gapseq: informed prediction of bacterial metabolic pathways and reconstruction of accurate metabolic models
Problem
Automated reconstruction of microbial metabolic models often fails to recapitulate known metabolic processes, limiting phenotype prediction from genomes.
Why it matters
Accurate metabolic models are needed for industrial microbiology, synthetic biology, and microbiome research.
What the AI did
gapseq uses a curated reaction database and a novel gap-filling algorithm to predict pathways and automatically reconstruct metabolic models.
Results
Outperforms state-of-the-art tools in predicting enzyme activity, carbon source utilisation, fermentation products, and metabolic interactions, validated on 14,931 bacterial phenotypes.
Record
| Venue | Genome biology |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Johannes Zimmermann, Christoph Kaleta, Silvio Waschina |
| Citations | 311 (OpenAlex, at import time) |
| References | 142 |
| Model or method | gapseq (gap-filling algorithm) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1186/s13059-021-02295-1 |
| Open access | gold |
| Keywords | metabolic modelling, gap-filling, bacterial pathways, genome-scale, phenotype prediction |
Importance rating
significant — thousands to millions affected
Genome-scale metabolic models are frameworks to predict phenotypes from genotype, relevant to industrial microbiology, synthetic biology, and microbiome research; abstract gives no impact scale.