Optimization of multiple molecules

Patent metadata

Field	Value
Publication number	US-12334195-B2
Application number	US-202117559595-A
Country	US
Kind code	B2
Filing date	Dec 22, 2021
Priority date	Dec 22, 2021
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

A computer implemented method of modifying molecular structures constrained by a budget is provided. The computer implemented method includes receiving from a user a subset of molecules, where each molecule is represented as a generation path, and receiving from the user an allotted budget for modifying a selection of molecules from the subset of molecules. The computer implemented method further includes testing a first molecule, and reducing the allotted budget based on the resources expended to test the first molecule. The computer implemented method further includes testing a second molecule, and reducing the allotted budget based on the resources expended to test the second molecule. The computer implemented method further includes determining a remaining amount of the allotted budget, and testing additional molecules from the subset of molecules until the allotted budget is exhausted. The computer implemented method further includes presenting the tested molecules to the user.

First claim

What is claimed is:

1. A computer implemented method of modifying molecular structures constrained by a budget, comprising:
receiving from a user a subset of molecules, where each molecule is represented as a generation path;
receiving from the user an allotted budget, that includes a time constraint, for modifying a selection of molecules from the subset of molecules;
testing a first molecule;
reducing the allotted budget based on resources expended to test the first molecule;
testing a second molecule;
reducing the allotted budget based on the resources expended to test the second molecule;
determining a remaining amount of the allotted budget;
testing additional molecules from the subset of molecules until the allotted budget is exhausted; and
presenting the tested molecules to the user.

2. The computer implemented method of claim 1 , wherein testing the first molecule includes, selecting the first molecule from the subset of molecules; and
modifying the generation path of the selected first molecule in a manner that changes a chemical, a physical, or a biological property value of the first molecule to be closer to a user defined value; and
testing the second molecule includes, selecting the second molecule from the subset of molecules; and
modifying the generation path of the selected second molecule in a manner that changes a chemical, a physical, or a biological property value of the second molecule to be closer to the user defined value; and
testing additional molecules includes, selecting the additional molecules from the subset of molecules; and
modifying the generation path of each of the selected additional molecule in a manner that changes a chemical, a physical, or a biological property value of the additional molecule to be closer to the user defined value.

3. The computer implemented method of claim 2 , wherein the selection of the first molecule, the second molecule, and the additional molecules is formulated as a multi-armed bandit problem, and wherein the first molecule, the second molecule, and the additional molecules are modified using an objective function to generate an objective value.

4. The computer implemented method of claim 3 , wherein the objective function is a Ridge Regression model or a Support Vector Regression model.

5. The computer implemented method of claim 3 , further comprising updating a generation path for each molecule being modified.

6. The computer implemented method of claim 5 , wherein the generation path is modified by inserting, deleting, or replacing a subcomponent of the selected molecule.

7. The computer implemented method of claim 5 , wherein a list of modified molecules is presented in a decreasing ordered based on the objective value of each modified molecule.

8. A computer system for modifying molecular structures constrained by a budget, comprising:
one or more processors;
a computer display;
a computer memory operatively coupled to the one or more processors; and
a chemical modification tool stored in the computer memory that is configured to receive from a user a subset of molecules, where each molecule is represented as a generation path;
receive from the user an allotted budget, that includes a time constraint, for modifying a selection of molecules from the subset of molecules;
test a first molecule;
reduce the allotted budget based on the resources expended to test the first molecule;
test a second molecule;
reduce the allotted budget based on the resources expended to test the second molecule;
determine a remaining amount of the allotted budget;
test additional molecules from the subset of molecules until the allotted budget is exhausted; and
present the tested molecules to the user on the computer display.

9. The computer system of claim 8 , wherein testing the first molecule includes, selecting the first molecule from the subset of molecules; and
modifying the generation path of the selected first molecule in a manner that changes a chemical, a physical, or a biological property value of the first molecule to be closer to a user defined value; and
testing the second molecule includes, selecting the second molecule from the subset of molecules; and
modifying the generation path of the selected second molecule in a manner that changes a chemical, a physical, or a biological property value of the second molecule to be closer to the user defined value; and
testing additional molecules includes, selecting the additional molecules from the subset of molecules; and
modifying the generation path of each of the selected additional molecule in a manner that changes a chemical, a physical, or a biological property value of the additional molecule to be closer to the user defined value.

10. The computer system of claim 9 , wherein the selection of the first molecule, the second molecule, and the additional molecules is formulated as a multi-armed bandit problem, and wherein the first molecule, the second molecule, and the additional molecules are modified using an objective function to generate an objective value.

11. The computer system of claim 10 , wherein the objective function is a Ridge Regression model or a Support Vector Regression model.

12. The computer system of claim 10 , further comprising updating a generation path for each molecule being modified.

13. The computer system of claim 12 , wherein the generation path is modified by inserting, deleting, or replacing a subcomponent of the selected molecule.

14. The computer system of claim 12 , wherein a list of modified molecules is presented in a decreasing ordered based on the objective value of each modified molecule.

15. A computer program product for modifying molecular structures constrained by a budget, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions are executable by a processor to cause a computer to:
receive from a user a subset of molecules, where each molecule is represented as a generation path;
receive from the user an allotted budget, that includes a time constraint, for modifying a selection of molecules from the subset of molecules;
test a first molecule;
reduce the allotted budget based on resources expended to test the first molecule;
test a second molecule;
reduce the allotted budget based on the resources expended to test the second molecule;
determine a remaining amount of the allotted budget;
test additional molecules from the subset of molecules until the allotted budget is exhausted; and
present the tested molecules to the user on a computer display.

16. The computer program product of claim 15 , wherein testing the first molecule includes, selecting the first molecule from the subset of molecules; and
modifying the generation path of the selected first molecule in a manner that changes a chemical, a physical, or a biological property value of the first molecule to be closer to a user defined value; and
testing the second molecule includes, selecting the second molecule from the subset of molecules; and
modifying the generation path of the selected second molecule in a manner that changes a chemical, a physical, or a biological property value of the second molecule to be closer to the user defined value; and
testing additional molecules includes, selecting the additional molecules from the subset of molecules; and
modifying the generation path of each of the selected additional molecule in a manner that changes a chemical, a physical, or a biological property value of the additional molecule to be cl

Assignees

• IBM

Inventors

• Kishimoto Akihiro
• Hama Toshiyuki
• Hsu Hsiang Han
• Bouneffouf Djallel

Classifications

• G16C60/00

  Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation · CPC title

• G16C20/10

  Analysis or design of chemical reactions, syntheses or processes · CPC title

• G16C20/20

  Identification of molecular entities, parts thereof or of chemical compositions · CPC title

• G16C20/70 Primary

  Machine learning, data mining or chemometrics · CPC title

• G16C20/50 Primary

  Molecular design, e.g. of drugs · CPC title