MODEL-BASED FEATURE SELECTION AND CLUSTERING OF RNA-SEQ DATA FOR UNSUPERVISED SUBTYPE DISCOVERY

ZINBMM: a general mixture model for simultaneous clustering and gene selection using single-cell transcriptomic data

Clustering is a critical component of single-cell RNA sequencing (scRNA-seq) data analysis and can help reveal cell types and infer cell lineages. Despite considerable successes, there are few methods tailored to investigating cluster-specific genes contributing to cell heterogeneity, which can promote biological understanding of cell heterogeneity. In this study, we propose a zero-inflated negative binomial mixture model (ZINBMM) that simultaneously achieves effective scRNA-seq data clustering and gene selection. ZINBMM conducts a systemic analysis on raw counts, accommodating both batch effects and dropout events. Simulations and the analysis of five scRNA-seq datasets demonstrate the practical applicability of ZINBMM.

Integrated Multi-Omic Analysis Reveals Immunosuppressive Phenotype Associated with Poor Outcomes in High-Grade Serous Ovarian Cancer

High-grade serous ovarian cancer (HGSOC) is characterized by a complex genomic landscape, with both genetic and epigenetic diversity contributing to its pathogenesis, disease course, and response to treatment. To better understand the association between genomic features and response to treatment among 370 patients with newly diagnosed HGSOC, we utilized multi-omic data and semi-biased clustering of HGSOC specimens profiled by TCGA. A Cox regression model was deployed to select model input features based on the influence on disease recurrence. Among the features most significantly correlated with recurrence were the promotor-associated probes for the NFRKB and DPT genes and the TREML1 gene. Using 1467 transcriptomic and methylomic features as input to consensus clustering, we identified four distinct tumor clusters-three of which had noteworthy differences in treatment response and time to disease recurrence. Each cluster had unique divergence in differential analyses and distinctly enriched pathways therein. Differences in predicted stromal and immune cell-type composition were also observed, with an immune-suppressive phenotype specific to one cluster, which associated with short time to disease recurrence. Our model features were additionally used as a neural network input layer to validate the previously defined clusters with high prediction accuracy (91.3%). Overall, our approach highlights an integrated data utilization workflow from tumor-derived samples, which can be used to uncover novel drivers of clinical outcomes.