Machine-learning for molecular genetics

Since the advent of next-generation sequencing, there has been an explosion in the number of molecular, genome-wide assays performed in the biomedical sciences. Advances in microfluidics technologies, gene-editing platforms and others, have further increased the amount of data generated by orders of magnitude. Rapidly growing repositories, such as the NIH BRAIN Initiative, ENCODE, TCGA, Roadmap Epigenomics Project and others, enable functional hypotheses to be tested via large-scale meta-analysis. We are particularly interested in machine-learning, network hypothesis testing, "Big Data" re-sampling, and screening methods.