Bioinformatics and Genomic Networks

Reassessing the modularity of gene co-expression networks using the Stochastic Block Model

This study uses the stochastic block model to analyze gene co-expression networks in Drosophila, finding more complex structures than traditional modular models.

INTREPPPID - An Orthologue-Informed Quintuplet Network for Cross-Species Prediction of Protein-Protein Interaction

INTREPPPID improves cross-species protein-protein interaction prediction using orthologue-informed neural networks and outperforms existing methods on evaluation datasets.

Unveiling Hidden Connections in Omics Data via pyPARAGON: an Integrative Hybrid Approach for Disease Network Construction

The paper introduces pyPARAGON, a tool for disease network construction using network propagation and graphlets, showing improved accuracy in cancer driver network discovery and patient stratification.

MultiOmicsAgent: Guided extreme gradient-boosted decision trees-based approaches for biomarker-candidate discovery in multi-omics data

MOAgent discovers biomarker candidates in multi-omics data using gradient-boosted decision trees, addressing data challenges and providing accessible analysis tools.

Contrastive Learning for Graph-Based Biological Interaction Discovery: Insights from Oncologic Pathways

This study applies contrastive learning to isomorphic graphs to discover biological interactions in cancer pathways, identifying new connections and central nodes.

Contextual AI models for single-cell protein biology

This paper introduces a geometric deep learning model for context-aware protein representations, improving therapeutic target nomination in immune-related diseases.

MENTOR: Multiplex Embedding of Networks for Team-Based Omics Research

MENTOR is a network-based algorithm that partitions gene sets into functions and identifies biological functions in Populus trichocarpa associated with microbial abundance using supervised and unsupervised learning.

Flexynesis: A deep learning framework for bulk multi-omics data integration for precision oncology and beyond

Flexynesis provides a versatile deep learning framework for integrating bulk multi-omics data, offering usability, adaptability, and benchmarking across diverse datasets.

Co-expression in tissue-specific gene networks links genes in cancer-susceptibility loci to known somatic driver genes

The paper links genes in cancer-susceptibility loci to known somatic driver genes through tissue-specific co-expression networks derived from non-cancer samples.

Modeling causal signal propagation in multi-omic factor space with COSMOS

The paper introduces COSMOS+ to integrate mechanistic prior knowledge with multi-omics data analysis to generate mechanistic hypotheses about disease resistance mechanisms.

PCMD: A Multilevel Comparison Database of Intra- and Cross-species Metabolic Profiling in 530 Plant Species

PCMD provides a multi-level comparative metabolomics database for 530 plant species, enabling species and metabolite comparisons with standardized numbering and analysis tools.

Network-based integrative multi-omics approach reveals biosignatures specific to COVID-19 disease phases.

This paper identifies biosignatures specific to different COVID-19 disease phases through integrative multi-omics network analysis and finds that disease severity correlates with increased biosignature interactions across omics data.

Elucidating the Type 2 Diabetes Regulatory Network: Identification of EGFR as a Key Hub and Novel Drug Candidates

This study identifies EGFR as a key hub in the T2D regulatory network and discovers three novel drug candidates with favorable ADMET properties and strong EGFR binding.

Directional integration and pathway enrichment analysis for multi-omics data

The paper introduces DPM, a directional integration method for multi-omics data that identifies consistent gene and pathway changes across datasets and highlights inconsistent evidence.

A variational autoencoder trained with priors from canonical pathways increases the interpretability of transcriptome data

This study introduces a prior-informed VAE for transcriptome data that improves interpretability by learning latent features aligned with biological pathways.

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection

DualNetGO selects features from PPI networks and protein attributes to predict protein functions, improving Fmax scores across Gene Ontology categories in human and mouse datasets.

DeepGSEA: Explainable Deep Gene Set Enrichment Analysis for Single-cell Transcriptomic Data

DeepGSEA provides an explainable deep learning approach for gene set enrichment analysis in single-cell RNA sequencing data, improving sensitivity and specificity over traditional methods.

Decoding proteome functional information in model organisms using protein language models.

This study compares protein language models and deep learning methods for decoding functional information from proteomes of model organisms, finding language models more precise and informative.

Network-Based Analysis Identifies Targetable Pathways in Comorbid Type II Diabetes and Neuropsychiatric Disorders

The paper identifies shared molecular pathways between Type II Diabetes and neuropsychiatric disorders using a network-based approach, highlighting potential therapeutic targets.

Resource: A Curated Database of Brain-Related Functional Gene Sets (Brain.GMT)

The paper introduces Brain.GMT, a curated database of brain-related gene sets to improve interpretation of neuroscience studies by addressing the limitations of traditional gene ontology databases.

A Computational Approach to Interpreting the Embedding Space of Dimension Reduction

This paper introduces a framework to interpret embedding spaces from dimension reduction by mapping biological functions to structural patterns in two datasets.

Discrete Correlate Summation Clustering of a Dopamine-Angiotensin Network

The paper uses discrete correlate summation clustering to analyze a dopamine-angiotensin protein network defined by Swiss-Prot keywords.

DeEPsnap: human essential gene prediction by integrating multi-omics data

DeEPsnap predicts human essential genes by integrating multi-omics data using a snapshot ensemble deep neural network, achieving high accuracy in cross-validation.

Assessing the impact of transcriptomics data analysis pipelines on downstream functional enrichment results

This study evaluates how different transcriptomics analysis pipelines affect downstream functional enrichment results using FLOP, finding that data filtering significantly impacts gene set correlation.

GOAT: efficient and robust identification of geneset enrichment

GOAT is a permutation-based algorithm for geneset enrichment analysis that outperforms current methods in identifying Gene Ontology terms.

Structural robustness and temporal vulnerability of the starvation-responsive metabolic network in liver of healthy and obese mice

The paper examines how obesity disrupts the temporally ordered metabolic network in the liver during starvation, revealing structural robustness but temporal vulnerability.

Large Scale and Stable Graph Differential Analysis via Multi-Layer Node Embeddings and Ranking

This paper introduces node2vec2rank, a method for graph differential analysis that identifies biologically relevant differences between weighted networks in cancer subtypes and single-cell dynamics.

Network nature of ligand-receptor interactions underlies disease comorbidity in the brain

The paper investigates ligand-receptor interactions (LRIs) in neurological diseases and finds that 96.8% of disease-associated LRIs are interconnected, highlighting their role in disease comorbidity and potential drug targets.

BiomiX, a User-Friendly Bioinformatic Tool for Automatized Multiomics Data Analysis and Integration

BiomiX automates multiomics data analysis and integration, enabling efficient comparison of two cohorts through MOFA and providing interpretable results using literature and clinical data.

Weighted variance component test for the integrative multi-omics analysis of microbiome data

The paper introduces a weighted variance components framework to integrate metagenomic and metabolomic data for pathway analysis, showing improved power while controlling type I error.