Discovering type I cis-AT polyketides through computational mass spectrometry and genome mining with Seq2PKS

Type 1 polyketides are a major class of natural products used as antiviral, antibiotic, antifungal, antiparasitic, immunosuppressive, and antitumor drugs. Analysis of public microbial genomes leads to the discovery of over sixty thousand type 1 polyketide gene clusters. However, the molecular produc...

Full description

Saved in:
Bibliographic Details
Published inNature communications Vol. 15; no. 1; pp. 5356 - 15
Main Authors Yan, Donghui, Zhou, Muqing, Adduri, Abhinav, Zhuang, Yihao, Guler, Mustafa, Liu, Sitong, Shin, Hyonyoung, Kovach, Torin, Oh, Gloria, Liu, Xiao, Deng, Yuting, Wang, Xiaofeng, Cao, Liu, Sherman, David H., Schultz, Pamela J., Kersten, Roland D., Clement, Jason A., Tripathi, Ashootosh, Behsaz, Bahar, Mohimani, Hosein
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 25.06.2024
Nature Publishing Group
Nature Portfolio
Subjects
Online AccessGet full text
ISSN2041-1723
2041-1723
DOI10.1038/s41467-024-49587-1

Cover

More Information
Summary:Type 1 polyketides are a major class of natural products used as antiviral, antibiotic, antifungal, antiparasitic, immunosuppressive, and antitumor drugs. Analysis of public microbial genomes leads to the discovery of over sixty thousand type 1 polyketide gene clusters. However, the molecular products of only about a hundred of these clusters are characterized, leaving most metabolites unknown. Characterizing polyketides relies on bioactivity-guided purification, which is expensive and time-consuming. To address this, we present Seq2PKS, a machine learning algorithm that predicts chemical structures derived from Type 1 polyketide synthases. Seq2PKS predicts numerous putative structures for each gene cluster to enhance accuracy. The correct structure is identified using a variable mass spectral database search. Benchmarks show that Seq2PKS outperforms existing methods. Applying Seq2PKS to Actinobacteria datasets, we discover biosynthetic gene clusters for monazomycin, oasomycin A, and 2-aminobenzamide-actiphenol. Type 1 polyketides are a major class of natural products with diverse bioactivities but are mostly identified via bioactivity-guided purification which is limited to relatively abundant compounds. Here, the authors present Seq2PKS, a machine learning algorithm that predicts the chemical structures derived from Type 1 polyketide synthases and use it to discover biosynthetic gene clusters for monazomycin, oasomycin A, and 2-aminobenzamideactiphenol.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
None
USDOE Office of Science (SC)
SC0021340
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-024-49587-1