Predicting pathogenicity of missense variants with weakly supervised regression. Issue 9 (7th August 2019)

• Record Type: Journal Article
• Authors: Cao, Yue; Sun, Yuanfei; Karimi, Mostafa; Chen, Haoran; Moronfoye, Oluwaseyi; Shen, Yang
• Editors: Moult, John; Brenner, Steven E.
• Other Names: Karchin Rachel guestEditor.; Pal Lipika R. specialEditor.
• Is Part Of: Human mutation. Volume 40:Issue 9(2019)
• Page Start: 1579
• Page End: 1592
• Publication Date: 2019-08-07
• Subjects: clinical significance -- genetic variation -- genome medicine -- machine learning -- model interpretability -- molecular mechanism -- weak supervision; Human chromosome abnormalities -- Periodicals; Mutation (Biology) -- Periodicals; 616.04205
• DOI: 10.1002/humu.23826
• Languages: English
• ISSNs: 1059-7794

Abstract

Abstract: Quickly growing genetic variation data of unknown clinical significance demand computational methods that can reliably predict clinical phenotypes and deeply unravel molecular mechanisms. On the platform enabled by the Critical Assessment of Genome Interpretation (CAGI), we develop a novel "weakly supervised" regression (WSR) model that not only predicts precise clinical significance (probability of pathogenicity) from inexact training annotations (class of pathogenicity) but also infers underlying molecular mechanisms in a variant‐specific manner. Compared to multiclass logistic regression, a representative multiclass classifier, our kernelized WSR improves the performance for the ENIGMA Challenge set from 0.72 to 0.97 in binary area under the receiver operating characteristic curve (AUC) and from 0.64 to 0.80 in ordinal multiclass AUC. WSR model interpretation and protein structural interpretation reach consensus in corroborating the most probable molecular mechanisms by which some pathogenic BRCA1 variants confer clinical significance, namely metal‐binding disruption for p.C44F and p.C47Y, protein‐binding disruption for p.M18T, and structure destabilization for p.S1715N. Abstract : Novel machine learning models predict the probability of pathogenicity for missense variants. They are further interpreted to identify the most contributing features (and the most probable molecular mechanisms) for each variant predicted to be pathogenic. Finally, protein structural modeling of such variations validate the hypothesized molecular mechanisms.