MutationTaster2021

Abstract

Here we present an update to MutationTaster, our DNA variant effect prediction tool. The new version uses a different prediction model and attains higher accuracy than its predecessor, especially for rare benign variants. In addition, we have integrated many sources of data that only became available after the last release (such as gnomAD and ExAC pLI scores) and changed the splice site prediction model. To more easily assess the relevance of detected known disease mutations to the clinical phenotype of the patient, MutationTaster now provides information on the diseases they cause. Further changes represent a major overhaul of the interfaces to increase user-friendliness whilst many changes under the hood have been designed to accelerate the processing of uploaded VCF files. We also offer an API for the rapid automated query of smaller numbers of variants from within other software. MutationTaster2021 integrates our disease mutation search engine, MutationDistiller, to prioritise variants from VCF files using the patient's clinical phenotype. The novel version is available at https://www.genecascade.org/MutationTaster2021/. This website is free and open to all users and there is no login requirement.

Graphical Abstract

Identification of disease-causing variants with MutationTaster2021.

Figure 1.

Balanced accuracy of MutationTaster2 and MutationTaster2021. Figure 1 shows the gains in the balanced accuracy of MutationTaster2021 (green) compared to MutationTaster2 (blue) for the five different prediction models (simple_aae: variants leading to single amino acid substitutions; complex_aae: variants changing more than one amino acid; 3utr: variants in the 3′ UTR; 5utr: variants in the 5′ UTR; without_aae: all other variants, i.e. non-coding variants). The models for UTR variants were not available in MutationTaster2. Please note that the accuracy of MutationTaster2 was validated in five-fold cross-validations whereas the accuracy of MutationTaster2021 was measured on data not used for training. A thorough description and detailed statistics can be found in the Supplement.