# US 2026/0100254 A1 · Generating three-dimensional molecule structures using generative artificial intelligence models

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

- Number: US 2026/0100254 A1
- Document ID: US20260100254A1
- Status: Published application
- Kind: A1
- Application number: 19/180,012
- Filed: 2025-04-15
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Assignees: NVIDIA Corporation
- Applicants: NVIDIA Corporation
- Inventors: Daniel Alexander Reidenbach; Filipp Nikitin
- Web page: https://patentgrep.com/patent/US20260100254A1

## CPC

- G16C 20/50: Molecular design, e.g. of drugs
- G06N 3/0475: Generative networks
- G16C 20/30: Prediction of properties of chemical compounds, compositions or mixtures
- G16C 20/70: Machine learning, data mining or chemometrics
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In various examples, methods for generating accurate three-dimensional molecular structures using a generative artificial intelligence model include receiving a request to generate a molecular structure, the request including an initial structure, atom type information, and bond type information for the molecular structure; generating a fused input feature based on embedding representations of the initial structure, the atom type information, and the bond type information; generating an intermediate predicted molecular structure based on a transformer layer of a generative artificial intelligence model and the fused input feature; refining, using a graph neural network-based layer in the generative artificial intelligence model, the intermediate predicted molecular structure into the molecular structure; and outputting the molecular structure.

## Claims

### Claim 1

A processor-implemented method, comprising:
receiving a request to generate a molecular structure, the request including an initial structure, atom type information, and bond type information for the molecular structure;
generating, using a transformer layer of a generative artificial intelligence model, a fused input feature based on embedding representations of the initial structure, the atom type information, and the bond type information;
generating, using the transformer layer of the generative artificial intelligence model, an intermediate predicted molecular structure for the fused input feature;
refining, using a graph neural network-based layer in the generative artificial intelligence model, the intermediate predicted molecular structure into the molecular structure; and
outputting the molecular structure for synthesis and experimental evaluation.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating an embedding representation of the initial structure, an embedding representation of the atom type information, and an embedding representation of the bond type information;
wherein generating the fused input feature comprises aggregating the embedding representation of the initial structure, the embedding representation of the atom type information, and the embedding representation of the bond type information into a plurality of input tokens.

### Claim 3 (depends on 2)

The method of claim 2, wherein the fused input feature is further based on a time variable associated with a number of inferencing rounds previously performed with respect to the request.

### Claim 4 (depends on 2)

The method of claim 2, wherein the embedding representation of the initial structure, the embedding representation of the atom type information, and the embedding representation of the bond type information is generated based on a feedforward neural network.

### Claim 5 (depends on 1)

The method of claim 1, wherein the atom type information comprises elemental and charge information for each atom in the molecular structure, and wherein the bond type information comprises a bond adjacency matrix.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
receiving feedback data based on results of the experimental evaluation of the molecular structure; and
updating one or more parameters of the generative artificial intelligence model based on the feedback data to improve accuracy of subsequent molecular structure generation.

### Claim 7 (depends on 1)

The method of claim 1, wherein the transformer layer of the generative artificial intelligence model comprises a diffusion layer configured to generate the intermediate predicted molecular structure based on denoising a noisy representation of the molecular structure.

### Claim 8 (depends on 1)

The method of claim 1, wherein the transformer layer of the generative artificial intelligence model comprises a flow-matching layer.

### Claim 9 (depends on 1)

The method of claim 1, wherein the outputted molecular structure comprises a three-dimensional conformer and a two-dimensional graph representation of the three-dimensional structure.

### Claim 10 (depends on 1)

The method of claim 1, wherein the graph neural network-based layer in the generative artificial intelligence model refines the intermediate predicted molecular structure based on positional update and a cross-product update.

### Claim 11

A processing system, comprising:
at least one memory having executable instructions stored thereon; and
one or more processors configured to execute the executable instructions to cause the processing system to:
receive a request to generate a molecular structure, the request including an initial structure, atom type information, and bond type information for the molecular structure;
generate, using a transformer layer of a generative artificial intelligence model, a fused input feature based on embedding representations of the initial structure, the atom type information, and the bond type information;
generate, using the transformer layer of the generative artificial intelligence model, an intermediate predicted molecular structure for the fused input feature;
refine, using a graph neural network-based layer in the generative artificial intelligence model, the intermediate predicted molecular structure into the molecular structure; and
output the molecular structure for use in a drug discovery pipeline.

### Claim 12 (depends on 11)

The processing system of claim 11, wherein the one or more processors are configured to cause the processing system to:
generate an embedding representation of the initial structure, an embedding representation of the atom type information, and an embedding representation of the bond type information;
wherein to generate the fused input feature, the one or more processors are configured to cause the processing system to aggregate the embedding representation of the initial structure, the embedding representation of the atom type information, and the embedding representation of the bond type information into a plurality of input tokens.

### Claim 13 (depends on 12)

The processing system of claim 12, wherein the fused input feature is further based on a time variable associated with a number of inferencing rounds previously performed with respect to the request.

### Claim 14 (depends on 12)

The processing system of claim 12, wherein the embedding representation of the initial structure, the embedding representation of the atom type information, and the embedding representation of the bond type information is generated based on a feedforward neural network.

### Claim 15 (depends on 11)

The processing system of claim 11, wherein the atom type information comprises elemental and charge information for each atom in the molecular structure, and wherein the bond type information comprises a bond adjacency matrix.

### Claim 16 (depends on 11)

The processing system of claim 11, wherein the one or more processors are further configured to cause the processing system to:
receive feedback data based on results of the experimental evaluation of the molecular structure; and
update one or more parameters of the generative artificial intelligence model based on the feedback data to improve accuracy of subsequent molecular structure generation.

### Claim 17 (depends on 11)

The processing system of claim 11, wherein the transformer layer of the generative artificial intelligence model comprises a diffusion layer configured to generate the intermediate predicted molecular structure based on denoising a noisy representation of the molecular structure.

### Claim 18 (depends on 11)

The processing system of claim 11, wherein the transformer layer of the generative artificial intelligence model comprises a flow-matching layer.

### Claim 19 (depends on 11)

The processing system of claim 11, wherein the outputted molecular structure comprises a three-dimensional conformer and a two-dimensional graph representation of the three-dimensional structure.

### Claim 20 (depends on 11)

The processing system of claim 11, wherein the graph neural network-based layer in the generative artificial intelligence model refines the intermediate predicted molecular structure based on positional update and a cross-product update.
