MYCOLab Ai Logo - gold and army green

XenoBug: machine learning-based tool to predict pollutant-degrading enzymes from environmental metagenomes

Summary

XenoBug is a new artificial intelligence tool that helps scientists find bacteria and their enzymes that can break down harmful pollutants like pesticides, plastics, and petroleum products. The tool analyzes genetic information from environmental samples to predict which enzymes can degrade specific toxic chemicals. This discovery approach could make environmental cleanup faster and cheaper by identifying the right microbes for the job. Researchers can use XenoBug to get starting points for developing new biological cleanup solutions.

Background

Environmental pollution from synthetic chemicals, pesticides, plastics, and petroleum products poses significant risks to ecology and human health. Bioremediation using microbial enzymes offers an inexpensive and sustainable approach to mitigate these pollutants. Current methods for discovering novel pollutant-degrading enzymes are limited and inadequate for diverse classes of contaminants.

Objective

To develop a machine learning-based tool (XenoBug) that predicts bacterial enzymes capable of degrading environmental pollutants and xenobiotics from metagenomic data. The tool aims to identify enzymatic reactions, source bacterial species, and metagenomic origins of predicted enzymes for bioremediation applications.

Results

XenoBug demonstrated high binary accuracies (>0.75) and F1 scores (>0.62) across reaction classes. Validation on 25 diverse xenobiotics including pesticides, hydrocarbons, and pharmaceuticals showed accurate prediction of both known and previously unreported metabolic enzymes. The tool successfully predicted enzyme sources, metagenomic origins, and provided protein sequences for experimental validation.

Conclusion

XenoBug represents a significant advancement in identifying pollutant-degrading enzymes from environmental metagenomes using machine learning. The tool provides valuable leads for developing novel bioremediation strategies by predicting enzymatic pathways and their microbial sources. XenoBug is publicly available and demonstrates broad utility for predicting metabolism of diverse xenobiotics.
  • Published in:NAR Genomics and Bioinformatics,
  • Study Type:Computational Tool Development and Validation Study,
  • Source: PMID: 40314024; DOI: 10.1093/nargab/lqaf037
Scroll to Top