Predicting Severity of Disease-Causing Variants

Abstract

Most diseases, including those of genetic origin, express a continuum of severity. Clinical interventions for numerous diseases are based on the severity of the phenotype. Predicting severity due to genetic variants could facilitate diagnosis and choice of therapy. Although computational predictions have been used as evidence for classifying the disease relevance of genetic variants, special tools for predicting disease severity in large scale are missing. Here, we manually curated a dataset containing variants leading to severe and less severe phenotypes and studied the abilities of variation impact predictors to distinguish between them. We found that these tools cannot separate the two groups of variants. Then, we developed a novel machine-learning-based method, PON-PS (http://structure.bmc.lu.se/PON-PS), for the classification of amino acid substitutions associated with benign, severe, and less severe phenotypes. We tested the method using an independent test dataset and variants in four additional proteins. For distinguishing severe and nonsevere variants, PON-PS showed an accuracy of 61% in the test dataset, which is higher than for existing tolerance prediction methods. PON-PS is the first generic tool developed for this task. The tool can be used together with other evidence for improving diagnosis and prognosis and for prioritization of preventive interventions, clinical monitoring, and molecular tests.

Large differences in proportions of harmful and benign amino acid substitutions between proteins and diseases

“…Many of these variants can have a variable phenotype depending on the other factors including severity, extent, and modulation in case of diseases (Vihinen, ). As the first application of the pathogenicity model, we recently introduced a method for predicting disease severity of variants (Niroula & Vihinen, ).…”

Variation Benchmark Datasets: Update, Criteria, Quality and Applications

“…It is important to note that diseases are not binary states (benign/disease) instead there is a continuum and certain disease state can appear due to numerous different combinations of disease components, see the pathogenicity model [35]. This aspect has not been taken into account in benchmark datasets apart from training data for PON-PS [36] and clinical data for cystic fibrosis [37].…”

“…One dataset contains information for disease phenotype, whether there is mild/moderate or severe disease due to substitutions. This dataset was used to train disease severity predictor called PON-PS [36].…”

PON‐P and PON‐P2 predictor performance in CAGI challenges: Lessons learned

“…Although many variants in several genes/proteins and diseases have been associated with certain phenotypic severity, extensive classification is available only for a few of them. Recently, we collected variants causing mild, moderate, or severe disease phenotypes from 91 proteins and developed a tool, PON‐PS, for predicting the severity of disease‐causing AASs (Niroula & Vihinen, ). As the disease severity is influenced by several factors, gene/protein‐ or disease‐specific predictors could provide useful information.…”