Bioinformatics and Genomic Networks

This paper introduces MIDAA, a framework for multi-omic data integration using deep learning and biological principles, showing it identifies interpretable and biologically relevant patterns better than existing methods.

This study identifies shared molecular mechanisms between schizophrenia and somatic disorders using a computational framework based on multi-rank non-negative matrix factorization.

TOTEM calculates tissue-specific gene enrichment from user gene lists using single-cell expression atlases, enabling analysis of gene function in specific tissues.

The paper develops two novel knowledge graph embedding algorithms, DLemb and BioKG2Vec, which outperform existing methods in predicting gene-disease associations, particularly for diseases with limited information.

This paper introduces a gene expression transfer learning model that enables cross-species gene mapping using reactome profiles, improving functional gene understanding and drug response prediction.

This paper introduces GTKM, a method for visualizing gene expression data in glioblastoma, showing it identifies gene patterns linked to clinical outcomes and subtypes.

The paper introduces G-S-M, a framework for integrative feature selection that combines machine learning and prior knowledge to identify discriminative feature groups for medical applications.

The paper investigates the role of immediate-early genes (IEGs) in genetic networks and identifies MARK4 as a potential therapeutic target for Alzheimer's disease using network analysis and GWAS data.

This paper introduces PPITrans, a Transformer-based model for protein-protein interaction prediction that outperforms existing methods on unseen species.

PathIntegrate integrates multi-omics data using pathway-based modeling to identify important pathways and molecules contributing to outcomes, demonstrated on COPD and COVID-19 datasets.

This study examines protein-protein interaction networks, validating power laws, identifying network compression during evolution, and exploring hub connectivity patterns.

The paper identifies drug contraindications in comorbid diseases by analyzing drug target networks and their association with disease-specific protein interaction networks and pathways.

This study identifies gene modules associated with melanoma immunotherapy response using dynamic Ollivier-Ricci curvature analysis of gene expression data.

This paper applies Ricci flow to model network rewiring during cellular differentiation using single-cell RNA-seq data, showing that network entropy and Ricci curvature provide complementary insights.

The paper introduces TkNA, a causal-inference framework for analyzing host-microbiota multi-omics data to identify master regulators of interactions.

playOmics is an open-source R package for multi-omics analysis that enables biomarker discovery and interpretable predictions through logistic regression models and visualization tools.

NetActivity improves gene set activity scores by using interpretable autoencoders, showing better consistency and biological relevance in prostate cancer analysis.

The paper develops GeneRAIN models trained on bulk RNA-seq data to predict gene attributes, showing they capture biological information beyond gene expression and outperform existing models.

MOCAT improves multi-omics data integration using auxiliary classifiers and attention mechanisms, achieving better classification and biomarker discovery than existing methods.

GDOP predicts drug 'on-target' pathways using graph convolutional networks, achieving high AUC-ROC and Top10 accuracy on LINCS data.

The paper introduces GRSA, a generalized reporter score-based method for multi-group and longitudinal omics data, showing increased sensitivity and applied it to microbiome, transcriptome, and metabolome data.

The paper visualizes key features of cellular responses to two radiation treatments using network-based tools and statistical analysis of transcriptomic data.

The paper introduces a deep learning framework called DepGPS to model tumor vulnerabilities using graph neural networks and transformers, showing improved prediction of context-specific vulnerabilities and utility in identifying synthetic lethal genes.

The paper measures gene expression responses to drugs in mouse and rat genomes across organs and finds that reactomes do not correlate with structural similarity, proposing a new cross-species mapping approach based on expression patterns.

This paper introduces a model-agnostic method to discover gene-phenotype relationships and infer gene networks using in silico gene perturbation, showing improved prognostic performance over conventional biomarkers.

The paper introduces transomics2cytoscape, an R package for automated 2.5D visualization of trans-omics networks, enabling rapid and dynamic interpretation of multi-omics data.

gget elm enables fast, scalable querying of Eukaryotic Linear Motifs from the ELM database using local computations.

CryptoCEN, a co-expression network for Cryptococcus neoformans, identifies 13 novel DNA damage repair genes with 100% predictive accuracy.

This study evaluates single-sample network inference methods for cancer subtyping using bulk RNA-seq data from cancer cell lines.