MAVE-NN: learning genotype-phenotype maps from multiplex assays of variant effect.
MAVE-NN: learning genotype-phenotype maps from multiplex assays of variant effect.
复制标题
DOI：
10.1186/s13059-022-02661-7
复制
发表时间：
2022-04-15
期刊：
影响因子：
12.3
通讯作者：
中科院分区：
文献类型：
--
作者：
变异效应多重检测（MAVE）是一系列方法，包括蛋白质的深度突变扫描实验和基因调控序列的大规模平行报告基因检测。尽管他们越来越受欢迎，从MAVE数据推断基因型-表型图的定量模型的一般策略是缺乏的。在这里，我们介绍MAVE-NN，一个基于神经网络的Python包，实现了一个广泛适用的信息理论框架，用于从MAVE数据集学习基因型-表型图，包括生物病理学可解释的模型。我们在多种生物背景下展示了MAVE-NN，并强调了我们的方法从其他混淆实验非线性和噪声中去卷积突变效应的能力。在线版本包含补充材料，可通过10.1186/s13059-022-02661-7获得。
Multiplex assays of variant effect (MAVEs) are a family of methods that includes deep mutational scanning experiments on proteins and massively parallel reporter assays on gene regulatory sequences. Despite their increasing popularity, a general strategy for inferring quantitative models of genotype-phenotype 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 genotype-phenotype 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. The online version contains supplementary material available at 10.1186/s13059-022-02661-7.