Discover, rate, and discuss biology preprints.

This paper presents an automated framework using LLMs to identify supporting and contradictory evidence in biomedical literature, validated on the BioNLI task with high accuracy and stability.

STAnalyzer automates spatial transcriptomics analysis through a multi-agent framework, enabling end-to-end processing and hypothesis generation with transparency and robustness.

GMIP-PLSR improves GWAS gene prioritization by integrating multi-omics data using PLSR to address multicollinearity, outperforming PoPS in NAFLD case studies.

This paper introduces SMRmix, a mixed effect model for integrating multiple microbiome datasets to identify consistent community-level associations with outcomes.

CoPhaser models biological cycles in scRNA-seq by decomposing data into periodic and non-periodic sources, revealing insights into cell cycle dynamics and other periodic processes across diverse contexts.

The paper develops a lightweight pipeline to process germline VCF files, enabling robust variant extraction and read evidence quality control for DDR loci analysis in colon crypts.

LOCOM2 improves differential abundance analysis in microbiome studies by controlling error rates and handling challenges like relative abundance data and unbalanced designs.

IEKB is a database that integrates curated gene-phenotype-disease associations, cochlear gene interactions, and a scientific network for inner-ear genetics research.

This study models NNAT isoforms and assesses their interaction with SERCA2b using computational methods, suggesting NNAT acts as a regulin-like protein with aggregation potential.

INTACT harmonizes time-varying physical activity data from multiple sources by removing device-specific effects while preserving biological variation, improving cross-study comparisons.

gbdraw generates genome diagrams for microbes and organelles as a web app and command-line tool, offering secure, local processing without data upload.

The paper evaluates MAG pipelines using MAG-E, revealing performance gaps in assembly, binning, and quality control for the human gut microbiome.

This paper presents a grid-search framework for calibrating actigraphy sleep detection algorithms, showing it can replace manual tuning with improved reproducibility and small performance gains.

This paper introduces a quaternion Fourier transform framework for DNA sequence analysis, demonstrating its ability to detect structural periodicities and spectral signatures across multiple species.

The paper introduces MoCL-GAT, a self-supervised learning framework for molecular representation, achieving state-of-the-art performance on molecular property prediction tasks.

The paper proposes a method to generate synthetic 3D cell segmentation data to reduce reliance on scarce hand-annotated samples, showing that a standard UNet trained on synthetic data can accurately segment single motile cells with branching filopodia.

TarDis disentangles multiple covariates in single-cell genomics, improving data integration and out-of-distribution predictions by generating structured latent representations.

The paper introduces an Adaptive Multi-Scale Graph Transformer (AMGT) for histopathological image classification, achieving better performance and efficiency than existing models.

This paper benchmarks 20 computational methods for multi-omics biomarker discovery in cancer using real and simulated datasets, finding that DeePathNet and Deep-KEGG perform best.

The paper improves phylogenetic inference by incorporating lineage abundance into maximum likelihood methods, showing significant accuracy gains in SARS-CoV-2 data.