Genome-wide prediction of pathogenic gain- and loss-of-function variants from ensemble learning of a diverse feature set

被引:9
作者
Stein, David [1 ,2 ,3 ]
Kars, Meltem Ece [2 ]
Wu, Yiming [2 ,4 ]
Bayrak, Cigdem Sevim [3 ]
Stenson, Peter D. [5 ]
Cooper, David N. [5 ]
Schlessinger, Avner [1 ,6 ]
Itan, Yuval [2 ,3 ]
机构
[1] Icahn Sch Med Mt Sinai, Dept Pharmacol Sci, New York, NY 10029 USA
[2] Icahn Sch Med Mt Sinai, Charles Bronfman Inst Personalized Med, New York, NY 10029 USA
[3] Icahn Sch Med Mt Sinai, Dept Genet & Genom Sci, New York, NY 10029 USA
[4] China West Normal Univ, Coll Life Sci, Nanchong 637009, Si Chuan, Peoples R China
[5] Cardiff Univ, Inst Med Genet, Sch Med, Cardiff CF14 4XN, Wales
[6] Icahn Sch Med Mt Sinai, Dept Artificial Intelligence & Human Hlth, New York, NY 10029 USA
关键词
Gain-of-function; Loss-of-function; Protein function; Variant functional impact; Pathogenicity prediction; Precision medicine; Genomic medicine; Phenome-wide association studies; Natural language processing; Machine learning; PROTEIN-STRUCTURE; MUTATION; DATABASE; FRAMEWORK; ASSOCIATION; ELEMENTS; DISEASE; IMPACT;
D O I
10.1186/s13073-023-01261-9
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
Gain-of-function (GOF) variants give rise to increased/novel protein functions whereas loss-of-function (LOF) variants lead to diminished protein function. Experimental approaches for identifying GOF and LOF are generally slow and costly, whilst available computational methods have not been optimized to discriminate between GOF and LOF variants. We have developed LoGoFunc, a machine learning method for predicting pathogenic GOF, pathogenic LOF, and neutral genetic variants, trained on a broad range of gene-, protein-, and variant-level features describing diverse biological characteristics. LoGoFunc outperforms other tools trained solely to predict pathogenicity for identifying pathogenic GOF and LOF variants and is available at https://itanlab.shinyapps.io/goflof/.
引用
收藏
页数:19
相关论文
empty
未找到相关数据