2026-10-14T13:11:26Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33828294 2026-09-16T05:12:15Z category_4 category_146 category_13 category_21 category_24 category_734 category_931 category_134 category_135 portal_63 item_type_3 month_year_09_2026

KRstereo: Predicting β‑Hydroxy Stereochemistry in Polyketides Using Protein Language Models Hsin-Ying Tsai (331820) Wenqiang Xu (4668949) Wen Jun Xie (2151394) Yousong Ding (787304) Biochemistry Space Science Genetics Biotechnology Evolutionary Biology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Virology Computational Biology pkss ), ketoreductase natural product discovery making accurate prediction machine learning framework including cases misclassified biosynthetic gene clusters aware genome mining antismash enabled large scale stereochemical annotation pks assembly lines modular kr domains krstereo improves reconstruction krstereo achieved accuracies based methods rely kr stereochemistry important domains establish stereochemical function current methods based approaches streptomyces krs present krstereo polyketide synthases polyketide structures pks engineering often determined mibig 4 mibig 3 major class limited set hydroxyl groups facilitates stereochemistry existing rule across taxa Polyketides are a major class of bioactive natural products whose activities are often determined by the stereochemistry of β-hydroxyl groups. In type I polyketide synthases (PKSs), ketoreductase (KR) domains establish these stereocenters, making accurate prediction of KR stereochemistry important for natural product discovery and PKS engineering. Existing rule-based methods rely on a limited set of sequence motifs and often perform poorly across phylogenetically diverse taxa. Here, we present KRstereo, a machine learning framework that predicts KR stereochemistry directly from sequence. Analysis of β-modular KR domains from MIBiG 3.1 identified informative sequence features beyond canonical motifs, motivating the use of protein language model embeddings. KRstereo achieved accuracies of up to 95.7% across taxa and 93.0% for non-Streptomyces KRs, consistently outperforming existing rule-based approaches. Validation using newly characterized KR domains from MIBiG 4.0 confirmed strong generalizability, including cases misclassified by current methods. Application of KRstereo to 20,840 β-modular KR domains from antiSMASH enabled large-scale stereochemical annotation of previously uncharacterized PKS systems. By linking sequence to stereochemical function, KRstereo improves reconstruction of polyketide structures from biosynthetic gene clusters and facilitates stereochemistry-aware genome mining and engineering of PKS assembly lines. 2026-09-16T00:00:00Z Dataset Dataset 10.1021/acs.jcim.6c02706.s002 https://figshare.com/articles/dataset/KRstereo_Predicting_Hydroxy_Stereochemistry_in_Polyketides_Using_Protein_Language_Models/33828294 CC BY-NC 4.0