A meta-learning framework using representation learning to predict drug-drug interaction

Autor: S.S. Deepika, T.V. Geetha
Rok vydání: 2018
Předmět:
0301 basic medicine
Drug-Related Side Effects and Adverse Reactions
Computer science
Drug-drug interaction
Health Informatics
02 engineering and technology
Machine learning
computer.software_genre
03 medical and health sciences
Drug Development
Predictive Value of Tests
0202 electrical engineering
electronic engineering
information engineering
Technology
Pharmaceutical
Drug Interactions
Probability
Drug discovery
business.industry
Computational Biology
Computer Science Applications
Support vector machine
ComputingMethodologies_PATTERNRECOGNITION
030104 developmental biology
Drug development
Pharmaceutical Preparations
Drug Design
Labeled data
020201 artificial intelligence & image processing
Artificial intelligence
Supervised Machine Learning
business
PU learning
Feature learning
computer
Classifier (UML)
Algorithms
Software
Zdroj: Journal of biomedical informatics. 84
ISSN: 1532-0480
Popis: Motivation Predicting Drug-Drug Interaction (DDI) has become a crucial step in the drug discovery and development process, owing to the rise in the number of drugs co-administered with other drugs. Consequently, the usage of computational methods for DDI prediction can greatly help in reducing the costs of in vitro experiments done during the drug development process. With lots of emergent data sources that describe the properties and relationships between drugs and drug-related entities (gene, protein, disease, and side effects), an integrated approach that uses multiple data sources would be most effective. Method We propose a semi-supervised learning framework which utilizes representation learning, positive-unlabeled (PU) learning and meta-learning efficiently to predict the drug interactions. Information from multiple data sources is used to create feature networks, which is used to learn the meta-knowledge about the DDIs. Given that DDIs have only positive labeled data, a PU learning-based classifier is used to generate meta-knowledge from feature networks. Finally, a meta-classifier that combines the predicted probability of interaction from the meta-knowledge learnt is designed. Results Node2vec, a network representation learning method and bagging SVM, a PU learning algorithm, are used in this work. Both representation learning and PU learning algorithms improve the performance of the system by 22% and 12.7% respectively. The meta-classifier performs better and predicts more reliable DDIs than the base classifiers.
Databáze: OpenAIRE
Externí odkaz: