Discover, rate, and discuss biology preprints.

ProDive detects cross-family local conservation using a pHMM-based framework, identifying 318,289 high confidence segment correspondences across 25,545 Pfam families.

Luxar compresses volumetric microscopy data into compact archives for interactive web visualization without requiring specialized software.

RNabel is a software tool for annotating tandem mass spectra of modified RNAs, supporting various modifications and formats, and providing quality metrics for spectral analysis.

AF3 Inspector provides an interactive web tool to visualize and analyze all AlphaFold 3 structural models, addressing limitations in the official service.

YieldLearn estimates yield-related traits in durum wheat using physiological indicators and machine learning, showing moderate accuracy and feature importance.

DS5 is an open-source framework that standardizes HTS data storage, analysis, and drug prioritization, validated against public benchmarks and applied in clinical settings.

NexuST is a hierarchical foundation model for spatial transcriptomics that improves cell-type annotation and spatial prediction by integrating gene-level and cell-level modeling.

This study evaluates genomic foundation models for viral sequence classification, finding that NTv3-650M achieves high accuracy comparable to BLAST on standard-length sequences.

Serval is a modular framework for decoding spatial transcriptomics data that introduces Cosine, a method improving transcript recovery and correlation with expression references.

CryoMV generates and validates continuous protein conformations from cryo-EM data using structure priors and real-particle validation, achieving high resolution and robustness on benchmark datasets.

UniWave-2 improves nucleic acid sequence analysis by integrating hydrophobicity, enhancing waveform resolution with Fourier and wavelet transforms, and using a lightweight GRU model for efficient feature extraction.

DSSNA v2026 analyzes nucleic acid structures in MD simulations, identifying base pairs, hydrogen bonds, and stacking interactions, showing that canonical pairs are stable while non-canonical ones are transient.

This study benchmarks single-cell foundation models for aging biology, finding that Geneformer excels in age prediction and pseudotime concordance, while SCimilarity outperforms others in rare state identification.

The paper shows targeted finetuning can enable co-folding models to learn ligand-induced conformational states not present in training data.

SpiderNet identifies cell-cell communication programs from spatial transcriptomics data, revealing key interactions and their associations with phenotypes and therapeutic responses.

CheckAMG identifies auxiliary viral genes by combining annotation-based prediction with a genome-language model, improving accuracy and uncovering novel genes with no sequence similarity to references.

PTMExplorer is a visualization platform that integrates PTM data with 3D structure, functional annotations, and disease associations to identify biologically significant modification sites.

Proteome-wide variant calling builds amino acid phylogenomic alignments orders of magnitude faster than a BUSCO marker pipeline, with similar tree signal in three of four test taxa.

HANAMI improves drug-gene-disease motif prediction by integrating heterogeneous biomedical data and using graph contrastive learning, achieving up to 6% better performance than existing methods.

RosaSeed improves short read alignment speed while maintaining accuracy comparable to BWA-MEM2 by using a configurable seeding strategy.