Discover, rate, and discuss biology preprints.

ATAClone identifies cancer clones and estimates copy numbers from scATAC-seq data, improving accuracy over existing methods.

This study analyzes 76 CALR exon 9 variants to refine their classification based on charge architecture, revealing subgroups within Type-1-like variants and linking tail chemistry to receptor activation.

BATTLE-AMP benchmarks antimicrobial peptide predictors using MIC data, showing that models trained on MIC data outperform binary classifiers and highlighting limitations in distinguishing active from inactive peptides.

This study evaluates reference-free methods for Mycobacterium tuberculosis lineage typing using simulated Illumina data, finding SKA2 to be the most accurate tool for strain classification.

This paper introduces a framework to stratify pharmacological data by action type and assay readout, improving QSAR model validity for opioid receptors.

This paper introduces a method to expand gene regulatory networks by incorporating prior knowledge, outperforming conventional methods in distinguishing true interactions from indirect associations.

InVitroGap is an open-source tool for automated quantification of wound closure in scratch assays, showing strong agreement with commercial software.

SELFormerMM integrates multiple molecular modalities to improve property prediction, outperforming single-modality models.

ComplexDesign is a method for designing multichain protein complexes by optimizing sequences to fold proteins and form inter-chain interactions, achieving high success rates in designing dimers, trimers, and tetramers.

SEMFA infers the statistical significance of Mahalanobis similarity between multi-omics samples using multiple factor analysis, showing effectiveness in both Gaussian and non-Gaussian scenarios.

The paper trains a supervised VAE on bulk RNA-seq data to learn a unified tissue-aware representation, achieving high tissue classification accuracy and demonstrating the impact of dataset scale.

The paper introduces effect size-based methods to rank transcription factor binding motifs, showing they outperform p-value rankings under heterogeneous sample sizes.

SegJointGene improves cell segmentation and spatial gene prioritization by integrating spatial gene expression with imaging data using deep learning.

This paper introduces NT-ABDiff, a diffusion model for antibody sequence-structure design that improves CDR recovery and structural accuracy using noisy and unreliable templates.

The paper introduces a data portal and open-source tools for single-cell transcriptomics of pediatric tumors, providing uniformly processed RNA-seq data and metadata from over 700 samples across 55 cancer types.

V3Cell predicts organoid responses to chemical perturbations using non-invasive bright-field microscopy, creating virtual 3D cell models that mimic real organoids in structure and developmental dynamics.

EnrichViz provides an interactive R Shiny tool for visualizing pathway enrichment results from omics data without requiring coding.

MLMarker computes tissue similarity scores for proteomics data, identifies tissue origins in biofluids, and provides interpretable predictions using a Random Forest model.

This study benchmarks tumor-naive ctDNA detection and quantification methods using WGS and methylation data from cancer patients, identifying performance trade-offs and optimal integration strategies.

trAIt uses large language models to retrieve species traits from scientific literature, achieving 47.1% accuracy in a case study, though expert curation remains more accurate.