Discover, rate, and discuss biology preprints.

The paper introduces a method for analyzing multicellular anatomical structures from spatial omics data and provides an open-source tool for this purpose.

This paper evaluates a self-architecting transformer for protein representation, showing it achieves better performance than existing models with a smaller dataset.

This study reconstructs the evolutionary origin of the GABAergic signaling system across 53 metazoan species, revealing a stepwise assembly from metabolic components into a synaptic inhibitory system.

97% of 184 high-impact biomedical AI studies compare cross-validated models with tests assuming fold independence; in 69% of re-analyzable studies a significant comparison does not survive correction.

This paper uses a deep learning model to identify potential drugs for cardiac hypertrophy by analyzing gene expression data and linking disease signals to known drug targets.

The paper proposes novel two-target combinations for LUSC using an AI research environment and validates them through experimental testing.

The paper introduces the GPCR Evolution Database, which provides evolutionary analysis of GPCRs to study their function and conservation across species.

GOlien annotates protein sequences with GO terms using a Shannon-entropy k-mer model, achieving high accuracy on Biological Process, Cellular Component, and Molecular Function.

EukaUTR is a foundation model for eukaryotic 3' UTRs that predicts function and generates new sequences with regulatory properties.

The paper introduces PlantLRR-PRR, a pipeline for annotating RLP/RLKs in tomato, revealing evolutionary patterns and TE enrichment in defense-related RLPs.

The paper introduces Atlas, a microbiome dataset, and Waypoint, a series of transformer-based models, showing improvements in downstream tasks through pretraining.

The paper identifies how hidden assumptions in nascent RNA sequencing pipelines lead to structured divergence in transcriptional profiles across datasets.

This paper introduces 3D-VirtualCM, a method to reconstruct full cardiomyocyte transcriptomes from spatial transcriptomic sections, revealing spatial and transcriptional heterogeneity in infarcted mouse hearts.

TAPAS integrates AlphaFold3 confidence and geometric features with sequence embeddings to improve TCR-pMHC binding prediction, outperforming individual metrics across benchmarks.

This study shows that k-mer-based whole-genome similarity can rapidly and accurately classify fungal taxa from genus to intraspecies variants, outperforming traditional methods in speed and efficiency.

dictyExpress 3.0 integrates bulk and single-cell transcriptomics data for Dictyostelium, offering interactive visualizations and cross-modal analysis.

This study evaluates STUNT, a meta-learning framework for microbiome-based disease classification, finding that its benefits are limited under data scarcity and diminish with more samples.

PKProbDesign optimizes thermodynamic folding probability for pseudoknotted RNA targets, achieving high pseudo-joint folding probability on most tested targets.

The paper introduces MultiStateFold, a framework that improves prediction of multiple protein conformations by integrating Parallel Tempering into a protein language model, achieving better performance than existing methods.

This paper uses quantum computing to assemble a large genome on current hardware, achieving high accuracy despite technical limitations.