Discover, rate, and discuss biology preprints.

This paper improves ctDNA detection by combining mutation detection with fragmentomic features, achieving higher AUC scores than mutation burden alone.

circStudio is a Python package that integrates actigraphy data preprocessing and circadian modeling into a single framework to streamline circadian rhythm analysis.

The paper evaluates how different linker designs affect the structure and function of an anti-GUCY2C scFv using computational methods.

IMMREP25 evaluates TCR:pMHC binding prediction for unseen peptides, showing improved performance with structural modeling but still below random guessing.

itBins refines metagenomic bins and estimates binning success using %GC content, coverage, and taxonomy, outperforming existing tools in speed and accuracy.

Baktfold improves protein functional annotation for microbial genomes using structural information, achieving higher annotation rates than existing tools for bacteria and archaea.

This study uses bee-collected pollen sequence data to train machine learning models for predicting sample origin, finding that Random Forest and k-Nearest Neighbors models achieve high accuracy.

The paper introduces DEGAS, a method to identify high-risk cells in spatial transcriptomics data by transferring disease attributes to individual cells, validated in cancer and diabetes datasets.

ProteoPy provides a framework for integrated proteomics analysis using AnnData, enabling proteoform group inference and differential analysis with integration into multi-omics workflows.

FluNexus provides a web platform for antigenic prediction and visualization of influenza A viruses, offering tools for data preprocessing, prediction, and visualization of antigenic evolution.

The paper develops a computational framework to predict small molecule GLP-1R agonists, identifying chemically distinct candidates with varying efficacy.

This study evaluates Conformal Prediction for predicting cancer cell growth inhibition by novel molecules, showing that smaller confidence intervals correlate with lower prediction errors across diverse cell lines.

Scarecrow improves data recovery from single-cell combinatorial barcoding by accounting for positional errors in barcode sequences, enhancing downstream analyses.

This paper introduces DPMM-Base and DPMM-FM autoencoders with Dirichlet Process priors for single-cell representation learning, showing improved geometry but reduced label recovery accuracy across multiple scRNA-seq datasets.

This paper introduces Topic-FM, a neural topic VAE for single-cell transcriptomics that improves interpretability and clustering performance across multiple datasets.

GraphBG detects spatial domains in multi-slice and multi-modal spatial transcriptomics data using spectral graph convolutions and Bayesian modeling, achieving high accuracy and scalability.

CGAS automates comparative chloroplast genome analysis by integrating multiple modules into a single pipeline, enabling batch processing and standardized outputs.

MoCoO improves single-cell trajectory inference by combining VAE, Neural ODE, MoCo, and Flow Matching, achieving top performance in clustering and embedding quality across multiple datasets.

DEPICT predicts drug-induced transcriptional responses from gene expression and drug data, outperforming existing methods and enabling drug screening and synergy discovery.

The paper introduces a structured pooling method for population-scale STARR-seq experiments, improving detection of rare regulatory variants by increasing signal-to-noise ratio and providing Bayesian effect size estimates.