949 papers
STAnalyzer is a transparent, multi-agent framework that automates the end-to-end spatial transcriptomics analysis workflow by leveraging intent-driven orchestration, multimodal self-refinement, and evidence-based cross-validation to transform complex raw data into verifiable biological insights.
The authors present GMIP-PLSR, a Nextflow-based pipeline that integrates GWAS with multi-omics data using Partial Least Squares Regression to overcome multicollinearity issues in existing tools like PoPS, thereby significantly improving gene prioritization and biological insights for complex traits such as NAFLD.
This paper introduces CompBioBench, a novel benchmark of 100 diverse computational biology tasks constructed via synthetic data augmentation and metadata scrambling to enable objective evaluation, demonstrating that leading agentic systems like Codex CLI and Claude Code can achieve high accuracy in solving complex, multi-step biological problems requiring tool use and external resource interaction.
The paper introduces SpecRNA-QA, a lightweight, reference-free method that leverages multi-scale spectral features of inter-nucleotide contact networks to effectively assess global topological coherence in RNA 3D structures, significantly outperforming existing local-geometry and statistical potential-based methods, particularly for large RNAs.
This paper proposes an automated, LLM-assisted framework that mitigates hallucinations in biomedical evidence synthesis by individually screening literature to rigorously quantify scientific consensus through the precise identification of supporting and contradictory evidence.
This paper presents a grid-search framework for calibrating actigraphy sleep detection algorithms that offers a reproducible alternative to manual tuning, demonstrating modest improvements in sleep timing estimation and enhanced handling of within-sleep wakefulness through ensemble methods.
ViralMap is a multi-label deep learning model that leverages ESM-2 representations to predict diverse structural and functional features directly from viral protein sequences, providing a scalable tool to accelerate antigen engineering and vaccine design for emerging pathogens.
gbdraw is a secure, serverless web application and command-line tool developed to generate customizable circular and linear genome diagrams for microbes and organelles directly within the user's browser, eliminating the need for data uploads while supporting both programmatic batch processing and graphical user interface accessibility.
ARACRA is a fully automated, interactive web-based pipeline built on Nextflow and Streamlit that streamlines RNA-seq analysis from raw FASTQ files to transcriptomics Point of Departure (tPoD) calculation, featuring a human-in-the-loop quality control step to facilitate robust chemical risk assessment.
LOCOM2 is a robust and computationally efficient method for differential abundance analysis of microbiome data that improves upon its predecessor by accurately controlling false discovery rates and maximizing sensitivity across diverse and challenging scenarios, including relative-abundance data and unbalanced study designs.
The paper introduces CLONEID, an event-based framework that integrates sparse molecular data with frequent phenotypic observations through time-stamped records to enable longitudinal, context-specific genotype-to-phenotype mapping, as demonstrated in a gastric cancer adaptation study.
This study utilizes multi-organ MRI data from 70,000 individuals to demonstrate that local and global imaging patterns can effectively quantify biological ageing, revealing significant associations with chronic diseases and lifestyle factors while establishing a framework for personalized health risk stratification.
This paper presents a minimal mathematical model driven by inflammation and demyelination that successfully reproduces the relapsing-remitting dynamics of multiple sclerosis through Hopf bifurcation and aligns with experimental data on contrast-enhancing lesions.
This paper presents a data-driven strategy to optimize BitBIRCH clustering parameters for large molecular libraries, demonstrating that specific similarity thresholds and high branching factors, combined with an iterative re-clustering procedure, effectively mitigate issues with singletons and oversized clusters to enhance the algorithm's robustness and usability.
This paper introduces a triangular geometric criterion that quantifies deviations of the HIV-1 capsid from an idealized fullerene lattice, revealing how these structural irregularities influence biophysical properties, cofactor binding, and interfacial frustration to inform future antiviral design and vector engineering.
This paper introduces TPCAV, a novel concept attribution framework that adapts and enhances the TCAV method with PCA-based decorrelation to provide robust, input-agnostic interpretations of diverse genomics deep learning models, enabling the analysis of both traditional DNA motifs and complex biological features like chromatin states and repetitive elements.
This paper introduces the Linearized Compressed Polar Coordinates (LCPC) Transform, a novel algorithm that converts 2D and 3D cell contours into discrete sinusoidal waves to capture spatial context features like chirality, thereby enabling robust quantitative stratification of morphological phenotypes to correlate with treatment resistance.
This paper introduces MultiStateFold (MSFold), a framework that integrates Parallel Tempering into the ESM3 protein language model's token space to overcome single-state prediction biases and accurately generate diverse protein conformations with improved confidence metrics.
This paper proposes an adaptive integration framework that combines heterogeneous foundation models via a lightweight weighting network to predict histologically relevant genes from breast cancer histopathology images, achieving superior accuracy and interpretability compared to individual models and classical ensembling methods when validated against spatial transcriptomics data.
This paper presents a modular framework that integrates Visium spatial transcriptomics with single-cell multiome data to infer spatially resolved regulatory programs in melanoma, revealing localized regulatory dynamics and demonstrating the critical impact of cell-to-spot mapping strategies on downstream stability.