Advancing Evidence Generation for Circulating Tumor DNA: Lessons Learned from A Multi-Assay Study of Baseline Circulating Tumor DNA Levels across Cancer Types and Stages.

Circulating tumor DNA (ctDNA) holds promise as a biomarker for predicting clinical responses to therapy in solid tumors, and multiple ctDNA assays are in development. However, the heterogeneity in ctDNA levels prior to treatment (baseline) across different cancer types and stages and across ctDNA assays has not been widely studied. Friends of Cancer Research formed a collaboration across multiple commercial ctDNA assay developers to assess baseline ctDNA levels across five cancer types in early- and late-stage disease. This retrospective study included eight commercial ctDNA assay developers providing summary-level de-identified data for patients with non-small cell lung cancer (NSCLC), bladder, breast, prostate, and head and neck squamous cell carcinoma following a common analysis protocol. Baseline ctDNA levels across late-stage cancer types were similarly detected, highlighting the potential use of ctDNA as a biomarker in these cancer types. Variability was observed in ctDNA levels across assays in early-stage NSCLC, indicative of the contribution of assay analytical performance and methodology on variability. We identified key data elements, including assay characteristics and clinicopathological metadata, that need to be standardized for future meta-analyses across multiple assays. This work facilitates evidence generation opportunities to support the use of ctDNA as a biomarker for clinical response.

A community challenge to predict clinical outcomes after immune checkpoint blockade in non-small cell lung cancer.

BACKGROUND: Predictive biomarkers of immune checkpoint inhibitor (ICI) efficacy are currently lacking for non-small cell lung cancer (NSCLC). Here, we describe the results from the Anti-PD-1 Response Prediction DREAM Challenge, a crowdsourced initiative that enabled the assessment of predictive models by using data from two randomized controlled clinical trials (RCTs) of ICIs in first-line metastatic NSCLC. METHODS: Participants developed and trained models using public resources. These were evaluated with data from the CheckMate 026 trial (NCT02041533), according to the model-to-data paradigm to maintain patient confidentiality. The generalizability of the models with the best predictive performance was assessed using data from the CheckMate 227 trial (NCT02477826). Both trials were phase III RCTs with a chemotherapy control arm, which supported the differentiation between predictive and prognostic models. Isolated model containers were evaluated using a bespoke strategy that considered the challenges of handling transcriptome data from clinical trials. RESULTS: A total of 59 teams participated, with 417 models submitted. Multiple predictive models, as opposed to a prognostic model, were generated for predicting overall survival, progression-free survival, and progressive disease status with ICIs. Variables within the models submitted by participants included tumor mutational burden (TMB), programmed death ligand 1 (PD-L1) expression, and gene-expression-based signatures. The best-performing models showed improved predictive power over reference variables, including TMB or PD-L1. CONCLUSIONS: This DREAM Challenge is the first successful attempt to use protected phase III clinical data for a crowdsourced effort towards generating predictive models for ICI clinical outcomes and could serve as a blueprint for similar efforts in other tumor types and disease states, setting a benchmark for future studies aiming to identify biomarkers predictive of ICI efficacy. TRIAL REGISTRATION: CheckMate 026; NCT02041533, registered January 22, 2014. CheckMate 227; NCT02477826, registered June 23, 2015.

Concurrent Tissue and Circulating Tumor DNA Molecular Profiling to Detect Guideline-Based Targeted Mutations in a Multicancer Cohort.

Importance: Tissue-based next-generation sequencing (NGS) of solid tumors is the criterion standard for identifying somatic mutations that can be treated with National Comprehensive Cancer Network guideline-recommended targeted therapies. Sequencing of circulating tumor DNA (ctDNA) can also identify tumor-derived mutations, and there is increasing clinical evidence supporting ctDNA testing as a diagnostic tool. The clinical value of concurrent tissue and ctDNA profiling has not been formally assessed in a large, multicancer cohort from heterogeneous clinical settings. Objective: To evaluate whether patients concurrently tested with both tissue and ctDNA NGS testing have a higher rate of detection of guideline-based targeted mutations compared with tissue testing alone. Design, Setting, and Participants: This cohort study comprised 3209 patients who underwent sequencing between May 2020, and December 2022, within the deidentified, Tempus multimodal database, consisting of linked molecular and clinical data. Included patients had stage IV disease (non-small cell lung cancer, breast cancer, prostate cancer, or colorectal cancer) with sufficient tissue and blood sample quantities for analysis. Exposures: Received results from tissue and plasma ctDNA genomic profiling, with biopsies and blood draws occurring within 30 days of one another. Main Outcomes and Measures: Detection rates of guideline-based variants found uniquely by ctDNA and tissue profiling. Results: The cohort of 3209 patients (median age at diagnosis of stage IV disease, 65.3 years [2.5%-97.5% range, 43.3-83.3 years]) who underwent concurrent tissue and ctDNA testing included 1693 women (52.8%). Overall, 1448 patients (45.1%) had a guideline-based variant detected. Of these patients, 9.3% (135 of 1448) had variants uniquely detected by ctDNA profiling, and 24.2% (351 of 1448) had variants uniquely detected by solid-tissue testing. Although largely concordant with one another, differences in the identification of actionable variants by either assay varied according to cancer type, gene, variant, and ctDNA burden. Of 352 patients with breast cancer, 20.2% (71 of 352) with actionable variants had unique findings in ctDNA profiling results. Most of these unique, actionable variants (55.0% [55 of 100]) were found in ESR1, resulting in a 24.7% increase (23 of 93) in the identification of patients harboring an ESR1 mutation relative to tissue testing alone. Conclusions and Relevance: This study suggests that unique actionable biomarkers are detected by both concurrent tissue and ctDNA testing, with higher ctDNA identification among patients with breast cancer. Integration of concurrent NGS testing into the routine management of advanced solid cancers may expand the delivery of molecularly guided therapy and improve patient outcomes.

Evaluation of crowdsourced mortality prediction models as a framework for assessing artificial intelligence in medicine.

OBJECTIVE: Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question. MATERIALS AND METHODS: Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system. RESULTS: The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort. DISCUSSION: Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data. CONCLUSION: This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

Machine learning in rare disease.

High-throughput profiling methods (such as genomics or imaging) have accelerated basic research and made deep molecular characterization of patient samples routine. These approaches provide a rich portrait of genes, molecular pathways and cell types involved in disease phenotypes. Machine learning (ML) can be a useful tool for extracting disease-relevant patterns from high-dimensional datasets. However, depending upon the complexity of the biological question, machine learning often requires many samples to identify recurrent and biologically meaningful patterns. Rare diseases are inherently limited in clinical cases, leading to few samples to study. In this Perspective, we outline the challenges and emerging solutions for using ML for small sample sets, specifically in rare diseases. Advances in ML methods for rare diseases are likely to be informative for applications beyond rare diseases for which few samples exist with high-dimensional data. We propose that the method community prioritize the development of ML techniques for rare disease research.

Validation of a Transcriptome-Based Assay for Classifying Cancers of Unknown Primary Origin.

INTRODUCTION: Cancers assume a variety of distinct histologies, and may originate from a myriad of sites including solid organs, hematopoietic cells, and connective tissue. Clinical decision-making based on consensus guidelines such as the National Comprehensive Cancer Network (NCCN) is often predicated on a specific histologic and anatomic diagnosis, supported by clinical features and pathologist interpretation of morphology and immunohistochemical (IHC) staining patterns. However, in patients with nonspecific morphologic and IHC findings-in addition to ambiguous clinical presentations such as recurrence versus new primary-a definitive diagnosis may not be possible, resulting in the patient being categorized as having a cancer of unknown primary (CUP). Therapeutic options and clinical outcomes are poor for patients with CUP, with a median survival of 8-11 months. METHODS: Here, we describe and validate the Tempus Tumor Origin (Tempus TO) assay, an RNA-sequencing-based machine learning classifier capable of discriminating between 68 clinically relevant cancer subtypes. Model accuracy was assessed using primary and/or metastatic samples with known subtype. RESULTS: We show that the Tempus TO model is 91% accurate when assessed on both a retrospectively held out cohort and a set of samples sequenced after model freeze that collectively contained 9210 total samples with known diagnoses. When evaluated on a cohort of CUPs, the model recapitulated established associations between genomic alterations and cancer subtype. DISCUSSION: Combining diagnostic prediction tests (e.g., Tempus TO) with sequencing-based variant reporting (e.g., Tempus xT) may expand therapeutic options for patients with cancers of unknown primary or uncertain histology.

USP10 Regulates ZEB1 Ubiquitination and Protein Stability to Inhibit ZEB1-Mediated Colorectal Cancer Metastasis.

Zinc finger E-box-binding homeobox 1 (ZEB1) is a transcription factor that can promote tumor invasion and metastasis by inducing epithelial-to-mesenchymal transition (EMT). To date, regulation of ZEB1 by RAS/RAF signaling remains unclear, and few studies have examined posttranslation modification of ZEB1, including its ubiquitination. In human colorectal cancer cell lines with RAS/RAF/MEK/ERK activation, an interaction of ZEB1 with the deubiquitinase ubiquitin-specific protease 10 (USP10) was identified whereby USP10 modifies ZEB1 ubiquitination and promotes its proteasomal degradation. Regulation of the USP10-ZEB1 interaction by MEK-ERK signaling was shown whereby constitutive activation of ERK can phosphorylate USP10 at Ser236 to impair its interaction with ZEB1 and enable ZEB1 protein stabilization. Stabilized ZEB1 was shown to promote colorectal cancer metastatic colonization in a mouse tail vein injection model. Conversely, MEK-ERK inhibition blocked USP10 phosphorylation and enhanced the USP10-ZEB1 interaction shown to suppress ZEB1-mediated tumor cell migration and metastasis. In conclusion, we demonstrate a novel function of USP10 in the regulation of ZEB1 protein stability and its ability to mediate tumor metastasis in a preclinical model. IMPLICATIONS: The MEK-ERK-regulated interaction of USP10 with ZEB1 can promote the proteasomal degradation of ZEB1 and thereby suppress its demonstrated ability to mediate tumor metastasis.

Molecular response in newly diagnosed chronic-phase chronic myeloid leukemia: prediction modeling and pathway analysis.

Tyrosine kinase inhibitor therapy revolutionized chronic myeloid leukemia treatment and showed how targeted therapy and molecular monitoring could be used to substantially improve survival outcomes. We used chronic myeloid leukemia as a model to understand a critical question: why do some patients have an excellent response to therapy, while others have a poor response? We studied gene expression in whole blood samples from 112 patients from a large phase III randomized trial (clinicaltrials gov. Identifier: NCT00471497), dichotomizing cases into good responders (BCR::ABL1 ≤10% on the International Scale by 3 and 6 months and ≤0.1% by 12 months) and poor responders (failure to meet these criteria). Predictive models based on gene expression demonstrated the best performance (area under the curve =0.76, standard deviation =0.07). All of the top 20 pathways overexpressed in good responders involved immune regulation, a finding validated in an independent data set. This study emphasizes the importance of pretreatment adaptive immune response in treatment efficacy and suggests biological pathways that can be targeted to improve response.

A Multifaceted benchmarking of synthetic electronic health record generation models.

Synthetic health data have the potential to mitigate privacy concerns in supporting biomedical research and healthcare applications. Modern approaches for data generation continue to evolve and demonstrate remarkable potential. Yet there is a lack of a systematic assessment framework to benchmark methods as they emerge and determine which methods are most appropriate for which use cases. In this work, we introduce a systematic benchmarking framework to appraise key characteristics with respect to utility and privacy metrics. We apply the framework to evaluate synthetic data generation methods for electronic health records data from two large academic medical centers with respect to several use cases. The results illustrate that there is a utility-privacy tradeoff for sharing synthetic health data and further indicate that no method is unequivocally the best on all criteria in each use case, which makes it evident why synthetic data generation methods need to be assessed in context.

External Validation of an Ensemble Model for Automated Mammography Interpretation by Artificial Intelligence.

Importance: With a shortfall in fellowship-trained breast radiologists, mammography screening programs are looking toward artificial intelligence (AI) to increase efficiency and diagnostic accuracy. External validation studies provide an initial assessment of how promising AI algorithms perform in different practice settings. Objective: To externally validate an ensemble deep-learning model using data from a high-volume, distributed screening program of an academic health system with a diverse patient population. Design, Setting, and Participants: In this diagnostic study, an ensemble learning method, which reweights outputs of the 11 highest-performing individual AI models from the Digital Mammography Dialogue on Reverse Engineering Assessment and Methods (DREAM) Mammography Challenge, was used to predict the cancer status of an individual using a standard set of screening mammography images. This study was conducted using retrospective patient data collected between 2010 and 2020 from women aged 40 years and older who underwent a routine breast screening examination and participated in the Athena Breast Health Network at the University of California, Los Angeles (UCLA). Main Outcomes and Measures: Performance of the challenge ensemble method (CEM) and the CEM combined with radiologist assessment (CEM+R) were compared with diagnosed ductal carcinoma in situ and invasive cancers within a year of the screening examination using performance metrics, such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Results: Evaluated on 37 317 examinations from 26 817 women (mean [SD] age, 58.4 [11.5] years), individual model AUROC estimates ranged from 0.77 (95% CI, 0.75-0.79) to 0.83 (95% CI, 0.81-0.85). The CEM model achieved an AUROC of 0.85 (95% CI, 0.84-0.87) in the UCLA cohort, lower than the performance achieved in the Kaiser Permanente Washington (AUROC, 0.90) and Karolinska Institute (AUROC, 0.92) cohorts. The CEM+R model achieved a sensitivity (0.813 [95% CI, 0.781-0.843] vs 0.826 [95% CI, 0.795-0.856]; P = .20) and specificity (0.925 [95% CI, 0.916-0.934] vs 0.930 [95% CI, 0.929-0.932]; P = .18) similar to the radiologist performance. The CEM+R model had significantly lower sensitivity (0.596 [95% CI, 0.466-0.717] vs 0.850 [95% CI, 0.766-0.923]; P < .001) and specificity (0.803 [95% CI, 0.734-0.861] vs 0.945 [95% CI, 0.936-0.954]; P < .001) than the radiologist in women with a prior history of breast cancer and Hispanic women (0.894 [95% CI, 0.873-0.910] vs 0.926 [95% CI, 0.919-0.933]; P = .004). Conclusions and Relevance: This study found that the high performance of an ensemble deep-learning model for automated screening mammography interpretation did not generalize to a more diverse screening cohort, suggesting that the model experienced underspecification. This study suggests the need for model transparency and fine-tuning of AI models for specific target populations prior to their clinical adoption.

A Crowdsourcing Approach to Develop Machine Learning Models to Quantify Radiographic Joint Damage in Rheumatoid Arthritis.

Importance: An automated, accurate method is needed for unbiased assessment quantifying accrual of joint space narrowing and erosions on radiographic images of the hands and wrists, and feet for clinical trials, monitoring of joint damage over time, assisting rheumatologists with treatment decisions. Such a method has the potential to be directly integrated into electronic health records. Objectives: To design and implement an international crowdsourcing competition to catalyze the development of machine learning methods to quantify radiographic damage in rheumatoid arthritis (RA). Design, Setting, and Participants: This diagnostic/prognostic study describes the Rheumatoid Arthritis 2-Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM Challenge), which used existing radiographic images and expert-curated Sharp-van der Heijde (SvH) scores from 2 clinical studies (674 radiographic sets from 562 patients) for training (367 sets), leaderboard (119 sets), and final evaluation (188 sets). Challenge participants were tasked with developing methods to automatically quantify overall damage (subchallenge 1), joint space narrowing (subchallenge 2), and erosions (subchallenge 3). The challenge was finished on June 30, 2020. Main Outcomes and Measures: Scores derived from submitted algorithms were compared with the expert-curated SvH scores, and a baseline model was created for benchmark comparison. Performances were ranked using weighted root mean square error (RMSE). The performance and reproductivity of each algorithm was assessed using Bayes factor from bootstrapped data, and further evaluated with a postchallenge independent validation data set. Results: The RA2-DREAM Challenge received a total of 173 submissions from 26 participants or teams in 7 countries for the leaderboard round, and 13 submissions were included in the final evaluation. The weighted RMSEs metric showed that the winning algorithms produced scores that were very close to the expert-curated SvH scores. Top teams included Team Shirin for subchallenge 1 (weighted RMSE, 0.44), HYL-YFG (Hongyang Li and Yuanfang Guan) subchallenge 2 (weighted RMSE, 0.38), and Gold Therapy for subchallenge 3 (weighted RMSE, 0.43). Bootstrapping/Bayes factor approach and the postchallenge independent validation confirmed the reproducibility and the estimation concordance indices between final evaluation and postchallenge independent validation data set were 0.71 for subchallenge 1, 0.78 for subchallenge 2, and 0.82 for subchallenge 3. Conclusions and Relevance: The RA2-DREAM Challenge resulted in the development of algorithms that provide feasible, quick, and accurate methods to quantify joint damage in RA. Ultimately, these methods could help research studies on RA joint damage and may be integrated into electronic health records to help clinicians serve patients better by providing timely, reliable, and quantitative information for making treatment decisions to prevent further damage.

A community challenge for a pancancer drug mechanism of action inference from perturbational profile data.

The Columbia Cancer Target Discovery and Development (CTD2) Center is developing PANACEA, a resource comprising dose-responses and RNA sequencing (RNA-seq) profiles of 25 cell lines perturbed with ∼400 clinical oncology drugs, to study a tumor-specific drug mechanism of action. Here, this resource serves as the basis for a DREAM Challenge assessing the accuracy and sensitivity of computational algorithms for de novo drug polypharmacology predictions. Dose-response and perturbational profiles for 32 kinase inhibitors are provided to 21 teams who are blind to the identity of the compounds. The teams are asked to predict high-affinity binding targets of each compound among ∼1,300 targets cataloged in DrugBank. The best performing methods leverage gene expression profile similarity analysis as well as deep-learning methodologies trained on individual datasets. This study lays the foundation for future integrative analyses of pharmacogenomic data, reconciliation of polypharmacology effects in different tumor contexts, and insights into network-based assessments of drug mechanisms of action.

A Continuously Benchmarked and Crowdsourced Challenge for Rapid Development and Evaluation of Models to Predict COVID-19 Diagnosis and Hospitalization.

Importance: Machine learning could be used to predict the likelihood of diagnosis and severity of illness. Lack of COVID-19 patient data has hindered the data science community in developing models to aid in the response to the pandemic. Objectives: To describe the rapid development and evaluation of clinical algorithms to predict COVID-19 diagnosis and hospitalization using patient data by citizen scientists, provide an unbiased assessment of model performance, and benchmark model performance on subgroups. Design, Setting, and Participants: This diagnostic and prognostic study operated a continuous, crowdsourced challenge using a model-to-data approach to securely enable the use of regularly updated COVID-19 patient data from the University of Washington by participants from May 6 to December 23, 2020. A postchallenge analysis was conducted from December 24, 2020, to April 7, 2021, to assess the generalizability of models on the cumulative data set as well as subgroups stratified by age, sex, race, and time of COVID-19 test. By December 23, 2020, this challenge engaged 482 participants from 90 teams and 7 countries. Main Outcomes and Measures: Machine learning algorithms used patient data and output a score that represented the probability of patients receiving a positive COVID-19 test result or being hospitalized within 21 days after receiving a positive COVID-19 test result. Algorithms were evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC) scores. Ensemble models aggregating models from the top challenge teams were developed and evaluated. Results: In the analysis using the cumulative data set, the best performance for COVID-19 diagnosis prediction was an AUROC of 0.776 (95% CI, 0.775-0.777) and an AUPRC of 0.297, and for hospitalization prediction, an AUROC of 0.796 (95% CI, 0.794-0.798) and an AUPRC of 0.188. Analysis on top models submitting to the challenge showed consistently better model performance on the female group than the male group. Among all age groups, the best performance was obtained for the 25- to 49-year age group, and the worst performance was obtained for the group aged 17 years or younger. Conclusions and Relevance: In this diagnostic and prognostic study, models submitted by citizen scientists achieved high performance for the prediction of COVID-19 testing and hospitalization outcomes. Evaluation of challenge models on demographic subgroups and prospective data revealed performance discrepancies, providing insights into the potential bias and limitations in the models.

Crowdsourced identification of multi-target kinase inhibitors for RET- and TAU- based disease: The Multi-Targeting Drug DREAM Challenge.

A continuing challenge in modern medicine is the identification of safer and more efficacious drugs. Precision therapeutics, which have one molecular target, have been long promised to be safer and more effective than traditional therapies. This approach has proven to be challenging for multiple reasons including lack of efficacy, rapidly acquired drug resistance, and narrow patient eligibility criteria. An alternative approach is the development of drugs that address the overall disease network by targeting multiple biological targets ('polypharmacology'). Rational development of these molecules will require improved methods for predicting single chemical structures that target multiple drug targets. To address this need, we developed the Multi-Targeting Drug DREAM Challenge, in which we challenged participants to predict single chemical entities that target pro-targets but avoid anti-targets for two unrelated diseases: RET-based tumors and a common form of inherited Tauopathy. Here, we report the results of this DREAM Challenge and the development of two neural network-based machine learning approaches that were applied to the challenge of rational polypharmacology. Together, these platforms provide a potentially useful first step towards developing lead therapeutic compounds that address disease complexity through rational polypharmacology.

Preview of "Interpretable systems biomarkers predict response to immune-checkpoint inhibitors".

Lapuente-Santana et al. (2021) developed Estimate Systems Immune Response (EaSIeR), a method for assessing the immune response to cancer using systems biology traits.

Clinical Characterization and Prediction of Clinical Severity of SARS-CoV-2 Infection Among US Adults Using Data From the US National COVID Cohort Collaborative.

Importance: The National COVID Cohort Collaborative (N3C) is a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools and inform clinical care and policy. Objectives: To evaluate COVID-19 severity and risk factors over time and assess the use of machine learning to predict clinical severity. Design, Setting, and Participants: In a retrospective cohort study of 1 926 526 US adults with SARS-CoV-2 infection (polymerase chain reaction >99% or antigen <1%) and adult patients without SARS-CoV-2 infection who served as controls from 34 medical centers nationwide between January 1, 2020, and December 7, 2020, patients were stratified using a World Health Organization COVID-19 severity scale and demographic characteristics. Differences between groups over time were evaluated using multivariable logistic regression. Random forest and XGBoost models were used to predict severe clinical course (death, discharge to hospice, invasive ventilatory support, or extracorporeal membrane oxygenation). Main Outcomes and Measures: Patient demographic characteristics and COVID-19 severity using the World Health Organization COVID-19 severity scale and differences between groups over time using multivariable logistic regression. Results: The cohort included 174 568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1 133 848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized, and 6565 (20.2%) of those had a severe clinical course (invasive ventilatory support, extracorporeal membrane oxygenation, death, or discharge to hospice). Of the hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March to April 2020 to 8.6% in September to October 2020 (P = .002 for monthly trend). Using 64 inputs available on the first hospital day, this study predicted a severe clinical course using random forest and XGBoost models (area under the receiver operating curve = 0.87 for both) that were stable over time. The factor most strongly associated with clinical severity was pH; this result was consistent across machine learning methods. In a separate multivariable logistic regression model built for inference, age (odds ratio [OR], 1.03 per year; 95% CI, 1.03-1.04), male sex (OR, 1.60; 95% CI, 1.51-1.69), liver disease (OR, 1.20; 95% CI, 1.08-1.34), dementia (OR, 1.26; 95% CI, 1.13-1.41), African American (OR, 1.12; 95% CI, 1.05-1.20) and Asian (OR, 1.33; 95% CI, 1.12-1.57) race, and obesity (OR, 1.36; 95% CI, 1.27-1.46) were independently associated with higher clinical severity. Conclusions and Relevance: This cohort study found that COVID-19 mortality decreased over time during 2020 and that patient demographic characteristics and comorbidities were associated with higher clinical severity. The machine learning models accurately predicted ultimate clinical severity using commonly collected clinical data from the first 24 hours of a hospital admission.

Brigatinib causes tumor shrinkage in both NF2-deficient meningioma and schwannoma through inhibition of multiple tyrosine kinases but not ALK.

Neurofibromatosis Type 2 (NF2) is an autosomal dominant genetic syndrome caused by mutations in the NF2 tumor suppressor gene resulting in multiple schwannomas and meningiomas. There are no FDA approved therapies for these tumors and their relentless progression results in high rates of morbidity and mortality. Through a combination of high throughput screens, preclinical in vivo modeling, and evaluation of the kinome en masse, we identified actionable drug targets and efficacious experimental therapeutics for the treatment of NF2 related schwannomas and meningiomas. These efforts identified brigatinib (ALUNBRIG®), an FDA-approved inhibitor of multiple tyrosine kinases including ALK, to be a potent inhibitor of tumor growth in established NF2 deficient xenograft meningiomas and a genetically engineered murine model of spontaneous NF2 schwannomas. Surprisingly, neither meningioma nor schwannoma cells express ALK. Instead, we demonstrate that brigatinib inhibited multiple tyrosine kinases, including EphA2, Fer and focal adhesion kinase 1 (FAK1). These data demonstrate the power of the de novo unbiased approach for drug discovery and represents a major step forward in the advancement of therapeutics for the treatment of NF2 related malignancies.

Bayesian multi-source regression and monocyte-associated gene expression predict BCL-2 inhibitor resistance in acute myeloid leukemia.

The FDA recently approved eight targeted therapies for acute myeloid leukemia (AML), including the BCL-2 inhibitor venetoclax. Maximizing efficacy of these treatments requires refining patient selection. To this end, we analyzed two recent AML studies profiling the gene expression and ex vivo drug response of primary patient samples. We find that ex vivo samples often exhibit a general sensitivity to (any) drug exposure, independent of drug target. We observe that this "general response across drugs" (GRD) is associated with FLT3-ITD mutations, clinical response to standard induction chemotherapy, and overall survival. Further, incorporating GRD into expression-based regression models trained on one of the studies improved their performance in predicting ex vivo response in the second study, thus signifying its relevance to precision oncology efforts. We find that venetoclax response is independent of GRD but instead show that it is linked to expression of monocyte-associated genes by developing and applying a multi-source Bayesian regression approach. The method shares information across studies to robustly identify biomarkers of drug response and is broadly applicable in integrative analyses.

A community challenge to evaluate RNA-seq, fusion detection, and isoform quantification methods for cancer discovery.

The accurate identification and quantitation of RNA isoforms present in the cancer transcriptome is key for analyses ranging from the inference of the impacts of somatic variants to pathway analysis to biomarker development and subtype discovery. The ICGC-TCGA DREAM Somatic Mutation Calling in RNA (SMC-RNA) challenge was a crowd-sourced effort to benchmark methods for RNA isoform quantification and fusion detection from bulk cancer RNA sequencing (RNA-seq) data. It concluded in 2018 with a comparison of 77 fusion detection entries and 65 isoform quantification entries on 51 synthetic tumors and 32 cell lines with spiked-in fusion constructs. We report the entries used to build this benchmark, the leaderboard results, and the experimental features associated with the accurate prediction of RNA species. This challenge required submissions to be in the form of containerized workflows, meaning each of the entries described is easily reusable through CWL and Docker containers at https://github.com/SMC-RNA-challenge. A record of this paper's transparent peer review process is included in the supplemental information.

Crowdsourced mapping of unexplored target space of kinase inhibitors.

Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound-kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.