OCOO-T: New AI Model Simplifies Prediction of Gene Expression Changes from Cellular Perturbations
Researchers have introduced OCOO-T, a flow-matching-based AI model designed to predict single-cell transcriptional responses to genetic, chemical, and cytokine perturbations. Unlike existing approaches that rely on complex architectural components such as hierarchical variational autoencoders or gene-interaction priors, OCOO-T uses a simplified vanilla Transformer stack operating directly on continuous gene expression profiles. The model achieves state-of-the-art performance on multiple benchmarks, potentially accelerating drug discovery and the study of gene regulatory networks.
OCOO-T is a newly proposed AI Virtual Cell model that frames transcriptional perturbation response prediction as a continuous-time denoising process using flow-matching, a generative modeling technique. The architecture deliberately avoids the auxiliary encoders, dedicated encoder-decoder modules, and biological priors that characterize many competing systems, instead relying on a standard Transformer stack that processes gene expression profiles directly. Perturbation type, dosage, and cell-line or cell-type identity are incorporated via adaptive layer normalization and in-context tokens, keeping the design modular and scalable. The model was evaluated on three benchmarks—Tahoe100M, Replogle, and PBMC—spanning diverse perturbation types and cell types, where it reportedly achieved state-of-the-art results. Scalability to long transcriptional profiles is addressed through a patching and depatching mechanism that segments high-dimensional expression data into manageable chunks. The authors argue that the minimalist design improves generalizability and reduces the risk of overfitting to domain-specific architectural assumptions. As a preprint, the work has not yet undergone formal peer review.
What's missing
As a preprint, OCOO-T has not been peer-reviewed, and independent replication of the benchmark results has not been reported. It is also unclear how the model performs relative to wet-lab experimental validation rather than held-out computational benchmarks.
What different sources said
- arXiv cs.AICenter
OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction
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.