← Back to feed
PublicationsJun 1178% confidenceConfidence 78% — the share of independent, credible sources corroborating the core facts.

New Semi-Supervised Method Improves Single-Cell RNA Sequencing Integration Using Virtual Adversarial Training

Center 100%
1 source

Researchers have developed scCRAFT+, a semi-supervised computational model that integrates single-cell RNA sequencing data more accurately by incorporating marker gene information through Virtual Adversarial Training (VAT). Existing integration methods often blur distinctions between closely related cell subtypes, reducing biological resolution, a problem scCRAFT+ is designed to address. The advance could improve the accuracy of cell type identification in large-scale genomic studies, even when marker gene annotations are incomplete or noisy.

Single-cell RNA sequencing (scRNA-seq) allows researchers to profile gene expression in individual cells, but combining datasets from different experiments — a process called integration — can inadvertently merge distinct cell subtypes that should remain separate. scCRAFT+ addresses this by using Virtual Adversarial Training, a machine learning technique that enforces smooth, consistent predictions among transcriptionally similar cells, making the model more robust to imperfect or incomplete marker gene sets. Unlike purely unsupervised methods that ignore prior biological knowledge, or fully supervised approaches that depend heavily on accurate annotations, scCRAFT+ occupies a semi-supervised middle ground that leverages available marker information without being brittle to its errors. Benchmarking against current unsupervised and supervised integration tools showed scCRAFT+ achieved consistently stronger performance across integration quality metrics and biologically meaningful sub-cell type annotations. The method is particularly relevant for studies involving rare or closely related cell populations where fine-grained distinctions carry significant biological and clinical importance.

What's missing

As a preprint posted to bioRxiv, this work has not yet undergone formal peer review, so findings should be interpreted with caution.

What different sources said

  • bioRxivCenter

    Robust semi-supervised scRNA-seq integration from virtual adversarial learning

Related

PublicationsConfidence 78% — the share of independent, credible sources corroborating the core facts.

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.

1 sourceJun 13
PublicationsConfidence 78% — the share of independent, credible sources corroborating the core facts.

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.

1 sourceJun 13
PublicationsConfidence 78% — the share of independent, credible sources corroborating the core facts.

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.

1 sourceJun 13