PT  - JOURNAL ARTICLE
AU  - Yu Li
AU  - Siyuan Chen
AU  - Trisevgeni Rapakoulia
AU  - Hiroyuki Kuwahara
AU  - Kevin Y. Yip
AU  - Xin Gao
TI  - Deep learning identifies and quantifies recombination hotspot determinants
AID  - 10.1101/2021.07.29.454133
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.07.29.454133
4099  - http://biorxiv.org/content/early/2021/07/29/2021.07.29.454133.short
4100  - http://biorxiv.org/content/early/2021/07/29/2021.07.29.454133.full
AB  - 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 to the hotspots, their contributions to the recombination hotspots have not been quantified, and other determinants are yet to be elucidated. Here, we develop a computational method, RHSNet, based on deep learning and signal processing, to identify and quantify the hotspot determinants in a purely data-driven manner, utilizing datasets from various studies, populations, sexes, and species. In addition to being able to identify hotspot regions and the well-known determinants accurately, RHSNet is sensitive to the difference between different PRDM9 alleles and different sexes, and can generalize to PRDM9-lacking species. The cross-sex, cross-population, and cross-species studies suggest that the proposed method has the potential to identify and quantify the evolutionary determinant motifs.Teaser RHSNet can accurately identify and quantify recombination hotspot determinants across different studies, sexes, populations, and species.Competing Interest StatementThe authors have declared no competing interest.