Discover, rate, and discuss biology preprints.

BioGraphX-RNA predicts RNA subcellular localization using physicochemical graph encoding, showing competitive performance and interpretability across mRNA, miRNA, and lncRNA.

siProGenA generates siRNA candidates by proposing positions and generating guide sequences, achieving high Hit@1 and Hit@5 scores in controlled evaluations.

The paper reports on a CAR-T therapy binder design competition where their BAGEL-CAR designs achieved high enrichment in experimental screening, highlighting the importance of validating design pipeline outputs.

The paper analyzes haplotype architecture of human antiviral restriction-factor loci across populations and finds reduced differentiation and private haplotype effects compared to genomic controls.

This study evaluates how face-to-BMI Vision Transformer models perform across diverse human populations, finding that training on population-specific data improves accuracy, while global training data enhances performance in underrepresented groups.

The paper evaluates the reliability of confidence measures from single-cell models on new data and shows that raw confidence scores are unreliable, requiring recalibration with target-specific labels.

This paper introduces a framework to improve survival prediction in spatial proteomics by incorporating spatially adjusted protein summaries into Cox models, showing better performance in simulations and applications to breast cancer data.

K-MARVEL is a computational tool that accurately identifies antimicrobial resistance genes and mutations from short and long-read sequencing data, outperforming existing methods in speed and accuracy.

The paper investigates whether functional frustration in proteins is an evolutionary adaptation or a byproduct of fold architecture, finding that frustration hotspots are inherent physical constraints co-opted for function.

PalmLab curates and analyzes palmitoylation data from human and mouse proteomes, providing tools for functional interrogation and cross-cohort comparisons.

The paper predicts cancer treatment response using a MIL-attention framework that analyzes macrophage states from single-cell RNA data, showing improved performance over existing methods.

spatialMET provides a scalable, open-source framework for end-to-end spatial metabolomics analysis, identifying spatial domains and differential metabolites in mouse cancer data.

Dory identifies differential spatial patterns in chromatin tracing data by analyzing structural differences between groups, linking changes to gene regulation.

This paper evaluates AlphaFold3's ability to predict amyloid structures using three datasets, finding it performs better on known fibrillar structures but struggles with non-fibrillar and short fragments.

HiC-LEGO reconstructs high-resolution 3D genomes from Hi-C data, preserving chromatin organization and regulatory interactions at kilobase resolution.

This paper describes an AI semantics workflow using LLM agents to integrate multimodal biomedical data through ontologies and knowledge graphs.

Bio-Babel reconstructs computational biology software in new ecosystems, enabling agent-callable usage and revealing pancreatic differentiation defects under SWI/SNF loss.

The paper introduces a benchmark for rare-disease gene prioritization using 1,047 cases and a recipe for building a PMC article index, without comparing tools.

The paper introduces a sparse feature circuit framework to identify causal features in ESM-2 for zero-shot mutation effect prediction, showing that shared circuits explain mutation effects through 3D contact residues.

DAQplugin provides real-time deep learning-based validation of cryo-EM protein models in ChimeraX, identifying residue errors and offering correction guidance.