Discover, rate, and discuss biology preprints.

DivQuant estimates species richness and entropy from small samples, achieving accurate confidence intervals and outperforming existing methods across multiple datasets.

TITAN-BBB predicts BBB permeability using multi-modal deep learning, achieving high accuracy and error reduction compared to existing methods.

This paper presents a high-quality chromosome-scale genome assembly for Asparagus racemosus var. CIM-Shakti, enabling research on medicinal traits and evolutionary studies.

This paper denoises MDS-UPDRS Part-III scores and performs high-dimensional analysis to show progression heterogeneity in Parkinson's disease is continuous and along two axes, not clustered subtypes.

This paper introduces robust normalization methods for metabolomics data to reduce technical variance and improve downstream analysis.

The paper identifies and validates copy number variation in dairy cattle using linked-read and short-read sequencing, finding 7218 high-confidence CNV regions with strong inheritance evidence.

This paper extends the HalluDesign framework to nucleic acid design using NA-MPNN, improving confidence scores in ssDNA, ssRNA, and aptamer design.

The paper presents a spatiotemporal transcriptome database of human embryogenesis, providing spatial gene expression and substructure data across 50 developing organs.

The paper introduces a label-free quantification feature in the Crux toolkit, demonstrating improved efficiency and accuracy compared to existing methods.

This paper introduces BootDA, a method to mitigate biases in microbiome differential abundance analysis, refining the coronary artery disease signature to two genera.

This study identifies multiple insecticide resistance mechanisms in Angolan Aedes aegypti using transcriptomic analysis, revealing shared and novel resistance genes compared to other regions.

SPARQ-MI provides a streamlined spatial single-cell analysis method for tumor microenvironments, revealing CD8 T cell state and spatial location associations with immunotherapy response.

SpliceSelectNet predicts splice sites from DNA sequences using a hierarchical Transformer model, achieving state-of-the-art performance and capturing long-range regulatory effects.

GEOAgent retrieves and preprocesses GEO datasets using AI and automation, achieving high precision and accuracy in dataset retrieval and assay classification.

SLiMNet detects functional similarity in SLiM pairs using deep learning and protein LLM embeddings, identifying new motifs and providing functional annotations.

Clair3 v2 improves variant calling accuracy for Oxford Nanopore Technologies sequencing by using move table data and dwelling time, achieving higher F1-scores for SNPs and Indels.

This study models the T4SS structure of Brucella melitensis and identifies three FDA-approved drugs that could target the system for anti-virulence therapy.

MolDeBERTa is a molecular language model pre-trained on SMILES data with novel objectives to improve property prediction and substructure similarity, outperforming existing models on multiple benchmarks.

APOSM improves generative small-molecule design by using pairwise preference learning to enhance surrogate model reliability and active candidate selection.

Promera is a generative model for biomolecular structure prediction, filtering, and design that improves binder filtering and controllable design compared to existing methods.