Genomic landscape of advanced prostate cancer patients with BRCA1 versus BRCA2 mutations as detected by comprehensive genomic profiling of cell-free DNA.

BRCA1-mutated prostate cancer has been shown to be less responsive to poly (ADP-ribose) polymerase (PARP) inhibitors as compared to BRCA2-mutated prostate cancer. The reason for this differential response is not clear. We hypothesized this differential sensitivity to PARP inhibitors may be explained by distinct genomic landscapes of BRCA1 versus BRCA2 co-segregating genes. In a large dataset of 7,707 men with advanced prostate cancer undergoing comprehensive genomic profiling (CGP) of cell-free DNA (cfDNA), 614 men harbored BRCA1 and/or BRCA2 alterations. Differences in the genomic landscape of co-segregating genes was investigated by Fisher's exact test and probabilistic graphical models (PGMs). Results demonstrated that BRCA1 was significantly associated with six other genes, while BRCA2 was not significantly associated with any gene. These findings suggest BRCA2 may be the main driver mutation, while BRCA1 mutations tend to co-segregate with mutations in other molecular pathways contributing to prostate cancer progression. These hypothesis-generating data may explain the differential response to PARP inhibition and guide towards the development of combinatorial drug regimens in those with BRCA1 mutation.

Comprehensive Genomic Profiling of Cell-Free DNA in Men With Advanced Prostate Cancer: Differences in Genomic Landscape Based on Race.

Advanced prostate cancer (aPC) in Black men was reported to present with aggressive features and to be associated with poor prognosis. Herein, we compared the cell-free DNA (cfDNA) genomic landscape of aPC in Black vs White men. Patients (pts) with aPC from 6 academic institutions and available cfDNA comprehensive genomic profiling (CGP) were included. Association between mutated genes and race was evaluated using Barnard's test and a Probabilistic Graphical Model (PGM) machine learning approach. Analysis included 743 aPC pts (217 Black, 526 White) with available cfDNA CGP. The frequency of alterations in the androgen receptor gene was significantly higher in Black vs White men (55.3% vs 35% respectively, P < .001). Additionally, alterations in EGFR, MYC, FGFR1, and CTNNB1 were present at higher frequencies in Black men. PGM analysis and Barnard's test were concordant. Findings from the largest cohort of Black men with aPC undergoing cfDNA CGP may guide further drug development in these men.

An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records.

Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children's Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.

Identification of Somatic Gene Signatures in Circulating Cell-Free DNA Associated with Disease Progression in Metastatic Prostate Cancer by a Novel Machine Learning Platform.

PURPOSE: Progression from metastatic castration-sensitive prostate cancer (mCSPC) to a castration-resistant (mCRPC) state heralds the lethal phenotype of prostate cancer. Identifying genomic alterations associated with mCRPC may help find new targets for drug development. In the majority of patients, obtaining a tumor biopsy is challenging because of the predominance of bone-only metastasis. In this study, we hypothesize that machine learning (ML) algorithms can identify clinically relevant patterns of genomic alterations (GAs) that distinguish mCRPC from mCSPC, as assessed by next-generation sequencing (NGS) of circulating cell-free DNA (cfDNA). EXPERIMENTAL DESIGN: Retrospective clinical data from men with metastatic prostate cancer were collected. Men with NGS of cfDNA performed at a Clinical Laboratory Improvement Amendments (CLIA)-certified laboratory at time of diagnosis of mCSPC or mCRPC were included. A combination of supervised and unsupervised ML algorithms was used to obtain biologically interpretable, potentially actionable insights into genomic signatures that distinguish mCRPC from mCSPC. RESULTS: GAs that distinguish patients with mCRPC (n = 187) from patients with mCSPC (n = 154) (positive predictive value = 94%, specificity = 91%) were identified using supervised ML algorithms. These GAs, primarily amplifications, corresponded to androgen receptor, Mitogen-activated protein kinase (MAPK) signaling, Phosphoinositide 3-kinase (PI3K) signaling, G1/S cell cycle, and receptor tyrosine kinases. We also identified recurrent patterns of gene- and pathway-level alterations associated with mCRPC by using Bayesian networks, an unsupervised machine learning algorithm. CONCLUSION: These results provide clinical evidence that progression from mCSPC to mCRPC is associated with stereotyped concomitant gain-of-function aberrations in these pathways. Furthermore, detection of these aberrations in cfDNA may overcome the challenges associated with obtaining tumor bone biopsies and allow contemporary investigation of combinatorial therapies that target these aberrations. IMPLICATIONS FOR PRACTICE: The progression from castration-sensitive to castration-resistant prostate cancer is characterized by worse prognosis and there is a pressing need for targeted drugs to prevent or delay this transition. This study used machine learning algorithms to examine the cell-free DNA of patients to identify alterations to specific pathways and genes associated with progression. Detection of these alterations in cell-free DNA may overcome the challenges associated with obtaining tumor bone biopsies and allow contemporary investigation of combinatorial therapies that target these aberrations.

A Poisson binomial-based statistical testing framework for comorbidity discovery across electronic health record datasets.

Discovering the concomitant occurrence of distinct medical conditions in a patient, also known as comorbidities, is a prerequisite for creating patient outcome prediction tools. Current comorbidity discovery applications are designed for small datasets and use stratification to control for confounding variables such as age, sex or ancestry. Stratification lowers false positive rates, but reduces power, as the size of the study cohort is decreased. Here we describe a Poisson binomial-based approach to comorbidity discovery (PBC) designed for big-data applications that circumvents the need for stratification. PBC adjusts for confounding demographic variables on a per-patient basis and models temporal relationships. We benchmark PBC using two datasets to compute comorbidity statistics on 4,623,841 pairs of potentially comorbid medical terms. The results of this computation are provided as a searchable web resource. Compared with current methods, the PBC approach reduces false positive associations while retaining statistical power to discover true comorbidities.

De novo and recessive forms of congenital heart disease have distinct genetic and phenotypic landscapes.

The genetic architecture of sporadic congenital heart disease (CHD) is characterized by enrichment in damaging de novo variants in chromatin-modifying genes. To test the hypothesis that gene pathways contributing to de novo forms of CHD are distinct from those for recessive forms, we analyze 2391 whole-exome trios from the Pediatric Cardiac Genomics Consortium. We deploy a permutation-based gene-burden analysis to identify damaging recessive and compound heterozygous genotypes and disease genes, controlling for confounding effects, such as background mutation rate and ancestry. Cilia-related genes are significantly enriched for damaging rare recessive genotypes, but comparatively depleted for de novo variants. The opposite trend is observed for chromatin-modifying genes. Other cardiac developmental gene classes have less stratification by mode of inheritance than cilia and chromatin-modifying gene classes. Our analyses reveal dominant and recessive CHD are associated with distinct gene functions, with cilia-related genes providing a reservoir of rare segregating variation leading to CHD.

SRSF shape analysis for sequencing data reveal new differentiating patterns.

MOTIVATION: Sequencing-based methods to examine fundamental features of the genome, such as gene expression and chromatin structure, rely on inferences from the abundance and distribution of reads derived from Illumina sequencing. Drawing sound inferences from such experiments relies on appropriate mathematical methods to model the distribution of reads along the genome, which has been challenging due to the scale and nature of these data. RESULTS: We propose a new framework (SRSFseq) based on square root slope functions shape analysis to analyse Illumina sequencing data. In the new approach the basic unit of information is the density of mapped reads over region of interest located on the known reference genome. The densities are interpreted as shapes and a new shape analysis model is proposed. An equivalent of a Fisher test is used to quantify the significance of shape differences in read distribution patterns between groups of density functions in different experimental conditions. We evaluated the performance of this new framework to analyze RNA-seq data at the exon level, which enabled the detection of variation in read distributions and abundances between experimental conditions not detected by other methods. Thus, the method is a suitable supplement to the state-of-the-art count based techniques. The variety of density representations and flexibility of mathematical design allow the model to be easily adapted to other data types or problems in which the distribution of reads is to be tested. The functional interpretation and SRSF phase-amplitude separation technique give an efficient noise reduction procedure improving the sensitivity and specificity of the method.

A Comparison of Methods for RNA-Seq Differential Expression Analysis and a New Empirical Bayes Approach.

Transcriptome-based biosensors are expected to have a large impact on the future of biotechnology. However, a central aspect of transcriptomics is differential expression analysis, where, currently, deep RNA sequencing (RNA-seq) has the potential to replace the microarray as the standard assay for RNA quantification. Our contributions here to RNA-seq differential expression analysis are two-fold. First, given the high cost of an RNA-seq run, biological replicates are rare, and therefore, information sharing across genes to obtain variance estimates is crucial. To handle such information sharing in a rigorous manner, we propose an hierarchical, empirical Bayes approach (R-EBSeq) that combines the Cufflinks model for generating relative transcript abundance measurements, known as FPKM (fragments per kilobase of transcript length per million mapped reads) with the EBArrays framework, which was previously developed for empirical Bayes analysis of microarray data. A desirable feature of R-EBSeq is easy-to-implement analysis of more than pairwise comparisons, as we illustrate with experimental data. Secondly, we develop the standard RNA-seq test data set, on the level of reads, where 79 transcripts are artificially differentially expressed and, therefore, explicitly known. This test data set allows us to compare the performance, in terms of the true discovery rate, of R-EBSeq to three other widely used RNAseq data analysis packages: Cuffdiff, DEseq and BaySeq. Our analysis indicates that DESeq identifies the first half of the differentially expressed transcripts well, but then is outperformed by Cuffdiff and R-EBSeq. Cuffdiff and R-EBSeq are the two top performers. Thus, R-EBSeq offers good performance, while allowing flexible and rigorous comparison of multiple biological conditions.