Predicting Pathogenicity: Benchmarking SIFT, REVEL and AlphaMissense on ClinVar Missense Variants
Abstract
This paper compared SIFT, REVEL, and AlphaMissense on 5,000 ClinVar missense variants: an original sample of 1,000 and 4,000 additional variants. All variants followed the same fixed transcript rule. The original sample yielded 752 complete cases and the additional sample 3,018. In the additional cases, ROC-AUC was 0.9035 for SIFT, 0.9794 for REVEL, and 0.9662 for AlphaMissense. The REVEL–AlphaMissense difference was small but clear at 0.0132 (95% paired bootstrap interval 0.0081–0.0187). Among 983 additional cases absent from a December 2023 ClinVar snapshot, the difference narrowed to 0.0045 (−0.0024 to 0.0115). Among selected-transcript missense variants in the expanded sample (n = 4,591), coverage was 97.84% for SIFT, 84.49% for REVEL, and 98.24% for AlphaMissense. A transcript audit found another missense transcript with a REVEL score for 109 of 155 original missing-score records. AlphaMissense placed 42 original complete cases in its ambiguous range. Both newer tools discriminated better than SIFT. REVEL held a slight advantage in the additional sample, although it is not shown in the historical snapshot subset. The results support computational scores for variant prioritization. Clinical interpretation still needs calibrated evidence thresholds and other patient-level evidence.
Downloads
References
Bergquist, T., Stenton, S. L., Nadeau, E. A. W., et al. (2025). Calibration of additional computational tools expands ClinGen recommendation options for variant classification with PP3/BP4 criteria. Genetics in Medicine, 27, 101402. https://doi.org/10.1016/j.gim.2025.101402
Cheng, J., Novati, G., Pan, J., et al. (2023). Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science, 381, eadg7492. https://doi.org/10.1126/science.adg7492
Ensembl (2026a). POST vep species region. REST API documentation, Accessed 13 September 2026. https://rest.ensembl.org/documentation/info/vep_region_post
Ensembl (2026b). AlphaMissense VEP plugin release 116. Official plugin documentation and source, Accessed 13 September 2026. https://github.com/Ensembl/VEP_plugins/blob/release/116/AlphaMissense.pm
Ensembl (2026c). REVEL VEP plugin release 116. Official source code, Accessed 13 September 2026. https://github.com/Ensembl/VEP_plugins/blob/release/116/REVEL.pm
Grimm, D. G., Azencott, C. A., Aicheler, F., et al. (2015). The evaluation of tools used to predict the impact of missense variants is hindered by two types of circularity. Human Mutation, 36, 513–523. https://doi.org/10.1002/humu.22768
Ioannidis, N. M., Rothstein, J. H., Pejaver, V., et al. (2016). REVEL: an ensemble method for predicting the pathogenicity of rare missense variants. American Journal of Human Genetics, 99, 877–885. https://doi.org/10.1016/j.ajhg.2016.08.016
Landrum, M. J., Chitipiralla, S., Kaur, K., et al. (2025). ClinVar: updates to support classifications of both germline and somatic variants. Nucleic Acids Research, 53, D1313–D1321. https://doi.org/10.1093/nar/gkae1090
Livesey, B. J., & Marsh, J. A. (2025). Variant effect predictor correlation with functional assays is reflective of clinical classification performance. Genome Biology, 26, 104. https://doi.org/10.1186/s13059-025-03575-w
McLaren, W., Gil, L., Hunt, S. E., et al. (2016). The Ensembl Variant Effect Predictor. Genome Biology, 17, 122. https://doi.org/10.1186/s13059-016-0974-4
Morales, J., Pujar, S., Loveland, J. E., et al. (2022). A joint NCBI and EMBL-EBI transcript set for clinical genomics and research. Nature, 604, 310–315. https://doi.org/10.1038/s41586-022-04558-8
National Center for Biotechnology Information (2023). ClinVar GRCh38 archived VCF dated 26 December 2023. Official data archive, Accessed 13 September 2026. https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/archive_2.0/2023/clinvar_20231226.vcf.gz
National Center for Biotechnology Information (2026). Review status in ClinVar. Official documentation, Accessed 13 September 2026. https://www.ncbi.nlm.nih.gov/clinvar/docs/review_status/
Ng, P. C., & Henikoff, S. (2003). SIFT: predicting amino acid changes that affect protein function. Nucleic Acids Research, 31, 3812–3814. https://doi.org/10.1093/nar/gkg509
Pejaver, V., Byrne, A. B., Feng, B. J., et al. (2022). Calibration of computational tools for missense variant pathogenicity classification and ClinGen recommendations for PP3/BP4 criteria. American Journal of Human Genetics, 109, 2163–2177. https://doi.org/10.1016/j.ajhg.2022.10.013
Richards, S., Aziz, N., Bale, S., et al. (2015). Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genetics in Medicine, 17, 405–424. https://doi.org/10.1038/gim.2015.30
Rothstein, J., & Sieh, W. (2021). REVEL Rare Exome Variant Ensemble Learner Scores version 1.3. Zenodo, 2021. https://doi.org/10.5281/zenodo.7072866
SIFT developers (2026). SIFT Help. Official documentation, Accessed 13 September 2026. https://sift.bii.a-star.edu.sg/www/SIFT_help.html
Copyright (c) 2026 Sajjaad Hassan Kassim, Zhang Enshuo
This work is licensed under a Creative Commons Attribution 4.0 International License.
