Discover, rate, and discuss biology preprints.

This paper introduces a fast method to predict protein contact maps from sequences, achieving high accuracy in 110 milliseconds.

The paper systematically extracts and catalogs acylcarnitine metabolites from multiple repositories, identifying previously unknown carnitines and providing a resource for further metabolic research.

EnzyGen2 co-designs protein sequences and structures with ligand-guided functionality, outperforming existing methods in in silico benchmarks and generating active enzymes with high novelty.

The paper curates and harmonizes celiac disease gut microbiome sequencing data into a repository to enable large-scale analysis and machine learning applications.

The paper introduces BlueSTARR, a predictive modeling framework trained on whole-genome STARR-seq data to assess variant effects on regulatory functions, revealing purifying selection against loss-of-function and gain-of-function variants.

The paper develops SLiMMine, a deep learning method to predict short linear motifs in the human proteome with reduced false positives and the ability to discover novel motifs.

The paper computationally designs a GluN1 peptide mimetic to neutralize autoantibodies in anti-NMDAR encephalitis and shows strong predicted binding affinity.

Panmap efficiently aligns, genotypes, and places reads on large pangenomes using phylogenetic compression, enabling rapid analysis of up to 8 million genomes.

The paper introduces Longevity-LLM, a foundation model fine-tuned on aging-related data, achieving high performance in age prediction and proteomic profile generation across multiple modalities.

Cellector detects rare foreign genotype cells in scRNAseq data, showing accuracy down to 0.05% microchimeric cells.

This paper introduces a symmetric self-play framework for protein inverse folding that improves sequence design self-consistency by decoupling structural objectives.

This paper presents an evolutionary algorithm framework combining generative AI and virtual screening to efficiently explore large chemical spaces and identify novel drug candidates.

This study investigates the evolutionary history of the TLR2 cavity in vertebrates and invertebrates using AI protein structure predictions, showing its ancestral origin and convergent evolution in different species.

scSAGA improves multimodal single-cell data integration by preserving geometry and scaling efficiently, outperforming existing methods on various datasets.

The paper classifies over 542,000 Swiss-Prot protein structure predictions into ECOD domains, expanding domain coverage and revealing novel evolutionary groups.

The paper introduces MES, a metric to evaluate variant effect predictors and MAVEs based on clinical evidence yield, showing discrepancies with AUROC.

ClumPyCells corrects cell size biases in spatial -omics data to accurately measure cell and marker aggregation in tissues.

The paper introduces CytoTable, a software package that harmonizes single-cell image-based profiling data from different tools, enabling reproducible and scalable data integration.

The paper develops an EEG-based brain age clock using machine learning to predict chronological age and assess brain aging, showing a decrease in brain age with intervention.