A model-agnostic framework to enhance knowledge graph-based drug combination prediction with drug-drug interaction data and supervised contrastive learning.
Jeonghyeon GuDongmin BangJungseob YiSangseon LeeDong Kyu KimSun KimPublished in: Briefings Bioinform. (2023)
Keyphrases
- prior knowledge
- learning models
- expert knowledge
- probabilistic model
- experimental data
- conceptual framework
- learning algorithm
- learning scheme
- probability distribution
- accurate models
- data analysis
- data sets
- conceptual model
- raw data
- background knowledge
- network structure
- data mining techniques
- knowledge discovery
- prediction model
- learned models
- human experts
- hidden variables
- knowledge space theory
- learning systems
- data mining
- active learning
- unsupervised learning
- theoretical framework
- training data
- neural network
- drug design
- missing information
- machine learning
- bayesian methods
- feature selection
- statistical methods
- data sources
- supervised learning
- user model
- knowledge acquisition
- learning process
- semi supervised learning
- sensory data
- bayesian framework