Parameter optimization of candidate molecules, target molecule design method, device, equipment and storage medium

Abstract

The application relates to a candidate molecule parameter optimization, target molecule design method, device, equipment and storage medium. The method comprises the following steps: determining a designable site and an optimizable parameter on a candidate molecule, adjusting the value of the optimizable parameter, determining an optimal complex, and determining the value of the optimizable parameter corresponding to the optimal complex as the optimal value of the optimizable parameter. The embodiment of the application determines the designable site on the candidate molecule and the optimizable parameter of the designable site, adjusts the value of the optimizable parameter, calculates the binding free energy of the candidate complex corresponding to each value, determines the optimal value of the optimizable parameter according to the binding free energy, determines the design direction of the candidate molecule according to the limitation of the chemical structure of the designable site to the optimal value of the optimizable parameter, provides an explicit idea for molecular design, effectively reduces the calculation amount of molecular design, improves experimental efficiency, simultaneously realizes complete automation of the whole molecular process, and reduces the difficulty of molecular design.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of molecular design, and in particular to a parameter optimization method for a candidate molecule, a target molecule design method, device, equipment and storage medium. BACKGROUND

[0002] Traditional drug design mainly relies on trial and error, and lacks mature and perfect drug discovery means and paths. With the development of science and technology and computers, the idea of rational design has gradually matured, and the design of active molecules based on structure has gradually begun to be applied.

[0003] In related technologies, a three-dimensional model can be constructed to better understand the shape, physicochemical properties, etc. of the small molecule pocket activity, and help to design molecules with good activity. However, this design method is too dependent on the personal experience of experts, and the iteration cycle of design is long. On the other hand, the interaction between the active pocket and the small molecule is very complex, and it is difficult to predict the change of activity, so it is impossible to accurately determine the design direction of the new molecule according to the design requirements, resulting in a waste of a large amount of computing power. In addition, for the new molecules designed, there may be too many new molecules, and the calculation demand for measuring the activity of the new molecules also increases sharply, increasing the difficulty of molecular design, which needs to be improved. SUMMARY

[0004] To solve or partially solve the problems in the related art, the present application provides a parameter optimization method for a candidate molecule, a target molecule design method, device, equipment and storage medium, which can automatically explore the active pocket, provide ideas for new molecule design, provide accurate design direction for new molecule design, complete the design of target new molecules, and save computing power.

[0005] The first aspect of the present application provides a parameter optimization method for a candidate molecule, comprising:

[0006] determining a designable site on the candidate molecule and an optimizable parameter of the designable site, wherein the candidate molecule can form a complex with a preset protein through the designable site, and the optimizable parameter is used to limit the chemical structure of the designable site;

[0007] adjusting the value of the optimizable parameter, calculating the binding free energy of the candidate complex corresponding to each value, determining a preferred complex in the plurality of candidate complexes based on the binding free energy, and determining the value of the optimizable parameter corresponding to the preferred complex as the preferred value of the optimizable parameter.

[0008] As a possible implementation manner of the present application, in this implementation manner, the adjusting the value of the optimizable parameter, calculating the binding free energy of the candidate complex corresponding to each value, determining a preferred complex in the plurality of candidate complexes based on the binding free energy, comprises:

[0009] S11, obtaining a gradient value of the binding free energy of the candidate complex based on the initial value of the optimizable parameter;

[0010] S12, judging whether the gradient value is less than or equal to a preset threshold value; if the gradient value is less than or equal to the preset threshold value, the initial value of the optimizable parameter is a preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold value, adjusting the initial value of the optimizable parameter according to a preset optimization step to obtain an adjusted value of the optimizable parameter; and assigning the adjusted value of the optimizable parameter as the initial value of the optimizable parameter;

[0011] S13, repeatedly performing steps S11 and S12 until the gradient value is less than or equal to the preset threshold value, to obtain the preferred value of the optimizable parameter.

[0012] As a possible implementation of the present application, when there are multiple optimizable parameters for one of the designable sites, the adjusting of the value of the optimizable parameter, the calculation of the binding free energy of the candidate complex corresponding to each value, and the determination of the preferred complex among the multiple candidate complexes based on the binding free energy, comprise:

[0013] For any optimizable parameter, keeping the rest of the parameters unchanged except the any optimizable parameter, adjusting the value of the any optimizable parameter, and calculating the binding free energy of the candidate complex corresponding to each value;

[0014] Determining the preferred complex among the multiple candidate complexes corresponding to all the optimizable parameters.

[0015] As a possible implementation of the present application, when there are multiple designable sites on the candidate molecule, the adjusting of the value of the optimizable parameter, the calculation of the binding free energy of the candidate complex corresponding to each value, and the determination of the preferred complex among the multiple candidate complexes based on the binding free energy, comprise:

[0016] For any designable site, keeping the parameters of the rest of the designable sites unchanged except the any designable site, adjusting the value of the optimizable parameter of the any designable site, and calculating the binding free energy of the candidate complex corresponding to each value; wherein the optimizable parameter of each designable site can be one or more;

[0017] Determining the preferred complex among the multiple candidate complexes corresponding to all the designable sites.

[0018] The second aspect of the present application provides a target molecule design method, which comprises:

[0019] design the candidate molecule based on the preferred value of the optimizable parameter to obtain a target molecule.

[0020] As a possible implementation of the present application, the designable site is optimized based on the preferred value of the optimizable parameter to obtain at least one optimized molecule.

[0021] The at least one optimized molecule is evaluated by using a first preset molecule evaluation method, and a first recommended molecule is determined based on the evaluation result.

[0022] As a possible implementation of the present application, in this implementation, the target molecule design method further comprises:

[0023] The at least one optimized molecule is combined with a preset protein to obtain at least one optimized complex;

[0024] The at least one optimized complex is evaluated by using a second preset molecule evaluation method, and a second recommended molecule is determined based on the evaluation result.

[0025] A target molecule is determined from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0026] As a possible implementation of the present application, in this implementation, the designable site is optimized based on the preferred value of the optimizable parameter, comprising:

[0027] According to the restriction of the optimizable parameter on the designable site, the designable site is operated in one or more of the following operations:

[0028] The designable site is deleted, and the candidate molecule is adjusted adaptively,

[0029] The designable site is replaced by using a preset replacement unit.

[0030] As a possible implementation of the present application, in this implementation, the at least one optimized molecule is evaluated by using a first preset molecule evaluation method, and a first recommended molecule is determined based on the evaluation result, comprising:

[0031] The preset parameter value of the at least one optimized molecule is calculated by using a first preset molecule evaluation method;

[0032] The optimized molecule with the preset parameter value higher than a first preset threshold value is determined as the first recommended molecule.

[0033] As a possible implementation of the present application, in this implementation, the target molecule is determined from the first recommended molecule and the second recommended molecule according to a preset screening rule, comprising:

[0034] determining a target molecule from the first recommended molecule and the second recommended molecule based on the evaluation result of the first recommended molecule and the evaluation result of the second recommended molecule using a weighted average algorithm.

[0035] The third aspect of the present application provides a parameter optimization device for a candidate molecule, comprising:

[0036] a parameter selection module configured to determine a designable site on a candidate molecule and an optimizable parameter of the designable site, wherein the candidate molecule is capable of forming a complex with a preset protein through the designable site, and the optimizable parameter is used to limit the chemical structure of the designable site;

[0037] a parameter determination module configured to adjust the value of the optimizable parameter, calculate the binding free energy of a candidate complex corresponding to each value, determine a preferred complex from a plurality of candidate complexes based on the binding free energy, and determine the value of the optimizable parameter corresponding to the preferred complex as the preferred value of the optimizable parameter.

[0038] As a possible implementation of the present application, in this implementation, when the parameter determination module adjusts the value of the optimizable parameter, calculates the binding free energy of a candidate complex corresponding to each value, and determines a preferred complex from a plurality of candidate complexes based on the binding free energy, it is configured to:

[0039] S11, obtaining a gradient value of the binding free energy of the candidate complex based on the initial value of the optimizable parameter;

[0040] S12, determining whether the gradient value is less than or equal to a preset threshold value; if the gradient value is less than or equal to the preset threshold value, the initial value of the optimizable parameter is the preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold value, adjusting the initial value of the optimizable parameter according to a preset optimization step to obtain an adjusted optimizable parameter value; and assigning the adjusted optimizable parameter value as the initial value of the optimizable parameter;

[0041] S13, repeating steps S11 and S12 until the gradient value is less than or equal to the preset threshold value, and obtaining the preferred value of the optimizable parameter.

[0042] As a possible implementation of the present application, in this implementation, when there are multiple optimizable parameters for one designable site, when the parameter determination module adjusts the value of the optimizable parameter, calculates the binding free energy of a candidate complex corresponding to each value, and determines a preferred complex from a plurality of candidate complexes based on the binding free energy, it is configured to:

[0043] For any one of the optimizable parameters, keep the rest of the parameters unchanged except for the any one of the optimizable parameters, adjust the value of the any one of the optimizable parameters, and calculate the binding free energy of the candidate complex corresponding to each value;

[0044] Determine the preferred complex among the plurality of candidate complexes corresponding to all the optimizable parameters.

[0045] As a possible implementation of the present application, in this implementation, when there are multiple designable sites on the candidate molecule, the parameter determination module adjusts the value of the optimizable parameter, calculates the binding free energy of the candidate complex corresponding to each value, and determines the preferred complex among the plurality of candidate complexes based on the binding free energy, for:

[0046] For any one of the designable sites, keep the parameters of the rest of the designable sites unchanged except for the any one of the designable sites, adjust the value of the optimizable parameter of the any one of the designable sites, and calculate the binding free energy of the candidate complex corresponding to each value; wherein the optimizable parameter of each of the designable sites can have one or more;

[0047] Determine the preferred complex among the plurality of candidate complexes corresponding to all the designable sites.

[0048] The fourth aspect of the present application provides a target molecule design device, which is used to design the candidate molecule according to the preferred value of the optimizable parameter obtained in the foregoing method embodiments, to obtain a target molecule.

[0049] As a possible implementation of the present application, in this implementation, the target molecule design device comprises:

[0050] An optimized molecule determination module is configured to optimize the designable sites based on the preferred value of the optimizable parameter, to obtain at least one optimized molecule;

[0051] A first recommended molecule determination module is configured to evaluate the at least one optimized molecule by using a first preset molecule evaluation method, and determine a first recommended molecule based on the evaluation result.

[0052] As a possible implementation of the present application, in this implementation, the target molecule design device further comprises:

[0053] An optimized complex determination module is configured to combine the at least one optimized molecule with a preset protein respectively, to obtain at least one optimized complex;

[0054] A second recommended molecule determination module is configured to evaluate the at least one optimized complex by using a second preset molecule evaluation method, and determine a second recommended molecule based on the evaluation result.

[0055] a target molecule determination module, configured to determine a target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0056] In a possible implementation of the present application, when the optimization molecule determination module optimizes the designable site based on the preferred value of the optimizable parameter, the optimization molecule determination module is configured to:

[0057] According to the restriction of the optimizable parameter on the designable site, the optimization molecule determination module is configured to perform one or more of the following operations on the designable site:

[0058] delete the designable site and adaptively adjust the candidate molecule,

[0059] replace the designable site with a preset replacement unit.

[0060] In a possible implementation of the present application, when there are multiple preset replacement units, when the optimization molecule determination module replaces the designable site with a preset replacement unit, the optimization molecule determination module is configured to:

[0061] replace the designable site with the multiple preset replacement units respectively to obtain multiple optimized molecules;

[0062] When the first recommended molecule determination module evaluates the at least one optimized molecule by using a first preset molecule evaluation method and determines the first recommended molecule based on the evaluation result, the first recommended molecule determination module is configured to:

[0063] evaluate the multiple optimized molecules by using the first preset molecule evaluation method and determine the first recommended molecule based on the evaluation result.

[0064] In a possible implementation of the present application, when the first recommended molecule determination module evaluates the at least one optimized molecule by using a first preset molecule evaluation method and determines the first recommended molecule based on the evaluation result, the first recommended molecule determination module is configured to:

[0065] calculate a preset parameter value of the at least one optimized molecule by using the first preset molecule evaluation method;

[0066] determine the optimized molecule with the preset parameter value higher than a first preset threshold as the first recommended molecule.

[0067] In a possible implementation of the present application, when the target molecule determination module determines a target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule, the target molecule determination module can be configured to:

[0068] Based on the evaluation results of the first recommended molecule and the evaluation results of the second recommended molecule, a weighted average algorithm is used to determine a target molecule from the first recommended molecule and the second recommended molecule.

[0069] The fifth aspect of the present application provides an electronic device, comprising:

[0070] a processor; and

[0071] a memory having stored thereon executable code that, when executed by the processor, causes the processor to perform the method as described above.

[0072] The sixth aspect of the present application provides a computer-readable storage medium having stored thereon executable code that, when executed by a processor of an electronic device, causes the processor to perform the method as described above.

[0073] The embodiments of the present application determine the designable site on the candidate molecule and the optimizable parameter of the designable site, adjust the value of the optimizable parameter, calculate the binding free energy of the candidate complex corresponding to each value, determine the preferred value of the optimizable parameter according to the binding free energy, determine the design direction of the candidate molecule according to the restriction of the chemical structure of the designable site by the preferred value of the optimizable parameter, provide an explicit idea for molecular design, effectively reduce the calculation amount of molecular design, improve the experimental efficiency, and at the same time, the entire molecular process is fully automated, reducing the difficulty of molecular design.

[0074] The embodiments of the present application also design the designable site by the preferred value of the optimizable parameter, determine the optimized molecule, evaluate the activity of the optimized molecule by using the easily preset molecular evaluation method, determine the recommended new molecule according to the activity, and finally determine the target molecule, which can effectively reduce the number of new molecules that need to be calculated for activity, further reduce the calculation amount of molecular design, and improve the efficiency of molecular design.

[0075] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0076] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like reference characters refer to like parts throughout the several views, and in which:

[0077] Figure 1 is a flowchart of the parameter optimization method of the candidate molecule shown in the embodiments of the present application;

[0078] Figure 2is a flowchart of a preferred complex determination method shown in an embodiment of the present application;

[0079] Figure 3 is a flowchart of a preferred complex determination method in multiple designable sites shown in an embodiment of the present application;

[0080] Figure 4 is a flowchart of a preferred complex determination method in multiple designable sites shown in an embodiment of the present application;

[0081] Figure 5 is a flowchart of a molecular design method of a target shown in an embodiment of the present application;

[0082] Figure 6 is a flowchart of a target determination design method shown in an embodiment of the present application;

[0083] Figure 7 is a flowchart of a first recommended molecule determination method shown in an embodiment of the present application;

[0084] Figure 8 is a structural diagram of a parameter optimization device of a candidate molecule shown in an embodiment of the present application;

[0085] Figure 9 is a structural diagram of a molecular design device of a target shown in an embodiment of the present application;

[0086] Figure 10 is a structural diagram of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0087] Embodiments of the present application will be described in more detail by referring to the attached drawings. Although embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0088] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the present application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0089] It should be understood that, although the terms "first", "second", "third", etc. can be used in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information without departing from the scope of the present application. Therefore, the features defined as "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0090] Traditional drug design is mainly trial and error, and there is a lack of mature and perfect drug discovery means and path. With the development of science and technology and computers, the idea of rational design gradually matures, and the design of active molecules based on structure gradually begins to be applied. In the related technology, the shape, physicochemical properties, etc. of the small molecule pocket activity can be better understood by constructing a three-dimensional model, which helps to design molecules with good activity. However, this design method relies too much on the personal experience of experts, and the iteration cycle of design is long. On the other hand, the interaction between the active pocket and the small molecule is very complex, and it is difficult to predict the change of activity, so it is impossible to accurately determine the design direction of the new molecule according to the design requirements, resulting in a waste of a large amount of computing power. And for the new molecules designed, there may be too many new molecules, and the calculation demand of the activity measurement of the new molecules also increases sharply, increasing the difficulty of molecular design, which needs to be improved.

[0091] In view of the above problems, the embodiments of the present application provide a candidate molecule parameter optimization method, a target molecule design method, device and storage medium, which can automatically explore the active pocket, provide ideas for new molecule design, provide accurate design direction for new molecule design, complete the design of target new molecules, and save computing power.

[0092] The technical solutions of the embodiments of the present application are described in detail below with reference to the drawings.

[0093] Figure 1 is a flowchart of the candidate molecule parameter optimization method shown in the embodiments of the present application.

[0094] Referring to Figure 1 The candidate molecule parameter optimization method provided by the embodiments of the present application comprises:

[0095] Step S101, determining a designable site on a candidate molecule and an optimizable parameter of the designable site, wherein the candidate molecule can form a complex with a preset protein through the designable site, and the optimizable parameter is used to limit the chemical structure of the designable site.

[0096] In the embodiment of the present application, the candidate molecule refers to a small molecule that can bind with the preset protein to form a complex with activity. By designing the designable site on the candidate molecule, the binding free energy of the binding between the candidate molecule and the preset protein is as low as possible, the stability of the binding between the candidate molecule and the preset protein is ensured, and a clear direction is provided for the design of the new molecule. The designable site on the candidate molecule refers to one or more atoms or groups on the candidate molecule, and the preset protein binds with the candidate molecule to form a complex through the designable site. The designable site on the candidate molecule can be determined according to the experience of researchers, or can be determined by analyzing the structure-activity relationship between the known data of the candidate molecule and the preset protein. The present application does not make any limitation. The optimizable parameter of the designable site is used to limit the chemical structure of the designable site, such as the atomic charge number, the van der Waals radius, etc. The value of the chemical structure can be taken as the value of the optimizable parameter. For example, if the atomic charge number needs to be limited, the optimizable parameter can be determined as the atomic charge number. When the chemical structure to be limited is the van der Waals radius, the optimizable parameter can be determined as the van der Waals radius. In the embodiment of the present application, the selection of the optimizable parameter can be determined according to the experience of researchers, or can be determined according to the actual situation. The present application does not make any limitation.

[0097] In step S102, the value of the optimizable parameter is adjusted, the binding free energy of the candidate complex corresponding to each value is calculated, the preferred complex in the plurality of candidate complexes is determined based on the binding free energy, and the value of the optimizable parameter corresponding to the preferred complex is determined as the preferred value of the optimizable parameter.

[0098] In the embodiment of the present application, for the candidate molecule, the value of the optimizable parameter of the designable site is adjusted, and for each adjustment, the binding free energy of the candidate complex generated by the binding between the preset protein and the candidate molecule through the designable site is calculated. According to the binding free energy, the preferred complex is determined in the plurality of candidate complexes obtained after the value of the optimizable parameter is adjusted for multiple times. The preferred complex can be the preset number of complexes with the lowest binding free energy in the plurality of candidate complexes, or can be the complex with the binding free energy lower than the preset binding free energy threshold. The value of the optimizable parameter corresponding to the preferred complex is determined as the preferred value of the optimizable parameter. Through the preferred value of the optimizable parameter, the design direction of the designable site can be determined, such as the chemical structure of the designable site should meet the limitation condition of the preferred value.

[0099] In one possible implementation of this application, if the optimizable parameter for the designable site is the van der Waals radius of a hydrogen atom, and after multiple adjustments to the optimizable parameter, among the candidate complexes obtained, complex A has the lowest binding free energy, then the van der Waals radius of the hydrogen atom corresponding to complex A can be used as the preferred value of the optimizable parameter. When subsequently designing the designable site, the van der Waals radius of the hydrogen atom at that designable site should be this preferred value, providing a clear direction for subsequent molecular design. Of course, this specific embodiment is merely an example of a possible implementation of this application and does not limit the scope of protection of this application.

[0100] This application embodiment determines the designable sites and optimizable parameters of the designable sites on candidate molecules, adjusts the values ​​of the optimizable parameters, calculates the binding free energy of the candidate complex corresponding to each value, and determines the preferred value of the optimizable parameters based on the binding free energy. Based on the restrictions on the chemical structure of the designable sites by the preferred values ​​of the optimizable parameters, the design direction of candidate molecules is determined, providing a clear idea for molecular design, effectively reducing the computational load of molecular design, improving experimental efficiency, and achieving full automation of the entire molecular process, thus reducing the difficulty of molecular design.

[0101] As one possible implementation of this application, such as Figure 2 As shown, in this embodiment, adjusting the value of the optimizable parameter, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the plurality of candidate complexes based on the binding free energy includes:

[0102] S11. Based on the initial values ​​of the optimizable parameters, obtain the gradient value of the binding free energy of the candidate complex.

[0103] In this embodiment of the application, an initial value is set for the values ​​of the optimizable parameters, and this initial value is taken as... To address the limitations imposed by the initial values ​​on the chemical structure of the designable sites, a pre-defined protein is combined with a candidate molecule to generate a first candidate complex, and the step size is optimized based on the pre-defined parameters. The initial value of this optimizable parameter Based on this, the optimization step size is increased by adding this parameter to obtain the corresponding second candidate complex. The binding free energy gradient of the second candidate complex compared with the first candidate complex is calculated by formula (1):

[0104] (1)

[0105] in, The value of the optimizable parameter is The binding free energy of the candidate complex at that time. The value of the optimizable parameter is the binding free energy of the corresponding candidate complex, is the value of the optimizable parameter, the binding free energy gradient of the corresponding candidate complex, h is the preset parameter optimization step.

[0106]

[0107] wherein the value of the optimizable parameter is denoted as , and the binding free energy of the candidate molecule when binding to the preset protein through the designable site is denoted as , is the binding free energy of the complex when the optimizable parameter is . is the solution binding free energy when the optimizable parameter is .

[0108] S12, judging whether the gradient value is less than or equal to a preset threshold value; if the gradient value is less than or equal to the preset threshold value, the initial value of the optimizable parameter is the preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold value, adjusting the initial value of the optimizable parameter according to a preset optimization step to obtain an adjusted value of the optimizable parameter; and assigning the adjusted value of the optimizable parameter as the initial value of the optimizable parameter.

[0109] In the embodiments of the present application, for the gradient value calculated in step S12, it is judged whether it is less than or equal to a preset threshold value. Optionally, the preset threshold value can be taken as When the gradient value is less than or equal to the preset threshold value, the initial value of the optimizable parameter is directly taken as the preferred value of the optimizable parameter. When the gradient value is greater than the preset threshold value, the value of the optimizable parameter can be adjusted by using formula (2):

[0110] (2)

[0111] wherein, is the optimizable parameter corresponding to the i-th iteration, i is the optimizable parameter corresponding to the (i+1)-th iteration, is the iteration parameter, which is usually taken as 0.1. i In the embodiments of the present application, the adjusted value of the optimizable parameter is taken as the initial value of the optimizable parameter again, and the corresponding binding free energy gradient is solved by using the steps in step S11.

[0112] In the embodiments of the present application, the adjusted value of the optimizable parameter is taken as the initial value of the optimizable parameter again, and the corresponding binding free energy gradient is solved by using the steps in step S11.

[0113] S13, repeatedly performing steps S11 and S12 until the gradient value is less than or equal to the preset threshold value, and obtaining the preferred value of the optimizable parameter.​

[0114] In the embodiments of the present application, the steps in steps S11 and S12 are repeatedly performed until the gradient value obtained is less than the preset threshold value, and the optimal value of the parameter to be optimized is determined.

[0115] The embodiments of the present application calculate the gradient of the binding free energy when the parameter to be optimized is optimized according to the optimization step size by combining the free energy gradient calculation formula, and determine the optimal value of the parameter to be optimized by taking the gradient of the binding free energy as the determination standard, thereby providing an accurate direction for molecular design.

[0116] As an embodiment of the present application, in this embodiment, as shown in Figure 3 When there are multiple parameters to be optimized for one of the designable sites, the value of the parameter to be optimized is adjusted, the binding free energy of the candidate complex corresponding to each value is calculated, and the preferred complex in the multiple candidate complexes is determined based on the binding free energy.

[0117] Step S301: For any parameter to be optimized, keep the rest of the parameters unchanged except for the any parameter to be optimized, adjust the value of the any parameter to be optimized, and calculate the binding free energy of the candidate complex corresponding to each value.

[0118] In the embodiments of the present application, one designable site of a candidate molecule can have one or more parameters to be optimized. When there is only one parameter to be optimized for the designable site, the optimal value of the parameter to be optimized can be determined by the method in the foregoing embodiments. When there are multiple parameters to be optimized for the designable site, for one of the parameters to be optimized X, keep the rest of the parameters to be optimized unchanged except for the parameter to be optimized X, determine the corresponding preferred complex of the parameter to be optimized X by the method in the foregoing embodiments, and the specific implementation method has been described in the foregoing embodiments, which will not be repeated here. Similarly, for each parameter to be optimized of the designable site, the above method can be used to determine the corresponding preferred complex of each parameter to be optimized one by one, and then determine the preferred complex of all the parameters to be optimized.

[0119] Step S302: Determine the preferred complex in the multiple candidate complexes corresponding to all the parameters to be optimized.

[0120] In the embodiments of the present application, after at least one preferred complex is determined for each parameter to be optimized, the preset number of complexes with the lowest binding free energy in all the preferred complexes are determined as the final preferred complex, or the complexes with the binding free energy lower than the preset binding free energy threshold value are determined as the preferred complex.

[0121] The embodiments of the present application provide a scheme for determining a preferred complex in the case that there are multiple parameters to be optimized for one designable site, and provide a wider application scenario for a parameter optimization method of a candidate molecule.

[0122] As a possible implementation manner of the present application, when there are multiple designable sites on the candidate molecule, the adjusting of the values of the parameters to be optimized, the calculation of the binding free energy of the candidate complex corresponding to each value, and the determination of the preferred complex from the multiple candidate complexes based on the binding free energy include the following steps. Figure 4

[0123] Step S401: For any designable site, the values of the parameters to be optimized of the any designable site are adjusted while the parameters of the remaining designable sites are kept unchanged, and the binding free energy of the candidate complex corresponding to each value is calculated; wherein the parameters to be optimized of each designable site can be one or more.

[0124] In the embodiments of the present application, for a candidate molecule, there can be multiple designable sites, and when the preferred values of the parameters to be optimized of the designable sites of the candidate molecule are determined, for one designable site M, the parameters to be optimized of all the designable sites of the candidate molecule except the designable site M are kept unchanged, and the preferred complex corresponding to the designable site M is determined by using the method in the foregoing embodiments, and the specific implementation method has been described in the foregoing embodiments, which will not be repeated here. Similarly, for each designable site of the candidate molecule, the above method can be used to determine the preferred complex corresponding to each designable site one by one, and then the preferred complex corresponding to all the designable sites M is determined.

[0125] Step S402: The preferred complex is determined from the multiple candidate complexes corresponding to all the designable sites.

[0126] In the embodiments of the present application, after at least one preferred complex is determined for each designable site, from all the preferred complexes, a preset number of complexes with the lowest binding free energy are determined as the final preferred complexes, or the complexes with a binding free energy lower than a preset binding free energy threshold are determined as the preferred complexes.

[0127] The embodiments of the present application provide a scheme for determining a preferred complex in the case that there are multiple designable sites for a candidate molecule, and provide a wider application scenario for a parameter optimization method of a candidate molecule.

[0128] ​The application embodiment determines the designable site on the candidate molecule and the optimizable parameter of the designable site, adjusts the value of the optimizable parameter, calculates the binding free energy of the candidate complex corresponding to each value, determines the preferred value of the optimizable parameter according to the binding free energy, determines the design direction of the candidate molecule according to the restriction of the chemical structure of the designable site on the preferred value of the optimizable parameter, provides an explicit idea for molecular design, effectively reduces the calculation amount of molecular design, improves the experimental efficiency, and at the same time, the entire molecular process is fully automated, reducing the difficulty of molecular design.

[0129] The target molecule design method provided in the application embodiment can design the candidate molecule based on the preferred value of the optimizable parameter determined in any of the preceding embodiments to obtain a target molecule.

[0130] As a possible implementation manner of the application, in the implementation manner, as shown in Figure 5 The target molecule design method comprises:

[0131] In step S501, the designable site is optimized based on the preferred value of the optimizable parameter to obtain at least one optimized molecule.

[0132] In the application embodiment, based on the preferred value of the optimizable parameter of the designable site obtained in the preceding embodiments, the designable site is optimized based on the restriction of the chemical structure of the designable site on the preferred value to obtain at least one optimized molecule.

[0133] In the application embodiment, for the designable site, there can be multiple optimizable parameters, and there can be multiple preferred values for each optimizable parameter, so when the designable site is optimized, an optimized molecule needs to be generated for each preferred value of each optimizable parameter, and therefore, multiple optimized molecules can be obtained.

[0134] In step S502, the at least one optimized molecule is evaluated by using a first preset molecular evaluation method, and a first recommended molecule is determined based on the evaluation result.

[0135] In the embodiments of the present application, the first preset molecular evaluation method can be one molecular evaluation method or multiple molecular evaluation methods. When the first preset molecular evaluation method is multiple molecular evaluation methods, the first recommended molecule can be determined based on the evaluation results of the optimized molecules obtained by using the multiple molecular evaluation methods.

[0136] In the embodiments of the present application, the first recommended molecule is selected by performing the first evaluation on the optimized molecules, so that the number of molecules to be evaluated in subsequent molecular design is reduced, the calculation amount is reduced, and the speed of molecular design is accelerated.

[0137] As a possible implementation manner of the present application, in the implementation manner, as shown in Figure 6 the method further includes:

[0138] In step S601, the at least one optimized molecule is combined with the preset protein to obtain at least one optimized complex.

[0139] In the embodiments of the present application, after the designable site of the candidate molecule is designed, at least one optimized molecule is obtained. The at least one optimized molecule is combined with the preset protein through the optimized designable site to obtain at least one optimized complex.

[0140] In step S602, a second preset molecular evaluation method is used to evaluate the at least one optimized complex, and a second recommended molecule is determined based on the evaluation result.

[0141] In the embodiments of the present application, the second recommended molecule is determined based on the evaluation result of the at least one optimized complex obtained in the foregoing embodiments by using the second preset molecular evaluation method. The second preset molecular evaluation method can be one molecular evaluation method or multiple molecular evaluation methods. When the second preset molecular evaluation method is multiple molecular evaluation methods, the second recommended molecule is determined based on the evaluation results of the at least one optimized complex obtained by using the multiple molecular evaluation methods. When the second preset molecular evaluation method is used to evaluate the optimized complex, the evaluation mainly includes an activity test of the optimized complex. The activity test is a test for the activity of the complex. An activity parameter is determined to represent the activity of the complex. The activity parameter can be (half-inhibitory concentration) or (dissociation equilibrium constant), and the like. The evaluation result of the optimized complex can be a numerical value of the activity parameter.

[0142] Step S603, determining a target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0143] In the embodiments of the present application, after the first recommended molecule and the second recommended molecule are determined respectively, when the target molecule is determined, the molecule which is both the second recommended molecule and the second recommended molecule can be determined as the target molecule, or other rules can be adopted to determine the target molecule, wherein the target molecule should be a molecule with good binding stability to the preset protein and high activity.

[0144] The embodiments of the present application determine the second recommended molecule by the activity of the optimized complex, and determine the target molecule according to the first recommended molecule and the second recommended molecule, so as to ensure that the target molecule is a molecule with good binding stability to the preset protein and high activity, and ensure that the target molecule meets the preset demand.

[0145] As a possible implementation manner of the present application, in the implementation manner, the optimization of the designable site based on the preferred value of the optimizable parameter comprises:

[0146] According to the limitation of the optimizable parameter on the designable site, the designable site is operated in one or more of the following operations:

[0147] The designable site is deleted, and the candidate molecule is adaptively adjusted,

[0148] The designable site is replaced by a preset replacement unit.

[0149] In the embodiments of the present application, when the designable site is optimized according to the optimizable parameter, according to the limitation of the optimizable parameter on the designable site, the designable site can be operated in one or more of the following operations: the designable site is deleted, and the candidate molecule is adaptively adjusted, the designable site is replaced by a preset replacement unit. Wherein, according to the limitation of the optimizable parameter, the atom or group on the designable site is selected to be deleted, or the atom or group on the designable site is replaced by a preset replacement unit, so as to ensure that the chemical structure of the designable site meets the limitation of the optimizable parameter.

[0150] The embodiments of the present application ensure that the chemical structure of the designable site of the candidate molecule meets the limitation of the preferred value of the optimizable parameter by designing the designable site, and provide a clear direction for molecular design.

[0151] As a possible implementation manner of the present application, in the implementation manner, when there are multiple preset replacement units, the replacement of the designable site by the preset replacement unit comprises:

[0152] Replace the designable sites with the plurality of preset replacement units respectively to obtain a plurality of optimized molecules;

[0153] The first recommended molecule is determined based on the evaluation result.

[0154] The first recommended molecule is determined based on the evaluation result.

[0155] In the embodiments of the present application, for each designable site, when the current corresponding replacement unit has multiple, the multiple replacement units are used to optimize the designable site respectively once, and then a plurality of optimized molecules are obtained. When the optimized molecules are evaluated subsequently, the first preset molecular evaluation method is used to evaluate the at least one optimized molecule, and the specific evaluation method has been described in the foregoing embodiments, which will not be described here. Based on the evaluation result, the first recommended molecule is determined from the plurality of optimized molecules.

[0156] In the embodiments of the present application, a solution is provided for the case that multiple preset replacement units exist for one designable site, thereby providing a wider application scenario for molecular design.

[0157] As a possible implementation manner of the present application, as shown in the figure, Figure 7 The first recommended molecule is determined based on the evaluation result.

[0158] In step S701, a preset parameter value of the at least one optimized molecule is calculated by using the first preset molecular evaluation method.

[0159] In the embodiments of the present application, the preset parameter value refers to a parameter for indicating the stability of the optimized molecule when the optimized molecule passes through the optimized designable site and binds with the preset protein. The value of the stability of each optimized molecule when binding with the protein is calculated by using the first preset molecular evaluation algorithm.

[0160] In step S702, the optimized molecule with the preset parameter value higher than a first preset threshold value is determined as the first recommended molecule.

[0161] In the embodiments of the present application, the optimized molecule with the value of the stability of the molecule when binding with the protein higher than the first preset value is determined as the first recommended molecule.

[0162] The embodiments of the present application determine the first recommended molecule by calculating the stability of the molecule when binding with the protein, thereby ensuring that the first recommended molecule is a molecule with good binding effect with the protein, and improving the efficiency of molecular design.

[0163] In one possible implementation of this application, the step of determining the target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule includes:

[0164] Based on the evaluation results of the first recommended molecule and the second recommended molecule, a weighted average algorithm is used to determine the target molecule from the first recommended molecule and the second recommended molecule.

[0165] In this embodiment, when determining the target molecule based on the first and second recommended molecules, a molecule that is simultaneously the second and second recommended molecules can be identified as the target molecule. Alternatively, other rules can be used to determine the target molecule. The target molecule should be a molecule with good binding stability and high activity to a preset protein. For example, a weighted average algorithm can be used to calculate the weighted value of all molecules among the first and second recommended molecules. Molecules with weighted values ​​higher than a preset threshold, or molecules with the highest weighted values ​​among the top preset number, are identified as target molecules.

[0166] This application embodiment determines the target molecule by combining a first recommended molecule and a second recommended molecule, ensuring the stability of the target molecule's binding to the protein and the activity of the target molecule, thus ensuring that the target molecule meets the design requirements.

[0167] This application embodiment also designs designable sites by optimizing the preferred values ​​of the parameters, determines the optimized molecule, evaluates the activity of the optimized molecule using an easily preset molecular evaluation method, and determines the recommended new molecule based on the activity, and finally determines the target molecule. This can effectively reduce the number of new molecules that need to be calculated for activity, further reduce the computational load of molecular design, and improve the efficiency of molecular design.

[0168] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a parameter design device for candidate molecules, a target molecule design device, an electronic device, and corresponding embodiments.

[0169] Figure 8 This is a schematic diagram of the parameter optimization device for candidate molecules shown in an embodiment of this application.

[0170] See Figure 8 The parameter optimization device 80 for candidate molecules provided in this application embodiment includes a parameter selection module 810 and a parameter determination module 820, wherein:

[0171] The parameter selection module 810 is used to determine the designable sites on the candidate molecule and the optimizable parameters of the designable sites, wherein the candidate molecule can bind to a preset protein through the designable sites to form a complex, and the optimizable parameters are used to limit the chemical structure of the designable sites.

[0172] The parameter determination module 820 adjusts the value of the optimizable parameter, calculates the binding free energy of each candidate complex corresponding to the value, determines the preferred complex in the plurality of candidate complexes based on the binding free energy, and determines the value of the optimizable parameter corresponding to the preferred complex as the preferred value of the optimizable parameter.

[0173] As a possible implementation of the present application, in this implementation, when the parameter determination module adjusts the value of the optimizable parameter, calculates the binding free energy of each candidate complex corresponding to the value, and determines the preferred complex in the plurality of candidate complexes based on the binding free energy, it is used for:

[0174] S11, obtaining the gradient value of the binding free energy of the candidate complex based on the initial value of the optimizable parameter;

[0175] S12, determining whether the gradient value is less than or equal to a preset threshold value; if the gradient value is less than or equal to the preset threshold value, the initial value of the optimizable parameter is the preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold value, adjusting the initial value of the optimizable parameter according to a preset optimization step to obtain an adjusted optimizable parameter value; and assigning the adjusted optimizable parameter value as the initial value of the optimizable parameter;

[0176] S13, repeatedly executing steps S11 and S12 until the gradient value is less than or equal to the preset threshold value, and obtaining the preferred value of the optimizable parameter.

[0177] As a possible implementation of the present application, in this implementation, when there are multiple optimizable parameters for one of the designable sites, the parameter determination module, when adjusting the value of the optimizable parameter, calculating the binding free energy of each candidate complex corresponding to the value, and determining the preferred complex in the plurality of candidate complexes based on the binding free energy, is used for:

[0178] For any optimizable parameter, keeping the remaining parameters unchanged except the any optimizable parameter, adjusting the value of the any optimizable parameter, and calculating the binding free energy of each candidate complex corresponding to the value;

[0179] Determining the preferred complex in the plurality of candidate complexes corresponding to all optimizable parameters.

[0180] As a possible implementation of the present application, in this implementation, when there are multiple designable sites on the candidate molecule, the parameter determination module, when adjusting the value of the optimizable parameter, calculating the binding free energy of each candidate complex corresponding to the value, and determining the preferred complex in the plurality of candidate complexes based on the binding free energy, is used for:

[0181] For any one of the designable sites, the values of the optimizable parameters of the any one of the designable sites are adjusted while the parameters of the rest of the designable sites remain unchanged, and the binding free energy of a candidate complex corresponding to each value is calculated; wherein the optimizable parameters of each of the designable sites can be one or more;

[0182] The preferred complex is determined among the plurality of candidate complexes corresponding to all the designable sites.

[0183] As to the apparatus in the above-mentioned embodiments, the specific manners in which the respective modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0184] The embodiments of the present application determine the designable sites on the candidate molecules and the optimizable parameters of the designable sites, adjust the values of the optimizable parameters, calculate the binding free energy of a candidate complex corresponding to each value, determine the preferred value of the optimizable parameter according to the binding free energy, determine the design direction of the candidate molecules according to the restriction of the chemical structure of the designable sites on the preferred value of the optimizable parameter, provide a clear idea for molecular design, effectively reduce the calculation amount of molecular design, improve the experimental efficiency, and at the same time, realize complete automation of the entire molecular process and reduce the difficulty of molecular design.

[0185] Referring to Figure 9 The embodiments of the present application also provide an apparatus for designing a target molecule, wherein the apparatus is used to design the candidate molecules according to the preferred value of the optimizable parameter obtained in the above-mentioned method embodiments, and obtain a target molecule.

[0186] As a possible implementation manner of the present application, in this implementation manner, the apparatus for designing a target molecule 90 comprises:

[0187] An optimization molecule determining module 910 is configured to optimize the designable sites based on the preferred value of the optimizable parameter, and obtain at least one optimized molecule.

[0188] A first recommended molecule determining module 920 is configured to evaluate the at least one optimized molecule by using a first preset molecule evaluation method, and determine a first recommended molecule based on the evaluation result.

[0189] As a possible implementation manner of the present application, in this implementation manner, the apparatus for designing a target molecule further comprises:

[0190] An optimized complex determining module 930 is configured to combine the at least one optimized molecule with a preset protein respectively, and obtain at least one optimized complex.

[0191] The second recommended molecule determination module 940 is configured to evaluate the at least one optimized compound by using a second preset molecule evaluation method, and determine a second recommended molecule based on an evaluation result.

[0192] The target molecule determination module 950 is configured to determine a target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0193] As a possible implementation form of the present application, in this implementation form, when optimizing the designable site based on the preferred value of the optimizable parameter, the optimized molecule determination module is configured to:

[0194] According to the restriction of the optimizable parameter on the designable site, the designable site is subjected to one or more of the following operations:

[0195] The designable site is deleted, and the candidate molecule is adaptively adjusted,

[0196] The designable site is replaced by using a preset replacement unit.

[0197] As a possible implementation form of the present application, in this implementation form, when there are multiple preset replacement units, when the designable site is replaced by using a preset replacement unit, the optimized molecule determination module is configured to:

[0198] The designable site is replaced by using the multiple preset replacement units respectively, to obtain multiple optimized molecules;

[0199] When the first recommended molecule determination module evaluates the at least one optimized molecule by using a first preset molecule evaluation method, and determines a first recommended molecule based on an evaluation result, the first recommended molecule determination module is configured to:

[0200] The multiple optimized molecules are evaluated by using the first preset molecule evaluation method, and a first recommended molecule is determined based on an evaluation result.

[0201] As a possible implementation form of the present application, in this implementation form, when the first recommended molecule determination module evaluates the at least one optimized molecule by using a first preset molecule evaluation method, and determines a first recommended molecule based on an evaluation result, the first recommended molecule determination module is configured to:

[0202] A preset parameter value of the at least one optimized molecule is calculated by using the first preset molecule evaluation method;

[0203] The optimized molecule with the preset parameter value higher than a first preset threshold is determined as the first recommended molecule.

[0204] As a possible implementation form of the present application, in which the target molecule determining module can be configured to:

[0205] determine the target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0206] determine the target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

[0207] As to the apparatus in the above embodiments, the specific manners in which the modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0208] The embodiments of the present application can further design the designable sites by the preferred values of the optimizable parameters, determine the optimized molecules, evaluate the activities of the optimized molecules by the easily preset molecule evaluation method, determine the recommended new molecules according to the activities, and finally determine the target molecules, which can effectively reduce the number of new molecules that need to be calculated for activities, further reduce the calculation amount of the molecule design, and improve the molecule design efficiency. Figure 10

[0209] FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application. Figure 10 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0210] The processor 1020 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0211] The memory 1010 can include various types of storage units such as a system memory, a read-only memory (ROM), and a permanent storage device. Among them, the ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device can be a rewritable storage device. The permanent storage device can be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device employs a mass storage device (e.g., a magnetic or optical disk, a flash memory) as a permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (e.g., a floppy disk, an optical drive). The system memory can be a readable and writable storage device or a volatile readable and writable storage device such as a dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during runtime. In addition, the memory 1010 can include a combination of any computer readable storage media, including various types of semiconductor storage chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks and / or optical disks. In some embodiments, the memory 1010 can include a readable and / or writable removable storage device such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., an SD card, a min SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wired transmission.

[0212] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to perform part or all of the above-mentioned methods.

[0213] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for performing part or all of the steps of the above-mentioned methods of the present application.

[0214] Alternatively, the present application can also be implemented as a computer readable storage medium (or non-transitory machine readable storage medium or machine readable storage medium) having executable code (or computer program or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or a server, etc.), causes the processor to perform part or all of the steps of the above-mentioned methods according to the present application.

[0215] Having described various embodiments of the application, it is to be understood that the above description is meant to be illustrative only, and that many modifications and variations of the embodiments described herein are possible. It is therefore to be understood that within the scope of the appended claims, and their equivalents, many alternatives to the embodiments described herein are possible. The selection of terms to be used in the description is not intended to limit the scope of the embodiments described herein, but rather to best explain the principles of the embodiments, practical application, or improvement over the technology in the art, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for optimizing the parameters of a candidate molecule, characterized in that, The method includes: The designable sites on candidate molecules and the optimizable parameters of the designable sites are determined, wherein the candidate molecules can bind to a preset protein through the designable sites to form a complex, and the optimizable parameters are used to limit the chemical structure of the designable sites, including the atomic number and / or van der Waals radius of the designable sites; The values ​​of the optimizable parameters are adjusted, and the binding free energy of the candidate complex corresponding to each value is calculated. Based on the binding free energy, the preferred complex among the multiple candidate complexes is determined, and the value of the optimizable parameter corresponding to the preferred complex is determined as the preferred value of the optimizable parameter. The preferred complex includes a preset number of complexes with the lowest binding free energy among the multiple candidate complexes; or, the preferred complex includes complexes among the multiple candidate complexes with a binding free energy lower than a preset binding free energy threshold.

2. The parameter optimization method for candidate molecules according to claim 1, characterized in that, The process of adjusting the values ​​of the optimizable parameters, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the multiple candidate complexes based on the binding free energy includes: S11. Based on the initial values ​​of the optimizable parameters, obtain the gradient value of the binding free energy of the candidate complex; S12. Determine whether the gradient value is less than or equal to a preset threshold; if the gradient value is less than or equal to the preset threshold, the initial value of the optimizable parameter is the preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold, adjust the initial value of the optimizable parameter according to a preset optimization step size to obtain the adjusted optimizable parameter value; designate the adjusted optimizable parameter value as the initial value of the optimizable parameter. S13. Repeat steps S11 and S12 until the gradient value is less than or equal to a preset threshold to obtain the preferred value of the optimizable parameter.

3. The parameter optimization method for candidate molecules according to claim 2, characterized in that, Obtaining the gradient value of the binding free energy of the candidate complex based on the initial value of the optimizable parameter includes: The binding free energy of the first candidate complex corresponding to the initial value of the optimizable parameter is determined, and the binding free energy of the second candidate complex corresponding to the initial value of the optimizable parameter after increasing the preset optimization step size is determined. The gradient values ​​of the changes in the binding free energy of the first candidate complex and the binding free energy of the second candidate complex relative to the optimization step size are calculated and used as the gradient values ​​of the binding free energy of the candidate complex.

4. The parameter optimization method for candidate molecules according to claim 1, characterized in that, When there are multiple optimizable parameters for a designable site, adjusting the values ​​of the optimizable parameters, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the multiple candidate complexes based on the binding free energy include: For any optimizable parameter, keep all other parameters unchanged, adjust the value of the optimizable parameter, and calculate the binding free energy of the candidate complex corresponding to each value; The preferred complex is determined from multiple candidate complexes corresponding to all optimizable parameters.

5. The parameter optimization method for candidate molecules according to claim 1, characterized in that, When the candidate molecule has multiple designable sites, the process involves adjusting the values ​​of the optimizable parameters, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the multiple candidate complexes based on the binding free energy, including: For any designable site, keeping the parameters of the other designable sites unchanged, the values ​​of the optimizable parameters of the designable site are adjusted, and the binding free energy of the candidate complex corresponding to each value is calculated; wherein, each designable site may have one or more optimizable parameters; The preferred complex is determined from multiple candidate complexes corresponding to all designable sites.

6. A method for designing target molecules, characterized in that, The candidate molecule is designed based on the preferred value of the optimizable parameter obtained in any one of claims 1-5 to obtain the target molecule.

7. The target molecule design method according to claim 6, characterized in that, The method includes: Based on the preferred values ​​of the optimizable parameters, the designable sites are optimized to obtain at least one optimized molecule; The first preset molecular evaluation method is used to evaluate the at least one optimized molecule, and the first recommended molecule is determined based on the evaluation results.

8. The target molecule design method according to claim 7, characterized in that, The method further includes: The at least one optimized molecule is combined with a preset protein to obtain at least one optimized complex; The at least one optimized complex is evaluated using a second preset molecular evaluation method, and a second recommended molecule is determined based on the evaluation results; The target molecule is determined from the first recommended molecule and the second recommended molecule according to the preset screening rules.

9. The target molecule design method according to claim 7, characterized in that, The optimization of the designable site based on the preferred values ​​of the optimizable parameters includes: Based on the constraints imposed on the designable site by the optimizable parameters, one or more of the following operations are performed on the designable site: The designable sites are deleted, and candidate molecules are adaptively adjusted. The designable sites are replaced using preset replacement units.

10. The target molecule design method according to claim 9, characterized in that, When there are multiple preset replacement units, replacing the designable site using the preset replacement units includes: The designable sites are replaced by the multiple preset replacement units to obtain multiple optimized molecules; The step of evaluating the at least one optimized molecule using a first preset molecular evaluation method and determining a first recommended molecule based on the evaluation results includes: The multiple optimized molecules are evaluated using a first preset molecular evaluation method, and a first recommended molecule is determined based on the evaluation results.

11. The target molecule design method according to claim 7, characterized in that, The at least one optimized molecule is evaluated using a first preset molecular evaluation method, and a first recommended molecule is determined based on the evaluation results, including: The preset parameter values ​​of the at least one optimized molecule are calculated using the first preset molecule evaluation method; The optimized molecules whose preset parameter values ​​are higher than the first preset threshold are identified as the first recommended molecules.

12. The target molecule design method according to claim 8, characterized in that, The step of determining the target molecule from the first recommended molecule and the second recommended molecule according to the preset screening rules includes: Based on the evaluation results of the first recommended molecule and the second recommended molecule, a weighted average algorithm is used to determine the target molecule from the first recommended molecule and the second recommended molecule.

13. A device for optimizing candidate molecule parameters, characterized in that, The candidate molecule parameter optimization device includes: A parameter selection module is used to determine the designable sites on candidate molecules and the optimizable parameters of the designable sites, wherein the candidate molecules can bind to a preset protein through the designable sites to form a complex, and the optimizable parameters are used to define the chemical structure of the designable sites, including the atomic number and / or van der Waals radius of the designable sites. The parameter determination module adjusts the values ​​of the optimizable parameters, calculates the binding free energy of the candidate complex corresponding to each value, determines the preferred complex among multiple candidate complexes based on the binding free energy, and determines the value of the optimizable parameter corresponding to the preferred complex as the preferred value of the optimizable parameter; the preferred complex includes a preset number of complexes with the lowest binding free energy among the multiple candidate complexes; or, the preferred complex includes complexes among the multiple candidate complexes with a binding free energy lower than a preset binding free energy threshold.

14. The candidate molecule parameter optimization device according to claim 13, characterized in that, When the parameter determination module adjusts the values ​​of the optimizable parameters, calculates the binding free energy of the candidate complex corresponding to each value, and determines the preferred complex among the multiple candidate complexes based on the binding free energy, it is used for: S11. Based on the initial values ​​of the optimizable parameters, obtain the gradient value of the binding free energy of the candidate complex; S12. Determine whether the gradient value is less than or equal to a preset threshold; If the gradient value is less than or equal to a preset threshold, the initial value of the optimizable parameter is the preferred value of the optimizable parameter; if the gradient value is greater than the preset threshold, the initial value of the optimizable parameter is adjusted according to a preset optimization step size to obtain the adjusted optimizable parameter value; the adjusted optimizable parameter value is designated as the initial value of the optimizable parameter. S13. Repeat steps S11 and S12 until the gradient value is less than or equal to a preset threshold to obtain the preferred value of the optimizable parameter.

15. The candidate molecule parameter optimization device according to claim 13, characterized in that, When there are multiple optimizable parameters for a designable site, the parameter determination module, when adjusting the values ​​of the optimizable parameters, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the multiple candidate complexes based on the binding free energy, is used for: For any optimizable parameter, keep all other parameters unchanged, adjust the value of the optimizable parameter, and calculate the binding free energy of the candidate complex corresponding to each value; The preferred complex is determined from multiple candidate complexes corresponding to all optimizable parameters.

16. The candidate molecule parameter optimization device according to claim 13, characterized in that, When the candidate molecule has multiple designable sites, the parameter determination module, when adjusting the values ​​of the optimizable parameters, calculating the binding free energy of the candidate complex corresponding to each value, and determining the preferred complex among the multiple candidate complexes based on the binding free energy, is used for: For any designable site, keeping the parameters of the other designable sites unchanged, the values ​​of the optimizable parameters of the designable site are adjusted, and the binding free energy of the candidate complex corresponding to each value is calculated; wherein, each designable site may have one or more optimizable parameters; The preferred complex is determined from multiple candidate complexes corresponding to all designable sites.

17. A target molecule design device, characterized in that, The candidate molecule is designed using the preferred value of the optimizable parameter obtained in any one of claims 1-5 to obtain the target molecule.

18. The target molecule design device according to claim 17, characterized in that, The target molecule design device includes: The molecule optimization determination module is used to optimize the designable sites based on the preferred values ​​of the optimizable parameters to obtain at least one optimized molecule. The first recommended molecule determination module is used to evaluate the at least one optimized molecule using a first preset molecule evaluation method, and determine the first recommended molecule based on the evaluation results.

19. The target molecule design device according to claim 18, characterized in that, The target molecule design device further includes: The optimized complex determination module is used to bind the at least one optimized molecule to a preset protein to obtain at least one optimized complex. The second recommended molecule determination module is used to evaluate the at least one optimized complex using a second preset molecule evaluation method, and determine the second recommended molecule based on the evaluation results. The target molecule determination module is used to determine the target molecule from the first recommended molecule and the second recommended molecule according to a preset screening rule.

20. The target molecule design device according to claim 18, characterized in that, When the optimized molecule determination module optimizes the designable site based on the preferred values ​​of the optimizable parameters, it is used to: Based on the constraints imposed on the designable site by the optimizable parameters, one or more of the following operations are performed on the designable site: The designable sites are deleted, and candidate molecules are adaptively adjusted. The designable sites are replaced using preset replacement units.

21. The target molecule design device according to claim 20, characterized in that, When there are multiple preset replacement units, the optimized molecule determination module, when replacing the designable site using the preset replacement units, is used to: The designable sites are replaced by the multiple preset replacement units to obtain multiple optimized molecules; When the first recommended molecule determination module evaluates the at least one optimized molecule using a first preset molecule evaluation method and determines the first recommended molecule based on the evaluation results, it is used to: The multiple optimized molecules are evaluated using a first preset molecular evaluation method, and a first recommended molecule is determined based on the evaluation results.

22. The target molecule design device according to claim 18, characterized in that, When the first recommended molecule determination module evaluates the at least one optimized molecule using a first preset molecule evaluation method and determines the first recommended molecule based on the evaluation results, it is used to: The preset parameter values ​​of the at least one optimized molecule are calculated using the first preset molecule evaluation method; The optimized molecules whose preset parameter values ​​are higher than the first preset threshold are identified as the first recommended molecules.

23. The target molecule design device according to claim 19, characterized in that, When determining the target molecule from the first and second recommended molecules according to preset screening rules, the target molecule determination module can be used for: Based on the evaluation results of the first recommended molecule and the second recommended molecule, a weighted average algorithm is used to determine the target molecule from the first recommended molecule and the second recommended molecule.

24. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-12.

25. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-12.

Images