Discover, rate, and discuss biology preprints.

The paper introduces MetaSBT, a tool for classifying microbial genomes and MAGs, and presents databases of over 190,000 viral genomes, including many previously unknown species clusters.

plsMD improves plasmid reconstruction from short-read assemblies, outperforming existing tools in recall, precision, and F1 scores on benchmark and novel datasets.

This study investigates how lithocholic acid modulates GPBAR1 activation and G protein engagement through molecular dynamics simulations and structural analysis.

This paper develops a framework combining machine learning and metabolic modeling to predict synergistic cancer therapies influenced by microbiome composition in colorectal cancer.

This study evaluates how large language models perform in-class learning for antibody classification using biological sequences, finding that few-shot prompting with diverse demonstrations achieves competitive results.

This paper shows that focusing on complementarity-determining regions (CDRs) in antibody sequences improves binding affinity prediction using region-aware pretraining strategies.

LncPNdeep classifies long non-coding RNAs using a deep learning model that combines nucleotide and peptide embeddings, achieving high accuracy in human transcript data.

This study benchmarks cell-type deconvolution methods across cross-platform transcriptomic data, finding that log-normal regression methods like SpatialDecon perform most reliably.

The paper quantifies numerical variability in MRI analyses of Parkinson's disease and shows it can significantly affect statistical conclusions and p-values.

This paper introduces a framework for comparing embedding spaces in molecular biology, demonstrating its utility in pre-filtering machine learning tasks and identifying differential patterns across embeddings.

This paper introduces vhPPIpred, a machine learning method for predicting virus-human PPIs that outperforms existing methods and provides a benchmark dataset.

GenomeProt integrates genomics, transcriptomics, and proteomics to characterise proteoforms, discovering novel proteins and variant-containing peptides in human brain and melanoma samples.

This paper introduces a guided AI framework for automating data harmonization to the OMOP Common Data Model, achieving high agreement with human experts while enabling scalable and efficient data integration.

DuplexFM uses miRNA interaction data to predict siRNA efficacy by integrating multiple evidence sources and transfer learning, achieving high accuracy across multiple test sets.

This study shows that filtering genomes based on coherent genotype-phenotype relationships improves cross-dataset prediction of microbial carbon utilisation, outperforming larger but less coherent datasets.

TBpop integrates genomic variation, population genetics, and metadata for Mycobacterium tuberculosis strains from China to enable comprehensive analysis of genetic diversity and evolution.

STR-PG provides a scalable framework for short-read STR genotyping by decoupling locus representation from allele content, reducing computational costs while maintaining accuracy.

fourSynergy combines multiple 4C-seq tools using gradient-free optimization to improve interaction calling performance across datasets.

A fine-tuned ProtT5 protein language model predicts per-residue energetic frustration from sequence (Pearson r 0.86 on unseen CATH topologies) and profiles the human proteome in ~17 minutes on one GPU.