MAVE-NN: learning genotype-phenotype maps from multiplex assays of variant effect

Abstract Multiplex assays of variant effect (MAVEs) are a family of methods that includes deep mutational scanning (DMS) experiments on proteins and massively parallel reporter assays (MPRAs) on gene regulatory sequences. However, a general strategy for inferring quantitative models of genotype-phenotype (G-P) maps from MAVE data is lacking. Here we introduce MAVE-NN, a neural-network-based Python package that implements a broadly applicable information-theoretic framework for learning G-P maps—including biophysically interpretable models—from MAVE datasets. We demonstrate MAVE-NN in multiple biological contexts, and highlight the ability of our approach to deconvolve mutational effects from otherwise confounding experimental nonlinearities and noise.