Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks
This work addresses the challenge of directed evolution for biochemical laboratories and computer scientists by providing an affordable and accurate tool for mutational effect prediction, though it is incremental as it builds on existing graph-based methods.
The researchers tackled the problem of predicting mutational effects in proteins by introducing a lightweight graph neural network that efficiently analyzes protein microenvironments and recommends higher-order mutations, achieving near-perfect correlation with ground truth across 19 proteins in deep mutational scanning assays.
Directed evolution as a widely-used engineering strategy faces obstacles in finding desired mutants from the massive size of candidate modifications. While deep learning methods learn protein contexts to establish feasible searching space, many existing models are computationally demanding and fail to predict how specific mutational tests will affect a protein's sequence or function. This research introduces a lightweight graph representation learning scheme that efficiently analyzes the microenvironment of wild-type proteins and recommends practical higher-order mutations exclusive to the user-specified protein and function of interest. Our method enables continuous improvement of the inference model by limited computational resources and a few hundred mutational training samples, resulting in accurate prediction of variant effects that exhibit near-perfect correlation with the ground truth across deep mutational scanning assays of 19 proteins. With its affordability and applicability to both computer scientists and biochemical laboratories, our solution offers a wide range of benefits that make it an ideal choice for the community.