Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses an immediate, major threat to public health across the globe. Here we report an in-depth molecular analysis to reconstruct the evolutionary origins of the enhanced pathogenicity of SARS-CoV-2 and other coronaviruses that are severe human pathogens. Using integrated comparative genomics and machine learning techniques, we identify key genomic features that differentiate SARS-CoV-2 and the viruses behind the two previous deadly coronavirus outbreaks, SARS-CoV and Middle East respiratory syndrome coronavirus (MERS-CoV), from less pathogenic coronaviruses. These features include enhancement of the nuclear localization signals in the nucleocapsid protein and distinct inserts in the spike glycoprotein that appear to be associated with high case fatality rate of these coronaviruses as well as the host switch from animals to humans. The identified features could be crucial contributors to coronavirus pathogenicity and possible targets for diagnostics, prognostication, and interventions.
The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.
Metabolic alterations play an important role in cancer and yet, few metabolic cancer driver genes are known. Here we perform a combined genomic and metabolic modeling analysis searching for metabolic drivers of colorectal cancer. Our analysis predicts FUT9, which catalyzes the biosynthesis of Ley glycolipids, as a driver of advanced‐stage colon cancer. Experimental testing reveals FUT9's complex dual role; while its knockdown enhances proliferation and migration in monolayers, it suppresses colon cancer cells expansion in tumorspheres and inhibits tumor development in a mouse xenograft models. These results suggest that FUT9's inhibition may attenuate tumor‐initiating cells (TICs) that are known to dominate tumorspheres and early tumor growth, but promote bulk tumor cells. In agreement, we find that FUT9 silencing decreases the expression of the colorectal cancer TIC marker CD44 and the level of the OCT4 transcription factor, which is known to support cancer stemness. Beyond its current application, this work presents a novel genomic and metabolic modeling computational approach that can facilitate the systematic discovery of metabolic driver genes in other types of cancer.
Disrupted regulation of cellular processes is considered one of the hallmarks of cancer. We analyze metabolomic and transcriptomic profiles jointly collected from breast cancer and hepatocellular carcinoma patients to explore the associations between the expression of metabolic enzymes and the levels of the metabolites participating in the reactions they catalyze. Surprisingly, both breast cancer and hepatocellular tumors exhibit an increase in their gene-metabolites associations compared to noncancerous adjacent tissues. Following, we build predictors of metabolite levels from the expression of the enzyme genes catalyzing them. Applying these predictors to a large cohort of breast cancer samples we find that depleted levels of key cancer-related metabolites including glucose, glycine, serine and acetate are significantly associated with improved patient survival. Thus, we show that the levels of a wide range of metabolites in breast cancer can be successfully predicted from the transcriptome, going beyond the limited set of those measured.
Driver mutations and chromosomal aneuploidy are major determinants of tumorigenesis that exhibit complex relationships. Here, we identify associations between driver mutations and chromosomal aberrations that define two tumor clusters, with distinct regimes of tumor evolution underpinned by unique sets of mutations in different components of DNA damage response. Gastrointestinal and endometrial tumors comprise a separate cluster for which chromosomal-arm aneuploidy and driver mutations are mutually exclusive. The landscape of driver mutations in these tumors is dominated by mutations in DNA repair genes that are further linked to microsatellite instability. The rest of the cancer types show a positive association between driver mutations and aneuploidy, and a characteristic set of mutations that involves primarily genes for components of the apoptotic machinery. The distinct sets of mutated genes derived here show substantial prognostic power and suggest specific vulnerabilities of different cancers that might have therapeutic potential.
The differences between high risk and low risk human papillomaviruses (HR-HPV and LR-HPV, respectively) that contribute to the tumorigenic potential of HR-HPV are not well understood but can be expected to involve the HPV oncoproteins, E6 and E7. We combine genome comparison and machine learning techniques to identify a previously unnoticed insert near the 3’-end of the E6 oncoprotein gene that is unique to HR-HPV. Analysis of the insert sequence suggests that it exerts a dual effect, by creating a PDZ domain-binding motif at the C-terminus of E6, as well as eliminating the overlap between the E6 and E7 coding regions in HR-HPV. We show that, as a result, the insert might enable coupled termination-reinitiation of the E6 and E7 genes, supported by motifs complementary to the human 18S rRNA. We hypothesize that the added functionality of E6 and positive regulation of E7 expression jointly account for the tumorigenic potential of HR-HPV.