Jung-Eun Shin; Adam J. Riesselman; Aaron W. Kollasch; Conor McMahon; Elana P. Simon; Chris Sander; Aashish Manglik; Andrew C. Kruse; Debora S. Marks · 2021 · Nature Communications
Paper
Abstract The ability to design functional sequences and predict effects of variation is central to protein engineering and biotherapeutics. State-of-art computational methods rely on models that leverage evolutionary information but are inadequate for important applications where multiple sequence alignments are not robust. Such applications include the prediction of variant effects of indels, disordered proteins, and the design of proteins such as antibodies due to the highly variable complementarity determining regions. We introduce a deep generative model adapted from natural language processing for prediction and design of diverse functional sequences without the need for alignments. The model performs state-of-art prediction of missense and indel effects and we successfully design and test a diverse 10 5 -nanobody library that shows better expression than a 1000-fold larger synthetic library. Our results demonstrate the power of the alignment-free autoregressive model in generalizing to regions of sequence space traditionally considered beyond the reach of prediction and design.
Analysis
This paper introduces an alignment-free autoregressive generative model, adapted from natural language processing, for protein sequence design and variant effect prediction, demonstrating its effectiveness in creating functional nanobodies.
Discovery
Anastassia A. Vorobieva; Rituparna Samanta; Toon Van Thillo
Laxmikant Gadhe; Katerina Konstantoulea; Aneesh Mazumder; Jie Chen; Lukasz A. Joachimiak; Nikolas Louros
Shaotong Luo; Bo Zhou
Maximilian Brackmann; Sophie Reiners; Masja Hoogendoorn; Michel Moser
Hoda M. Hammad; Anna M. Duraj‐Thatte
Jakob Agamia; Martin Zacharias
Source record