A platform-independent AI tumor lineage and site (ATLAS) classifier.

Histopathologic diagnosis and classification of cancer plays a critical role in guiding treatment. Advances in next-generation sequencing have ushered in new complementary molecular frameworks. However, existing approaches do not independently assess both site-of-origin (e.g. prostate) and lineage (e.g. adenocarcinoma) and have minimal validation in metastatic disease, where classification is more difficult. Utilizing gradient-boosted machine learning, we developed ATLAS, a pair of separate AI Tumor Lineage and Site-of-origin models from RNA expression data on 8249 tumor samples. We assessed performance independently in 10,376 total tumor samples, including 1490 metastatic samples, achieving an accuracy of 91.4% for cancer site-of-origin and 97.1% for cancer lineage. High confidence predictions (encompassing the majority of cases) were accurate 98-99% of the time in both localized and remarkably even in metastatic samples. We also identified emergent properties of our lineage scores for tumor types on which the model was never trained (zero-shot learning). Adenocarcinoma/sarcoma lineage scores differentiated epithelioid from biphasic/sarcomatoid mesothelioma. Also, predicted lineage de-differentiation identified neuroendocrine/small cell tumors and was associated with poor outcomes across tumor types. Our platform-independent single-sample approach can be easily translated to existing RNA-seq platforms. ATLAS can complement and guide traditional histopathologic assessment in challenging situations and tumors of unknown primary.

Machine Learning & Molecular Radiation Tumor Biomarkers.

Developing radiation tumor biomarkers that can guide personalized radiotherapy clinical decision making is a critical goal in the effort towards precision cancer medicine. High-throughput molecular assays paired with modern computational techniques have the potential to identify individual tumor-specific signatures and create tools that can help understand heterogenous patient outcomes in response to radiotherapy, allowing clinicians to fully benefit from the technological advances in molecular profiling and computational biology including machine learning. However, the increasingly complex nature of the data generated from high-throughput and "omics" assays require careful selection of analytical strategies. Furthermore, the power of modern machine learning techniques to detect subtle data patterns comes with special considerations to ensure that the results are generalizable. Herein, we review the computational framework of tumor biomarker development and describe commonly used machine learning approaches and how they are applied for radiation biomarker development using molecular data, as well as challenges and emerging research trends.

Identification of phenocopies improves prediction of targeted therapy response over DNA mutations alone.

DNA mutations in specific genes can confer preferential benefit from drugs targeting those genes. However, other molecular perturbations can "phenocopy" pathogenic mutations, but would not be identified using standard clinical sequencing, leading to missed opportunities for other patients to benefit from targeted treatments. We hypothesized that RNA phenocopy signatures of key cancer driver gene mutations could improve our ability to predict response to targeted therapies, despite not being directly trained on drug response. To test this, we built gene expression signatures in tissue samples for specific mutations and found that phenocopy signatures broadly increased accuracy of drug response predictions in-vitro compared to DNA mutation alone, and identified additional cancer cell lines that respond well with a positive/negative predictive value on par or better than DNA mutations. We further validated our results across four clinical cohorts. Our results suggest that routine RNA sequencing of tumors to identify phenocopies in addition to standard targeted DNA sequencing would improve our ability to accurately select patients for targeted therapies in the clinic.

Longitudinal Molecular Profiling of Circulating Tumor Cells in Metastatic Renal Cell Carcinoma.

PURPOSE: Liquid biopsies in metastatic renal cell carcinoma (mRCC) provide a unique approach to understand the molecular basis of treatment response and resistance. This is particularly important in the context of immunotherapies, which target key immune-tumor interactions. Unlike metastatic tissue biopsies, serial real-time profiling of mRCC is feasible with our noninvasive circulating tumor cell (CTC) approach. METHODS: We collected 457 longitudinal liquid biopsies from 104 patients with mRCC enrolled in one of two studies, either a prospective cohort or a phase II multicenter adaptive immunotherapy trial. Using a novel CTC capture and automated microscopy platform, we profiled CTC enumeration and expression of HLA I and programmed cell death-ligand 1 (PD-L1). Given their diametric immunological roles, we focused on the HLA I to PD-L1 ratio (HP ratio). RESULTS: Patients with radiographic responses showed significantly lower CTC abundances throughout treatment. Furthermore, patients whose CTC enumeration trajectory was in the highest quartile (> 0.12 CTCs/mL annually) had shorter overall survival (median 17.0 months v 21.1 months, P < .001). Throughout treatment, the HP ratio decreased in patients receiving immunotherapy but not in patients receiving tyrosine kinase inhibitors. Patients with an HP ratio trajectory in the highest quartile (≥ 0.0012 annually) displayed significantly shorter overall survival (median 18.4 months v 21.2 months, P = .003). CONCLUSION: In the first large longitudinal CTC study in mRCC to date to our knowledge, we identified the prognostic importance of CTC enumeration and the change over time of both CTC enumeration and the HP ratio. These insights into changes in both tumor burden and the molecular profile of tumor cells in response to different treatments provide potential biomarkers to predict and monitor response to immunotherapy in mRCC.

A clinical-grade liquid biomarker detects neuroendocrine differentiation in prostate cancer.

BackgroundNeuroendocrine prostate cancer (NEPC) is an aggressive subtype, the presence of which changes the prognosis and management of metastatic prostate cancer.MethodsWe performed analytical validation of a Circulating Tumor Cell (CTC) multiplex RNA qPCR assay to identify the limit of quantification (LOQ) in cell lines, synthetic cDNA, and patient samples. We next profiled 116 longitudinal samples from a prospectively collected institutional cohort of 17 patients with metastatic prostate cancer (7 NEPC, 10 adenocarcinoma) as well as 265 samples from 139 patients enrolled in 3 adenocarcinoma phase II trials of androgen receptor signaling inhibitors (ARSIs). We assessed a NEPC liquid biomarker via the presence of neuroendocrine markers and the absence of androgen receptor (AR) target genes.ResultsUsing the analytical validation LOQ, liquid biomarker NEPC detection in the longitudinal cohort had a per-sample sensitivity of 51.35% and a specificity of 91.14%. However, when we incorporated the serial information from multiple liquid biopsies per patient, a unique aspect of this study, the per-patient predictions were 100% accurate, with a receiver-operating-curve (ROC) AUC of 1. In the adenocarcinoma ARSI trials, the presence of neuroendocrine markers, even while AR target gene expression was retained, was a strong negative prognostic factor.ConclusionOur analytically validated CTC biomarker can detect NEPC with high diagnostic accuracy when leveraging serial samples that are only feasible using liquid biopsies. Patients with expression of NE genes while retaining AR-target gene expression may indicate the transition to neuroendocrine differentiation, with clinical characteristics consistent with this phenotype.FundingNIH (DP2 OD030734, 1UH2CA260389, R01CA247479, and P30 CA014520), Department of Defense (PC190039 and PC200334), and Prostate Cancer Foundation (Movember Foundation - PCF Challenge Award).

Predicting cancer drug TARGETS - TreAtment Response Generalized Elastic-neT Signatures.

We are now in an era of molecular medicine, where specific DNA alterations can be used to identify patients who will respond to specific drugs. However, there are only a handful of clinically used predictive biomarkers in oncology. Herein, we describe an approach utilizing in vitro DNA and RNA sequencing and drug response data to create TreAtment Response Generalized Elastic-neT Signatures (TARGETS). We trained TARGETS drug response models using Elastic-Net regression in the publicly available Genomics of Drug Sensitivity in Cancer (GDSC) database. Models were then validated on additional in-vitro data from the Cancer Cell Line Encyclopedia (CCLE), and on clinical samples from The Cancer Genome Atlas (TCGA) and Stand Up to Cancer/Prostate Cancer Foundation West Coast Prostate Cancer Dream Team (WCDT). First, we demonstrated that all TARGETS models successfully predicted treatment response in the separate in-vitro CCLE treatment response dataset. Next, we evaluated all FDA-approved biomarker-based cancer drug indications in TCGA and demonstrated that TARGETS predictions were concordant with established clinical indications. Finally, we performed independent clinical validation in the WCDT and found that the TARGETS AR signaling inhibitors (ARSI) signature successfully predicted clinical treatment response in metastatic castration-resistant prostate cancer with a statistically significant interaction between the TARGETS score and PSA response (p = 0.0252). TARGETS represents a pan-cancer, platform-independent approach to predict response to oncologic therapies and could be used as a tool to better select patients for existing therapies as well as identify new indications for testing in prospective clinical trials.

Prognosis Associated With Luminal and Basal Subtypes of Metastatic Prostate Cancer.

IMPORTANCE: Luminal and basal subtypes of primary prostate cancer have been shown to be molecularly distinct and clinically important in predicting response to therapy. These subtypes have not been described in metastatic prostate cancer. OBJECTIVES: To identify clinical and molecular correlates of luminal and basal subtypes in metastatic castration-resistant prostate cancer (mCRPC) and investigate differences in survival, particularly after treatment with androgen-signaling inhibitors (ASIs). DESIGN, SETTING, AND PARTICIPANTS: In this cohort study, a retrospective analysis was conducted of 4 cohorts with mCRPC (N = 634) across multiple academic centers. Treatment was at the physicians' discretion. Details of the study cohorts have been published elsewhere between 2016 and 2019. Data were analyzed from March 2018 to February 2021. MAIN OUTCOMES AND MEASURES: The primary clinical end point was overall survival from the date of tissue biopsy/molecular profiling. Luminal and basal subtypes were also stratified by postbiopsy ASI treatment. The primary molecular analyses included associations with small cell/neuroendocrine prostate cancer (SCNC), molecular pathways, and DNA alterations. RESULTS: In the 634 patients, 288 (45%) had tumors classified as luminal, and 346 (55%) had tumors classified as basal. However, 53 of 59 (90%) SCNC tumors were basal (P < .001). Similar to primary prostate cancer, luminal tumors exhibited overexpression of AR pathway genes. In basal tumors, a significantly higher rate of RB1 loss (23% basal vs 4% luminal; P < .001), FOXA1 alterations (36% basal vs 27% luminal; P = .03) and MYC alterations (73% basal vs 56% luminal; P < .001) were identified. Patients with basal tumors had worse overall survival compared with those with luminal tumors only in patients treated with an ASI postbiopsy (East Coast Dream Team: hazard ratio [HR], 0.39; 95% CI, 0.20-0.74; P = .004; West Coast Dream Team: HR, 0.57; 95% CI, 0.33-0.97; P = .04). Among patients with luminal tumors, those treated with an ASI had significantly better survival (HR, 0.27; 95% CI, 0.14-0.53; P < .001), whereas patients with basal tumors did not (HR, 0.62; 95% CI, 0.36-1.04, P = .07). The interaction term between subtype and ASI treatment was statistically significant (HR, 0.42; 95% CI, 0.20-0.89; P = .02). CONCLUSIONS AND RELEVANCE: These findings represent the largest integrated clinical, transcriptomic, and genomic analysis of mCRPC samples to date, and suggest that mCRPC can be classified as luminal and basal tumors. Analogous to primary prostate cancer, these data suggest that the benefit of ASI treatment is more pronounced in luminal tumors and support the use of ASIs in this population. In the basal tumors, a chemotherapeutic approach could be considered in some patients given the similarity to SCNC and the diminished benefit of ASI therapy. Further validation in prospective clinical trials is warranted.