Skip to content

BGCFlow

BGCFlow is the standard pipeline for mining biosynthetic gene clusters (BGCs) across bacterial pangenomes, but its output is hard to interpret without expert time, and every novelty-relevant stage (antiSMASH, MIBiG, Pfam

Code Video Cerebral Valley

Core trick

Adds an ESM2 protein-language-model side channel that flags biosynthetic-core proteins lacking close MIBiG neighbors, leaving antiSMASH calls untouched.

Tags

science

Description

BGCFlow is the standard pipeline for mining biosynthetic gene clusters (BGCs) across bacterial pangenomes, but its output is hard to interpret without expert time, and every novelty-relevant stage (antiSMASH, MIBiG, Pfam, GTDB) can only recognize what already resembles something known — homology-matching is the ceiling. We built two additive tools to break past it. BGCLens is a read-only layer that ingests a finished BGCFlow project, recommends and runs the right statistics (PCoA, PERMANOVA, enrichment, diversity), renders figures, and writes plain-English interpretations via a guarded LLM pass that strips any invented numbers or accessions. BGCFlow-PLM adds an ESM2 protein-language-model side-channel that flags biosynthetic-core proteins with no close MIBiG neighbor — a remote-homology novelty axis the databases miss — without ever touching an antiSMASH call. Together they lower the expertise barrier to acting on genome-mining results and help researchers surface genuinely novel candidates instead of only re-finding the already-catalogued.
kaylaque/bgcflow-plm★ 00 forksPythonMITCreated Jul 10, 2026 · last push Jul 13, 2026

README excerpt

# BGCFlow
[![Snakemake](https://img.shields.io/badge/snakemake-≥7.14.0-brightgreen.svg)](https://snakemake.bitbucket.io)
[![PEP compatible](https://pepkit.github.io/img/PEP-compatible-green.svg)](https://pep.databio.org)
[![wiki](https://img.shields.io/badge/wiki-documentation-forestgreen)](https://github.com/NBChub/bgcflow/wiki)
<a href="https://pypi.python.org/pypi/bgcflow_wrapper">
    <img src="https://img.shields.io/pypi/v/bgcflow_wrapper.svg"
        alt = "Release Status">
</a>
[![example report](https://img.shields.io/badge/demo-report-blue)](https://nbchub.github.io/bgcflow_report_demo/)

`BGCFlow` is a systematic workflow for the analysis of biosynthetic gene clusters across large collections of genomes (pangenomes) from internal &amp; public datasets.

At present, `BGCFlow` is only tested and confirmed to work on **Linux** systems with `conda` / `mamba` package manager.

## Publication
> Matin Nuhamunada, Omkar S Mohite, Patrick V Phaneuf, Bernhard O Palsson, Tilmann Weber, BGCFlow: systematic pangenome workflow for the analysis of biosynthetic gene clusters across large genomic datasets, Nucleic Acids Research, 2024;, gkae314, [https://doi.org/10.1093/nar/gkae314](https://doi.org/10.1093/nar/gkae314)

## Pre-requisites
`BGCFlow` requires `gcc` and the `conda`/`mamba` package manager. See [installation instruction](https://github.com/NBChub/bgcflow/wiki/00-Installation-Guide) for details.

Please use the latest version of `BGCFlow` available.
## Quick Start
A quick

Team