In the era of precision medicine, cancer therapy can be tailored to an individual patient based on the genomic profile of a tumour. Despite the ever-increasing abundance of cancer genomic data, linking mutation profiles to drug efficacy remains a challenge. Herein, we report Cancer Drug Response profile scan (CDRscan) a novel deep learning model that predicts anticancer drug responsiveness based on a large-scale drug screening assay data encompassing genomic profiles of 787 human cancer cell lines and structural profiles of 244 drugs. CDRscan employs a two-step convolution architecture, where the genomic mutational fingerprints of cell lines and the molecular fingerprints of drugs are processed individually, then merged by ‘virtual docking’, an in silico modelling of drug treatment. Analysis of the goodness-of-fit between observed and predicted drug response revealed a high prediction accuracy of CDRscan (R2 > 0.84; AUROC > 0.98). We applied CDRscan to 1,487 approved drugs and identified 14 oncology and 23 non-oncology drugs having new potential cancer indications. This, to our knowledge, is the first-time application of a deep learning model in predicting the feasibility of drug repurposing. By further clinical validation, CDRscan is expected to allow selection of the most effective anticancer drugs for the genomic profile of the individual patient.

Summary Vertebrate ancestors had only cone-like photoreceptors. The duplex retina evolved in jawless vertebrates with the advent of highly photosensitive rod-like photoreceptors. Despite cones being the arbiters of high-resolution color vision, rods emerged as the dominant photoreceptor in mammals during a nocturnal phase early in their evolution. We investigated the evolutionary and developmental origins of rods in two divergent vertebrate retinae. In mice, we discovered genetic and epigenetic vestiges of short wavelength cones in developing rods and cell lineage tracing validated the genesis of rods from S-cones. Curiously, rods did not derive from S-cones in zebrafish. Our study illuminates several questions regarding the evolution of duplex retina and supports the hypothesis that, in mammals, the S-cone lineage was recruited via the Maf-family transcription factor NRL to augment rod photoreceptors. We propose that this developmental mechanism allowed the adaptive exploitation of scotopic niches during the nocturnal bottleneck early in mammalian evolution.

SUMMARY Gene regulatory networks (GRNs) guiding differentiation of cell types and cell assemblies in the nervous system are poorly understood because of inherent complexities and interdependence of signaling pathways. Here, we report transcriptome dynamics of differentiating rod photoreceptors in the mammalian retina. As the transcription factor NRL determines rod cell fate, we performed expression profiling of developing NRL-positive (rods) and NRL-negative (S-cone like) mouse photoreceptors. We identified a large-scale, sharp transition in the transcriptome landscape between postnatal day 6 and 10 concordant with rod morphogenesis. Rod-specific temporal DNA methylation corroborated gene expression patterns. De novo assembly and alternative splicing analyses revealed previously un-annotated rod-enriched transcripts and the role of NRL in transcript maturation. Furthermore, we defined the relationship of NRL with other transcriptional regulators and downstream cognate effectors. Our studies provide the framework for comprehensive system-level analysis of the GRN underlying the development of a single sensory neuron, the rod photoreceptor.