Bioinformatics and Genomic Networks

This paper introduces OntoVAE, a VAE that incorporates ontologies to predict genetic and drug-induced perturbations using bulk and single-cell transcriptomic data.

MCPNet constructs high-quality gene networks efficiently and scalably using a novel maximum-capacity-path metric, outperforming existing methods in speed and accuracy.

networkGWAS improves network-based GWAS by using mixed models and permutation schemes to detect genetic associations with better statistical control.

The paper applies transfer learning to predict network biology features across different biological contexts.

Seidr is a toolkit for gene regulatory and co-expression network inference that reduces algorithmic bias and improves robustness across species and conditions.

The paper analyzes a PPI network for root development in rice to identify hub proteins and sub-network modules, revealing 75 novel candidate proteins and 6 sub-modules.

This paper introduces GraNA, a deep learning framework for supervised biological network alignment that improves functional annotation transfer between species.

The paper introduces a positive statistical benchmark to assess network agreement, showing that observed overlaps are often close to the best-case scenario despite limited shared interactions.

The paper introduces a fuzzy semantic scoring function to assess protein binding affinity using Gene Ontology graphs and applies it to a human PPI network of 180 million potential interactions.

Gemini integrates hundreds of gene networks using memory-efficient high-order pooling, improving protein function prediction performance.

The paper describes a standardized approach to represent Inherited Metabolic Disorders in WikiPathways, highlights limitations in machine-readable disease information, and introduces methods for data curation and analysis using SPARQL queries.

The paper introduces a Python package for constructing context-specific biological networks using omics data and demonstrates its application in yeast fermentation.

Pathformer integrates multi-omics data using a pathway-informed Transformer to improve cancer diagnosis and prognosis prediction.

The paper introduces a novel composite selection index, the C-Index, to identify significant gene pathways and a 4-gene biomarker signature for early diagnosis of NSCLC using topological network analysis.

The paper introduces mantra, a method to estimate metabolic reaction activity changes from untargeted metabolomics data, demonstrating its utility in identifying biomarkers and enabling multi-omics integration.

This paper introduces a multi-network gene prioritization method for Alzheimer's Disease that complements mQTL-based approaches, showing significant concordance in prioritizing risk genes.

This paper identifies factors related to lymph node metastasis in breast cancer using differential modular and mutational structural analysis of protein networks.

This study introduces a graph-based method to infer temporal signaling networks from high-resolution phosphoproteomics data, improving the identification of signaling-relevant interactions.

The paper introduces PIONEER, a deep learning framework for predicting protein-protein interfaces, and shows disease mutations are enriched in these interfaces, identifying oncoPPIs linked to cancer survival and drug responses.

MultiCens identifies inter-tissue molecular mediators by analyzing multi-layer network centrality, revealing genes involved in hormone signaling and Alzheimer's disease brain regions.

This study uses multi-omics data from grass hybrids to identify gene and metabolite networks associated with agronomic traits, finding conserved hubs but limited predictive power of network features.

This paper introduces a framework to integrate omics data types and generate interpretable embeddings by addressing regularization challenges in deep generative models.

This paper introduces PS-SNC, a method for detecting protein complexes from multiple state-specific signed PPI networks, showing improved performance over existing methods.

This paper accelerates AlphaFold2-based PPI network prediction by 40x and reduces disk space by 4000x for 1000 proteins using a new protocol.

bootRanges generates null genomic ranges for hypothesis testing, improving reliability by preserving genomic correlation structure through block bootstrap methods.

piTracer identifies synergistic drug targets by analyzing metabolomics data to reconstruct molecular cascades and predict combination therapies.

MOGAT improves multi-omics integration for cancer subtype prediction by addressing limitations in existing graph neural network approaches.

The paper introduces the hidecan R package for visualizing GWAS and differential expression results along with manually curated candidate genes.

SUPREME predicts cancer subtypes using multiomics data and graph convolutions, outperforming existing methods and showing significant survival differences.

aPEAR provides an R package for automated visualization of pathway enrichment networks by clustering similar pathways into meaningful biological themes.