TY - JOUR
T1 - De novo and somatic structural variant discovery with SVision-pro
AU - Wang, Songbo
AU - Lin, Jiadong
AU - Jia, Peng
AU - Xu, Tun
AU - Li, Xiujuan
AU - Liu, Yuezhuangnan
AU - Xu, Dan
AU - Bush, Stephen J.
AU - Meng, Deyu
AU - Ye, Kai
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2025/2
Y1 - 2025/2
N2 - Long-read-based de novo and somatic structural variant (SV) discovery remains challenging, necessitating genomic comparison between samples. We developed SVision-pro, a neural-network-based instance segmentation framework that represents genome-to-genome-level sequencing differences visually and discovers SV comparatively between genomes without any prerequisite for inference models. SVision-pro outperforms state-of-the-art approaches, in particular, the resolving of complex SVs is improved, with low Mendelian error rates, high sensitivity of low-frequency SVs and reduced false-positive rates compared with SV merging approaches.
AB - Long-read-based de novo and somatic structural variant (SV) discovery remains challenging, necessitating genomic comparison between samples. We developed SVision-pro, a neural-network-based instance segmentation framework that represents genome-to-genome-level sequencing differences visually and discovers SV comparatively between genomes without any prerequisite for inference models. SVision-pro outperforms state-of-the-art approaches, in particular, the resolving of complex SVs is improved, with low Mendelian error rates, high sensitivity of low-frequency SVs and reduced false-positive rates compared with SV merging approaches.
UR - https://www.scopus.com/pages/publications/85188436352
U2 - 10.1038/s41587-024-02190-7
DO - 10.1038/s41587-024-02190-7
M3 - 文章
C2 - 38519720
AN - SCOPUS:85188436352
SN - 1087-0156
VL - 43
SP - 181
EP - 185
JO - Nature Biotechnology
JF - Nature Biotechnology
IS - 2
M1 - 189
ER -