Deep learning identifies and quantifies recombination hotspot determinants

• DOI: 10.1093/bioinformatics/btac234
• Publication Date: 2022-04-12T13:27:51Z
• Authors: Yu Li; Siyuan Chen; Trisevgeni Rapako...; Hiroyuki Kuwahara; Kevin Y Yip; Xin Gao
• Keywords: Hotspot (geology); Sequence motif

Abstract Motivation Recombination is one of the essential genetic processes for sexually reproducing organisms, which can happen more frequently in some regions, called recombination hotspots. Although several factors, such as PRDM9 binding motifs, are known to be related hotspots, their contributions hotspots have not been quantified, and other determinants yet elucidated. Here, we propose a computational method, RHSNet, based on deep learning signal processing, identify quantify hotspot purely data-driven manner, utilizing datasets from various studies, populations, sexes species. Results RHSNet significantly outperform sequence-based methods multiple across different species, studies. In addition being able regions well-known accurately, importantly, that contribute formation relation between motif, histone modification GC content. Further cross-sex, cross-population cross-species studies suggest proposed method has generalization power potential evolutionary determinant motifs. Availability implementation https://github.com/frankchen121212/RHSNet. Supplementary information data available at Bioinformatics online.