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 CAGI (Critical Assessment of Genome Interpretation), 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 fashion. Compared to multi-class logistic regression, a representative multi-class classifier, our kernelized WSR improves the performance for the ENIGMA Challenge set from 0.72 to 0.97 in binary AUC (Area Under the receiver operating characteristic Curve) and from 0.64 to 0.80 in ordinal multi-class 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 C44F and C47Y, protein-binding disruption for M18T, and structure destabilization for S1715N.
Predicting venous thromboembolism risk from exomes in the Critical Assessment of Genome Interpretation (CAGI) challenges