Deep Learning Approach to Genomic Breakage Study from Primary Sequence

Abstract

Identifying the molecular mechanisms related to genomic breakage is an important goal of cancer mechanism studies. Among the diverse location of the breakpoints of structural variants, the fusion genes, which have the breakpoints in the gene bodies and typically identified from RNA-seq data, can provide a highlighted structural variant resource for studying the genomic breakages with expression and potential pathogenic impacts. In this study, we developed FusionAI which utilizes deep learning to predict gene fusion breakpoints based on primary sequences and let us identify fusion breakage code and genomic context. FusionAI leverages the known fusion breakpoints to provide a prediction model of the fusion genes from the primary genomic sequences via deep learning, thereby helping researchers a more accurate selection of fusion genes and better understand genomic breakage. HighlightsO_LIFusionAI, a 9-layer deep neural network, predicts fusion gene breakpoints from a DNA sequence C_LIO_LIFusonAI reduce the cost and effort for validating fusion genes by decreasing specificity C_LIO_LIHigh feature importance scored regions were apart 100nt on average from the exon junction breakpoints C_LIO_LIHigh feature importance scored regions overlapped with 44 different human genomic features C_LIO_LITranscription factor fusion genes are targeted by the GC-rich motif TFs C_LIO_LIFusionAI gives less scores to the non-disease derived breakpoints C_LI