Rational incorporation of any unnatural amino acid into proteins by machine learning on existing experimental proofs.

ABSTRACT: The unnatural amino acid (UAA) incorporation technique through genetic code expansion has been extensively used in protein engineering for the last two decades. Mutations into UAAs offer more dimensions to tune protein structures and functions. However, the huge library of optional UAAs and various circumstances of mutation sites on different proteins urge rational UAA incorporations guided by artificial intelligence. Here we collected existing experimental proofs of UAA-incorporated proteins in literature and established a database of known UAA substitution sites. By program designing and machine learning on the database, we showed that UAA incorporations into proteins are predictable by the observed evolutional, steric and physiochemical factors. Based on the predicted probability of suc

SUBMITTER: Zhang H 

PROVIDER: S-EPMC9472073 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature