학술논문
The landscape of tolerated genetic variation in humans and primates.
Document Type
Article
Author
Hong Gao; Hamp, Tobias; Ede, Jeffrey; Schraiber, Joshua G.; McRae, Jeremy; Singer-Berk, Moriel; Yanshen Yang; Dietrich, Anastasia S. D.; Fiziev, Petko P.; Kuderna, Lukas F. K.; Sundaram, Laksshman; Yibing Wu; Adhikari, Aashish; Field, Yair; Chen Chen; Batzoglou, Serafim; Aguet, Francois; Lemire, Gabrielle; Reimers, Rebecca; Balick, Daniel
Source
Subject
*HUMAN genetic variation
*DEEP learning
*PRIMATES
*MACHINE learning
*CAPUCHIN monkeys
*CONVOLUTIONAL neural networks
*AMINO acid sequence
*
*
*
*
*
*
Language
ISSN
0036-8075
Abstract
Common primate variants generated from 233 primate species (left) were validated as benign (98.7%) in the human ClinVar database. RESULTS: Following the strategy outlined above we obtained whole-genome sequencing data for 809 individuals from 233 primate species and cataloged 4.3 million common missense variants. By generating the most comprehensive primate sequencing dataset to date and pairing this resource with a deep learning architecture that leverages 3D protein structures, we were able to achieve meaningful improvements in variant effect prediction across multiple clinical benchmarks. [Extracted from the article]