Discover, rate, and discuss biology preprints.

Phyling is a tool for phylogenetic inference from protein sequences, offering faster performance than OrthoFinder with comparable accuracy.

Triad-LMF improves cancer subtype classification by integrating multi-omics data through hierarchical low-rank multimodal fusion, showing better performance and interpretability.

Tripso, a self-supervised transformer model, identifies gene program-specific embeddings and discovers novel gene programs, revealing biological insights in hematopoietic development and disease.

Allos provides a Python framework for isoform-level analysis of single-cell and spatial transcriptomics data, integrating with existing tools and enabling differential isoform usage screening and visualization.

This paper introduces PerturbGraph, a graph neural network framework that predicts transcriptional responses to unseen gene perturbations by integrating biological priors, outperforming existing methods on benchmark datasets.

This study uses discrete diffusion models to generate tumor phylogenies, finding that mid-scale models outperform deeper ones and that diverse training improves cross-regime generalization.

The paper introduces DVPNet, an XAI framework combining Nucleotide Transformer and probabilistic circuits to identify important genes in cancer classification using single-cell data.

DCS Tools provides a high-performance, resource-efficient genomic analysis suite with significant speedup and storage reduction for population-scale sequencing data.

The paper introduces CoMPLip, a method that improves membrane-protein structure prediction by co-folding proteins with lipid molecules during AlphaFold 3 predictions, enhancing ligand-pose prediction and conformational sampling.

This paper benchmarks circRNA detection tools using a simulation framework and finds they vary in performance, with limited overlap in detected circRNAs and significant computational efficiency differences.

This paper introduces SR-MEM, a mixed-effects model for microbiome data that accounts for compositional data issues, achieving better false discovery rate control and power than existing methods.

Isopedia reduces apparent isoform novelty by up to 26-fold in HG002 benchmarks and provides a reference-agnostic framework for population-scale isoform annotation.

The paper computationally designs a VHH nanobody targeting Cas9's PI/RuvC interface and validates its structure and stability through molecular dynamics simulations.

The paper benchmarks four AI tools for designing BMPR1A-binding peptides, identifies top candidates, and highlights differences in binding site targeting.

The paper introduces the Duplicate Monophyly Criterion to calibrate distance-matrix perturbations for phylogenetic support estimation using synthetic duplicates.

ProteinMCP accelerates and democratizes protein engineering by automating workflows and integrating 38 tools, achieving a comprehensive fitness modeling task in 11 minutes.

The paper identifies noncoding variants that alter gene regulatory networks using a combination of single-molecule deaminase footprinting and variant effect prediction, applied to UK Biobank genomes.

This study compares feature configurations from mixed-format lifestyle questionnaires for ALS classification, finding that compact longitudinal representations outperform static text features.

The paper introduces SelectZyme, a platform using protein language models and dimensionality reduction to visualize and explore protein sequence space for enzyme discovery, enabling candidate selection without relying on sequence identity or annotations.

STRmie-HD is a tool for high-resolution genotyping of HTT repeat expansions and somatic mosaicism across sequencing platforms, capturing interruptions and rare variants with high sensitivity.