New Benchmark 'ProMiSE' Reveals Gaps in AI Protein Structure Models' Ability to Capture Dynamic Conformational States
Researchers have introduced ProMiSE, the first systematic benchmark for evaluating how well protein structure prediction models capture functionally relevant conformational dynamics. While tools like AlphaFold3 have largely solved static structure prediction, ProMiSE tests whether models can represent proteins transitioning between multiple biological states. The findings expose a significant gap: current models poorly sample intrinsic multi-states and often ignore biological context in induced conformational changes.
ProMiSE (Protein Multi-State Evaluation) is a newly proposed benchmark that provides both a curated dataset and an evaluation framework built around native biological assemblies. It categorizes conformational change mechanisms into three types — intrinsic, ligand-induced, and protein-induced — and tests state-of-the-art models including AlphaFold3 and recent generative approaches against all three. The study finds that current models have limited capacity to sample intrinsic multi-states and tend to be insensitive to biological context when conformational changes are externally triggered. Internal representation analysis suggests that training data exposure biases models toward dominant conformational states, with this bias manifesting primarily at the structure module rather than in upstream pair representations. Notably, BioEmu, a model that reduces decoding-stage bias, showed substantially improved multi-state sampling, suggesting that architectural choices at the output stage are a key lever for improvement. The work highlights that solving static structure prediction does not equate to capturing the dynamic nature of protein function, which has broad implications for drug discovery and mechanistic biology.
What's missing
The study does not discuss whether experimental ground-truth multi-state structures used for benchmarking are themselves subject to resolution or data-quality limitations (e.g., cryo-EM vs. X-ray crystallography biases). The generalizability of findings to intrinsically disordered proteins or membrane proteins is not addressed.
What different sources said
- bioRxivCenter
ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts
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.