# US 2026/0066039 A1 · Training and using generative thermodynamics neural networks to determine binding affinities from energy distributions

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

- Number: US 2026/0066039 A1
- Document ID: US20260066039A1
- Status: Published application
- Kind: A1
- Application number: 18/825,331
- Filed: 2024-09-05
- Published: 2026-03-05
- Earliest claimed: 2024-09-05
- Assignees: Recursion Pharmaceuticals, Inc.
- Applicants: Recursion Pharmaceuticals, Inc.
- Inventors: Oscar MENDEZ LUCIO
- Web page: https://patentgrep.com/patent/US20260066039A1

## CPC

- G16B 15/30: Drug targeting using structural data; Docking or binding prediction
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing generative thermodynamics neural networks to utilize an energy-to-base distribution transformation process to determine a binding conformation for a query compound and a target protein. For example, the disclosed systems can sample a conformation of the query compound from a known distribution and utilize the base-to-energy distribution transformation process to map the compound from the known distribution to a binding conformation. Moreover, the disclosed systems can determine an energy value associated with the binding conformation. In some bases, the disclosed systems can utilize an energy-to-base distribution transformation process to determine a binding metric for the binding conformation.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, from a computing device, a binding query for a query compound and a target protein;
generating, utilizing a generative thermodynamics neural network in a base-to-energy distribution transformation process, a binding conformation of the query compound corresponding to a binding interaction between the query compound and the target protein;
generating, utilizing the generative thermodynamics neural network in an energy-to-base distribution transformation process, a predicted series of conformations and corresponding conformation probabilities between the binding conformation and an unbound conformation of the query compound; and
generating, in response to the binding query from the computing device, a binding metric representative of the binding interaction between the target protein and the query compound from the conformation probabilities of the predicted series of conformations.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
training the generative thermodynamics neural network by:
sampling, from a base distribution, an initial conformation of a training compound; and
generating, from the initial conformation of the training compound, a binding conformation of the training compound relative to a training protein.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
determining a measure of energy corresponding to the binding conformation; and
modifying parameters of the generative thermodynamics neural network based on the measure of energy.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising determining the measure of energy by utilizing a force field model to generate a force field value based on the binding conformation of the training compound in binding with the training protein.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising generating the binding conformation of the query compound by:
sampling an initial conformation of the query compound from a base distribution; and
generating, at a first time step utilizing the generative thermodynamics neural network, a first conformation of the query compound from the initial conformation and the target protein, wherein the first conformation comprises at least one of a first rotation of the query compound, a first translation of the query compound, or a first set of modified dihedral angles of the query compound.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, further comprising generating the binding conformation of the query compound by generating, at an additional time step utilizing the generative thermodynamics neural network, the binding conformation of the query compound based on the first conformation and the target protein.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein the base-to-energy distribution transformation process comprises an ordinary differential equation that utilizes the generative thermodynamics neural network over a series of time steps to transform the base distribution for the query compound to an energy distribution for the query compound.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the energy-to-base distribution transformation process comprises a reverse ordinary differential equation integrated over time steps of the generative thermodynamics neural network to determine the binding metric.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the generative thermodynamics neural network is trained to map a base distribution of query compound conformations to an energy distribution for query compound conformations relative to target proteins.

### Claim 10

A system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
receive, from a computing device, a binding query for a query compound and a target protein;
generate, utilizing a generative thermodynamics neural network in a base-to-energy distribution transformation process, a binding conformation of the query compound corresponding to a binding interaction between the query compound and the target protein;
generate, utilizing the generative thermodynamics neural network in an energy-to-base distribution transformation process, a predicted series of conformations and corresponding conformation probabilities between the binding conformation and an unbound conformation of the query compound; and
generate, in response to the binding query from the computing device, a binding metric representative of the binding interaction between the target protein and the query compound from the conformation probabilities of the predicted series of conformations.

### Claim 11 (depends on 10)

The system of claim 10, further comprising instructions that, when executed by the at least one processor, cause the system to:
train the generative thermodynamics neural network by:
sampling, from a base distribution, an initial conformation of a training compound; and
generating, from the initial conformation of the training compound, a binding conformation of the training compound relative to a training protein.

### Claim 12 (depends on 11)

The system of claim 11, further comprising instructions, that, when executed by the at least one processor, cause the system to:
determine a measure of energy corresponding to the binding conformation; and
modify parameters of the generative thermodynamics neural network based on the measure of energy.

### Claim 13 (depends on 12)

The system of claim 12, further comprising instructions that, when executed by the at least one processor, cause the system to determine the measure of energy by utilizing a force field model to generate a force field value based on the binding conformation of the training compound in binding with the training protein.

### Claim 14 (depends on 10)

The system of claim 10, further comprising instructions that, when executed by the at least one processor, cause the system to generate the binding conformation of the query compound by:
sampling an initial conformation of the query compound from a base distribution; and
generating, at a first time step utilizing the generative thermodynamics neural network, a first conformation of the query compound from the initial conformation and the target protein, wherein the first conformation comprises at least one of a first rotation of the query compound, a first translation of the query compound, or a first set of modified dihedral angles of the query compound.

### Claim 15 (depends on 14)

The system of claim 14, further comprising instructions that, when executed by the at least one processor, cause the system to generate the binding conformation of the query compound by generating, at an additional time step utilizing the generative thermodynamics neural network, a binding conformation of the query compound based on the first conformation and the target protein.

### Claim 16

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:
receive, from a computing device, a binding query for a query compound and a target protein;
generate, utilizing a generative thermodynamics neural network in a base-to-energy distribution transformation process, a binding conformation of the query compound corresponding to a binding interaction between the query compound and the target protein;
generate, utilizing the generative thermodynamics neural network in an energy-to-base distribution transformation process, a predicted series of conformations and corresponding conformation probabilities between the binding conformation and an unbound conformation of the query compound; and
generate, in response to the binding query from the computing device, a binding metric representative of the binding interaction between the target protein and the query compound from the conformation probabilities of the predicted series of conformations.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, further comprising instructions that, when executed by the at least one processor, cause the computing device to:
train the generative thermodynamics neural network by:
sampling, from a base distribution, an initial conformation of a training compound; and
generating, from the initial conformation of the training compound, a binding conformation of the training compound relative to a training protein.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine a measure of energy corresponding to the binding conformation; and
modify parameters of the generative thermodynamics neural network based on the measure of energy.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, further comprising instructions that, when executed by the at least one processor, cause the computing device to determine the measure of energy by utilizing a force field model to generate a force field value based on the binding conformation of the training compound in binding with the training protein.

### Claim 20 (depends on 16)

The non-transitory computer-readable medium of claim 16, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the binding conformation of the query compound by:
sampling an initial conformation of the query compound from a base distribution; and
generating, at a first time step utilizing the generative thermodynamics neural network, a first conformation of the query compound from the initial conformation and the target protein, wherein the first conformation comprises at least one of a first rotation of the query compound, a first translation of the query compound, or a first set of modified dihedral angles of the query compound.
