BrcaDx: precise identification of breast cancer from expression data using a minimal set of features

Identification of modules and key genes associated with breast cancer subtypes through network analysis

Breast cancer is the most common malignancy in women around the world. Intratumor and intertumoral heterogeneity persist in mammary tumors. Therefore, the identification of biomarkers is essential for the treatment of this malignancy. This study analyzed 28,143 genes expressed in 49 breast cancer cell lines using a Weighted Gene Co-expression Network Analysis to determine specific target proteins for Basal A, Basal B, Luminal A, Luminal B, and HER2 ampl breast cancer subtypes. Sixty-five modules were identified, of which five were characterized as having a high correlation with breast cancer subtypes. Genes overexpressed in the tumor were found to participate in the following mechanisms: regulation of the apoptotic process, transcriptional regulation, angiogenesis, signaling, and cellular survival. In particular, we identified the following genes, considered as hubs: IFIT3, an inhibitor of viral and cellular processes; ETS1, a transcription factor involved in cell death and tumorigenesis; ENSG00000259723 lncRNA, expressed in cancers; AL033519.3, a hypothetical gene; and TMEM86A, important for regulating keratinocyte membrane properties, considered as a key in Basal A, Basal B, Luminal A, Luminal B, and HER2 ampl breast cancer subtypes, respectively. The modules and genes identified in this work can be used to identify possible biomarkers or therapeutic targets in different breast cancer subtypes.

PRADclass: Hybrid Gleason Grade-Informed Computational Strategy Identifies Consensus Biomarker Features Predictive of Aggressive Prostate Adenocarcinoma

BACKGROUND

Prostate adenocarcinoma (PRAD) is a common cancer diagnosis among men globally, yet large gaps in our knowledge persist with respect to the molecular bases of its progression and aggression. It is mostly indolent and slow-growing, but aggressive prostate cancers need to be recognized early for optimising treatment, with a view to reducing mortality.

METHODS

Based on TCGA transcriptomic data pertaining to PRAD and the associated clinical metadata, we determined the sample Gleason grade, and used it to execute: (i) Gleason-grade wise linear modeling, followed by five contrasts against controls and ten contrasts between grades; and (ii) Gleason-grade wise network modeling via weighted gene correlation network analysis (WGCNA). Candidate biomarkers were obtained from the above analysis and the consensus found. The consensus biomarkers were used as the feature space to train ML models for classifying a sample as benign, indolent or aggressive.

RESULTS

The statistical modeling yielded 77 Gleason grade-salient genes while the WGCNA algorithm yielded 1003 trait-specific key genes in grade-wise significant modules. Consensus analysis of the two approaches identified two genes in Grade-1 (SLC43A1 and PHGR1), 26 genes in Grade-4 (including LOC100128675, PPP1R3C, NECAB1, UBXN10, SERPINA5, CLU, RASL12, DGKG, FHL1, NCAM1, and CEND1), and seven genes in Grade-5 (CBX2, DPYS, FAM72B, SHCBP1, TMEM132A, TPX2, UBE2C). A RandomForest model trained and optimized on these 35 biomarkers for the ternary classification problem yielded a balanced accuracy ∼ 86% on external validation.

CONCLUSIONS

The consensus of multiple parallel computational strategies has unmasked candidate Gleason grade-specific biomarkers. PRADclass, a validated AI model featurizing these biomarkers achieved good performance, and could be trialed to predict the differentiation of prostate cancers. PRADclass is available for academic use at: https://apalania.shinyapps.io/pradclass (online) and https://github.com/apalania/pradclass (command-line interface).