Discover, rate, and discuss biology preprints.

The paper introduces ISPat-3D to estimate conditional cell population associations in 3D tissue images, finding stable associations in colorectal cancer but less stable in breast cancer.

OmegaTherm predicts mutation-induced protein stability responses by jointly modeling folding free energy and melting temperature, achieving state-of-the-art performance in prediction and variant ranking.

This paper identifies four molecular subtypes of sepsis using transcriptomic data and proposes subtype-specific drug repurposing opportunities, including potential therapies for high mortality subtypes.

The paper identifies oxidative stress and inflammation gene networks in Parkinson's disease through cross-dataset transcriptomic analysis and nutrigenomic integration, revealing candidate diet-gene associations.

MuseDrift generates protein variants with specified sequence identity to a wild-type sequence, achieving higher structural prediction confidence and better mutation-effect scores than existing methods.

This paper introduces TMCA, a multimodal framework that integrates SMILES, molecular graphs, and 3D conformations for molecular property prediction, achieving the best performance on benchmark datasets.

The paper evaluates an AI framework for evidence analysis in panvascular intervention using clinical trial data and NLI4CT tasks, showing improved accuracy with checklist prompts over generic ones.

RiboBA improves ncORF identification by accounting for protocol-induced biases in ribosome profiling data.

This paper introduces Minkowski Tensors as interpretable 3D shape descriptors, showing competitive performance on biomedical image classification tasks.

A sparse mixture-of-experts DNA model conditioned on hyperbolic taxonomy embeddings learns better microbial representations than its taxonomy-free twin and comes close to Evo2-7B in probing and fine-tuning at lower compute.

This paper introduces scDIVIDE, a framework to infer division rates and cellular dynamics from time-series scRNA-seq data, showing it accurately captures birth rates in biological processes.

The paper introduces CellHub Database, a consolidated ligand-receptor interaction resource for cell-cell communication analysis across multiple species.

BiomiX 3.0 is a multi-omics integration platform that introduces PRAMIGO, a supervised heterogeneous graph transformer, and benchmarks five methods on CLL and PTB datasets, showing that no single method captures all biologically relevant signals.

The paper introduces MorphAgent, a biologically grounded AI framework for cell profiling across microscopy modalities, improving feature design and performance in drug screening and disease analysis.

Non3nExonFinder identifies shared non-triplet coding exons across transcripts, prioritizing candidates based on CDS status and divisibility by three, with high concordance in validation.

The paper evaluates tabular foundation models on genetic data, identifies ancestry-dependent non-stationarity as a key challenge, and proposes synthetic tasks to improve performance across ancestry groups.

CSGDA predicts drug responses across biological heterogeneities by addressing distribution shifts using a cell state-guided graph domain adaptation framework.

A marker audit finds 97.9% of CEREBRI's 45,051 official 'glutamatergic neuron' cells are not glutamatergic (four-check composite 82.6%), creating false ion-channel and OXPHOS signals; true neurons show acute KCNC3 up-regulation.

This paper introduces spEnhance, a computational framework that improves spatial resolution and reliability of spot-level spatial omics data across multiple modalities.

AtlasOT improves multimodal integration of disease atlases by addressing unpaired data constraints through a novel optimal transport framework.