Agent-based multi-scale drug cooperative prediction method

Abstract

The invention provides an agent-based multi-scale drug cooperative prediction method. By building a drug cooperative model, drug interaction is subjected to effect estimation. The method specificallycomprises the steps of 1, preprocessing experimental data; 2, establishing a cell survival state rule; 3, performing stepwise estimation on parameters in the model by applying a machine learning algorithm; 4, verifying the model, testing the model by utilizing a real data set and a simulated data set, and analyzing the accuracy of the drug cooperative prediction model through significant difference; and 5, performing secondary verification on the accuracy of the model by utilizing a drug cooperative index. According to the method, a law of influence on a cell life state under a combined actionof multiple drugs, and the cooperative effect and cooperative intensity of the drugs can be explored.

Description

technical field [0001] The invention relates to the technical field of systems biology, mainly to bioinformatics and machine learning, and in particular to a method for establishing an agent-based multi-scale collaborative prediction model and a model system thereof. Background technique [0002] Drug combination refers to the simultaneous or sequential application of two or more drugs to achieve therapeutic purposes. Combination drugs often have in vivo or in vitro drug interactions. The interaction of drugs in vitro is called incompatibility, which refers to the physical or chemical reactions that occur when drugs are mixed together. The interaction of drugs in the body is called interaction, which mainly occurs in some aspects of pharmacokinetics and pharmacodynamics. [0003] No matter which aspect occurs, there are only two final changes: one is to enhance the original effect, which is called synergism, and the other is to weaken the original effect, which is called a...

AI Technical Summary

Problems solved by technology

However, such models do not take into account the interaction between cells and between cells and the environment, and it is difficult to discover the efficacy of drugs under the influence of multi-cell interactions

To this end, Ryall, K.A et al., used a systems biology approach to develop a model to explore the effects of drug combinations, but did not use experimental data to train key parameters of the model

In addition, Sun. et al developed a bone growth model based on differential equations, although considering the synergy of growth factors and using experimental data to train key parameters, they did not use the experimentally obtained synergy interval to verify the calculated drug synergy strength Is it reasonable

Images