Tag: computational biology

A spatially resolved model of the yeast galactose switch shows that intracellular architecture, especially ER-bound translation, changes gene regulation predictions.

Graph-Attentive AI Generates Rare Cells to Sharpen Single-Cell RNA Analysis

A new graph-attention-based generative adversarial network called GARAGE produces realistic synthetic single-cell RNA-seq data that preserves rare cell types and ...

New AI Framework Reads Gene Maps Like Images to Reveal Hidden Cell States

A new computational framework called STARIT converts the spatial positions of mRNA molecules inside cells into image tensors, allowing deep ...

New Optimal Transport Framework Reconstructs Gene Networks and Cell Fates From Single-Cell Snapshots

Researchers have developed CardamomOT, an optimal transport-based framework that jointly infers gene regulatory networks, reconstructs unobserved protein trajectories, and enables ...

AI Scans Entire Proteomes to Find the Next Generation of Sustainable Food Proteins

Researchers at Kookmin University have developed AlterProtX, an AI framework that compares animal and non-animal proteomes at scale to identify ...

A New Blueprint for Building Life-Size Models of Living Systems

A new framework called Process Bigraph, implemented in Vivarium 2.0, provides a formal architecture for composing multiscale biological simulations from ...

Ant Colonies Keep Idle Reserves of Workers to Survive Hard Times, Study Finds

A computational study of Aphaenogaster senilis ants shows that idle workers act as a dynamic reserve workforce that stabilizes colony ...

Why the Brain’s Master Clock Refuses to Reset When Temperatures Shift

A new computational model shows that phase differences between subregions of the suprachiasmatic nucleus explain why the brain's master circadian ...

Cellular Recycling Routes Reshape How Hormone Receptors Send Their Signals

A new computational model shows that a small pool of internalized follicle-stimulating hormone receptors can drive outsized endosomal signaling, revealing ...

Computational Microscope Opens a New Window on Chromatin Folding

An international team has developed OpenCGChromatin, an open-source simulation tool that acts as a computational microscope to reveal how chromatin ...

DyME: A New Engine Automates Thousands of Protein Simulations for Molecular Design

Researchers have developed DyME, an open-source platform that automates high-throughput mutagenesis, molecular dynamics simulation, and comparative analysis of thousands of ...

Flawed Benchmarks Hid AI Success in Gene Perturbation Prediction

A new calibration framework shows that common benchmarking metrics masked real perturbation-specific signal, and that deep learning models can outperform ...

New Standard PEtab Select Brings Order to the Chaos of Choosing Biological Models

A new open standard called PEtab Select brings automated, reproducible model selection to systems biology, enabling researchers to compare billions ...

AI Reads Protein Shapes to Unmask Bacterial Weapons

A new multimodal deep learning framework called GeoEPred combines protein language model semantics with predicted 3D structures to more accurately ...

AI-Designed Protein Binders Face Real-World Test in Landmark CAR T Cell Competition