Research And Implementation Of Drug Target Interaction Confidence Measurement Method Based On Causal Intervention

by   Wenting Ye, et al.

The identification and discovery of drug-target Interaction (DTI) is an important step in the field of Drug research and development, which can help scientists discover new drugs and accelerate the development process. KnowledgeGraph and the related knowledge graph Embedding (KGE) model develop rapidly and show good performance in the field of drug discovery in recent years. In the task of drug target identification, the lack of authenticity and accuracy of the model will lead to the increase of misjudgment rate and the low efficiency of drug development. To solve the above problems, this study focused on the problem of drug target link prediction with knowledge mapping as the core technology, and adopted the confidence measurement method based on causal intervention to measure the triplet score, so as to improve the accuracy of drug target interaction prediction model. By comparing with the traditional Softmax and Sigmod confidence measurement methods on different KGE models, the results show that the confidence measurement method based on causal intervention can effectively improve the accuracy of DTI link prediction, especially for high-precision models. The predicted results are more conducive to guiding the design and development of followup experiments of drug development, so as to improve the efficiency of drug development.


page 1

page 7


Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

Many practical graph problems, such as knowledge graph construction and ...

Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

Predicting interactions among heterogenous graph structured data has num...

Wasserstein Adversarial Autoencoders for Knowledge Graph Embedding based Drug-Drug Interaction Prediction

Interaction between pharmacological agents can trigger unexpected advers...

Graph Distance Neural Networks for Predicting Multiple Drug Interactions

Since multidrug combination is widely applied, the accurate prediction o...

Intelligent wayfinding vehicle design based on visual recognition

Intelligent drug delivery trolley is an advanced intelligent drug delive...

Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery

Knowledge Graphs (KG) and associated Knowledge Graph Embedding (KGE) mod...

DTI-SNNFRA: Drug-Target interaction prediction by shared nearest neighbors and fuzzy-rough approximation

In-silico prediction of repurposable drugs is an effective drug discover...

Please sign up or login with your details

Forgot password? Click here to reset