Discover, rate, and discuss biology preprints.

Inverse FoldDir designs protein sequences compatible with a given backbone structure, achieving high accuracy and experimental validation in nanobody redesign.

MIA is a tensor-based framework for multi-omics data integration that improves clustering and feature discovery, showing effectiveness in cancer subtype identification.

miDGD predicts microRNA expression from bulk and single-cell mRNA profiles using a deep generative decoder, achieving high accuracy across diverse datasets and cell types.

Looplook integrates 3D chromatin topology with functional genomics to improve CRE-target gene assignment and functional inference in chromatin regulatory networks.

The paper benchmarks small variant calling pipelines for long-read RNA sequencing data, finding that sequencing quality is the main factor affecting performance, followed by variant caller and alignment strategy.

HyphAeon is a transformer model that accelerates detection of episodic diversifying selection in mammalian genomes and enables new analytical capabilities beyond traditional dN/dS methods.

Cavebear improves pseudotime inference by using reference species time-series data to guide ordering of cells in query species or conditions without time labels.

This study uses a large language model agent to iteratively develop an RNA 3D structure prediction model, achieving performance comparable to existing methods at lower cost.

The paper develops a closed-loop framework for designing receptor-selective cell-penetrating peptides using multi-objective optimization and evaluates its effectiveness through experimental validation.

CoTRA provides an R/Shiny framework for bulk and single-cell RNA-seq analysis, offering integrated workflows and reproducibility across 49 criteria.

The paper identifies a shared A-to-G and G-to-A substitution bias in nanopore sequencing, amplified by bacterial DNA methylation, and shows this bias is concentrated around methylation motifs.

The paper quantifies metadata richness in three biological repositories using NLP metrics, finding differences in word count, information density, and entity consistency across repositories.

This paper introduces a real-time forecasting framework for livestock disease outbreaks, showing improved accuracy after the outbreak peak and consistent spatial forecast skill.

A web database and REST API of 124,687 AlphaFold 3 structures for human splice isoforms, annotated against canonical proteins for domains, decay, modifications, neoantigens and drug pockets.

PHAROS uses a pretrained single-cell perturbation model to predict and prioritize effective drug combinations without retraining, showing success in cell lines and patient-derived tumors.

Pioneer and Altimeter provide fast, accurate analysis of DIA proteomics data, improving peptide coverage and speed compared to existing tools.

PePApipe is a bioinformatics pipeline for ASFV genome analysis that integrates multiple tools into an automated workflow, enabling rapid and reproducible genomic analysis with minimal bioinformatics expertise.

MycoAI ITS classifiers trail alignment, SINTAX and HiTaC on full-length ITS and drop to 28.3% and 18.5% seen-genus family accuracy on ITS2, as predictions track flanking regions.

spaCraft provides calibrated power analysis and sample-size planning for multi-sample spatial transcriptomics by integrating domain recovery and clustering uncertainty.