Machine learning and molecular simulation based methods for enhancing binding and activity prediction

1. A method performed by one or more computers for predicting a relationship between a ligand and a receptor, the method comprising:

identifying a plurality of clustered conformations of the receptor, comprising:

performing a simulation of molecular dynamics of the receptor over a time interval, wherein the simulation defines a collection of simulated conformations of the receptor; and

clustering the collection of simulated conformations of the receptor to generate the plurality of clustered conformations of the receptor;

computing, for each of the plurality of clustered conformations of the receptor, a respective docking score between the clustered conformation of the receptor and the ligand; and

receiving, by a machine learning model, a model input to the machine learning model that comprises the respective docking score for each of the plurality of clustered conformations of the receptor,

wherein the machine learning model is parameterized by a set of machine learning model parameters that have been trained by a supervised machine learning technique;

processing the model input that comprises the respective docking score for each of the plurality of clustered conformations of the receptor using the machine learning model, in accordance with trained values of the set of machine learning model parameters, to generate a model output of the machine learning model that comprises a binding score,

wherein the binding score is a score that characterizes a binding affinity of the ligand for the receptor.

2. The method of claim 1 , wherein the collection of simulated conformations of the receptor comprises at least one non-crystallographic state.

3. The method of claim 1 , wherein performing the simulation of the molecular dynamics of the receptor comprises simulating an interaction of the receptor with the ligand.

4. The method of claim 1 , wherein clustering the collection of simulated conformations of the receptor comprises performing a dimensionality reduction operation on the collection of simulated conformations of the receptor.

5. The method of claim 1 , wherein for each of the plurality of clustered conformations of the receptor, computing the docking score between the clustered conformation of the receptor and the ligand comprises:

simulating a docking of the ligand and the clustered conformation of the receptor.

6. The method of claim 1 , wherein the machine learning model comprises one or more random forest models.

7. The method of claim 1 , further comprising physically testing reactions of the ligand with the receptor.

8. The method of claim 1 , wherein the machine learning model comprises a neural network model.

9. The method of claim 1 , wherein the model output of the machine learning model further comprises an agonist score that characterizes a likelihood that the ligand is an agonist for the receptor.

10. The method of claim 1 , wherein the model output of the machine learning model comprises: (i) the binding score that characterizes the binding affinity of the ligand for the receptor, and (ii) an agonist score that characterizes a likelihood that the ligand is an agonist for the receptor; and

wherein the method further comprises:

generating an overall score by combining the binding score and the agonist score.

11. The method of claim 10 , wherein generating the overall score by combining the binding score and the agonist score comprises:

computing a product of the binding score and the agonist score.

12. The method of claim 1 , wherein the time interval of the molecular dynamics simulation has a duration of at least one millisecond.

13. The method of claim 1 , wherein clustering the collection of simulated conformations of the receptor comprises:

applying k-means clustering to the collection of simulated conformations of the receptor.

14. The method of claim 1 , wherein the collection of simulated conformations of the receptor comprises at least 100,000 simulated conformations of the receptor.

15. The method of claim 1 , wherein clustering the collection of simulated conformations of the receptor comprises:

generating a set of clusters, wherein a number of clusters in the set of clusters is less than a number of simulated conformations of the receptor in the collection of simulated conformations of the receptor.

16. One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations for predicting a relationship between a ligand and a receptor, the operations comprising:

identifying a plurality of clustered conformations of the receptor, comprising:

performing a simulation of molecular dynamics of the receptor over a time interval, wherein the simulation defines a collection of simulated conformations of the receptor; and

clustering the collection of simulated conformations of the receptor to generate the plurality of clustered conformations of the receptor;

computing, for each of the plurality of clustered conformations of the receptor, a respective docking score between the clustered conformation of the receptor and the ligand; and

receiving, by a machine learning model, a model input to the machine learning model that comprises the respective docking score for each of the plurality of clustered conformations of the receptor,

wherein the machine learning model is parameterized by a set of machine learning model parameters that have been trained by a supervised machine learning technique;

processing the model input that comprises the respective docking score for each of the plurality of clustered conformations of the receptor using the machine learning model, in accordance with trained values of the set of machine learning model parameters, to generate a model output of the machine learning model that comprises a binding score,

wherein the binding score is a score that characterizes a binding affinity of the ligand for the receptor.

17. A system comprising:

one or more computers; and

one or more storage devices communicatively coupled to the one or more computers, wherein the one or more storage devices store instructions that, when executed by the one or more computers, cause the one or more computers to perform operations for predicting a relationship between a ligand and a receptor, the operations comprising:

identifying a plurality of clustered conformations of the receptor, comprising:

performing a simulation of molecular dynamics of the receptor over a time interval, wherein the simulation defines a collection of simulated conformations of the receptor; and

clustering the collection of simulated conformations of the receptor to generate the plurality of clustered conformations of the receptor;

computing, for each of the plurality of clustered conformations of the receptor, a respective docking score between the clustered conformation of the receptor and the ligand; and

receiving, by a machine learning model, a model input to the machine learning model that comprises the respective docking score for each of the plurality of clustered conformations of the receptor,

wherein the machine learning model is parameterized by a set of machine learning model parameters that have been trained by a supervised machine learning technique;

processing the model input that comprises the respective docking score for each of the plurality of clustered conformations of the receptor using the machine learning model, in accordance with trained values of the set of machine learning model parameters, to generate a model output of the machine learning model that comprises a binding score,

wherein the binding score is a score that characterizes a binding affinity of the ligand for the receptor.

18. The system of claim 17 , wherein the collection of simulated conformations of the receptor comprises at least one non-crystallographic state.

19. The system of claim 17 , wherein performing the simulation of the molecular dynamics of the receptor comprises simulating an interaction of the receptor with the ligand.

20. The system of claim 17 , wherein clustering the collection of simulated conformations of the receptor comprises performing a dimensionality reduction operation on the collection of simulated conformations of the receptor.