Evolutionary Action-Machine Learning Model Identifies Candidate Genes Associated With Early-Onset Coronary Artery Disease.

Background Coronary artery disease is a primary cause of death around the world, with both genetic and environmental risk factors. Although genome-wide association studies have linked >100 unique loci to its genetic basis, these only explain a fraction of disease heritability. Methods and Results To find additional gene drivers of coronary artery disease, we applied machine learning to quantitative evolutionary information on the impact of coding variants in whole exomes from the Myocardial Infarction Genetics Consortium. Using ensemble-based supervised learning, the Evolutionary Action-Machine Learning framework ranked each gene's ability to classify case and control samples and identified 79 significant associations. These were connected to known risk loci; enriched in cardiovascular processes like lipid metabolism, blood clotting, and inflammation; and enriched for cardiovascular phenotypes in knockout mouse models. Among them, INPP5F and MST1R are examples of potentially novel coronary artery disease risk genes that modulate immune signaling in response to cardiac stress. Conclusions We concluded that machine learning on the functional impact of coding variants, based on a massive amount of evolutionary information, has the power to suggest novel coronary artery disease risk genes for mechanistic and therapeutic discoveries in cardiovascular biology, and should also apply in other complex polygenic diseases.

Functional variants identify sex-specific genes and pathways in Alzheimer's Disease.

The incidence of Alzheimer's Disease in females is almost double that of males. To search for sex-specific gene associations, we build a machine learning approach focused on functionally impactful coding variants. This method can detect differences between sequenced cases and controls in small cohorts. In the Alzheimer's Disease Sequencing Project with mixed sexes, this approach identified genes enriched for immune response pathways. After sex-separation, genes become specifically enriched for stress-response pathways in male and cell-cycle pathways in female. These genes improve disease risk prediction in silico and modulate Drosophila neurodegeneration in vivo. Thus, a general approach for machine learning on functionally impactful variants can uncover sex-specific candidates towards diagnostic biomarkers and therapeutic targets.

Evolution of cisplatin resistance through coordinated metabolic reprogramming of the cellular reductive state.

BACKGROUND: Cisplatin (CDDP) is a mainstay treatment for advanced head and neck squamous cell carcinomas (HNSCC) despite a high frequency of innate and acquired resistance. We hypothesised that tumours acquire CDDP resistance through an enhanced reductive state dependent on metabolic rewiring. METHODS: To validate this model and understand how an adaptive metabolic programme might be imprinted, we performed an integrated analysis of CDDP-resistant HNSCC clones from multiple genomic backgrounds by whole-exome sequencing, RNA-seq, mass spectrometry, steady state and flux metabolomics. RESULTS: Inactivating KEAP1 mutations or reductions in KEAP1 RNA correlated with Nrf2 activation in CDDP-resistant cells, which functionally contributed to resistance. Proteomics identified elevation of downstream Nrf2 targets and the enrichment of enzymes involved in generation of biomass and reducing equivalents, metabolism of glucose, glutathione, NAD(P), and oxoacids. This was accompanied by biochemical and metabolic evidence of an enhanced reductive state dependent on coordinated glucose and glutamine catabolism, associated with reduced energy production and proliferation, despite normal mitochondrial structure and function. CONCLUSIONS: Our analysis identified coordinated metabolic changes associated with CDDP resistance that may provide new therapeutic avenues through targeting of these convergent pathways.

EPIMUTESTR: a nearest neighbor machine learning approach to predict cancer driver genes from the evolutionary action of coding variants.

Discovering rare cancer driver genes is difficult because their mutational frequency is too low for statistical detection by computational methods. EPIMUTESTR is an integrative nearest-neighbor machine learning algorithm that identifies such marginal genes by modeling the fitness of their mutations with the phylogenetic Evolutionary Action (EA) score. Over cohorts of sequenced patients from The Cancer Genome Atlas representing 33 tumor types, EPIMUTESTR detected 214 previously inferred cancer driver genes and 137 new candidates never identified computationally before of which seven genes are supported in the COSMIC Cancer Gene Census. EPIMUTESTR achieved better robustness and specificity than existing methods in a number of benchmark methods and datasets.

A general calculus of fitness landscapes finds genes under selection in cancers.

Genetic variants drive the evolution of traits and diseases. We previously modeled these variants as small displacements in fitness landscapes and estimated their functional impact by differentiating the evolutionary relationship between genotype and phenotype. Conversely, here we integrate these derivatives to identify genes steering specific traits. Over cancer cohorts, integration identified 460 likely tumor-driving genes. Many have literature and experimental support but had eluded prior genomic searches for positive selection in tumors. Beyond providing cancer insights, these results introduce a general calculus of evolution to quantify the genotype-phenotype relationship and discover genes associated with complex traits and diseases.

Sensitive and selective plasmon ruler nanosensors for monitoring the apoptotic drug response in leukemia.

Caspases are proteases involved in cell death, where caspase-3 is the chief executioner that produces an irreversible cutting event in downstream protein substrates and whose activity is desired in the management of cancer. To determine such activity in clinically relevant samples with high signal-to-noise, plasmon rulers are ideal because they are sensitively affected by their interparticle separation without ambiguity from photobleaching or blinking effects. A plasmon ruler is a noble metal nanoparticle pair, tethered in close proximity to one another via a biomolecule, that acts through dipole-dipole interactions and results in the light scattering to increase exponentially. In contrast, a sharp decrease in intensity is observed when the pair is confronted by a large interparticle distance. To align the mechanism of protease activity with building a sensor that can report a binary signal in the presence or absence of caspase-3, we present a caspase-3 selective plasmon ruler (C3SPR) composed of a pair of Zn0.4Fe2.6O4@SiO2@Au core-shell nanoparticles connected by a caspase-3 cleavage sequence. The dielectric core (Zn0.4Fe2.6O4@SiO2)-shell (Au) geometry provided a brighter scattering intensity versus solid Au nanoparticles, and the magnetic core additionally acted as a purification handle during the plasmon ruler assembly. By monitoring the decrease in light scattering intensity per plasmon ruler, we detected caspase-3 activity at single molecule resolution across a broad dynamic range. This was observed to be as low as 100 fM of recombinant material or 10 ng of total protein from cellular lysate. By thorough analyses of single molecule trajectories, we show caspase-3 activation in a drug-treated chronic myeloid leukemia (K562) cancer system as early as 4 and 8 h with greater sensitivity (2- and 4-fold, respectively) than conventional reagents. This study provides future implications for monitoring caspase-3 as a biomarker and efficacy of drugs.

MEK-dependent negative feedback underlies BCR-ABL-mediated oncogene addiction.

UNLABELLED: The clinical experience with BCR-ABL tyrosine kinase inhibitors (TKI) for the treatment of chronic myelogenous leukemia (CML) provides compelling evidence for oncogene addiction. Yet, the molecular basis of oncogene addiction remains elusive. Through unbiased quantitative phosphoproteomic analyses of CML cells transiently exposed to BCR-ABL TKI, we identified persistent downregulation of growth factor receptor (GF-R) signaling pathways. We then established and validated a tissue-relevant isogenic model of BCR-ABL-mediated addiction, and found evidence for myeloid GF-R signaling pathway rewiring that profoundly and persistently dampens physiologic pathway activation. We demonstrate that eventual restoration of ligand-mediated GF-R pathway activation is insufficient to fully rescue cells from a competing apoptotic fate. In contrast to previous work with BRAF(V600E) in melanoma cells, feedback inhibition following BCR-ABL TKI treatment is markedly prolonged, extending beyond the time required to initiate apoptosis. Mechanistically, BCR-ABL-mediated oncogene addiction is facilitated by persistent high levels of MAP-ERK kinase (MEK)-dependent negative feedback. SIGNIFICANCE: We found that BCR­ABL can confer addiction in vitro by rewiring myeloid GF-R signaling through establishment of MEK-dependent negative feedback. Our findings predict that deeper, more durable responses to targeted agents across a range of malignancies may be facilitated by maintaining negative feedback concurrently with oncoprotein inhibition.