Built-in drug target interaction prediction method based on heterogeneous network

Abstract

The invention discloses a built-in drug target interaction prediction method based on a heterogeneous network. The built-in drug target interaction prediction method includes the steps: based on the assumption that a chemically similar drug can often interact with a similar target, combining a drug-drug similarity network, a target-target similarity network, and a drug-target interaction network into a drug-target heterogeneous network; using a starting-node-based migrating sequence, constructing a neural network classification model, taking the migrating sequence as input of the neural network classification model, training the classification model and learning to obtain vector representation of all nodes; and for prediction of drug-target interaction, giving a pair of drug-target pairs,extracting vector representation of the corresponding drug and target from the node vectors obtained from learning, performing Hadamard product operation on the two vectors, and taking the obtained result as the input of a random forest classifier to obtain the final prediction result. According to the experimental verification, the built-in drug target interaction prediction method based on a heterogeneous network has preferable prediction effect and applicability.

Description

technical field [0001] The invention belongs to the field of drug prediction and analysis, in particular to a drug-target interaction prediction method based on heterogeneous network embedding. Background technique [0002] Drug research and development technology has developed rapidly in the past three decades, and various methods including genomics, proteomics and systems biology have been widely used in the identification of drugs and targets and the development of innovative drugs. However, the development of drugs with a new structure still has the problems of huge cost, high risk, long cycle and low success rate. Currently, it takes an average of 10-15 years and billions of dollars to successfully develop a drug with a new structure. Because drugs with new structures often have unpredictable side effects, about 90% of experimental drugs fail to pass the first phase of clinical trials. Facing the increasing investment in research and development of original innovative...

AI Technical Summary

Problems solved by technology

Both network analysis-based and machine learning-based drug-target interaction prediction methods have their own advantages and disadvantages. Network-based computational models rely too much on known accessible paths, while machine learning-based model prediction accuracy is largely It depends on whether the features of the extracted drugs and targets are accurate, and the selection of negative samples also affects the prediction accuracy to a certain extent

Images