PhenoSV: interpretable phenotype-aware model for the prioritization of genes affected by structural variants.
PhenoSV: interpretable phenotype-aware model for the prioritization of genes affected by structural variants.
复制标题
DOI：
10.1038/s41467-023-43651-y
复制
发表时间：
2023-11-28
影响因子：
16.6
通讯作者：
Wang, Kai
中科院分区：
文献类型：
--
作者：
Xu, Zhuoran;Li, Quan;Marchionni, Luigi;Wang, Kai
结构变异（SV）代表与表型多样性和疾病易感性相关的遗传变异的主要来源。虽然长读长测序可以发现每个人类基因组超过 20,000 个 SV，但解释它们的功能后果仍然具有挑战性。现有的识别疾病相关 SV 的方法仅关注删除/重复，无法优先考虑受 SV 影响的单个基因，尤其是非编码 SV。在这里，我们介绍 PhenoSV，一种表型感知机器学习模型，可以解释所有主要类型的 SV 和受影响的基因。 PhenoSV 对具有不同基因组特征的 SV 进行分段和注释，并采用基于 Transformer 的架构来预测它们在多实例学习框架下的影响。有了表型信息，PhenoSV 进一步利用基因-表型关联来优先考虑表型相关的 SV。对涵盖所有 SV 类型的广泛人类 SV 数据集的评估表明，PhenoSV 比竞争方法具有优越的性能。在疾病中的应用表明 PhenoSV 可以从 SV 中确定与疾病相关的基因。 PhenoSV 的 Web 服务器和命令行工具可从 https://phenosv.wglab.org 获取。在这里，作者提出了 PhenoSV，这是一种表型感知机器学习模型，用于对各种类型的结构变异 (SV) 以及 SV 内部或外部的基因进行功能解释，从而促进从编码和非编码 SV 中提取生物学见解。
Structural variants (SVs) represent a major source of genetic variation associated with phenotypic diversity and disease susceptibility. While long-read sequencing can discover over 20,000 SVs per human genome, interpreting their functional consequences remains challenging. Existing methods for identifying disease-related SVs focus on deletion/duplication only and cannot prioritize individual genes affected by SVs, especially for noncoding SVs. Here, we introduce PhenoSV, a phenotype-aware machine-learning model that interprets all major types of SVs and genes affected. PhenoSV segments and annotates SVs with diverse genomic features and employs a transformer-based architecture to predict their impacts under a multiple-instance learning framework. With phenotype information, PhenoSV further utilizes gene-phenotype associations to prioritize phenotype-related SVs. Evaluation on extensive human SV datasets covering all SV types demonstrates PhenoSV’s superior performance over competing methods. Applications in diseases suggest that PhenoSV can determine disease-related genes from SVs. A web server and a command-line tool for PhenoSV are available at https://phenosv.wglab.org. Here, authors present PhenoSV, a phenotype-aware machine-learning model for the functional interpretation of various types of structural variants (SVs) and genes within or outside SVs, facilitating the extraction of biological insights from coding and noncoding SVs.
登录
查看更多内容
影响因子：
14.9
作者：
Geoffroy V;Guignard T;Kress A;Gaillard JB;Solli-Nowlan T;Schalk A;Gatinois V;Dollfus H;Scheidecker S;Muller J
通讯作者：
Muller J
影响因子：
64.8
作者：
Boix CA;James BT;Park YP;Meuleman W;Kellis M
通讯作者：
Kellis M
影响因子：
56.9
作者：
Gonzalez, E;Kulkarni, H;Ahuja, SK
通讯作者：
Ahuja, SK
影响因子：
64.8
作者：
通讯作者：
--
影响因子：
64.5
作者：
Collins, Ryan L.;Glessner, Joseph T.;Porcu, Eleonora;Lepamets, Maarja;Brandon, Rhonda;Lauricella, Christopher;Han, Lide;Morley, Theodore;Niestroj, Lisa-Marie;Ulirsch, Jacob;Everett, Selin;Howrigan, Daniel P.;Boone, Philip M.;Fu, Jack;Karczewski, Konrad J.;Kellaris, Georgios;Lowther, Chelsea;Lucente, Diane;Mohajeri, Kiana;Noukas, Margit;Nuttle, Xander;Samocha, Kaitlin E.;Trinh, Mi;Ullah, Farid;Vosa, Urmo;Hurles, Matthew E.;Aradhya, Swaroop;Davis, Erica E.;Finucane, Hilary;Gusella, James F.;Janze, Aura;Katsanis, Nicholas;Matyakhina, Ludmila;Neale, Benjamin M.;Sanders, David;Warren, Stephanie;Hodge, Jennelle C.;Lal, Dennis;Ruderfer, Douglas M.;Meck, Jeanne;Magi, Reedik;Esko, Tonu;Reymond, Alexandre;Kutalik, Zoltan;Hakonarson, Hakon;Sunyaev, Shamil;Brand, Harrison;Talkowski, Michael E.
通讯作者：
Talkowski, Michael E.