Discover, rate, and discuss biology papers.

The paper develops a spatial-statistical framework to model cell-type interactions in glioblastoma using CosMx data, revealing patient-specific spatial patterns and their molecular correlates.

The paper develops a graph neural network that combines ligand molecular graphs with protein language model embeddings to predict GPCR ligand activity, showing improved performance over baseline models.

EventHorizon is a foundation model for clinical flow cytometry that uses self-supervised learning to generate embeddings for diagnostic use, achieving high accuracy in identifying genetic abnormalities.

This paper introduces a context-aware framework for DNA methylation biomarker discovery, showing it identifies context-dependent candidate regions and validates them with PCR assays in independent cohorts.

The paper introduces onsite, a framework for estimating false localization rates in phosphoproteomics, showing pyLucXor achieves high accuracy and localization count.

The paper introduces scProfiterole, a framework for clustering single-cell proteomic data using graph contrastive learning with spectral filters, showing improved cell type identification.

This paper introduces a human-in-the-loop cell tracking framework that integrates human feedback during tracking to reduce correction needs and improve track quality.

This paper develops a machine learning model to classify riboswitch performance for detecting Coxsackievirus B3, showing strong accuracy and computational efficiency.

InSTability identifies seed-sensitive clustering regions in spatial transcriptomics data, revealing instability patterns and their impact on downstream analyses.

qPyCR is a Python tool for analyzing qPCR data that computes Cq values, performs background subtraction, and provides global fitting to quantify template abundance and assess reaction quality.

This paper evaluates genomic foundation models using splice-variant perturbations, finding they match task-specific networks and generalize across mutation types.

The paper introduces fastEmu, a scalable method for estimating differential abundance in microbial metagenomics data, achieving faster runtime with minimal impact on error rates.

This paper introduces a generative AI framework for drug discovery that efficiently navigates large chemical spaces while ensuring synthetic feasibility and functional success.

The paper predicts antibiotic resistance mutations in Mycobacterium tuberculosis by integrating structural context with mutation data, finding that structural clustering improves prediction accuracy.

The paper introduces a structured-evidence framework for predicting bacteriophage-host interactions using a large language model, achieving high accuracy and enabling interpretable inference.

DEPICT prioritizes therapies within tumor contexts using deep learning, showing effectiveness across different tumor states and spatial heterogeneity.

This paper presents a statistical framework for correcting SARS-CoV-2 genomic sequences using phylogenetic priors, improving call rate and accuracy in challenging regions.

PRISM estimates sample-specific correlation networks for cross-sectional and longitudinal omics data, improving accuracy and uncertainty quantification over existing methods.

A Biolink-compliant graph (∼15 million nodes, ∼113 million edges) adds RefMet and LIPID MAPS metabolite and lipid classifications, plus polygenic score and clinical data element entities, to Translator content.

This study benchmarks reference-based metagenomic tools for species-level detection in closely related bacterial families, finding metapresence and sylph perform best.