Machine learning in protein engineering

By Kevin Kaichuang Yang, Zachary Wu, Frances H. Arnold. 2018

33 citations recorded by the source corpus.

Machine learning-guided protein engineering is a new paradigm that enables the optimization of complex protein functions. Machine-learning methods use data to predict protein function without requiring a detailed model of the underlying physics or biological pathways. They accelerate protein engineering by learning from information contained in all measured variants and using it to select variants that are likely to be improved. In this review, we introduce the steps required to collect protein data, train machine-learning models, and use trained models to guide engineering. We make recommendations at each stage and look to future opportunities for machine learning to enable the discovery of new protein functions and uncover the relationship between protein sequence and function.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Evaluating Protein Transfer Learning with TAPE (2019, neutral): “Machine learning methods have already seen some success in related protein engineering tasks [44].”
Conditioning by adaptive sampling for robust design (2019, background): “allow for the possibility to improve such design cycles with computational approaches ( e. g., Schneider & Wrede (1994); Schneider et al. (1998); G´omez-Bombarelli et al. (2018); Killoran et al. (2017); Brookes & Listgarten (2018); Gupta & Zou (2019); Yang et al. (2018)).”
How to Hallucinate Functional Proteins (2019, result): “In a recent review, (21) postulate the possibility of a model similar to BioSeqVAE.”
Machine learning-assisted directed protein evolution with combinatorial libraries (2019, background): “Previous applications of machine learning in protein engineering have identified beneficial mutations (13) and optimal combinations of protein fragments (14) for increased enzyme activity and protein stability, as reviewed recently (15).”
Generative Models for Graph-Based Protein Design (2019, background): “Generative models for proteins A number of works have explored the use of generative models for protein engineering and design (Yang et al., 2018).”