkers, the development of novel therapeutic targets and strategies, and the possibility to guide first-line treatment algorithms. Although the driving elements within the tumor microenvironment of individual primary organ sites differ, many of the salient features remain the same. The presence of a robust antitumor milieu characterized by an abundance of CD8+ cytotoxic T-cells, Th1 helper cells, and associated cytokines often indicates a degree of tumor containment by the immune system and can even lead to tumor elimination. Some of these features have been combined into an 'Immunoscore', which has been shown to complement the prognostic ability of the current TNM staging for early stage colorectal carcinomas. Features of the immune microenvironment are also potential therapeutic targets, and immune checkpoint inhibitors targeting the PD-1/PD-L1 axis are especially promising. FDA-approved indications for anti-PD-1/PD-L1 are rapidly expanding across numerous tumor types and, in certain cases, are accompanied by companion or complimentary PD-L1 immunohistochemical diagnostics. Pathologists have direct visual access to tumor tissue and in-depth knowledge of the histological variations between and within tumor types and thus are poised to drive forward our understanding of the tumor microenvironment. This review summarizes the key components of the tumor microenvironment, presents an overview of and the challenges with PD-L1 antibodies and assays, and addresses newer candidate biomarkers, such as CD8+ cell density and mutational load. Characteristics of the local immune contexture and current pathology-related practices for specific tumor types are also addressed. In the future, characterization of the host antitumor immune response using multiplexed and multimodality biomarkers may help predict which patients will respond to immune-based therapies.

Rediagnosis of Lung Cancer as NUT Midline Carcinoma Based on Clues From Tumor Genomic Profiling.

Tumor DNA sequencing can identify rare driver genomic alterations that suggest targets for cancer therapy, even when these drivers cannot be suspected on clinical grounds. In some cases, genomic alterations identified in the tumor can lead to a change in diagnosis with implications for prognosis and therapy. This report describes a case in which evaluation of tumor sequencing results by a molecular tumor board (MTB) led to rediagnosis of a non-small cell lung cancer as highly aggressive NUT midline carcinoma, with implications for targeted therapy using an investigational bromodomain and extraterminal (BET) inhibitor. We discuss the molecular biology and diagnosis of this rare tumor, and suggest how improved annotation of tumor sequencing reports and multidisciplinary expertise of MTBs can facilitate timely diagnosis of rare tumors and application of potential targeted therapies.

A benchmark for microRNA quantification algorithms using the OpenArray platform.

BACKGROUND: Several techniques have been tailored to the quantification of microRNA expression, including hybridization arrays, quantitative PCR (qPCR), and high-throughput sequencing. Each of these has certain strengths and limitations depending both on the technology itself and the algorithm used to convert raw data into expression estimates. Reliable quantification of microRNA expression is challenging in part due to the relatively low abundance and short length of the miRNAs. While substantial research has been devoted to the development of methods to quantify mRNA expression, relatively little effort has been spent on microRNA expression. RESULTS: In this work, we focus on the Life Technologies TaqMan OpenArray(Ⓡ) system, a qPCR-based platform to measure microRNA expression. Several algorithms currently exist to estimate expression from the raw amplification data produced by qPCR-based technologies. To assess and compare the performance of these methods, we performed a set of dilution/mixture experiments to create a benchmark data set. We also developed a suite of statistical assessments that evaluate many different aspects of performance: accuracy, precision, titration response, number of complete features, limit of detection, and data quality. The benchmark data and software are freely available via two R/Bioconductor packages, miRcomp and miRcompData. Finally, we demonstrate use of our software by comparing two widely used algorithms and providing assessments for four other algorithms. CONCLUSIONS: Benchmark data sets and software are crucial tools for the assessment and comparison of competing algorithms. We believe that the miRcomp and miRcompData packages will facilitate the development of new methodology for microRNA expression estimation.

A Retrospective Analysis of the Effect on Survival of Time from Diagnosis to Neoadjuvant Chemotherapy to Cystectomy for Muscle Invasive Bladder Cancer.

PURPOSE: We determine the impact of the timing of radical cystectomy from the diagnosis of muscle invasive bladder cancer on survival in patients also treated with neoadjuvant chemotherapy. MATERIALS AND METHODS: We performed a retrospective chart review of consecutive patients with muscle invasive bladder cancer who received neoadjuvant chemotherapy followed by cystectomy between 1996 and 2014 at a single institution. Cox proportional hazards regression models were used to investigate the effect of treatment time intervals on overall survival. Three treatment intervals were analyzed for survival impact, from diagnosis of muscle invasive bladder cancer to initiation of neoadjuvant chemotherapy, from initiation of neoadjuvant chemotherapy to cystectomy and from diagnosis to cystectomy. Other pretreatment and posttreatment clinicopathological parameters were also analyzed. RESULTS: Median time from the diagnosis of muscle invasive bladder cancer to radical cystectomy was 28 weeks. Cystectomy performed less than 28 weeks from the diagnosis did not result in significant improvement in overall survival outcomes (HR 0.68, 95% CI 0.28-1.63, p=0.388). Neither the timing of neoadjuvant chemotherapy initiation from diagnosis (median 6 weeks) nor the timing of cystectomy from neoadjuvant chemotherapy initiation (median 22 weeks) was associated with survival. Patient age, variant histology, extravesical and/or lymph node involvement (T3-4 and/or N1 or greater) were significantly associated with survival. CONCLUSIONS: The timing of radical cystectomy in relation to muscle invasive bladder cancer diagnosis date does not significantly impact overall survival in patients with muscle invasive bladder cancer receiving neoadjuvant chemotherapy.

Ki-67 index as an ancillary tool in the differential diagnosis of proliferative endometrial lesions with secretory change.

"Secretory change" can accompany a variety of proliferative endometrial lesions, ranging from hyperplasia to carcinoma. It is characterized by subnuclear or supranuclear vacuolization, mimicking early secretory endometrium (SEM). As an additional diagnostic challenge, mitotic activity and cytologic atypia are often low in hyperplastic lesions with secretory change. As mitotic activity in lesions with secretory change is decreased, the mitotic index may not be useful to distinguish SEM with glandular crowding from hyperplasia with secretory change. We therefore hypothesized that Ki-67 immunohistochemistry, an alternative marker of proliferative activity, might be useful in this setting. Forty-four endometrial lesions with secretory change and 30 controls were stained for Ki-67. Three "hot spot" areas per case were photographed and 200 to 300 cells were manually counted to obtain the ratio of Ki-67-positive cells versus total cells. A second pathologist performed an independent review of the same preselected fields and estimates without preselection. There was an incremental increase in the Ki-67 index from 2.6% in SEM to 17% in nonatypical hyperplasia, 36% in atypical hyperplasia, and 60% in endometrial carcinoma. The Ki-67 index for SEM was significantly (P<0.01) lower than hyperplastic lesions and carcinoma with secretory change. Similar, statistically significant results were obtained by independent estimates of Ki-67 immunopositivity. In the setting of secretory morphology, the Ki-67 index was highly sensitive and specific (>90%) for the differential diagnosis of SEM with crowding versus nonatypical hyperplasia, atypical hyperplasia, and endometrial carcinoma. In summary, the Ki-67-labeling index is a useful technique to distinguish SEM with crowding, an exaggerated physiological condition, from cancer precursors.

Characterization of Non-Monotonic Relationships between Tumor Mutational Burden and Clinical Outcomes.

Potential clinical biomarkers are often assessed with Cox regressions or their ability to differentiate two groups of patients based on a single cutoff. However, both of these approaches assume a monotonic relationship between the potential biomarker and survival. Tumor mutational burden (TMB) is currently being studied as a predictive biomarker for immunotherapy, and a single cutoff is often used to divide patients. In this study, we introduce a two-cutoff approach that allows splitting of patients when a non-monotonic relationship is present and explore the use of neural networks to model more complex relationships of TMB to outcome data. Using real-world data, we find that while in most cases the true relationship between TMB and survival appears monotonic, that is not always the case and researchers should be made aware of this possibility. SIGNIFICANCE: When a non-monotonic relationship to survival is present it is not possible to divide patients by a single value of a predictor. Neural networks allow for complex transformations and can be used to correctly split patients when a non-monotonic relationship is present.

Multiple-instance learning of somatic mutations for the classification of tumour type and the prediction of microsatellite status.

Large-scale genomic data are well suited to analysis by deep learning algorithms. However, for many genomic datasets, labels are at the level of the sample rather than for individual genomic measures. Machine learning models leveraging these datasets generate predictions by using statically encoded measures that are then aggregated at the sample level. Here we show that a single weakly supervised end-to-end multiple-instance-learning model with multi-headed attention can be trained to encode and aggregate the local sequence context or genomic position of somatic mutations, hence allowing for the modelling of the importance of individual measures for sample-level classification and thus providing enhanced explainability. The model solves synthetic tasks that conventional models fail at, and achieves best-in-class performance for the classification of tumour type and for predicting microsatellite status. By improving the performance of tasks that require aggregate information from genomic datasets, multiple-instance deep learning may generate biological insight.

The Journey to Improve the College of American Pathologists Cancer Biomarker Reporting Protocols.

CONTEXT.­: Biomarker reporting has increasingly become a key component of pathology reporting, providing diagnostic, prognostic, and actionable therapeutic data for patient care. OBJECTIVE.­: To expand and improve the College of American Pathologists (CAP) biomarker protocols. DESIGN.­: We surveyed CAP members to better understand the limitations they experienced when reporting cancer biomarker results. A Biomarker Workgroup reviewed the survey results and developed a strategy to improve and standardize biomarker reporting. Drafts of new and revised biomarker protocols were reviewed in both print and electronic template formats during interactive webinars presented to the CAP House of Delegates. Feedback was collected, and appropriate revisions were made to finalize the protocols. RESULTS.­: The first phase of the CAP Biomarker Workgroup saw the development of (1) a new stand-alone general Immunohistochemistry Biomarker Protocol that includes reporting for ER (estrogen receptor), PR (progesterone receptor), Ki-67, HER2 (human epidermal growth factor receptor 2), PD-L1 (programmed death ligand-1), and mismatch repair; (2) a new Head and Neck Biomarker Protocol that updates the prior 2017 paper-only version into an electronic template, adding new diagnostic and theranostic markers; (3) a major revision to the Lung Biomarker Protocol to streamline it and add in pan-cancer markers; and (4) a revision to the Colon and Rectum Biomarker Protocol to add HER2 reporting. CONCLUSIONS.­: We have taken a multipronged approach to improving biomarker reporting in the CAP cancer protocols. We continue to review current biomarker reporting protocols to reduce and eliminate unnecessary methodologic details and update with new markers as needed. The biomarker templates will serve as standardized modular units that can be inserted into cancer-reporting protocols.

Placental bands on MRI in the setting of placenta accreta spectrum: Case report with radiologic-pathologic correlation.

Placental bands on T2-weighted magnetic resonance imaging (MRI) are a known imaging finding in placenta accreta spectrum (PAS). It is believed that these linear T2 hypo-intensities may reflect increased fibrin deposition in the setting of placental hemorrhage or infarct. However, to date there is little published data regarding histopathologic analysis of placental parenchyma at the site of identified bands. We report the case of a 34-year-old female with a single placental band demonstrated on preoperative MRI which was evaluated postoperatively and found to represent a placental infarct.

Probabilistic Mixture Models Improve Calibration of Panel-derived Tumor Mutational Burden in the Context of both Tumor-normal and Tumor-only Sequencing.

Background: Tumor mutational burden (TMB) has been investigated as a biomarker for immune checkpoint blockade (ICB) therapy. Increasingly, TMB is being estimated with gene panel-based assays (as opposed to full exome sequencing) and different gene panels cover overlapping but distinct genomic coordinates, making comparisons across panels difficult. Previous studies have suggested that standardization and calibration to exome-derived TMB be done for each panel to ensure comparability. With TMB cutoffs being developed from panel-based assays, there is a need to understand how to properly estimate exomic TMB values from different panel-based assays. Design: Our approach to calibration of panel-derived TMB to exomic TMB proposes the use of probabilistic mixture models that allow for nonlinear relationships along with heteroscedastic error. We examined various inputs including nonsynonymous, synonymous, and hotspot counts along with genetic ancestry. Using The Cancer Genome Atlas cohort, we generated a tumor-only version of the panel-restricted data by reintroducing private germline variants. Results: We were able to model more accurately the distribution of both tumor-normal and tumor-only data using the proposed probabilistic mixture models as compared with linear regression. Applying a model trained on tumor-normal data to tumor-only input results in biased TMB predictions. Including synonymous mutations resulted in better regression metrics across both data types, but ultimately a model able to dynamically weight the various input mutation types exhibited optimal performance. Including genetic ancestry improved model performance only in the context of tumor-only data, wherein private germline variants are observed. Significance: A probabilistic mixture model better models the nonlinearity and heteroscedasticity of the data as compared with linear regression. Tumor-only panel data are needed to properly calibrate tumor-only panels to exomic TMB. Leveraging the uncertainty of point estimates from these models better informs cohort stratification in terms of TMB.

A deep learning model to triage and predict adenocarcinoma on pancreas cytology whole slide imaging.

Pancreatic fine-needle aspirations are the gold-standard diagnostic procedure for the evaluation of pancreatic ductal adenocarcinoma. A suspicion for malignancy can escalate towards chemotherapy followed by a major surgery and therefore is a high-stakes task for the pathologist. In this paper, we propose a deep learning framework, MIPCL, that can serve as a helpful screening tool, predicting the presence or absence of cancer. We also reproduce two deep learning models that have found success in surgical pathology for our cytopathology study. Our MIPCL significantly improves over both models across all evaluated metrics (F1-Score: 87.97% vs 88.70% vs 91.07%; AUROC: 0.9159 vs. 0.9051 vs 0.9435). Additionally, our model is able to recover the most contributing regions on the slide for the final prediction. We also present a dataset curation strategy that increases the number of training examples from an existing dataset, thereby reducing the resource burden tied to collecting and scanning additional cases.

Precision Oncology Core Data Model to Support Clinical Genomics Decision Making.

PURPOSE: Precision oncology mandates developing standardized common data models (CDMs) to facilitate analyses and enable clinical decision making. Expert-opinion-based precision oncology initiatives are epitomized in Molecular Tumor Boards (MTBs), which process large volumes of clinical-genomic data to match genotypes with molecularly guided therapies. METHODS: We used the Johns Hopkins University MTB as a use case and developed a precision oncology core data model (Precision-DM) to capture key clinical-genomic data elements. We leveraged existing CDMs, building upon the Minimal Common Oncology Data Elements model (mCODE). Our model was defined as a set of profiles with multiple data elements, focusing on next-generation sequencing and variant annotations. Most elements were mapped to terminologies or code sets and the Fast Healthcare Interoperability Resources (FHIR). We subsequently compared our Precision-DM with existing CDMs, including the National Cancer Institute's Genomic Data Commons (NCI GDC), mCODE, OSIRIS, the clinical Genome Data Model (cGDM), and the genomic CDM (gCDM). RESULTS: Precision-DM contained 16 profiles and 355 data elements. 39% of the elements derived values from selected terminologies or code sets, and 61% were mapped to FHIR. Although we used most elements contained in mCODE, we significantly expanded the profiles to include genomic annotations, resulting in a partial overlap of 50.7% between our core model and mCODE. Limited overlap was noted between Precision-DM and OSIRIS (33.2%), NCI GDC (21.4%), cGDM (9.3%), and gCDM (7.9%). Precision-DM covered most of the mCODE elements (87.7%), with less coverage for OSIRIS (35.8%), NCI GDC (11%), cGDM (26%) and gCDM (33.3%). CONCLUSION: Precision-DM supports clinical-genomic data standardization to support the MTB use case and may allow for harmonized data pulls across health care systems, academic institutions, and community medical centers.

A 20-gene model for molecular nodal staging of bladder cancer: development and prospective assessment.

BACKGROUND: Neoadjuvant chemotherapy before cystectomy confers a survival benefit in bladder cancer, but it has not been widely adopted since most patients do not benefit and we are at present unable to predict those that do. Since the most important predictor of recurrence after cystectomy is pathologically positive nodes, our aim was to assess techniques that define this stage for the selection of patients for neoadjuvant chemotherapy. METHODS: We developed a gene expression model (GEM) to predict the pathological node status in primary tumour tissue from three independent cohorts of patients who were clinically node negative. From a subset of transcripts detected faithfully by microarrays from both paired frozen and formalin-fixed tissues (32 pairs), we developed both the GEM and cutoffs that identified patient strata with raised risk of nodal involvement by use of two separate training cohorts (90 and 66 patients). We then assessed the GEM and cutoffs to predict node-positive disease in tissues from a phase 3 trial cohort (AUO-AB-05/95; 185 patients). FINDINGS: We developed a 20-gene GEM with an area under the curve of 0·67 (95% CI 0·60-0·75) for prediction of nodal disease at cystectomy in AUO-AB-05/95. The cutoff system identified patients with high relative risk (1·74, 95% CI 1·03-2·93) and low relative risk (0·70, 95% CI 0·51-0·96) of node-positive disease. Multivariate logistic regression showed the GEM predictor was independent of age, sex, pathological stage, and lymphovascular space invasion (coefficient 9·81, 95% CI 1·64-18·00; p=0·019). INTERPRETATION: Selecting patients for neoadjuvant chemotherapy on the basis of risk of node-positive disease has the potential to benefit high-risk patients while sparing other patients toxic effects and delay to cystectomy. FUNDING: US National Cancer Institute (R01CA143971).

Deep learning reveals predictive sequence concepts within immune repertoires to immunotherapy.

T cell receptor (TCR) sequencing has been used to characterize the immune response to cancer. However, most analyses have been restricted to quantitative measures such as clonality that do not leverage the complementarity-determining region 3 (CDR3) sequence. We use DeepTCR, a framework of deep learning algorithms, to reveal sequence concepts that are predictive of response to immunotherapy. We demonstrate that DeepTCR can predict response and use the model to infer the antigenic specificities of the predictive signature and their unique dynamics during therapy. The predictive signature of nonresponse is associated with high frequencies of TCRs predicted to recognize tumor-specific antigens, and these tumor-specific TCRs undergo a higher degree of dynamic changes on therapy in nonresponders versus responders. These results are consistent with a biological model where the hallmark of nonresponders is an accumulation of tumor-specific T cells that undergo turnover on therapy, possibly because of the dysfunctional state of these T cells in nonresponders.

Genomic Landscapes and Hallmarks of Mutant RAS in Human Cancers.

The RAS family of small GTPases represents the most commonly activated oncogenes in human cancers. To better understand the prevalence of somatic RAS mutations and the compendium of genes that are coaltered in RAS-mutant tumors, we analyzed targeted next-generation sequencing data of 607,863 mutations from 66,372 tumors in 51 cancer types in the AACR Project GENIE Registry. Bayesian hierarchical models were implemented to estimate the cancer-specific prevalence of RAS and non-RAS somatic mutations, to evaluate co-occurrence and mutual exclusivity, and to model the effects of tumor mutation burden and mutational signatures on comutation patterns. These analyses revealed differential RAS prevalence and comutations with non-RAS genes in a cancer lineage-dependent and context-dependent manner, with differences across age, sex, and ethnic groups. Allele-specific RAS co-mutational patterns included an enrichment in NTRK3 and chromatin-regulating gene mutations in KRAS G12C-mutant non-small cell lung cancer. Integrated multiomic analyses of 10,217 tumors from The Cancer Genome Atlas (TCGA) revealed distinct genotype-driven gene expression programs pointing to differential recruitment of cancer hallmarks as well as phenotypic differences and immune surveillance states in the tumor microenvironment of RAS-mutant tumors. The distinct genomic tracks discovered in RAS-mutant tumors reflected differential clinical outcomes in TCGA cohort and in an independent cohort of patients with KRAS G12C-mutant non-small cell lung cancer that received immunotherapy-containing regimens. The RAS genetic architecture points to cancer lineage-specific therapeutic vulnerabilities that can be leveraged for rationally combining RAS-mutant allele-directed therapies with targeted therapies and immunotherapy. SIGNIFICANCE: The complex genomic landscape of RAS-mutant tumors is reflective of selection processes in a cancer lineage-specific and context-dependent manner, highlighting differential therapeutic vulnerabilities that can be clinically translated.