Bioinformatics and Genomic Networks

Evaluation of Gene Set Enrichment Analysis (GSEA) tools highlights the value of single sample approaches over pairwise for robust biological discovery.

This study compares GSEA tools and finds single sample approaches better capture biological distinctions than pairwise methods in cancer recurrence analysis.

Uncovering the domain language of protein function and proteinnetworks using DANSy

This paper introduces DANSy, a method converting proteins into linguistic networks using domain architecture to uncover functional relationships in proteomes, showing it complements traditional interaction networks.

Selecting genes for analysis using historically contingent progress: from RNA changes to protein-protein interactions

The paper uses RNA silencing in C. elegans to prioritize understudied genes by clustering them based on mutual information derived from their functional relatedness and historical research trends, suggesting regulatory links between RNA silencing and other biological processes.

MetaGXplore: Integrating Multi-Omics Data with Graph Convolutional Networks for Pan-cancer Patient Metastasis Identification

MetaGXplore uses graph convolutional networks to predict tumor metastasis likelihood and identify key genes across pan-cancer multi-omics data.

Genomic network analysis characterizes genetic architecture and identifies trait-specific biology

This paper introduces GNA, a framework that uses network modeling on GWAS data to identify genetic architecture and trait-specific biology.

Mondrian Abstraction and Language Model Embeddings for Differential Pathway Analysis

This paper introduces the Mondrian Map, a visualization tool for differential pathway analysis, and demonstrates its application in glioblastoma multiforme to reveal pathway patterns across disease stages.

Dissect mitochondrial activity by transcriptome data with mitology R package

The paper introduces the mitology R package to specifically analyze mitochondrial activity using transcriptomic data, including single-cell and spatial transcriptomics.

DyNDG: Identifying Leukemia-Related Genes based on the Time-Series Dynamical Network by Integrating Differential Genes

DyNDG identifies leukemia-related genes using a dynamic network model integrating time-series differential genes, showing improved accuracy over existing methods.

The Lorenz's side of Gene Set Enrichment Analysis: Similarity and divergences of the Gene Set Enrichment Analysis from the measure of wealth inequality

This paper links Gene Set Enrichment Analysis to the Lorenz curve from economics, showing their statistical relationship and conceptual parallels.

Transcriptomic and multi-scale network analyses reveal key drivers of cardiovascular disease

The paper analyzes gene expression and protein networks in vascular injury models to show similarities with cardiovascular disease mechanisms.

Non Parametric Differential Network Analysis: A Tool for Unveiling Specific Molecular Signatures.

This paper introduces a non-parametric differential network analysis method to identify gender-specific molecular signatures in disease-related gene expression data.

Identification of Potential Hub Genes and Therapeutic Targets in Colorectal Cancer Using Integrated Bioinformatics Approaches

This study identifies potential hub genes and therapeutic targets in colorectal cancer using integrated bioinformatics analyses of gene expression and functional data.

Predicting Prognostic Bidirectional Molecular Signatures Associating Myocardial Infarction and Lung Cancer: An In-Silico Perspective

The paper identifies common molecular signatures between myocardial infarction and lung cancer subtypes, proposes potential therapeutic drugs, and demonstrates predictive models for MI classification.

Systems-level reconstruction of kinase phosphosignaling networks regulating endothelial barrier integrity using temporal data

The paper uses two computational methods to reconstruct kinase phosphosignaling networks regulating endothelial barrier integrity from temporal data.

ICoN: Integration using Co-attention across Biological Networks

ICoN integrates multiple protein-protein association networks using co-attention and denoising to improve downstream tasks like gene module detection and protein function prediction.

Harnessing full-text publications for deep insights into C. elegans and Drosophila connectomes

The paper extracts and analyzes connectivity information from publications to build searchable connectomes for C. elegans and Drosophila using AI and bioinformatics tools.

Machine Learning Approaches for Predicting Virus-Human Protein-Protein Interactions: An Evaluation of Retroviral Interaction Networks

The paper evaluates machine learning models for predicting retroviral-human protein-protein interactions using public databases and feature importance analysis.

Identifying Alzheimer's disease-associated genes using PhenoGeneRanker

This study uses network biology methods to prioritize potential Alzheimer's disease-associated genes by integrating multimodal datasets and applying PhenoGeneRanker.

Transformer-based deep learning integrates multi-omic data with cancer pathways

This paper introduces DeePathNet, a Transformer-based model that integrates cancer pathways with multi-omic data to improve drug response prediction and cancer classification.

gen3DNet: An R Package for Generating 3D Network Models

The paper introduces an R package, gen3DNet, for generating 3D network models from two correlated data objects with shared factors, using non-negative matrix factorization and partial least squares regression.

Protein-protein interaction is a major source of epistasis in genetic interaction networks

The paper shows that genetic interactions correlate with protein-protein interactions in yeast and human genomes, and that GI and PPI networks share overlapping topological features.

Integrating knowledge, omics and AI to develop patient-specific virtual avatars

The paper develops a method to create personalized regulatory networks for cancer patients using PDX models, integrating gene expression data and genetic algorithms with GCNs to predict treatment outcomes.

GPS-Net: discovering prognostic pathway modules based on network regularized kernel learning

GPS-Net identifies prognostic pathway modules using network regularized kernel learning to improve biomarker accuracy and reduce computational complexity in cancer immunotherapy studies.

Evaluation of Bayesian Linear Regression Models for Gene Set Prioritization in Complex Diseases

This study evaluates Bayesian Linear Regression models for gene set prioritization in complex diseases, showing improved performance in identifying T2D-related pathways using multi-trait analysis.

Data driven refinement of gene expression signatures for enrichment analysis

The paper refines gene expression signatures using multi-omics data to improve enrichment analysis by addressing lack of coordinate expression in gene sets.

A single-gene-based AI model to identify core and context-specific essential genes by biological interpretation from pooled genome-wide CRISPR and omics data

The paper develops an AI model to identify core and context-specific essential genes using CRISPR and omics data, finding 3,213 pan-cancer CEGs with 60% overlap to prior studies.

Sample-specific network analysis identifies gene coexpression patterns of immunotherapy response in advanced kidney cancer

Confidence: A Web App for Cross-Platform Differential Gene Expression Analysis, Gene Scoring, and Enrichment Analysis

Confidence is a web app that performs differential gene expression analysis, gene scoring, and enrichment analysis to prioritize genes for further investigation.

Predicting The Pathway Involvement For All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Gene and Genomes

The paper predicts pathway involvement for all KEGG pathway and compound entries using machine learning, achieving higher performance than metabolic pathways alone.

Unified knowledge-driven network inference from omics data

The paper introduces CORNETO, a unified framework for knowledge-driven network inference from omics data, improving performance on biological tasks using simulated and real data.