Towards mechanistic models of mutational effects: Deep learning on Alzheimer?s A? peptide

Deep Mutational Scanning (DMS) has enabled multiplexed measurement of mutational effects on protein properties, including kinematics and self-organization, with unprecedented resolution. However, potential bottlenecks of DMS characterization include experimental design, data quality, and depth of mutational coverage. Here, we apply deep learning to comprehensively model the mutational effect of the Alzheimer's Disease associated peptide A beta 42 on aggregation-related biochemical traits from DMS measurements. Among tested neural network architectures, Convolutional Neural Networks and Recurrent Neural Networks are found to be the most cost-effective models with high performance even under insufficiently-sampled DMS studies. While sequence features are essential for satisfactory prediction from neural networks, geometric -structural features further enhance the prediction performance. Notably, we demonstrate how mechanistic insights into phenotype may be extracted from the neural networks themselves suitably designed. This methodological benefit is particularly relevant for biochemical systems displaying a strong coupling be-tween structure and phenotype such as the conformation of A beta 42 aggregate and nucleation, as shown here using a Graph Convolutional Neural Network (GCN) developed from the protein atomic structure input. In addition to accurate imputation of missing values (which here ranged up to 55% of all phenotype values at key residues), the mutationally-defined nucleation phenotype generated from a GCN shows improved re-solution for identifying known disease-causing mutations relative to the original DMS phenotype. Our study suggests that neural network derived sequence-phenotype mapping can be exploited not only to provide direct support for protein engineering or genome editing but also to facilitate therapeutic design with the gained perspectives from biological modeling.(c) 2023 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. This is an open access article under the CC BY-NC-ND license (http://creative-commons.org/licenses/by-nc-nd/4.0/).

Automated summary

Deep Mutational Scanning (DMS) allows for the measurement of mutational effects on protein properties with high resolution. In this study, deep learning is applied to model the mutational effects of the Alzheimer's Disease associated peptide A beta 42 on aggregation-related biochemical traits. Neural network architectures such as Convolutional Neural Networks and Recurrent Neural Networks are found to be effective models, even with limited data. The study demonstrates the potential of neural network derived sequence-phenotype mapping in protein engineering and therapeutic design.