AI Protein-Folding Tools Show Limitations in Distinguishing Real from Spurious Proteins
A new preprint study finds that three leading protein structure prediction tools — AlphaFold2, AlphaFold3, and ESMFold — assign unexpectedly high confidence scores to spurious protein sequences that should not fold into real structures. Spurious proteins arise from gene prediction errors and are not expected to produce stable folded structures, making high confidence scores from these tools potentially misleading. The findings raise concerns about the reliability of AI-based structure prediction for validating protein databases at scale.
Researchers tested whether state-of-the-art protein structure prediction methods could distinguish between real proteins and spurious sequences — those arising from gene prediction errors that are not expected to correspond to functional proteins. Using sequences from AntiFam, a database of known spurious protein families, the study found that AlphaFold2, AlphaFold3, and ESMFold all assigned high pLDDT confidence scores to short spurious sequences, meaning none of the tools reliably flagged them as non-proteins. Discrimination between spurious and real proteins improved only for sequences longer than approximately 100 amino acids. By cross-referencing sequences with divergent pTM and pLDDT scores, the authors identified two likely spurious entries in Swiss-Prot, a widely used curated protein database, and one AntiFam entry that may not actually be spurious. The team developed a Gaussian Process Model trained on these prediction scores and applied it to the AlphaFold Database to flag potentially spurious entries at scale, though they caution the model is most useful when combined with other validation methods rather than used in isolation.
What's missing
The study is a preprint posted on bioRxiv and has not yet undergone peer review, so its findings and the performance of the Gaussian Process Model should be treated as preliminary. The study does not report experimental wet-lab validation of the proposed spurious Swiss-Prot entries, leaving their status unconfirmed.
What different sources said
- bioRxivCenter
Folding the unfoldable 2: using AlphaFold and ESMFold to explore spurious proteins
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.