Predicting 3D Structures of Lasso Peptides

Lasso peptides (LPs), characterized by their entangled slipknot-like structures, are a large class of ribosomally synthesized and post-translationally modified peptides (RiPPs), with examples functioning as antibiotics, enzyme inhibitors, and molecular switches. Despite thousands of LP sequences predicted by bioinformatics, only around 50 distinct LPs have been structurally characterized in the past 30 years. Existing computational tools, such as AlphaFold2, AlphaFold3 and ESMfold, fail to accurately predict LP structures due to their irregular scaffold, featuring a lariat-like fold and the presence of an isopeptide bond. To address this challenge, we developed LassoPred, designed with a classifier to annotate the ring, loop, and tail of an LP sequence and a constructor to build a 3D structure. LassoPred achieves an average root mean square deviation of 3.4 Å for constructed LP structures, outperforming AlphaFold and ESM (~10 Å). Leveraging LassoPred, we predicted 3D structures for 3,131 unique LP core sequences, creating the largest in silico-predicted lasso peptide structure database to date. LassoPred is publicly available through a web interface (https://lassopred.accre.vanderbilt.edu/) and a command-line tool, supporting future structure-function relationship studies and aiding in the discovery of functional lasso peptides for chemical and biomedical applications.