Deep learning-based inverse synthesis prediction method and device, medium and equipment

A technology of synthesis prediction and deep learning, applied in chemical property prediction, chemical machine learning, chemical statistics, etc., can solve the problem that SMILES sequence cannot fully consider molecular structure information, and achieve the effect of improving accuracy

Pending Publication Date: 2022-03-22
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings and deficiencies in the prior art, the object of the present invention is to provide a retrosynthetic prediction method, device, medium and equipment based on deep learning; the method solves the problem that the SMILES sequence cannot fully consider the molecular structure information, and improves The accuracy of the model's prediction results

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
  • Deep learning-based inverse synthesis prediction method and device, medium and equipment
  • Deep learning-based inverse synthesis prediction method and device, medium and equipment
  • Deep learning-based inverse synthesis prediction method and device, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039]At present, most retrosynthesis prediction methods based on sequence-to-sequence models only consider the SMILES sequence information of molecules, and lack the consideration of molecular structure information, which is very important in the chemical reaction process. Aiming at the problem that the SMILES sequence in the retrosynthesis prediction method based on the sequence-to-sequence model cannot fully consider the structural information of the molecule.

[0040] This example proposes a retrosynthetic prediction method based on deep learning. By embedding molecular structure information into the Transformer model, it solves the problems existing in SMILES sequence representation and improves the accuracy of retrosynthetic prediction results. The principle is as follows figure 1 shown.

[0041] The retrosynthetic prediction method includes the following steps, such as figure 2 Shown:

[0042] In step S1, the target product is converted into the corresponding SMILES ...

Embodiment 2

[0068] This embodiment is a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the inverse synthesis prediction method based on deep learning described in Embodiment 1.

Embodiment 3

[0070] In this embodiment, a computing device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the inverse synthesis prediction method based on deep learning described in Embodiment 1 is implemented.

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 provides an inverse synthesis prediction method and device based on deep learning, a medium and equipment. The method comprises the following steps: converting a target product into an SMILES sequence; extracting structure information of the SMILES sequence, wherein the structure information comprises degree information and adjacent matrix information; encoding to obtain a degree information code and an adjacent information code; the SMILES sequence is input into a Transform model encoder, and the encoding of the SMILES sequence is optimized by utilizing degree information encoding and adjacency information encoding; and the Transformer model inputs an encoding result of the encoder into a decoder for decoding to obtain an SMILES sequence of the reactant set, and then the SMILES sequence is converted to obtain a corresponding reactant. According to the method, the problem that molecular structure information cannot be fully considered by the SMILES sequence is solved, and the accuracy of a model prediction result is improved.

Description

technical field [0001] The present invention relates to the technical field of retrosynthesis prediction, and more specifically, to a method, device, medium and equipment for retrosynthesis prediction based on deep learning. Background technique [0002] Today, organic synthesis has become one of the most important disciplines in the field of chemistry. Its research content covers various disciplines such as materials, energy, and life, and plays an extremely important role in the development of social civilization and people's daily life. Organic synthesis refers to the process of making simple substances, simple inorganic substances or simple organic substances into more complex organic substances by chemical methods. In recent years, the technology of Computer-Assisted Synthetic Planning (CASP) has developed rapidly, especially retrosynthetic design has brought great convenience to chemists in drug synthesis. Retrosynthesis design aims to find a series of commercially av...

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): G16C20/30G16C20/20G16C20/70
CPCG16C20/30G16C20/20G16C20/70
Inventor 陈俊龙黄国彬孟献兵
Owner SOUTH CHINA UNIV OF TECH
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