Bioinformatics and Genomic Networks

Analyzing associations and higher-order effects in multi-omics data with double machine learning

The paper introduces ROMY, a framework for analyzing multi-omics data with robust association testing, variance-covariance effects, and interaction testing using double machine learning.

An Integrative Multi-Omics Random Forest Framework for Robust Biomarker Discovery

This paper introduces a multivariate random forest framework for multi-omics biomarker discovery, showing it outperforms existing methods in identifying biologically relevant biomarkers and pathways.

GeDi: Simplifying Gene Set Distances for Enhanced Omics Interpretation in R/Bioconductor

GeDi streamlines functional enrichment results by clustering gene sets and integrating PPI data, improving interpretation and hypothesis generation.

LaCONIC: A Label-Aware and Graph-Guided Contrastive Multi-Omics Collaborative Learning Model for Cancer Risk Prediction

LaCONIC improves cancer survival prediction by integrating multi-omics data with gene regulatory networks and cancer subtypes, achieving better performance and interpretability.

Prior knowledge informs graph neural networks to improve phenotype prediction from proteomics

The paper develops a graph neural network framework that integrates biological knowledge to predict phenotypes from proteomics data, outperforming linear models and other architectures.

PathWeigh II: Graph Based Belief Propagation for Pathway Activity Analysis

PathWeigh II improves pathway activity analysis by using graph decomposition and belief propagation to handle feedback loops and integrate gene-level evidence.

Characterizing drug activity with sensitive interactomes in human living cells

The paper introduces a method to identify drug-sensitive protein-protein interactions in live cells using ERK1 as a case study, showing how inhibitory molecules affect these interactions.

A Practical Resource for Multi-Omics Data Integration in Microbial Systems

This paper introduces an R-based workflow for integrating microbial multi-omics data, enabling analysis of transcriptomic, proteomic, and metabolomic datasets and generating pathway-level insights.

High-Quality Predicted Pathway Annotations Greatly Improve Pathway Enrichment Analysis of Metabolomics Datasets

The paper improves pathway enrichment analysis of metabolomics datasets by generating high-quality predicted metabolite-pathway annotations, increasing the number of detected enriched pathways by 8-fold.

OmniPath: integrated knowledgebase for multi-omics analysis

OmniPath integrates molecular knowledge from 168 resources to support multi-omics analysis, offering curated data, predictions, and tools for causal modeling across bulk, single-cell, and spatial data.

Model-based Standardization of Correlation Coefficients Improves Multi-Omic Clustering and Biological Signal Discovery

The paper introduces a method to standardize correlation coefficients across batches in multi-omic data, improving clustering and biological signal discovery by removing batch-specific biases.

BioPrediction-PPI: Simplifying the Prediction of Protein-Protein Interactions through Artificial Intelligence

BioPrediction-PPI is an end-to-end machine learning framework for predicting protein-protein interactions without deep learning, offering interpretability and competitive performance across multiple datasets.

PLAID: ultrafast single-sample gene set enrichment scoring

PLAID provides an ultrafast and memory-efficient gene set enrichment method for single-sample analysis across transcriptomics and proteomics data, outperforming existing approaches.

Proteome-wide in silico screening for human protein-protein interactions

The paper develops a computational pipeline to predict human protein-protein interactions, identifying 16,000 high-confidence interactions, many previously unknown or structurally unresolved.

A critical evaluation of Gene Ontology priors in biologically-informed neural networks

This study evaluates the impact of Gene Ontology priors in biologically-informed neural networks using RNA-seq data, finding limited performance improvement and interpretability beyond predefined gene sets.

SALVE: prediction of interorgan communication with transcriptome latent space representation

SALVE predicts interorgan communication by analyzing RNA-seq data to link secretome-encoding transcripts with gene modules in distal organs, identifying new candidate organokines and their signaling mechanisms.

Uncovering biological patterns across studies through automated large-scale reanalyses of public transcriptomic data

UORCA automates large-scale reanalysis of public transcriptomic data to identify biological patterns and generate hypotheses for drug design.

SynOmics: Integrating Multi-omics Data Through Feature Interaction Networks

SynOmics improves multi-omics integration by modeling feature interactions through a graph convolutional network, outperforming existing methods in biomedical classification tasks.

An adversarial scheme for integrating multi-modal data on protein function

The paper introduces MIRAGE, a multi-modal generative model that integrates protein sequence, interaction, and localization data to improve function prediction and module detection.

DeSciDe: A tool for unbiased literature searching and gene list cu-ration unveils a new role for the acidic patch mutation H2A E92K

DeSciDe ranks gene lists using precedence and connectivity metrics to identify novel biological insights, revealing a new loss of function role for the H2A E92K mutation.

Genetic Mapping of All Human Paralog Pairs to Characterize Synthetic Lethality and Buffering

This study screens all human paralog pairs to identify synthetic lethal interactions and finds that their strength depends on shared protein interaction networks and cellular context.

Natural language processing of gene descriptions for overrepresentation analysis with GeneTEA

GeneTEA uses natural language processing to analyze gene descriptions and improve overrepresentation analysis by creating a de novo gene set database that better controls false discovery.

Quantum Deep Learning Pipeline for Next Generation Network Biology

The paper uses quantum optimization to identify biologically relevant modules in latent representations of omics data from human tissues.

Analysis of intracellular and intercellular crosstalk from omics data.

The paper introduces Ulisse, a method to analyze altered intracellular and intercellular crosstalk from omics data, applied to triple negative breast cancer using single-cell RNA sequencing.

COSIME: Cooperative multi-view integration with Scalable and Interpretable Model Explainer

COSIME integrates multi-omics data to predict Alzheimer's disease phenotypes, improving accuracy and interpretability by analyzing feature interactions across data views.

GRASP: Gene-relation adaptive soft prompt for scalable and generalizable gene network inference with large language models

GRASP improves gene network inference using LLMs by adapting prompts to gene pairs, outperforming other strategies and recovering unannotated interactions.

Effects of Spearman's and Pearson's correlations on construction of cancer regulatory networks and biomarker selection

This study compares Spearman's and Pearson's correlations in cancer network construction and biomarker selection, finding Spearman identifies more survival-related hubs and enriched cancer-related GO terms.

Molecular exploration of host-pathogen interactions in severe Pseudomonas aeruginosa infection through a multi-level data integration approach

The paper integrates multi-omics data to explore host-pathogen interactions in severe Pseudomonas aeruginosa infection, identifying key molecular mechanisms and interactions.

Protein-protein interaction priors shape biologically coherent latent spaces for causally concordant cross-omic translation

This paper introduces a PPI prior to guide autoencoder embeddings, improving biological coherence and downstream task performance in multi-omic data.

panomiX: Investigating Mechanisms Of Trait Emergence Through Multi-Omics Data Integration

panomiX integrates multi-omics data to identify molecular interactions and trait-related networks in tomato under heat stress.