(305g) High-Throughput Molecular Simulations and Experiments for Machine Learning Guided Protein Engineering (Invited Speaker) | AIChE

(305g) High-Throughput Molecular Simulations and Experiments for Machine Learning Guided Protein Engineering (Invited Speaker)

Authors 

Shukla, D. - Presenter, University of Illinois At Urbana-Champaign
Deep mutational scans is one of the approaches that could provide such a detailed map of protein-protein interactions. However, this technique suffers from several issues such as experimental noise, expensive experimental protocol and lack of techniques that could provide second or higher-order mutation effects. In this talk, we employ a recently developed platform, TLmutation that could enable rapid investigation of sequence-structure-function relationship of proteins. In particular, we employ a transfer learning approach to generate high-fidelity scans from noisy experimental data, transfer the knowledge from single point mutation data to generate higher- order mutational scans from the single amino-acid substitution data. In this talk, we investigate two systems related to neurotransmitter transport in human brain and the binding between SARS-CoV-2 viral spike protein S and human ACE2 receptor. AI-guided deep mutagenesis of human serotonin transporter (SERT) is used to determine the effects of nearly all amino acid substitutions on human SERT surface expression and transport of the fluorescent substrate analogue APP+. We identified hundreds of gain-of-function mutations were discovered that richly inform molecular mechanism and provided insight into conformational changes that limit transport kinetics. We also demonstrate how Soluble ACE2 variants identified using our approach inhibit entry of both SARS and SARS-2 coronaviruses by acting as a decoy for S binding sites, and is a candidate for therapeutic and prophylactic development.