InMeRF: prediction of pathogenicity of missense variants by individual modeling for each amino acid substitution

Jun-Ichi Takeda; Kentaro Nanatsue; Ryosuke Yamagishi; Mikako Ito; Nobuhiko Haga; Hiromi Hirata; Tomoo Ogi; Kinji Ohno

doi:10.1093/nargab/lqaa038

InMeRF: prediction of pathogenicity of missense variants by individual modeling for each amino acid substitution

NAR Genom Bioinform. 2020 May 26;2(2):lqaa038. doi: 10.1093/nargab/lqaa038. eCollection 2020 Jun.

Authors

Jun-Ichi Takeda¹, Kentaro Nanatsue¹, Ryosuke Yamagishi¹, Mikako Ito¹, Nobuhiko Haga², Hiromi Hirata³, Tomoo Ogi⁴, Kinji Ohno¹

Affiliations

¹ Division of Neurogenetics, Center for Neurological Diseases and Cancer, Nagoya University Graduate School of Medicine, 65 Tsurumai, Showa-ku, Nagoya 466-8550, Japan.
² Department of Rehabilitation Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, Japan.
³ Department of Chemistry and Biological Science, College of Science and Engineering, Aoyama Gakuin University, 5-10-1 Fuchinobe, Chuo-ku, Sagamihara 252-5258, Japan.
⁴ Department of Genetics, Research Institute of Environmental Medicine (RIeM), Nagoya University, Furo, Chikusa-ku, Nagoya 464-8601, Japan.

Abstract

In predicting the pathogenicity of a nonsynonymous single-nucleotide variant (nsSNV), a radical change in amino acid properties is prone to be classified as being pathogenic. However, not all such nsSNVs are associated with human diseases. We generated random forest (RF) models individually for each amino acid substitution to differentiate pathogenic nsSNVs in the Human Gene Mutation Database and common nsSNVs in dbSNP. We named a set of our models 'Individual Meta RF' (InMeRF). Ten-fold cross-validation of InMeRF showed that the areas under the curves (AUCs) of receiver operating characteristic (ROC) and precision-recall curves were on average 0.941 and 0.957, respectively. To compare InMeRF with seven other tools, the eight tools were generated using the same training dataset, and were compared using the same three testing datasets. ROC-AUCs of InMeRF were ranked first in the eight tools. We applied InMeRF to 155 pathogenic and 125 common nsSNVs in seven major genes causing congenital myasthenic syndromes, as well as in VANGL1 causing spina bifida, and found that the sensitivity and specificity of InMeRF were 0.942 and 0.848, respectively. We made the InMeRF web service, and also made genome-wide InMeRF scores available online (https://www.med.nagoya-u.ac.jp/neurogenetics/InMeRF/).