Drug small molecule optimization method based on evolutionary computation and multi-granularity agent model approximation

Abstract

The invention discloses a drug small molecule optimization method based on evolutionary computation and multi-granularity agent model approximation. The method comprises the steps that 1, a drug small molecule multi-attribute optimization problem is modeled as an expensive constraint multi-objective optimization problem; 2, uniformly generating an initial molecular population in a discrete chemical space, and carrying out expensive optimization target evaluation and constraint evaluation on the initial molecular population; 3, coding the evaluated drug small molecules into a continuous potential space to obtain continuous vector representation of the molecules; 4, using continuous vector representation of molecules, taking corresponding target values and constraint values as training data, and training a multi-granularity agent model; 5, executing an agent model assisted evolutionary algorithm, selecting high-quality drug small molecules, decoding the high-quality drug small molecules to a discrete chemical space, and performing expensive optimization target evaluation and constraint evaluation on the high-quality drug small molecules; and 6, repeating the steps 3-5 so as to output the optimal drug molecule. The method aims at efficiently optimizing multiple attributes of the drug small molecules with low evaluation cost, and therefore technical support is provided for drug research and development.

Description

Technical Field

[0001] The present invention relates to multiple interdisciplinary fields such as computer science, artificial intelligence, bioinformatics, etc. Specifically, the present invention proposes a drug small molecule optimization method based on evolutionary computing and multi-granularity agent model approximation. Background Art

[0002] The basic process of new drug research and development includes four stages: drug discovery, preclinical research, clinical research, and registration and approval. It usually takes more than ten years and hundreds of millions of dollars for a new drug to be approved for market use from discovery to approval. In the first stage of new drug research and development, namely the drug discovery stage, it is necessary to first discover biological target macromolecules that have pharmacodynamic functions and can be acted upon by drugs; secondly, use high-throughput screening and other technologies to obtain lead compounds with certain biological activity; then, optimize the lead compounds to obtain lead compounds with higher biological activity, pharmacodynamic properties and safety; finally, evaluate and optimize the lead compounds to obtain preclinical candidate compounds with higher drugability. It is worth mentioning that many new drug research and development projects often fail due to the poor properties of preclinical candidate compounds. Therefore, the optimization of two types of drug small molecule compounds, lead compounds and lead compounds, has become a key link in new drug research and development.

[0003] In order to optimize the hit compounds and lead compounds, it is necessary to explore all possible chemical small molecules (10 23 ~10 60The traditional optimization method of small drug molecules is mainly experimental screening method, which is time-consuming and labor-intensive. In recent years, with the rapid development of artificial intelligence optimization technology and the massive accumulation of biological big data, the optimization of small drug molecules has become more economical and efficient. Although existing research has made great progress in the optimization of single attributes of small drug molecules, most actual drug development requires small molecules to have multiple excellent attributes at the same time. It is difficult to meet the actual needs of drug development by achieving the best in only a single attribute. The difficulty of multi-attribute optimization of small drug molecules lies in the interrelationship of different attributes. Optimizing a single attribute of a small drug molecule may cause other attributes to change or even deteriorate. In addition, the optimization of small drug molecules often involves some complex constraints, such as constraints on the similarity of the skeleton structure of small drug molecules, non-toxic constraints, Lipinski's five rules, etc., which makes the problem of optimizing the attributes of small drug molecules more difficult to solve. As a type of meta-heuristic intelligent optimization algorithm inspired by various natural phenomena and biological group behaviors, evolutionary algorithms have strong adaptability, stability, concurrency, self-organization, are not easy to fall into local optimality, and can be combined with various constraint processing strategies. They are suitable for solving constrained multi-attribute optimization problems of small drug molecules. At present, many studies have used evolutionary algorithms to solve constrained multi-attribute optimization problems of small drug molecules, and have achieved good results. Nevertheless, actual small drug molecule optimization often involves some expensive attributes, and an evaluation of these attributes often takes a long time or a lot of financial and material resources; obviously, this type of small drug molecule optimization problem poses a huge challenge to evolutionary algorithms that require multiple iterations. Summary of the invention

[0004] In order to solve the above-mentioned problems, the present invention proposes a drug small molecule optimization method based on evolutionary computation and multi-granularity proxy model approximation, in order to dynamically adjust the approximate granularity of the proxy model according to the constraint violation, so as to achieve higher proxy model approximation accuracy with less computing resources, thereby reducing the cost of evaluating drug small molecules and thus better optimizing drug small molecules.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme:

[0006] The present invention is characterized in that a small molecule drug optimization method based on evolutionary computation and multi-granularity agent model approximation is performed according to the following steps:

[0007] Step 1: Obtain the kth drug small molecule to be optimized , and use the RDKit tool to identify the kth drug small molecule The biological properties were evaluated and obtained Molecular drug properties , synthetic accessibility and molecular toxicity ; Thus, using formula (1) to construct The multi-attribute optimization objective And its constraints:

[0008] (1)

[0009] In formula (1), represents the search space, and Respectively represent The molecular weight constraint violation and the hydrogen bond donor number constraint violation are and Represents small molecule drugs The molecular weight and number of hydrogen bond donors, and Represent the maximum values ​​of molecular weight and number of hydrogen bond donors respectively;

[0010] Drug-like properties of molecules , synthetic accessibility and molecular toxicity Recorded as Any j-th optimization goal of ; j = 1, 2, 3;

[0011] Will and Recorded as Any i-th constraint of ; i = 1, 2;

[0012] Step 2: Define and initialize the current iteration number as Iter=0; and define the Iter generation drug small molecule population ,in, represent The kth drug molecule in , N represents the size of the population;

[0013] Generate SMILES strings uniformly in discrete chemical space for initialization Each drug small molecule in, thus calculated according to formula (1) The violation degree of the multi-attribute optimization objectives and constraints of each drug molecule in;

[0014] Step 3: Train the variational autoencoder to convert Encoding from discrete chemical space to continuous latent space yields The optimal latent vector ;

[0015] Step 4: Build two proxy models and use The optimal potential vector of each drug small molecule and its corresponding multi-attribute optimization target value and constraint violation degree are used as training data, and each proxy model is trained separately to obtain a trained proxy model;

[0016] Step 5: Use the trained zth proxy model to assist the evolutionary algorithm to iteratively optimize the drug molecule properties, so as to obtain the final drug small molecule population as the final optimization result.

[0017] The present invention also has the characteristics of a small molecule drug optimization method based on evolutionary computation and multi-granularity agent model approximation, in that step three is performed according to the following steps:

[0018] Step 3.1: Construct a variational autoencoder, including an encoder and a decoder, and Process and obtain The reconstructed word vector ;

[0019] Step 3.2: Use formula (3) to calculate the total loss of the variational autoencoder in the Iter generation :

[0020] = (3)

[0021] In formula (3), represents the kl divergence loss of the Iter generation, represents the reconstruction loss of the Iter generation, , Represents the weights corresponding to the two losses; and:

[0022] (4)

[0023] (5)

[0024] In formula (4) and formula (5), represents the logarithmic function;

[0025] Step 3.3: Train the variational autoencoder using back propagation and gradient descent, and calculate To update the network parameters until Until convergence, the variational autoencoder with the optimal parameters of the Iter generation is obtained;

[0026] Step 3.4: Add the kth drug molecule Input the optimal parameters of the Iter generation variational autoencoder and get The optimal latent vector ,in, express The optimal potential feature of the rth dimension in , thus obtaining The optimal latent vector .

[0027] Furthermore, the step 3.1 includes:

[0028] Step 3.1.1, randomly initialize the neural network weights in the encoder and decoder;

[0029] Step 3.1.2: For the kth drug molecule Perform word embedding to obtain the kth word vector of the Iter generation ,in, express The nth word vector in , Represents the total number of word vectors;

[0030] Step 3.1.3: Input into the encoder and get The mean and variance , thus according to formula (2) we can get the kth drug molecule of the Iter generation The latent vector ,in, express The r-th dimension feature in ;

[0031] (2)

[0032] In formula (2), e represents the exponential function, esp is the random noise sampled from the standard normal distribution;

[0033] Step 3.1.4: The decoder performs autoregression Process and obtain the kth drug molecule The reconstructed word vector ={ },in, express The mth word vector in .

[0034] Furthermore, the step 4 includes:

[0035] Step 4.1: Use formula (6) to calculate the zth dimension: The correlation matrix The kth row in Column Elements , thus obtaining the kth drug small molecule and The correlation vector :

[0036] (6)

[0037] In formula (6), is the r-th dimension parameter of the z-th proxy model of the Iter-th generation; Indicates Small molecule drug The optimal latent vector The optimal potential feature of the rth dimension in; z=1,2;

[0038] Step 4.2: Construct training data for the zth proxy model , including: training data set of the first proxy model and the coarse-grained training dataset of the second proxy model ;

[0039] Step 4.3: Use formula (8) to get the mean of the zth proxy model of the Iter generation: :

[0040] (8)

[0041] In formula (8), represents an N-dimensional all-1 vector, and T represents transpose;

[0042] Step 4.4: Use formula (9) to solve the parameter set of the zth proxy model of the Iter generation: { }, and get the trained z-th proxy model:

[0043] (9)

[0044] In formula (9), Indicates the training data of the z-th surrogate model The true objective optimization value or true constraint violation degree of ; and ∈{ , , }.

[0045] Further, the step 4.2 includes:

[0046] Step 4.2.1: Build a training dataset for training the first proxy model ,in, Represents the kth drug small molecule The sum of the three optimization objectives;

[0047] Step 4.2.2: If The molecular weight constraint violation and hydrogen bond donor number constraint violation are both greater than 0, that is, any i-th constraint is not satisfied. Then, the k-th drug small molecule of the Iter generation is obtained using formula (7): Constraint violation of aggregate value , thereby obtaining the coarse-grained training data of the second proxy model :

[0048] (7)

[0049] In formula (7), respectively The maximum and minimum values ​​on the i-th constraint;

[0050] like Among the molecular weight constraint violation and hydrogen bond donor number constraint violation, only one constraint violation is greater than 0, that is, there is only one unsatisfied constraint, denoted as , then construct the fine-grained training data of the second proxy model ,in, Represents the kth drug small molecule of the Iter generation The constraint violation degree of the unsatisfied constraints.

[0051] Furthermore, the step five includes:

[0052] Step 5.1: The corresponding optimal latent vector set As the parent molecule;

[0053] Step 5.2: Based on the optimization target value and constraint violation degree of the drug small molecule, perform crossover mutation operation on the optimal potential vector in the parent molecule to generate the daughter molecule ;

[0054] Step 5.3, use The corresponding trained z-th proxy model pair The multi-attribute optimization objectives and constraint violation degrees of each drug small molecule in the molecule are predicted, and then the environmental selection method of the non-dominated sorting genetic algorithm NSGA-II is used to select the parent molecule according to the prediction results. and daughter molecules After screening N high-quality drug small molecules as new parent molecules, return to step 5.2 and execute sequentially Second, get the The parent molecule in the second cycle is used as the Iter+1 generation drug small molecule population ;

[0055] Step 5.4: Input the trained decoder for processing and obtain The optimal latent vector of each drug small molecule in is decoded into a SMILES string;

[0056] Step 5.5: Use RDKit to The decoded SMILES string is evaluated to obtain its true multi-attribute optimization objective and constraint violation degree;

[0057] Step 5.6: After assigning Iter+1 to Iter, return to step 3 and execute sequentially until the maximum number of iterations is reached, thereby outputting the last generation of drug small molecule population as the final optimization result.

[0058] The electronic device of the present invention includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the drug small molecule optimization method, and the processor is configured to execute the program stored in the memory.

[0059] The present invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program executes the steps of the drug small molecule optimization method when executed by a processor.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] 1. The multi-granularity proxy model approximation method proposed in the present invention dynamically adjusts the proxy model approximation granularity according to the position of the evolving molecular population in the adaptation landscape. If the evolving molecular population violates all constraints, a proxy model is trained for each target and a coarse-grained model is trained for all constraints; if the evolving molecular population only violates some constraints, a proxy model is trained for each target and a fine-grained model is trained for each constraint that is not fully satisfied; if the evolving molecular population does not violate any constraints, only one proxy model is trained for each target. Based on this strategy, the proposed method can dynamically adjust the strategy of the training model according to the constraint violation of the drug small molecule, thereby improving the approximation accuracy of the proxy model.

[0062] 2. The present invention designs a special model updating strategy to dynamically adjust the comparison criteria of the advantages and disadvantages of drug molecules according to the distance between the molecular population and the feasible region. When the molecular population is far away from the feasible domain, the constraint dominance principle is used to update the training data and the molecular population, so as to improve the degree of constraint satisfaction of the drug molecules; when the molecular population is close to the feasible domain, the multi-objective method is used to update the training data and the molecular population, so as to balance the optimization of drug molecule properties and constraint satisfaction; when the molecular population completely enters the feasible domain, the training data and the molecular population are updated only based on the multi-attribute target value, so as to maximize the optimization of molecular properties. By dynamically adjusting the update method of the training data and the molecular population, the proposed strategy can reduce the impact caused by the approximate error of the proxy model and avoid the drug molecules from falling into the local optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is a flow chart of the method of the present invention;

[0064] Figure 2 Schematic diagram of training the multi-granularity proxy model in the present invention. DETAILED DESCRIPTION

[0065] In this embodiment, a small molecule drug optimization method based on evolutionary computation and multi-granularity agent model approximation is described. Figure 1 As shown, it is applied to optimize the structure of small drug molecules and is carried out in the following steps:

[0066] Step 1: Obtain the kth drug small molecule to be optimized , and use the RDKit tool to identify the kth drug small molecule The biological properties were evaluated and obtained Molecular drug properties , synthetic accessibility and molecular toxicity ; Thus, using formula (1) to construct The multi-attribute optimization objective And its constraints:

[0067] (1)

[0068] In formula (1), represents the search space, and Respectively represent The molecular weight constraint violation and the hydrogen bond donor number constraint violation are and Represents small molecule drugs The molecular weight and number of hydrogen bond donors, and Represent the maximum molecular weight and the number of hydrogen bond donors, respectively.

[0069] Drug-like properties of molecules , synthetic accessibility and molecular toxicity Recorded as Any j-th optimization goal of ; j = 1, 2, 3;

[0070] Will and Recorded as Any i-th constraint of ; i=1,2.

[0071] Step 2: Generate an initial population of drug small molecules uniformly in the discrete chemical space, and evaluate the violation of the multi-attribute optimization objectives and their constraints;

[0072] Step 2.1, define and initialize the current iteration number as Iter=0; and define the Iter generation drug small molecule population ,in, represent The kth drug molecule in , N represents the size of the population;

[0073] Generate SMILES strings uniformly in discrete chemical space for initialization Each drug small molecule in

[0074] Step 2.2: According to formula (1), we can get The violation degree of the multi-attribute optimization objectives and their constraints for each drug molecule in .

[0075] Step 3: Train the variational autoencoder Encoding from discrete chemical space to continuous latent space yields Continuous vector representation of ;

[0076] Step 3.1: Construct a variational autoencoder, including an encoder and a decoder, and Process and obtain The reconstructed word vector ;

[0077] Step 3.1.1, randomly initialize the neural network weights in the encoder and decoder;

[0078] Step 3.1.2: For the kth drug molecule Perform word embedding to obtain the kth word vector of the Iter generation ,in, express The nth word vector in , Represents the total number of word vectors;

[0079] Step 3.1.3: Input into the encoder and get The mean and variance , thus according to formula (2) we can get the kth drug molecule of the Iter generation The latent vector ,in, express The r-th dimension feature in ;

[0080] (2)

[0081] In formula (2), e represents the exponential function, and esp is the random noise sampled from the standard normal distribution.

[0082] Step 3.1.4: The decoder performs autoregression Process and obtain the kth drug molecule The reconstructed word vector ={ },in, express The mth word vector in .

[0083] Step 3.2: Use formula (3) to calculate the total loss of the variational autoencoder in the Iter generation :

[0084] = (3)

[0085] In formula (3), represents the kl divergence loss of the Iter generation, represents the reconstruction loss of the Iter generation, , Represents the weights corresponding to the two losses; and:

[0086] (4)

[0087] (5)

[0088] In formula (4) and formula (5), Represents a logarithmic function.

[0089] Step 3.3: Train the variational autoencoder using back propagation and gradient descent, and calculate To update the network parameters until Until convergence, the variational autoencoder with the optimal parameters of the Iter generation is obtained;

[0090] Step 3.4: Add the kth drug molecule Input the optimal parameters of the Iter generation variational autoencoder and get The optimal latent vector ,in, express The optimal potential feature of the rth dimension in . Thus we get The optimal latent vector .

[0091] Step 4: Figure 2 As shown, build two proxy models and use The optimal potential vector of each drug small molecule and its corresponding multi-attribute optimization target value and constraint violation degree are used as training data to train each proxy model separately and obtain the hyperparameters of each model:

[0092] Step 4.1: Use formula (6) to calculate the zth dimension: The correlation matrix The kth row in Column Elements :

[0093] (6)

[0094] In formula (6), is the r-th dimension parameter of the z-th proxy model of the Iter-th generation; Indicates Small molecule drug The optimal latent vector The optimal potential feature of the rth dimension in; z=1,2;

[0095] Using formula (6), we can get the relationship between the kth drug small molecule and the zth agent model. The correlation vector .

[0096] Step 4.2: Construct training data for the zth proxy model , including: training data set of the first proxy model and the coarse-grained training dataset of the second proxy model ;

[0097] Step 4.2.1: Build a training dataset for training the first proxy model ,in, Represents the kth drug small molecule The weighted summation of the three optimization objectives is performed. Since the dimensions of the three optimization objectives are different, the target value of each optimization objective is first normalized to the interval [0, 1] and then the summation operation is performed.

[0098] Step 4.2.2: If The molecular weight constraint violation and hydrogen bond donor number constraint violation are both greater than 0, that is, any i-th constraint is not satisfied. Then, the k-th drug small molecule of the Iter generation is obtained using formula (7): Constraint violation of aggregate value , thereby obtaining the coarse-grained training data of the second proxy model :

[0099] (7)

[0100] In formula (7), respectively The maximum and minimum values ​​on the ith constraint.

[0101] like Among the molecular weight constraint violation and hydrogen bond donor number constraint violation, only one constraint violation is greater than 0, that is, there is only one unsatisfied constraint, denoted as , then construct the fine-grained training data of the second proxy model ,in, Represents the kth drug small molecule of the Iter generation The constraint violation degree of the unsatisfied constraints.

[0102] Step 4.4: Use formula (8) to get the mean of the zth proxy model of the Iter generation: :

[0103] (8)

[0104] In formula (8), represents an N-dimensional all-1 vector, and T represents transpose.

[0105] Step 4.5: Use formula (9) to solve the parameter set of the zth proxy model of the Iter generation: { }, and get the trained z-th proxy model:

[0106] (9)

[0107] In formula (9), Indicates the training data of the z-th surrogate model The true objective optimization value or true constraint violation degree of ; and ∈{ , , }.

[0108] Step 5: Use the surrogate model trained in step 4 to assist the evolutionary algorithm to iteratively optimize the molecular properties of the drug;

[0109] Step 5.1: The corresponding optimal latent vector set As the parent molecule;

[0110] Step 5.2: Based on the optimization target value and constraint violation degree of the drug small molecule, perform crossover mutation operation on the optimal potential vector in the parent molecule to generate the daughter molecule ;

[0111] Step 5.3, use The corresponding trained z-th proxy model pair The multi-attribute optimization objectives and constraint violation degrees of each drug small molecule in the molecule are predicted, and then the environmental selection method of the non-dominated sorting genetic algorithm NSGA-II is used to select the parent molecule according to the prediction results. and daughter molecules After screening N high-quality drug small molecules as new parent molecules, return to step 5.2 and execute sequentially Second, get the The parent molecule in the second cycle is used as the Iter+1 generation drug small molecule population .

[0112] In order to balance the property optimization and constraint satisfaction of the molecular population, when screening high-quality drug small molecules, the proposed method dynamically adjusts the method of comparing the pros and cons of molecules according to the position of the molecular population in the search space. Specifically, when the molecular population is far away from the feasible domain, the proposed method uses the constraint dominance principle to compare the pros and cons of different molecules, as shown in formula (10):

[0113] (10)

[0114] In formula (10), and For two small drug molecules, Representative drug small molecules The degree of constraint violation, Representative molecules The i-th constraint value of Representative molecules The jth target value of The degree of violation Equal to the numerator The degree of violation , if we consider that the molecule Better than molecules , then the molecule All target values ​​of and is better than at least one target value If the numerator The degree of violation Smaller than the molecule The degree of violation , then we can directly consider the molecule Better than molecules .

[0115] When the molecular population is close to the boundary of the feasible domain, the proposed method first calculates the constraint violation values ​​of all molecules, and then takes the constraint violation values ​​as optimization targets and processes them together with the original three optimization targets, so as to compare the advantages and disadvantages of different molecules based on the four optimization target values; when the molecular population completely enters the feasible domain, the proposed method only compares the advantages and disadvantages of molecules based on the three optimization target values.

[0116] Step 5.4: Input the trained decoder for processing and obtain The optimal latent vector of each drug small molecule in is decoded into a SMILES string;

[0117] Step 5.5: Use RDKit to The decoded SMILES string is evaluated to obtain its true multi-attribute optimization objective and constraint violation degree;

[0118] Step 6: After assigning Iter+1 to Iter, return to step 3 and execute sequentially until the maximum number of iterations is reached, thereby outputting the last generation of drug small molecule population as the final optimization result.

[0119] In this embodiment, an electronic device includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0120] In this embodiment, a computer-readable storage medium stores a computer program on the computer-readable storage medium, and the computer program executes the steps of the above method when executed by a processor.

Claims

1. A small molecule drug optimization method based on evolutionary computation and multi-granularity agent model approximation, characterized in that: The steps are as follows: Step 1: Obtain the kth drug small molecule to be optimized , and use the RDKit tool to identify the kth drug small molecule The biological properties were evaluated and obtained Molecular drug properties , synthetic accessibility and molecular toxicity ; Thus, using formula (1) to construct The multi-attribute optimization objective And its constraints: (1) In formula (1), represents the search space, and Respectively represent The molecular weight constraint violation and the hydrogen bond donor number constraint violation are and Represents small molecule drugs The molecular weight and number of hydrogen bond donors, and Represent the maximum values ​​of molecular weight and number of hydrogen bond donors respectively; Drug-like properties of molecules , synthetic accessibility and molecular toxicity Recorded as Any j-th optimization goal of ; j = 1, 2, 3; Will and Recorded as Any i-th constraint of ; i = 1, 2; Step 2: Define and initialize the current iteration number as Iter=0; and define the Iter generation drug small molecule population ,in, represent The kth drug molecule in , N represents the size of the population; Generate SMILES strings uniformly in discrete chemical space for initialization Each drug small molecule in, thus calculated according to formula (1) The violation degree of the multi-attribute optimization objectives and constraints of each drug molecule in; Step 3: Train the variational autoencoder to convert Encoding from discrete chemical space to continuous latent space yields The optimal latent vector ; Step 4: Build two proxy models and use The optimal potential vector of each drug small molecule and its corresponding multi-attribute optimization target value and constraint violation degree are used as training data, and each proxy model is trained separately to obtain a trained proxy model; Step 5: Use the trained zth proxy model to assist the evolutionary algorithm to iteratively optimize the drug molecule properties, so as to obtain the final drug small molecule population as the final optimization result.

2. The method for optimizing small drug molecules based on evolutionary computation and multi-granularity agent model approximation according to claim 1, characterized in that: Step three is to proceed as follows: Step 3.1: Construct a variational autoencoder, including an encoder and a decoder, and Process and obtain The reconstructed word vector ; Step 3.2: Use formula (3) to calculate the total loss of the variational autoencoder in the Iter generation : = (3) In formula (3), represents the kl divergence loss of the Iter generation, represents the reconstruction loss of the Iter generation, , Represents the weights corresponding to the two losses; and: (4) (5) In formula (4) and formula (5), represents the logarithmic function; Step 3.3: Train the variational autoencoder using back propagation and gradient descent, and calculate To update the network parameters until Until convergence, the variational autoencoder with the optimal parameters of the Iter generation is obtained; Step 3.4: Add the kth drug molecule Input the optimal parameters of the Iter generation variational autoencoder and get The optimal latent vector ,in, express The optimal potential feature of the rth dimension in , thus obtaining The optimal latent vector .

3. The method for optimizing small drug molecules based on evolutionary computation and multi-granularity agent model approximation according to claim 2, characterized in that: The step 3.1 comprises: Step 3.1.1, randomly initialize the neural network weights in the encoder and decoder; Step 3.1.2: For the kth drug molecule Perform word embedding to obtain the kth word vector of the Iter generation ,in, express The nth word vector in , Represents the total number of word vectors; Step 3.1.3: Input into the encoder and get The mean and variance , thus according to formula (2) we can get the kth drug molecule of the Iter generation The latent vector ,in, express The r-th dimension feature in ; (2) In formula (2), e represents the exponential function, esp is the random noise sampled from the standard normal distribution; Step 3.1.4: The decoder performs autoregression Process and obtain the kth drug molecule The reconstructed word vector ={ },in, express The mth word vector in .

4. The method for optimizing small drug molecules based on evolutionary computation and multi-granularity agent model approximation according to claim 3, characterized in that: The fourth step comprises: Step 4.1: Use formula (6) to calculate the zth dimension: The correlation matrix The kth row in Column Elements , thus obtaining the kth drug small molecule and The correlation vector : (6) In formula (6), is the r-th dimension parameter of the z-th proxy model of the Iter-th generation; Indicates Small molecule drug The optimal latent vector The optimal latent feature of the rth dimension in; z=1,2; Step 4.2: Construct training data for the zth proxy model , including: training data set of the first proxy model and the coarse-grained training dataset of the second proxy model ; Step 4.3: Use formula (8) to get the mean of the zth proxy model of the Iter generation: : (8) In formula (8), represents an N-dimensional all-1 vector, and T represents transpose; Step 4.4: Use formula (9) to solve the parameter set of the zth proxy model of the Iter generation: { }, and get the trained z-th proxy model: (9) In formula (9), Indicates the training data of the z-th surrogate model The true objective optimization value or true constraint violation degree of ; and ∈{ , , }.

5. The method for optimizing small drug molecules based on evolutionary computation and multi-granularity agent model approximation according to claim 4, characterized in that: The step 4.2 comprises: Step 4.2.1: Build a training dataset for training the first proxy model ,in, Represents the kth drug small molecule The sum of the three optimization objectives; Step 4.2.2: If The molecular weight constraint violation and hydrogen bond donor number constraint violation are both greater than 0, that is, any i-th constraint is not satisfied. Then, the k-th drug small molecule of the Iter generation is obtained using formula (7): Constraint violation of aggregate value , thereby obtaining the coarse-grained training data of the second proxy model : (7) In formula (7), respectively The maximum and minimum values ​​on the i-th constraint; like Among the molecular weight constraint violation and hydrogen bond donor number constraint violation, only one constraint violation is greater than 0, that is, there is only one unsatisfied constraint, denoted as , then construct the fine-grained training data of the second proxy model ,in, Represents the kth drug small molecule of the Iter generation The constraint violation degree of the unsatisfied constraints.

6. The method for optimizing small drug molecules based on evolutionary computation and multi-granularity agent model approximation according to claim 5, characterized in that: The step five comprises: Step 5.1: The corresponding optimal latent vector set As the parent molecule; Step 5.2: Based on the optimization target value and constraint violation degree of the drug small molecule, perform crossover mutation operation on the optimal potential vector in the parent molecule to generate the daughter molecule ; Step 5.3, use The corresponding trained z-th proxy model pair The multi-attribute optimization objectives and constraint violation degrees of each drug small molecule in the molecule are predicted, and then the environmental selection method of the non-dominated sorting genetic algorithm NSGA-II is used to select the parent molecule according to the prediction results. and daughter molecules After screening N high-quality drug small molecules as new parent molecules, return to step 5.2 and execute sequentially Second, get the The parent molecule in the second cycle is used as the Iter+1 generation drug small molecule population ; Step 5.4: Input the trained decoder for processing and obtain The optimal latent vector of each drug small molecule in is decoded into a SMILES string; Step 5.5: Use RDKit to The decoded SMILES string is evaluated to obtain its true multi-attribute optimization objective and constraint violation degree; Step 5.6: After assigning Iter+1 to Iter, return to step 3 and execute sequentially until the maximum number of iterations is reached, thereby outputting the last generation of drug small molecule population as the final optimization result.

7. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute the drug small molecule optimization method described in any one of claims 1 to 6, and the processor is configured to execute the program stored in the memory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the drug small molecule optimization method according to any one of claims 1 to 6 are executed.

Images