DeePEn: New Benchmark Measures Protein Engineering Models' Performance on Distant Mutations
Researchers have introduced DeePEn, a new benchmarking framework that tests how well AI models predict protein fitness as mutations move further from a known reference sequence. The benchmark evaluates several recent models—including protein language models and biophysics-informed networks—using deep mutational scanning datasets drawn from ProteinGym. The work highlights a consistent performance gap in current models at high mutational distances, a limitation with direct implications for real-world protein engineering applications.
A team of researchers has developed DeePEn (Depth-sensitive benchmark for Protein Engineering), a framework designed to evaluate how predictive models handle increasingly distant protein variants relative to a wildtype or training sequence. The benchmark defines mutational distance as the number of simultaneous single amino acid variants (SAVs), drawing on four deep mutational scanning datasets from the ProteinGym collection that contain sufficient multi-mutation data points. Models tested include general and biophysics-informed protein language models (pLMs) as well as a non-transformer neural network. Results consistently showed that all evaluated models degrade in predictive performance as mutational distance increases, suggesting a fundamental generalization challenge not yet solved by current architectures. The study also found that no single evaluation metric adequately captures the full range of requirements relevant to practical protein engineering. DeePEn is presented as a publicly accessible, multi-metric resource intended to help the field develop and compare models better suited to predicting distant protein variants.
What's missing
It is unclear whether the observed performance degradation reflects a fundamental modeling limitation or a data scarcity problem at high mutational distances in existing DMS datasets. The paper is a preprint and has not yet undergone peer review.
What different sources said
- bioRxivCenter
DeePEn - A Depth sensitive benchmark for Protein Engineering
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.