Discover, rate, and discuss biology preprints.

Echo identifies desynchronized cell states and their drivers from paired single-cell RNA and ATAC data, revealing structured desynchronization in human fetal retina and hematopoiesis.

MARRVEL-MCP enables natural language variant interpretation by allowing LLMs to autonomously construct workflows using curated genomic tools, improving performance over models without tool access.

ERVmancer is a phylogeny-informed method that resolves read-mapping ambiguity for HERVs, outperforming existing approaches and revealing new biology in breast cancer.

This paper introduces HAST, a framework for spatial transcriptomics that adapts graph learning scales to tissue heterogeneity, improving spatial structure identification and tumor region characterization.

The paper introduces S-IGTD, a supervised method for converting tabular biological data into image layouts for classification, showing improved performance over existing methods.

The paper constructs a cross-tissue fibroblast atlas to identify a conserved POSTN+ program across multiple disease contexts and validates its robustness through multiple analyses.

NanoCortex provides a unified agentic framework for nanopore sequencing analysis, improving usability over general-purpose models by integrating data processing and biological interpretation.

The paper benchmarks full-length ITS metabarcoding across Illumina, PacBio, and Oxford Nanopore platforms using mock and soil communities, finding PacBio has the lowest error rate and recommends standard pipelines for biodiversity assessments.

ParaDISM improves read placement and variant calling accuracy in highly homologous genomic regions by reducing misalignment artifacts.

RANKOR ranks candidate drugs from transcriptomic signatures using a machine learning framework, outperforming existing methods in bulk and single-cell data.

This study uses multimodal single-cell analysis to identify transcription factor networks involved in T-cell aging.

geneML improves fungal gene prediction accuracy and recall using deep learning, outperforming existing tools and enabling faster, more comprehensive genome annotation.

This paper introduces a method to recover cell-type and systems architecture from bulk and single-cell RNA-seq data using spectral unfolding, revealing new gene expression signatures in human hair follicles.

GIRAFI improves sparse single-cell proteomics by imputing missing values and revealing cell states using graph-informed statistical learning, outperforming existing methods and recovering biological structure.

resLens improves antibiotic resistance gene detection by using genomic language models trained on curated datasets, outperforming reference-based methods in varied scenarios.

MirMachine 2 annotates microRNAs across thousands of animal genomes, revealing methodological biases in apparent microRNA absence.

The paper predicts gene-rare disease associations using a network-based algorithm to improve variant prioritization and guide functional validation.

DNAS-Bench evaluates Biosecurity Screening Software by testing its ability to detect malicious sequences in synthetic DNA, finding that simple sequence manipulations can bypass many systems.

This paper improves mRNA stability prediction by incorporating fine-scale structural metrics into a regression model, achieving better accuracy than existing methods.