Bioinformatics and Genomic Networks

The paper introduces a tool for visualizing up to four omics datasets on organism-scale metabolic network diagrams using interactive web-based charts.

G2PDeep-v2 is a web-based deep learning platform for phenotype prediction and biomarker discovery using multi-omics data across organisms, offering model training and visualization tools.

The paper introduces pyPAGE, an improved gene-set enrichment analysis tool, and applies it to uncover AD-associated regulons and their relationship to disease pathology.

AutoFocus identifies multi-omic disease-associated modules across biological scales using a hierarchical framework, applied to type 2 diabetes and Alzheimer's datasets.

This paper develops a graph curvature-based pipeline to identify immune checkpoint response biomarkers from tumor RNA-sequencing data using PPI networks and transfer learning.

This paper introduces a statistical method using Gaussian Graphical Models to construct gene networks in bacteria, demonstrating its effectiveness in uncovering gene functions and interactions across multiple bacterial species.

This paper introduces CCC, a machine learning-based correlation coefficient that detects both linear and nonlinear patterns in gene expression data, outperforming linear-only methods in identifying biologically relevant relationships.

HBIcloud is an online platform that integrates multi-omics tools to simplify complex data analysis for researchers without requiring extensive programming skills.

PICASO integrates single-cell gene expression data with biomedical databases to create networks that compare disease states and identify druggable targets.

This paper generates and evaluates computationally derived hallmarks of aging and cancer using DNA methylation data, showing stronger disease associations at the hallmark level than individual genes.

MetaFun performs functional meta-analysis of transcriptomic datasets to uncover sex differences across multiple omics studies.

This paper proposes a graph neural network approach for phenotype prediction that incorporates protein-protein interactions, outperforming existing methods in Alzheimer's disease prediction.

funkea provides a scalable Python tool for functional enrichment analysis in genetics using Spark, supporting pathway, cell-type, and tissue enrichment across annotation datasets.

The paper introduces NeEDL, a network medicine-based method for detecting higher-order epistatic interactions in complex diseases, showing improved statistical significance and applicability across eight diseases.

The paper introduces a graph neural network framework that integrates multi-omics data with biological priors to identify biomarkers in Alzheimer's disease.

SmCCNet 2.0 integrates multi-omics data with a phenotype to reconstruct networks specific to that phenotype, offering improved setup flexibility and user experience.

MOGDx integrates multi-omic data using a graph convolutional network to classify heterogeneous diseases, achieving state-of-the-art performance and identifying relevant genomic markers.

GenPPi 1.5 improves protein interaction prediction by integrating Random Forest with Reduced Interaction Sampling, enhancing performance in low sequence identity scenarios.

SocialGene creates and leverages knowledge graphs for multi-omics data analysis in genomics and drug discovery, enabling integration and exploration of diverse datasets.

This study identifies key genes, miRNAs, and pathways in cardiac arrest using NGS data and bioinformatics analysis.

This study introduces a hierarchical network-based approach to analyze functional gene interactions within microbial genomes, identifying key subnetworks and functional motifs across diverse environments.

The paper introduces a machine learning model that predicts metabolite associations with KEGG Level 3 pathways, achieving high accuracy and transfer learning to Level 2 categories.

GREMI improves multi-omics disease prediction by integrating biomolecular interactions and provides interpretable module identification.

The paper reconstructs patient-specific gene co-expression networks in lung adenocarcinoma to identify subtypes and survival predictive biomarkers.

This paper introduces laruGL-PPI, a label-aware hierarchical subgraph learning method for protein-protein interaction prediction that improves performance and efficiency by addressing topological shortcuts and computational costs.

The paper develops interpretable neural networks for multi-omics data to predict smoking status, age, and LDL levels, showing improved performance and generalizability across cohorts.

ExpOmics provides a web platform with multi-omics analysis tools for differential expression, co-expression, and functional enrichment, supporting diverse data types and cancer subtype analysis.

This study introduces mosGraphFlow, a graph AI model for analyzing multi-omic data to identify AD-associated biomarkers and signaling pathways, achieving high classification accuracy.

mosGraphGPT is a foundation model for multi-omic signaling graphs trained on cancer data and fine-tuned for Alzheimer's Disease, improving classification accuracy and interpretability.

BEAM integrates multiple omics profiles with multiple clinical outcomes using bootstrap resampling to identify significant associations, outperforming existing methods in simulations and a pediatric leukemia application.