• Corpus ID: 202577929

Learning interpretable disease self-representations for drug repositioning

@article{Frasca2019LearningID,
  title={Learning interpretable disease self-representations for drug repositioning},
  author={Fabrizio Frasca and Diego Galeano and Guadalupe Gonzalez and Ivan Laponogov and Kirill A. Veselkov and Alberto Paccanaro and Michael M. Bronstein},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.06609}
}
Drug repositioning is an attractive cost-efficient strategy for the development of treatments for human diseases. Here, we propose an interpretable model that learns disease self-representations for drug repositioning. Our self-representation model represents each disease as a linear combination of a few other diseases. We enforce proximity in the learnt representations in a way to preserve the geometric structure of the human phenome network - a domain-specific knowledge that naturally adds… 
1 Citations

Figures and Tables from this paper

Interpretable Drug Target Predictions using Self-Expressiveness
TLDR
Inception, an integrative and interpretable matrix completion model for predicting drug targets, outperforms two state-of-the-art drug target prediction models in all the scenarios, suggesting that Inception could be useful for predicting missing drug target interactions while providing interpretable predictions.

References

SHOWING 1-10 OF 30 REFERENCES
Drug repositioning: a machine-learning approach through data integration
TLDR
This work proposes a novel computational approach to predict drug repositioning based on state-of-the-art machine-learning algorithms that can significantly accelerate the translation into the clinics of known compounds for novel therapeutic uses.
Computational drug repositioning using low-rank matrix approximation and randomized algorithms
TLDR
A drug repositioning recommendation system (DRRS) to predict novel drug indications by integrating related data sources and validated information of drugs and diseases is proposed and improves the prediction accuracy compared with the other state-of-the-art approaches.
PREDICT: a method for inferring novel drug indications with application to personalized medicine
TLDR
A novel method for the large‐scale prediction of drug indications (PREDICT) that can handle both approved drugs and novel molecules and lays the computational foundation for future personalized drug treatments, where gene expression signatures from individual patients would replace the disease‐specific signatures.
Disease gene prediction for molecularly uncharacterized diseases
TLDR
A novel network approach to prioritize gene-disease associations that is able to also predict genes for diseases with no known molecular basis is presented, which uses semi-supervised learning and exploits a measure of similarity between disease phenotypes.
Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm
TLDR
A novel computational method named MBiRW is proposed, which utilizes some comprehensive similarity measures and Bi-Random walk (BiRW) algorithm to identify potential novel indications for a given drug, and outperforms several recent computational drug repositioning approaches.
A network medicine approach to quantify distance between hereditary disease modules on the interactome
TLDR
It is shown that the MeSH similarity measure can be used effectively in the prediction of candidate disease genes and that the structure of MeSH provides a natural way of combining individual MeSH vocabularies.
Drug repurposing: progress, challenges and recommendations
TLDR
Approaches used for drug repurposing (also known as drug repositioning) are presented, the challenges faced by the repurpose community are discussed, and innovative ways by which these challenges could be addressed are recommended to help realize the full potential of drugRepurposing.
Representation Learning on Graphs: Methods and Applications
TLDR
A conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks are provided.
DrugBank 5.0: a major update to the DrugBank database for 2018
TLDR
This year’s update, DrugBank 5.0, represents the most significant upgrade to the database in more than 10 years and significant improvements have been made to the quantity, quality and consistency of drug indications, drug binding data as well as drug-drug and drug-food interactions.
Drug repositioning: identifying and developing new uses for existing drugs
TLDR
Repositioning existing drugs for new indications could deliver the productivity increases that the industry needs while shifting the locus of production to biotechnology companies.
...
...