Cue: a deep-learning framework for structural variant discovery and genotyping.
Cue: a deep-learning framework for structural variant discovery and genotyping.
复制标题
DOI:
10.1038/s41592-023-01799-x
复制
发表时间:
2023-04
期刊:
影响因子:
48
通讯作者:
Maheshwari, Anant
中科院分区:
文献类型:
--
作者:
Popic, Victoria;Rohlicek, Chris;Cunial, Fabio;Hajirasouliha, Iman;Meleshko, Dmitry;Garimella, Kiran;Maheshwari, Anant
Structural variants (SV) are a major driver of genetic diversity and disease in the human genome and their discovery is imperative to advances in precision medicine. Existing SV callers rely on hand-engineered features and heuristics to model SVs, which cannot scale to the vast diversity of SVs nor fully harness the information available in sequencing datasets. Here we propose an extensible deep learning framework, Cue, to call and genotype SVs, which can learn complex SV abstractions directly from the data. At a high level, Cue converts alignments to images that encode SV-informative signals and uses a stacked hourglass convolutional neural network to predict the type, genotype, and genomic locus of the SVs captured in each image. We show that Cue outperforms the state of the art in the detection of several classes of SVs on synthetic and real short-read data and that it can be easily extended to other sequencing platforms while achieving competitive performance.
登录
查看更多内容
影响因子:
7
作者:
Huddleston J;Chaisson MJP;Steinberg KM;Warren W;Hoekzema K;Gordon D;Graves-Lindsay TA;Munson KM;Kronenberg ZN;Vives L;Peluso P;Boitano M;Chin CS;Korlach J;Wilson RK;Eichler EE
通讯作者:
Eichler EE
影响因子:
6
作者:
Luo R;Sedlazeck FJ;Darby CA;Kelly SM;Schatz MC
通讯作者:
Schatz MC
影响因子:
7
作者:
Marks, Patrick;Garcia, Sarah;Church, Deanna M.
通讯作者:
Church, Deanna M.
影响因子:
46.9
作者:
Poplin, Ryan;Chang, Pi-Chuan;DePristo, Mark A.
通讯作者:
DePristo, Mark A.
影响因子:
9.5
作者:
Liu, Yongzhuang;Huang, Yalin;Wang, Yadong
通讯作者:
Wang, Yadong