Large-Scale Analysis of Disease Pathways in the Human Interactome

  title={Large-Scale Analysis of Disease Pathways in the Human Interactome},
  author={Monica Agrawal and Marinka Zitnik and Jure Leskovec},
Discovering disease pathways, which can be defined as sets of proteins associated with a given disease, is an important problem that has the potential to provide clinically actionable insights for disease diagnosis, prognosis, and treatment. Computational methods aid the discovery by relying on protein-protein interaction (PPI) networks. They start with a few known disease-associated proteins and aim to find the rest of the pathway by exploring the PPI network around the known disease proteins… 

Figures and Tables from this paper

Disease Protein Pathway Discovery using Higher-Order Network Structures
This project will focus on studying higher-order network structures and applying the methods to a PPI network to robustly uncover disease protein pathways to more effectively elucidate disease pathways with similar patterns.
Profiling of Disease-Associated Proteins Neighborhood Networks
An experimental study to understand the interaction between disease-associated proteins and their neighbors, a score metric to capture the reachability of disease- associated proteins via common neighborhood proteins that not necessarily associated with a disease, and a reachability metric to profile diseases based on the connectedness of associated proteinsbased on the number of components and the density of disease proteins in a Disease-associated protein neighborhood network.
Locally Adjust Networks Based on Connectivity and Semantic Similarities for Disease Module Detection
An effective disease module identification method IDMCSS is proposed, where the used human PPI networks are obtained by adding some potential missing interactions from existing PPI Networks, as well as removing some potential incorrect interactions.
Graph Convolutional Networks to explore Drug and Disease Relationships in Biological Networks
This project could potentially be applied to predicting and uncovering previously undiscovered or incompletely identified disease-drug interactions, with the help of learned features, bootstrapping off a relatively smaller number of labeled nodes at the start of training (inductive learning).
Graph embeddings of enriched protein-protein interaction (PPI) networks for identification of disease nodes
The first group to incorporate UniProt features in predicting disease labels on a PPI network and graph algorithms such as GraphSage performs comparably Graph Convolutional Networks are analyzed.
Disease Module Identification Based on Representation Learning of Complex Networks Integrated From GWAS, eQTL Summaries, and Human Interactome
N2V-HC, an algorithm framework aiming to unbiasedly discover the scattered disease modules based on deep representation learning of integrated multi-layer biological networks, is proposed and shown to perform better than existing methods in network module discovery.
Network-based methods for disease-gene prediction
It is demonstrated that connectivity alone is not sufficient to classify disease-related genes, so an extended version of random walks is proposed, named Random Watcher-Walker, which is able to learn rich representations of disease genes (or gene products) features.
Construction of in silico protein-protein interaction networks across different topologies using machine learning
B4PPI, an open-source framework for benchmarking that accounts for a range of biological and statistical pitfalls while facilitating reproducibility, is designed and used to shed light on the impact of network topology and how different algorithms deal with highly connected proteins.
Recent Advances in Network-based Methods for Disease Gene Prediction
A comprehensive and up-to-date review of network-based methods for disease gene prediction and an empirical analysis on 14 state-of-the-art methods are conducted.
Alignment of Protein Interaction Networks and Disease Prediction: A Survey
  • Vishwanath R Anooja Ali
  • Computer Science
    International Journal of Advanced Trends in Computer Science and Engineering
  • 2019
The authors compared the various aligners, the performance evaluation metrics, the common databases used for PPI evaluation and the importance of PPI network in biomedical research.


Corneil and I . Jurisica , Bioinformatics 22 , 974 ( 2006 ) . 20 . N . Pržulj
  • Pacific Symposium on Biocomputing
  • 2016