AI Models Identify H3K18ac as New Marker of Active Gene Enhancers
Researchers used multiple AI models, including an explainable fuzzy logic system, to predict active enhancers across human and mouse cell lines, identifying H3K18ac as a previously unrecognized enhancer mark. The study combined convolutional neural networks, XGBoost, logistic regression, and a type-2 fuzzy logic system, with the fuzzy logic model showing the strongest generalization to cell lines not seen during training. The findings suggest that as few as seven epigenetic marks in humans and five in mice are sufficient to accurately annotate enhancers, potentially enabling better enhancer mapping in disease contexts where experimental data is limited.
A new study posted to bioRxiv presents several AI-based models trained to predict enhancer activity across human and mouse cell lines using epigenetic features. The explainable AI approach — specifically a type-2 fuzzy logic system (type2-FLS) — outperformed other models in generalizing to unseen cell lines, a critical requirement for practical application in tissues and disease states lacking experimental enhancer maps. A key discovery is the identification of H3K18ac, a histone acetylation mark, as an important predictor of enhancer activity, a role not previously well established. The researchers validated novel putative enhancers identified by the models using both global epigenetic perturbations and targeted CRISPRi-based enhancer rewriting, lending experimental support to the computational predictions. Notably, the study found that a minimal set of seven epigenetic marks in humans and five in mice is sufficient to annotate enhancers without significant loss of accuracy, streamlining future experimental designs. The work aims to address a longstanding gap in the field: the absence of reliable enhancer maps in many human cell types, tissues, and disease contexts. Because enhancers regulate gene transcription from non-coding DNA regions, improved mapping has broad implications for understanding gene regulation in development and disease.
What's missing
As a preprint, this work has not yet undergone peer review, and the extent of CRISPRi validation is not fully detailed — it is unclear how many novel enhancers were experimentally confirmed versus computationally predicted. The study does not address whether H3K18ac is causally required for enhancer activity or is merely correlated with it.
What different sources said
- bioRxivCenter
Explainable AI identifies H3K18ac as a new marker of active enhancers
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.