A Drug Sensitivity Prediction Method Based on Cell Line and Drug Similarity Network

Abstract

The invention discloses a drug sensitivity prediction method based on a cell line and drug similarity network, comprising: constructing a drug similarity network, a cell line similarity network, and a drug-cell line relationship network; The corresponding drug adjacency matrix, cell line adjacency matrix, and drug-cell line relationship initial matrix are obtained from the drug-cell line similarity network and the drug-cell line relationship network; based on the drug-adjacency matrix, cell line adjacency matrix, and drug-cell line relationship initial matrix The balanced double random walk algorithm is used to obtain the drug sensitivity prediction matrix of the drug-cell line, wherein, each element in the drug-cell line drug sensitivity prediction matrix obtained after using the unbalanced double random walk formula is Corresponding to the predicted sensitivity value of the drug to the cell line. The invention fully considers the characteristics of the drug similarity network and the cell line similarity network, thereby improving the reliability of the drug sensitivity prediction result.

Description

technical field [0001] The invention belongs to the technical field of biomedicine, and in particular relates to a drug sensitivity prediction method based on a cell line and drug similarity network. Background technique [0002] Over the past two decades, substantial improvements in high-throughput analytical techniques have raised expectations for personalized or precision medicine to become the future paradigm of medical science. Patients with the same cancer may respond differently to specific drug treatments. Personalized medicine hopes to understand the cause of a specific patient's cancer at the molecular level, and then tailor treatment to address the patient's cancer. Compared with chemotherapy-based monotherapy approaches, personalized medicine looks at tumor response based on established molecular profiles of cancer cells to overcome some of the limitations associated with conventional symptom-oriented disease diagnosis and treatment. The most important step in p...

AI Technical Summary

Problems solved by technology

In fact, this two-layer network-based drug sensitivity prediction experiment is to mine the influence of drugs and cell lines on drug sensitivity, but this method does not take into account the drug similarity network and the similarity network of cell lines Biological network characteristics

At the same time, Zhang et al. used heterogeneous networks to achieve network fusion, which failed to fully mine their topological structures; in addition, someone applied the MRSF algorithm to drug sensitivity prediction based on similarity networks. Fully mining the biological network characteristics of drugs and cell lines themselves and their topological structures, the effect is not ideal

[0004] Therefore, the process of merging drug similarity and cell line similarity into drug sensitivity prediction in the prior art fails to fully mine the topology of the network, resulting in poor prediction results and needs to be improved

Images