PARAS: High-Accuracy Machine Learning of Substrate Specificities in Nonribosomal Peptide Synthetases

Nonribosomal peptides are diverse natural products with important applications in medicine and agriculture. Bacterial and fungal genomes contain thousands of nonribosomal peptide biosynthetic gene clusters (BGCs) of unknown function, providing a promising resource for peptide discovery. Core structural features of such peptides can be inferred by predicting the substrate(s) of adenylation (A) domains in nonribosomal peptide synthetases (NRPSs). However, existing approaches to A domain prediction rely on limited data sets and often struggle with domains selecting large substrates and domains from underrepresented taxa. Here, we systematically curate and computationally analyze 3653 A domains and present two high-accuracy specificity predictors, PARAS and PARASECT. A type of A domain with unusually high l-tryptophan specificity was identified through the application of PARAS. Cloning and expression of the biosynthetic gene cluster encoding the NRPS showed that it directs the biosynthesis of tryptopeptin-related metabolites in Streptomyces species. Together, these technologies will accelerate the characterization of novel NRPSs and their metabolic products. PARAS and PARASECT are available at https://paras.bioinformatics.nl.