PT  - JOURNAL ARTICLE
AU  - Namrata Anand
AU  - Raphael R. Eguchi
AU  - Alexander Derry
AU  - Russ B. Altman
AU  - Po-Ssu Huang
TI  - Protein Sequence Design with a Learned Potential
AID  - 10.1101/2020.01.06.895466
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.01.06.895466
4099  - http://biorxiv.org/content/early/2020/01/07/2020.01.06.895466.short
4100  - http://biorxiv.org/content/early/2020/01/07/2020.01.06.895466.full
AB  - The primary challenge of fixed-backbone protein sequence design is to find a distribution of sequences that fold to the backbone of interest. In practice, state-of-the-art protocols often find viable but highly convergent solutions. In this study, we propose a novel method for fixed-backbone protein sequence design using a learned deep neural network potential. We train a convolutional neural network (CNN) to predict a distribution over amino acids at each residue position conditioned on the local structural environment around the residues. Our method for sequence design involves iteratively sampling from this conditional distribution. We demonstrate that this approach is able to produce feasible, novel designs with quality on par with the state-of-the-art, while achieving greater design diversity. In terms of generalizability, our method produces plausible and variable designs for a de novo TIM-barrel structure, showcasing its practical utility in design applications for which there are no known native structures.