Method, device and system for predicting dynamic solubility of active ingredients through artificial intelligence

A technology of active ingredients and artificial intelligence, applied in prediction, neural learning methods, analysis materials, etc., can solve problems such as long research and development time, too much basic data, and low accuracy of prediction results, so as to improve prediction accuracy and reduce experimental data. volume effect

Pending Publication Date: 2020-02-07
王昊昱 +2
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to overcome the defects of the prior art, provide artificial intelligence methods, equipment and systems for predicting the dynamic solubility of active ingredients, and solve the problem of too much basic data required in the current solid preparation research and development process, resulting in too long research and development time And the accuracy of the prediction results is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and system for predicting dynamic solubility of active ingredients through artificial intelligence
  • Method, device and system for predicting dynamic solubility of active ingredients through artificial intelligence
  • Method, device and system for predicting dynamic solubility of active ingredients through artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 1 As shown, the present invention provides artificial intelligence to predict the method for dynamic solubility of active ingredient, and this system adopts two kinds of neural network models (BP neural network model / RBF neural network model) in artificial intelligence, designs in conjunction with the stripping experimental method of solid active ingredient . First establish the influencing factors of the solubility of the active ingredient compound, establish the influencing factor table, randomly select the data of one of the factors affecting the solubility of the active ingredient compound as the variable data, and conduct multiple groups of single-factor dissolution experiments under the condition that other influencing factors remain unchanged. , the solubility data is obtained through multiple sets of experiments, and the variable data and the corresponding solubility data are used as parallel sample experimental data to establish the experimental ...

Embodiment 2

[0069] The present invention also provides a system for artificial intelligence to predict the dynamic solubility of active ingredients, including a neural network training module, a data input module, a neural network selection module, a solubility prediction module, and an export module;

[0070] The neural network training module adopts the parallel sample experimental data of single factor investigation to train the BP neural network model and the RBF neural network model in the system, and after obtaining the trained BP neural network model and the RBF neural network model, the BP neural network model is Network model and RBF neural network model data are delivered to the data input module;

[0071] The data input module inputs variable parameter data of unknown results into the trained BP neural network model and RBF neural network model, and the system automatically eliminates data with large errors according to the set data error threshold. And pass the data into the n...

Embodiment 3

[0075] The present invention also provides a device embodiment corresponding to the first method embodiment.

[0076] The embodiment of the device of the present invention is a device for artificial intelligence to predict the dynamic solubility of active ingredients, which may include but not limited to: one or more memories and processors; the memories include storage media of computer systems, commonly referred to as hard drives, for storing A computer program; when the computer program is executed, the processor can realize the aforementioned method for predicting the dynamic solubility of active ingredients by artificial intelligence.

[0077] The device embodiment is basically similar to the method embodiment, and for detailed information, refer to the detailed description of Embodiment 1, which will not be repeated here.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method, device and a system for predicting dynamic solubility of active ingredients by artificial intelligence. The method comprises the following steps: S1, randomly selecting data in a factor influencing the solubility of an active component compound as variable data, obtaining solubility data through multiple groups of experiments under the condition that other influence factors are not changed, and establishing a neural network model by taking the variable data and the corresponding solubility data as parallel sample experiment data; and S2, inputting new variabledata of the active component into the neural network model established in the step S1 as an input variable, calculating prediction data through the neural network model established in the step S1, and performing correction by utilizing an export formula to predict the solubility of the active component compound. Artificial intelligence is adopted to predict a single-factor investigation experiment result to reduce the experiment amount required by an experiment, so that the research and development time and cost are reduced, abnormal data with relatively large experiment errors are eliminatedaccording to the standard deviation of parallel experiments, and the solubility prediction accuracy is improved.

Description

technical field [0001] The invention relates to a technology for predicting the solubility of active ingredients, in particular to a method, equipment and system for predicting the dynamic solubility of active ingredients by artificial intelligence. Background technique [0002] In the R&D process of solid preparations, the dynamic solubility of active ingredients (drug substances) is a key factor. The most widely used dynamic solubility (solid particle dissolution curve) prediction software is DDDplus, a product of Simulations Plus in the United States, and has been used by many multinational pharmaceutical companies. It is used by enterprises and FDA (US Food and Drug Administration), China Food and Drug Administration and other institutions. The prediction method is to use the core formula to analyze and calculate the data. It is necessary to parameterize the properties of the raw material (solubility / particle size / pKa / LogP, etc.) and the overall environment, and input al...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/08G06Q10/04G01N13/00
CPCG06N3/08G06Q10/04G01N13/00
Inventor 王昊昱曹兆洋王中彦覃宁远
Owner 王昊昱
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap