Training method and apparatus for reaction product prediction model, application method, device, and computer program

The method employs self-supervised learning with auxiliary networks to automatically label data, addressing the high cost of artificial labeling in deep learning for organic chemical reaction prediction, enhancing accuracy and efficiency in predicting reaction products and supporting drug development.

JP7874191B2Active Publication Date: 2026-06-15TENCENT TECHNOLOGY (SHENZHEN) CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
JP2024559865
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2022-07-14
Filing Date
2023-04-20
Publication Date
2026-06-15
Estimated Expiration
2043-04-20

AI Technical Summary

Technical Problem

Current deep learning techniques for organic chemical reaction product prediction rely heavily on expensive artificial labeling, leading to high labor and time costs as the amount of chemical reaction data increases.

Method used

A method for training a reaction product prediction model using self-supervised learning through auxiliary networks to automatically label data, reducing the need for artificial labeling and improving prediction accuracy by learning reactant relationships, product correlations, and atomic changes during reactions.

Benefits of technology

Enables accurate prediction of reaction products without artificial labeling, reducing costs and enhancing the model's ability to handle complex reactions, thereby improving the efficiency of drug development and new reaction prediction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Embodiments of this application disclose a method for training a reaction product prediction model, an application method, an apparatus, and a device. Related embodiments are applied to various scenarios such as artificial intelligence and are used to improve prediction accuracy while reducing model training costs. Such a method includes constructing a positive sample reactant set and a negative sample reactant set through a first auxiliary network, calculating a reaction prediction loss value based on the positive sample reactant set and the negative sample reactant set, constructing a positive sample reaction group set and a negative sample reaction group set through a second auxiliary network, calculating a reaction relationship prediction loss value based on the positive sample reaction group set and the negative sample reaction group set, obtaining a predicted probability value and an atomic label of atoms in the sample reactant existing in the main product through a third auxiliary network, calculating an atomic prediction loss value, and training a reaction product prediction model based on the reaction prediction loss value, the reaction relationship prediction loss value, and the atomic prediction loss value to obtain a target reaction product prediction model.
Need to check novelty before this filing date? Find Prior Art