Discover, rate, and discuss biology papers.

vartracker analyzes and visualizes pathogen variants over time, tracking their evolution and classification across longitudinal datasets.

This study shows CHIKV infection transforms monocytes into persistently infected macrophages that drive chronic arthritis through IFN-π/IL-27-STAT1 and NF-κB pathways.

The paper presents PeTriPPI2, a hybrid model for protein-protein interaction prediction that combines sequence and structural features, achieving high accuracy on the Pinder dataset.

A free Meta Quest virtual reality app harmonizes CODEX, Visium, Xenium, volumetric immunofluorescence and electron microscopy data from 5 organs into 4 scale levels using the Human Reference Atlas.

The paper introduces a method to time copy-number amplification events in cancer genomes, revealing that whole-genome duplication (WGD) enables bursts of oncogene amplification.

ProxiNet transfers spatially learned cellular proximity from spatial transcriptomics to dissociated single-cell transcriptomes, revealing tissue organization and age-related changes in Alzheimer's.

This paper develops an unsupervised pipeline to predict viral fitness using sequence data and finds that protein alignment, not model size, is key for accurate prediction.

This paper uses a multi-model consensus framework to identify a dual-interferon gene signature in ischemic stroke using single-cell RNA sequencing data from a mouse model.

BatchVaria evaluates batch correction methods by comparing variance changes across configurations using TCGA breast cancer RNA-seq data.

The paper evaluates clustering methods for multivariate longitudinal data using a real-world eCDF-Copula resampling framework to address missing data and improve benchmarking.

The paper introduces MGM2, a multimodal foundation model for microbial communities that predicts responses to interventions and interprets community changes using shared representations of molecular identity and context.

The paper develops a scaffold-constrained generative model for protein design, showing it produces high-quality candidates with better ranking scores than previous methods.

This study identifies information leakage in enzyme-substrate prediction models and datasets, showing performance drops when leakage is removed.

This paper evaluates synthetic data generation methods using random projection and multivariate similarity assessment in low-dimensional settings to address small-sample challenges in biomedical research.

This study introduces a robust cooperative learning method for multiview regression that reduces outlier influence while preserving view information sharing, showing improved predictive performance in labor onset prediction.

This study analyzes the evolution of Achromobacter ruhlandii over 30 years, identifying genomic features associated with epidemic potential and chronic infections.

StrucNS predicts protein stability using network topology features, outperforming existing models and revealing key topological predictors of stability.

This paper evaluates AlphaFold3's ability to predict protein-RNA interaction specificity using omics data and structural information, highlighting both its potential and limitations.

This study uses molecular dynamics simulations to analyze thermodynamic effects of 22 cancer hotspot mutations on nucleosome-DNA binding stability across 10 oncogene families, revealing gene-family-dependent trends.

BEACON improves demultiplexing accuracy in single-cell RNA sequencing by learning background counts, outperforming existing methods and enabling new biological insights.