Bioinformatics and Genomic Networks

ANYI integrates yeast PPI data with sixteen biophysical and regulatory annotations to enable cross-layer interactome analysis.

BiGER is a Bayesian rank aggregation method for meta-analysis of gene lists, handling mixed rankings and missing data with high accuracy.

This study evaluates gene embeddings from large language models and finds that functional descriptions yield high-quality, biologically meaningful representations.

The paper constructs disease maps by integrating omics data with protein network embeddings, identifying more disease-relevant proteins than omics analysis alone.

This study compares p-value and correlation strength for selecting gene pairs in single-cell data, finding p-values more robust for co-expression network estimation and benchmarking.

This paper introduces TEA-GCN, a method for constructing gene co-functional and co-regulatory networks from public RNA-seq data, showing improved performance and cross-species conservation.

The paper evaluates hypergraph embedding methods for clustering metabolic hypergraphs to capture taxonomy-based features, finding that certain methods outperform others.

The paper identifies two gene interaction mechanisms linking ageing and ageing-related diseases using network analysis and machine learning.

MIMIR is a deep learning framework that imputes missing modalities and features in multi-omic data using shared representation learning, outperforming existing methods on pan-cancer data.

This paper introduces a computational method to predict higher-order genetic interactions, demonstrating its effectiveness in yeast by predicting trigenic interactions and uncovering biological functions related to cell growth.

The paper integrates cross-dataset proteomic profiles using differential change directionality, identifying a central hub for doxorubicin treatment and associating proteome clusters with tumor stage.

The paper expands P-NET, a deep learning framework that uses biological pathways for genomic and transcriptomic predictions, showing competitive performance and interpretability.

The paper introduces a geometric framework to represent multi-omic signatures as multidimensional objects, revealing discordance and structural patterns in cancer metabolic circuitries.

This study compares neural network-based and other machine learning models for automated function prediction in yeast using co-expression data and updated Gene Ontology annotations, finding neural networks more accurate and robust.

BioTrendFinder is a web tool that identifies functional drivers in bulk omics data by integrating sample-ranking, statistical results, and functional information for hypothesis-driven and exploratory analysis.

This paper introduces a residual-ratio framework to audit transcriptomic gene signatures by quantifying their independence from background expression structure, showing it discriminates biological signatures from random gene sets across multiple cancer types.

The paper maps the human protein interactome onto a hyperbolic representation to analyze how intrinsic disorder and structure-mediated interactions influence network organization and molecular functions.

The paper integrates three computational methods to predict E. coli protein-protein interactions and functional networks, identifying over 20K high-confidence interactions.

GMIP-PLSR improves GWAS gene prioritization by integrating multi-omics data using PLSR to address multicollinearity, outperforming PoPS in NAFLD case studies.

This paper benchmarks 20 computational methods for multi-omics biomarker discovery in cancer using real and simulated datasets, finding that DeePathNet and Deep-KEGG perform best.

GATSBI improves protein embeddings by using biologically relevant data splits, showing better performance for understudied proteins in various tasks.

CLEAR improves gene set enrichment analysis by jointly modeling gene sets with continuous statistics, reducing redundancy and improving sensitivity.

CyNET analyzes immune system networks to identify functional hubs and maturation patterns across age groups using single-cell transcriptomics.

The paper introduces a method using Krylov subspace trajectories for analyzing biological networks, demonstrating its application in community detection and perturbation analysis on the C. elegans neural network.

The paper introduces GO Big, a new Gene Ontology subset for plants that improves gene function prediction by focusing on taxon-specific biological terms.

WayFindR converts pathway data into graph structures to analyze feedback loops, revealing their underrepresentation in curated databases.

The paper shows common and rare genetic variants converge on shared molecular networks for most human traits, influenced by heritability and tissue specificity.

Triad-LMF improves cancer subtype classification by integrating multi-omics data through hierarchical low-rank multimodal fusion, showing better performance and interpretability.

This paper introduces PerturbGraph, a graph neural network framework that predicts transcriptional responses to unseen gene perturbations by integrating biological priors, outperforming existing methods on benchmark datasets.

This paper introduces a graph-based machine learning approach to predict gene perturbation effects on molecular phenotypes using existing experimental data and biological networks.