Motivation Improvements in next-generation sequencing have enabled genome-based diagnosis for patients with genetic diseases. However, accurate interpretation of human variants requires knowledge from a number of clinical cases. Additionally, manual analysis of each variant detected in a patient's genome requires enormous time and effort. To reduce the cost of diagnosis, various computational tools have been developed to predict the pathogenicity of human variants, but the shortage and bias of available clinical data can lead to overfitting of algorithms. Results We developed a pathogenicity predictor, 3Cnet, that uses recurrent neural networks to analyse the amino acid context of human variants. As 3Cnet is trained on simulated variants reflecting evolutionary conservation and clinical data, it can find disease-causing variants in patient genomes with 2.2 times greater sensitivity than currently available tools, more effectively discovering pathogenic variants and thereby improving diagnosis rates. Availability Codes (https://github.com/KyoungYeulLee/3Cnet/) and data (https://zenodo.org/record/4716879#.YIO-xqkzZH1) are freely available to non-commercial users. Supplementary information Supplementary data are available at Bioinformatics online.

In the process of finding the causative variant of rare diseases (RD), accurate assessment and prioritization of genetic variants is essential. Although quality control (QC) of genetic variants is strictly performed, the presence of artefactual variants in the remaining set of variants can deteriorate the process. Variant QC and prioritization have been treated as separate processes, leading to limited efficiency and risk of misdiagnosis. We developed a disease-causing variant recommendation system that integrates quality control into variant prioritization by adjusting scores for artefactual variants. We confirmed that the QC-related features of the variants contribute to a significant performance improvement. For genomic data from 2,878 patients with rare disorders, the recall rate of finding causative variants was 0.961 for the top 5 ranked variants. We also found that our system recognized the anomaly of QC-related features, so that the scores of artifactual variants to be disease-causing were assessed relatively low. Integration of variant QC and prioritization help reduce the risk of misdiagnosis based on artefactual variants and increase the effectiveness of clinical genome interpretation.