Agent K: An Agent-Orchestrated Pipeline for Mapping Genes to Biosynthetic Pathway towards Metabolite Discovery
- 1Texas A & M University
Abstract
The identification of biosynthetic gene clusters (BGCs) and their associated metabolic path- ways is central to genome-guided natural product discovery. However, existing computational tools depend on fragmented workflows for data processing, annotation, and analysis, which re- quire substantial manual intervention and lack seamless integration across heterogeneous plat- forms and tools. Here, we present, Agent K, an agent-orchestrated framework that automates the end-to-end process from bacterial whole genome sequence analysis to biosynthetic pathway mapping and metabolite discovery as candidate gene products for functional insights. The sys- tem employs a large-language-model (LLM) agent to coordinate multiple bioinformatics tools, enabling dynamic execution, data integration, result interpretation, and flexible and intuitive visualization. By integrating genomic sequences to functional annotations and pathway-level reconstructions, the framework facilitates the identification of candidate gene products, their biosynthetic pathways associated with individual BGCs, and the putative metabolites produced by those pathways. The developed novel agentic framework provides a user-friendly scalable and extensible solution for automated high-throughput analysis and mapping of bacterial secondary metabolism pathways for interactive exploration of candidate potential.
Related
- Flow Orchestrated Regulatory Genomics Engine (FORGE): A Configurable Nextflow Pipeline for End-to-End snMultiome Analysis
- drugMR: A multi-omics pipeline for genetically anchored drug-target discovery
- LRP2: A proteogenomics pipeline for long-read informed protein isoform analysis and discovery
- Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery
- Mapping sex-specific hormone-metabolite coupling in the adolescent brain: a longitudinal whole-brain spectroscopic imaging study
BibTeX
@misc{roy2026agent,
title = {{Agent K: An Agent-Orchestrated Pipeline for Mapping Genes to Biosynthetic Pathway towards Metabolite Discovery}},
author = {R. S. Roy and J. J. Han and J. L. Narayana and A. Zhou and A. Han and P. d. Figueiredo and X. Qian},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.760272},
url = {https://www.biorxiv.org/content/10.64898/2026.10.19.760272v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Agent K: An Agent-Orchestrated Pipeline for Mapping Genes to Biosynthetic Pathway towards Metabolite Discovery
AU - R. S. Roy
AU - J. J. Han
AU - J. L. Narayana
AU - A. Zhou
AU - A. Han
AU - P. d. Figueiredo
AU - X. Qian
PY - 2026
DA - 2026/10/19
PB - bioRxiv
DO - 10.64898/2026.10.19.760272
UR - https://www.biorxiv.org/content/10.64898/2026.10.19.760272v1
AB - The identification of biosynthetic gene clusters (BGCs) and their associated metabolic path- ways is central to genome-guided natural product discovery. However, existing computational tools depend on fragmented workflows for data processing, annotation, and analysis, which re- quire substantial manual intervention and lack seamless integration across heterogeneous plat- forms and tools. Here, we present, Agent K, an agent-orchestrated framework that automates the end-to-end process from bacterial whole genome sequence analysis to biosynthetic pathway mapping and metabolite discovery as candidate gene products for functional insights. The sys- tem employs a large-language-model (LLM) agent to coordinate multiple bioinformatics tools, enabling dynamic execution, data integration, result interpretation, and flexible and intuitive visualization. By integrating genomic sequences to functional annotations and pathway-level reconstructions, the framework facilitates the identification of candidate gene products, their biosynthetic pathways associated with individual BGCs, and the putative metabolites produced by those pathways. The developed novel agentic framework provides a user-friendly scalable and extensible solution for automated high-throughput analysis and mapping of bacterial secondary metabolism pathways for interactive exploration of candidate potential.
ER -