Quantitative missense variant effect prediction using large-scale mutagenesis data

By Vanessa E. Gray, Ronald J. Hause, Jens Luebeck, Jay Shendure, Douglas M. Fowler. 2017

204 citations recorded by the source corpus.

SUMMARY Large datasets describing the quantitative effects of mutations on protein function are becoming increasingly available. Here, we leverage these datasets to develop Envision, which predicts the magnitude of a missense variant’s molecular effect. Envision combines 21,026 variant effect measurements from nine large-scale experimental mutagenesis datasets, a hitherto untapped training resource, with a supervised, stochastic gradient boosting learning algorithm. Envision outperforms other missense variant effect predictors both on large-scale mutagenesis data and on an independent test dataset comprising 2,312 TP53 variants whose effects were measured using a low-throughput approach. This data set was never used for hyperparameter tuning or model training, and thus serves as an independent validation set. Envision prediction accuracy is also more consistent across amino acids than other predictors. Finally, we demonstrate that Envision’s performance improves as more large-scale mutagenesis data is incorporated. We precompute Envision predictions for every possible single amino acid variant in human, mouse, frog, zebrafish, fruit fly, worm and yeast proteomes (https://envision.gs.washington.edu/).

Subfields: Cancer Research, Genetics, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cancer Research

In Genetics

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Evolutionary context-integrated deep sequence modeling for protein engineering (2020, methodology): “We compared the two approaches on the Envision dataset [39] , composed of 12 DMS studies that generated fitness values of single amino acid variants of ten proteins (Supplementary Note ).”
Language models enable zero-shot prediction of the effects of mutations on protein function (2021, methodology): “Models have been designed specifically for proteins, using feature engineering such as Envision [38] and PolyPhen-2 [39], ensemble methods such as Revel [40], MPC [41], CADD [42], and M-CAP [43], language models such as UniRep [21, 16] and ESM [12], and other representation learning approaches [44, ”
Protein design and variant prediction using autoregressive generative models (2021, methodology): “…in this paper, we validated our model ﬁ rst on deep mutational scan data, with on-par performance with the best currently available model 29 – 31, 34, 77 , and demonstrated Due to their ﬂ exibility, deep autoregressive models could also open the door to new opportunities in biological…”
A saturation mutagenesis approach to understanding PTEN lipid phosphatase activity and genotype-phenotypes relationships (2018, result): “These findings are consistent with a recent meta-analysis of similar experiments.(73) We leveraged the correlation among amino acid substitutions, along with several other features, to generate a random forest regression model that could accurately predict the fitness scores of unseen mutations and ”
Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations (2020, unknown): “These are fully independent from any training and testing data used by the predictors (with one exception Gray et al , 2018).”
A structure-based deep learning framework for protein engineering (2019, background): “9-11 ).”