Researchers develop AI-powered system to predict functions of thousands of plant enzymes
Scientists have developed a computational framework combining a large language model database and machine learning classifiers to functionally annotate BAHD acyltransferases, a large family of plant enzymes involved in specialized metabolism. The team assembled FuncZymeDB-BAHD, a curated database of over 2,700 enzyme activities, and built two complementary prediction tools—one phylogenomics-based and one AI-based—that together annotated nearly all enzymes tested. The work addresses a major bottleneck in plant biology where genomic sequencing has far outpaced experimental characterization of gene function.
A research team has published a preprint on bioRxiv describing a scalable computational pipeline for predicting the biochemical functions of BAHD acyltransferases, a large and diverse enzyme family found across plant genomes. The foundation of the framework is FuncZymeDB-BAHD, a database of 2,705 curated enzyme-acceptor-donor activity records covering 336 characterized enzymes from 156 plant species, representing a two- to six-fold expansion over existing resources such as Swiss-Prot. The first prediction tool, FuncPred-OG, uses orthologous group mapping to link uncharacterized enzymes to well-studied relatives, successfully annotating over half of BAHDs across 85 plant proteomes, with five novel predictions subsequently validated through in vitro experiments. For enzymes that FuncPred-OG could not annotate, a second tool, FuncPred-AI, applies logistic regression classifiers trained on protein language model embeddings, achieving Area-Under-the-Precision-Recall-curve scores and correct-hit rates as high as 93%. Together, the two tools provided at least one probable functional annotation for 99.9% of the nearly 9,000 BAHD sequences in the study's pan-plant dataset. The entire workflow and database have been deployed as a public web portal, with the authors suggesting it could reduce the time researchers spend selecting experimental candidates from days to minutes. The authors frame the approach as a generalizable template applicable to other enzyme families beyond BAHDs.
What's missing
As a preprint, this work has not yet undergone formal peer review. The study validates only five novel FuncPred-OG predictions experimentally; the accuracy of FuncPred-AI predictions at scale remains unvalidated in the wet lab. The authors do not fully address how performance may degrade for highly divergent or orphan enzymes with no close characterized relatives, nor do they discuss potential biases introduced by the LLM-based curation of FuncZymeDB-BAHD. The generalizability of the framework to other enzyme families is asserted but not demonstrated.
What different sources said
- bioRxivCenter
Systematic functional annotation of thousands of BAHD acyltransferases in plant genomes using Protein Language Model and phylogenomic tools
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.