Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations
By B. Livesey, Joseph A. Marsh. 2020
161 citations recorded by the source corpus.
To deal with the huge number of novel protein‐coding variants identified by genome and exome sequencing studies, many computational variant effect predictors (VEPs) have been developed. Such predictors are often trained and evaluated using different variant data sets, making a direct comparison between VEPs difficult. In this study, we use 31 previously published deep mutational scanning (DMS) experiments, which provide quantitative, independent phenotypic measurements for large numbers of single amino acid substitutions, in order to benchmark and compare 46 different VEPs. We also evaluate the ability of DMS measurements and VEPs to discriminate between pathogenic and benign missense variants. We find that DMS experiments tend to be superior to the top‐ranking predictors, demonstrating the tremendous potential of DMS for identifying novel human disease mutations. Among the VEPs, DeepSequence clearly stood out, showing both the strongest correlations with DMS data and having the best ability to predict pathogenic mutations, which is especially remarkable given that it is an unsupervised method. We further recommend SNAP2, DEOGEN2, SNPs&GO, SuSPect and REVEL based upon their performance in these analyses.
Subfields: Genetics, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Genetics
In Molecular Biology
- Debora Marks
- Christopher Sander
- Adam J. Riesselman
- Jung-Eun Shin
- A. Kruse
- Conor McMahon
- A. Manglik
- Elana Simon
Citations in the corpus
- Accurate proteome-wide missense variant effect prediction with AlphaMissense (2023, background): “2A;seesupplementarynote)( 11 , 17 , 29 ).”
- Protein design and variant prediction using autoregressive generative models (2021, methodology): “…only on evolutionary sequences are proving the most accurate for predicting the effect of mutations when compared to large data-sets of experimentally measured mutation effects 30,34 , and they avoid the risk of over fi tting that can occur as a result of circularity in supervised methods 68 .”
- Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning (2020, methodology): “In the case of the Brugada syndrome ion channel gene SCN5A the number of labels, 8, is too small to compute reliable AUCs, but these labels are perfectly separated by both EVE scores and experimental fitness metrics 15 (Supplementary Table 5”
- Efficient evolution of human antibodies from general protein language models (2023, unknown): “We then used experimental measurements from high-throughput scanning mutagenesis experiments 8,48 to validate the language-model-recommended predictions (notably, these measurements were not provided to the model).”