Discover, rate, and discuss biology preprints.

Modtector efficiently extracts RNA modification signals from sequencing data, outperforming existing tools on large datasets.

STADiffuser simulates spatial transcriptomic data with high fidelity and enables 3D modeling of large-scale spatial datasets.

The paper develops a multi-compartment metabolic model of the chicken gut to identify dietary interventions that enhance short-chain fatty acid production.

ICFinder uses protein language models to identify ion channels and predict permeation residues, outperforming existing methods and providing a public resource.

This study benchmarks ambient RNA decontamination methods using simulated and experimental datasets, finding that no single method is optimal across all scenarios, with CellBender, DecontX, and SoupX performing well.

LinkLlama improves linker design by combining natural language prompts with 3D spatial awareness, achieving higher chemical validity than existing methods.

ERFMTDA predicts tsRNA-disease associations by modeling complex feature interactions and using a biologically informed negative sampling strategy, outperforming existing methods.

This paper introduces a protein language model-based decoy generation method for proteomics and benchmarks it against classical decoy strategies, finding it less distinguishable by neural networks but not superior in search performance.

This paper introduces ZEN, a normalization method for genomic data that reduces technical noise while preserving biological signals, improving alignment across different experimental platforms.

Melody predicts DNA methylation from genomic sequences across human tissues and outperforms existing methods, also generalizing to methylation quantitative trait locus effect prediction.

This paper introduces scRICH, a framework for analyzing cell-cell communication in single-cell and spatial transcriptomics data, showing its ability to capture communication heterogeneity and link it to cell fate decisions.

The paper presents a deep learning approach that uses phylogenetic dynamic program outputs to predict edges in maximum parsimony trees, achieving high accuracy on simulated and empirical datasets.

This paper shows that polygenic risk scores can be used to infer genotypes and de-anonymize individuals, and proposes a framework to assess and mitigate privacy risks when sharing PRS values.

The paper introduces tidesurf, a tool for quantifying spliced and unspliced transcripts in scRNA-seq, showing improved accuracy over velocyto for 5' chemistry data.

scE2TM improves single-cell embedding interpretability by integrating external knowledge, achieving better clustering and revealing biological perturbation signatures across datasets.

This paper introduces MagicImpute, a genotype imputation tool for multiparental populations that improves computational efficiency and error handling, showing accuracy across real datasets with missing parents and sequencing errors.

RobustCell evaluates attack-defense methods in single-cell and spatial transcriptomic data analysis, showing attacks can impair clustering and annotation, while defenses can protect model performance.

ABCDscores is an R package that computes summary scores for the ABCD Study dataset, offering a flexible, transparent, and reproducible solution for data analysis.

CLASPP is a unified deep learning model that predicts multiple PTM types from protein sequences, addressing data imbalance and improving prediction performance across organisms.

plinkQC is an R package that performs ancestry inference, sample selection, and quality control in population genetics, achieving 98% accuracy with minimal marker overlap.