Bioinformatics and Genomic Networks

Rank-based integration identifies convergent disease mechanisms across omics

ORBIT integrates omics data across studies and layers to identify convergent disease mechanisms by prioritizing concordant signals using rank-based methods.

Virus-human protein-protein interactions predict viral phenotypes

This study shows that predicted virus-human protein-protein interactions can better predict viral phenotypes like infectivity and virulence than genomic or sequence-based methods.

BFWalk: backtrack-free network propagation with in-degree normalization

BFWalk is a network propagation algorithm that avoids bias toward highly connected proteins, outperforming existing methods in identifying phenotype-associated genes across four human diseases.

ProcessNets: Towards an efficient approach for ensemble analysis of biological networks

ProcessNets efficiently analyzes ensembles of biological networks by leveraging their similarities, achieving significant space and time savings in network property computations.

Quantitative machine learning of protein interactions reveals the multiscale organization and molecular syntax of signaling networks

The paper develops a quantitative statistical mechanical model to predict protein interactions from sequences and uses it to analyze the structure and organization of human signaling networks.

BiomiX 3.0: A user-friendly platform for democratized multi-omics integration with graph-based learning.

BiomiX 3.0 is a multi-omics integration platform that introduces PRAMIGO, a supervised heterogeneous graph transformer, and benchmarks five methods on CLL and PTB datasets, showing that no single method captures all biologically relevant signals.

HiMaLAYAS: enrichment-based annotation and visualization of hierarchically clustered matrices

HiMaLAYAS, a Python package, cuts dendrograms, tests clusters for categorical annotation enrichment (hypergeometric, Benjamini-Hochberg FDR), and renders significant annotations beside clustered heatmaps in one workflow.

Biologically Informed Multi-Omics Integration Reveals Clinically Meaningful Patient Representations in Acute Myeloid Leukemia

This paper introduces SurvMOCA-GNN, a multi-omics integration framework that improves patient stratification in AML by incorporating biological networks and clinical data.

BRIDGE-AD reveals Alzheimer's disease effectors through interpretable large-scale omics integration

BRIDGE-AD integrates multimodal AD datasets to prioritize disease effectors, identifying 19 functional clusters and validating SCARB2 as a novel candidate.

LoGoPPI enables fast and accurate protein protein interaction mapping at scale

LoGoPPI infers protein-protein interactions from sequence using a combination of global and local representations, achieving faster inference than state-of-the-art models.

fastACCORD enables ultrahigh-dimensional partial correlation modeling for multi-omic data integration

fastACCORD enables efficient ultrahigh-dimensional partial correlation modeling for multi-omic data integration, revealing cancer-specific methylation-expression dependencies.

From mice to humans: A multi-omic predictive framework for translational immunology

This paper develops a multi-omic framework to predict human immune responses from mouse models across various stimuli, finding that functional modules are more conserved than individual genes.

Modular core network constructed from Escherichia coli transcriptome datasets using a hypergraph-based pan-network approach

The paper constructs a modular core network from Escherichia coli transcriptome datasets using a hypergraph-based pan-network approach, revealing operon-related modules and their dynamic reorganization.

Extracting interpretable single-cell metabolic states with graph-guided representation learning

The paper introduces MeRN, a graph-guided variational autoencoder for learning single-cell metabolic states from transcriptomes, and identifies metabolic drivers in various biological contexts.

A Temporal Interactome Atlas across RNA Viruses reveals Convergent Vulnerabilities for Antiviral Repurposing

The paper builds an InterVir Atlas to map temporal interactome changes across RNA viruses and identifies convergent host vulnerabilities for antiviral drug repurposing.

ANIMA: predicting protein-protein interactions across species

ANIMA predicts protein-protein interactions across species using an AI model trained on diverse animal species, achieving high accuracy in under-researched species.

Structured cross-omics interaction discovery with a triple-graph model

The paper introduces TriGer, a triple-graph model that identifies cross-omics modules by combining cross-layer associations with dependency structures, showing effectiveness in inflammatory bowel disease and colorectal cancer.

Resolving context-specific protein-protein interactomes forbiological discovery and therapeutic target prioritisation

ProtScape learns context-specific protein interactomes across 200 cell types, improving interaction reconstruction and identifying disease-related mechanisms.

Iterative Gene Enrichment Analysis: interpretable networks for human and AI-assisted biological insights

The paper introduces iGEA, a framework that transforms gene enrichment results into interpretable networks, enabling human and AI-assisted biological insights.

Towards reconstruction of the human interactome from positive and negative experimental evidence

Inferring tested-but-undetected pairs from prey lists of 5,530 published interaction screens yields 97 million tested human protein pairs and 18,982,508 non-interactions (≥3 tests) for calibrating screens and predictors.

LiverDCP: A Disease-Cell-Protein Framework for Multi-scale Modeling of Disease Biology

LiverDCP models disease biology by integrating single-cell data and protein interactions to identify disease-risk genes and therapeutic targets.

Tensor-based representation learning for multi-omics integrative clustering and feature discovery

MIA is a tensor-based framework for multi-omics data integration that improves clustering and feature discovery, showing effectiveness in cancer subtype identification.

A shared functional organisation underlies vascular disease remodelling

The paper identifies a reproducible functional organisation in vascular remodelling across diseases, showing coordinated rebalancing of biological functions rather than isolated pathway changes.

ProMaya: a hierarchical universal Deep Learning framework for accurate and interpretable Protein-Protein interaction identification

ProMaya identifies protein-protein interactions using a hierarchical graph-transformer framework, achieving >95% accuracy across nine species and outperforming existing tools by >12%.

Modeling pathway overlap increases accuracy of GWAS gene set enrichment

This paper introduces GSR, a method to adjust for pathway overlap in GWAS gene set enrichment, improving the accuracy of identifying biologically relevant pathways.

WGCNA+: AI-powered WGCNA for Integration of Multi-Omics Data

WGCNA+ extends WGCNA to multi-omics data, enabling cross-omics module analysis and visualization with AI-powered interpretation.

Gene function prediction from bulk coexpression is bounded by cell-type-level signal

This paper shows that gene function prediction from bulk coexpression is limited by cell-type-level resolution rather than fine-grained biochemical function.

The human metabolite - protein interactome reveals a global layer of cellular coordination

The paper maps human metabolite-protein interactions using LIGMAP and shows improved pathway coverage and prediction when combined with STRING and BioLiP2.

geneslator: an R package for comprehensive gene identifier conversion and annotation

geneslator provides a unified R package for gene identifier conversion, ortholog mapping, and pathway annotation across eight species, improving data integration and cross-species analysis.

Knowledge-Driven Interpretable Neural Networks for Mechanistic Insight

The paper introduces a knowledge-driven framework that models biological interactions in omics data using pathway graphs, enabling interpretable mechanistic insights into disease progression.