# US 2021/0174910 A1 · Method and apparatus for generating new chemical structure using neural network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0174910 A1
- Document ID: US20210174910A1
- Status: Published application
- Kind: A1
- Application number: 17/114,713
- Filed: 2020-12-08
- Published: 2021-06-10
- Earliest claimed: 2019-12-09
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Youngchun KWON; Jiho YOO; Younsuk CHOI; Youngmin NAM; Minsik PARK; Jinwoo PARK; Dongseon LEE
- Web page: https://patentgrep.com/patent/US20210174910A1

## CPC

- G16C 20/50: Molecular design, e.g. of drugs
- G06N 3/02: Neural networks
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/08: Learning methods
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G16C 20/70: Machine learning, data mining or chemometrics
- G06N 3/048: Activation functions
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A neural network apparatus for generating a new chemical structure may receive a structure input of a chemical structure; generate, based on the structure input, a negative attention vector that indicates a respective probability of presence of each of a plurality of blacklists in the structure input; generate a structure expression by encoding the structure input; generate a final reverse blacklist vector that does not include the plurality of blacklists, based on the negative attention vector and the structure expression; and generate the new chemical structure by decoding the final reverse blacklist vector.

## Claims

### Claim 1

A method of generating a new chemical structure, the method performed by a neural network apparatus and comprising:
receiving a structure input of a chemical structure;
generating, based on the structure input, a negative attention vector that indicates a respective probability of presence of each of a plurality of blacklists in the structure input;
generating a structure expression by encoding the structure input;
generating a final reverse blacklist vector that does not include the plurality of blacklists, based on the negative attention vector and the structure expression; and
generating the new chemical structure by decoding the final reverse blacklist vector.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
calculating a reverse negative attention vector using the negative attention vector, and
wherein the generating of the final reverse blacklist vector comprises generating the final reverse blacklist vector based on the reverse negative attention vector and the structure expression.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
generating a final blacklist vector that includes the plurality of blacklists based on the negative attention vector and the structure expression during a learning process of a chemical structure generation model; and
training the chemical structure generation model based on the new chemical structure and a blacklist prediction result corresponding to the new chemical structure.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
calculating the blacklist prediction result using a non-negative parameter.

### Claim 5 (depends on 1)

The method of claim 1, wherein the structure input includes chemical structures confirmed not to include at least a part of the plurality of blacklists during a learning process of a chemical structure generation model.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
selecting a part of the plurality of blacklists,
wherein the generating of the negative attention vector comprises generating, based on the structure input, the negative attention vector in which the respective probability of presence of each of the selected blacklists in the structure input is indicated, and
wherein the generating of the final reverse blacklist vector comprises generating the final reverse blacklist vector that does not include the selected blacklists based on the negative attention vector and the structure expression.

### Claim 7 (depends on 2)

The method of claim 2, wherein the generating of the final reverse blacklist vector comprises generating the final reverse blacklist vector based on an element-wise multiplication between the reverse negative attention vector and the structure expression.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
generating, based on the structure input, a positive attention vector that indicates a respective probability of presence of each of a plurality of whitelists in the structure input;
generating a final whitelist vector including the plurality of whitelists based on the positive attention vector and the structure expression; and
generating the new chemical structure by decoding the final whitelist vector.

### Claim 9 (depends on 8)

The method of claim 8, wherein the structure input includes chemical structures confirmed to include at least a part of the plurality of whitelists during a learning process of a chemical structure generation model.

### Claim 10 (depends on 8)

The method of claim 8, wherein the structure input includes chemical structures confirmed not to include at least a part of the plurality of blacklists, and confirmed to include at least a part of the plurality of whitelists during a learning process of a chemical structure generation model.

### Claim 11

A neural network apparatus for generating a new chemical structure, the neural network apparatus comprising:
a memory in which at least one program is stored; and
a processor configured to execute the at least one program to:
receive a structure input of a chemical structure;
generate, based on the structure input, a negative attention vector that indicates a respective probability of presence of each of a plurality of blacklists in the structure input;
generate a structure expression by encoding the structure input;
generate a final reverse blacklist vector that indicates portions not corresponding to the plurality of blacklists, based on the negative attention vector and the structure expression; and
generate the new chemical structure based on the final reverse blacklist vector.

### Claim 12 (depends on 11)

The neural network apparatus of claim 11, wherein the processor is further configured to:
calculate a reverse negative attention vector using the negative attention vector; and
generate the final reverse blacklist vector that indicates portions not corresponding to the plurality of blacklists based on a computation between the reverse negative attention vector and the structure expression.

### Claim 13 (depends on 12)

The neural network apparatus of claim 12, wherein the processor is further configured to:
generate a final blacklist vector including the plurality of blacklists based on the negative attention vector and the structure expression during a learning process of a chemical structure generation model; and
train the chemical structure generation model based on the new chemical structure and a blacklist prediction result corresponding to the new chemical structure.

### Claim 14 (depends on 13)

The neural network apparatus of claim 13, wherein the processor is further configured to:
calculate the blacklist prediction result using a non-negative parameter.

### Claim 15 (depends on 11)

The neural network apparatus of claim 11, wherein the structure input includes chemical structures confirmed not to include at least a part of the plurality of blacklists during a learning process of a chemical structure generation model.

### Claim 16 (depends on 11)

The neural network apparatus of claim 11, wherein the processor is further configured to:
select a part of the plurality of blacklists;
generate, based on the structure input, the negative attention vector that indicates a respective probability of presence of each of the selected blacklists in the structure input; and
generate the final reverse blacklist vector that does not include the selected blacklists based on the negative attention vector and the structure expression.

### Claim 17 (depends on 11)

The neural network apparatus of claim 11, wherein the processor is further configured to:
generate, based on the structure input, a positive attention vector that indicates a respective probability of presence of each of a plurality of whitelists in the structure input;
generate a final whitelist vector that indicates portions corresponding to the plurality of whitelists, based on the positive attention vector and the structure expression; and
generate the new chemical structure by decoding the final whitelist vector.

### Claim 18 (depends on 17)

The neural network apparatus of claim 17, wherein the structure input includes chemical structures confirmed to include at least a part of the plurality of whitelists during a learning process of a chemical structure generation model.

### Claim 19 (depends on 17)

The neural network apparatus of claim 17, wherein the structure input includes chemical structures confirmed not to include at least a part of the plurality of blacklists and confirmed to include at least a part of the plurality of whitelists during a learning process of a chemical structure generation model.

### Claim 20

A non-transitory computer-readable medium configured to store a program that, when executed by a neural network apparatus, causes the neural network apparatus to:
receive a structure input of a chemical structure;
generate, based on the structure input, a negative attention vector that indicates a respective probability of presence of each of a plurality of blacklists in the structure input;
generate a structure expression by encoding the structure input;
generate a final reverse blacklist vector that does not include the plurality of blacklists, based on the negative attention vector and the structure expression; and
generate the new chemical structure by decoding the final reverse blacklist vector.
