Method, device, equipment and storage medium for determining molecular design scheme
By calculating the molecular descriptor and distance, the crystallization experimental plan for drug molecules is recommended, which solves the problems of low efficiency and high cost of selection of drug crystallization experimental plan in the prior art, and achieves efficient and low-cost design plan recommendations.
Patent Information
- Application Number
- CN202111511073.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-10
- Publication Date
- 2024-12-27
- Estimated Expiration
- 2041-12-10
AI Technical Summary
The prior art is difficult to efficiently, conveniently and at low cost to screen out reasonable drug crystallization experimental plans and parameters, resulting in high-experimental cost and low efficiency, and it is difficult to achieve high-throughput design based on experience.
By obtaining the molecular descriptor of the target molecule, calculating the distance between it and the preset molecule, selecting the candidate molecule, and determining the design plan of the target molecule based on the design plan of the candidate molecule, so as to achieve a rapid and low-cost recommendation of reasonable experimental plans.
It realizes efficient, fast and low-cost recommendations of corresponding design schemes for target molecules, which reduces the number of experiments, saves costs, and improves the efficiency and throughput of crystallization experiments.
Smart Images
Figure CN114300065B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computational chemistry technology, and in particular to a method, device, equipment and storage medium for determining a molecular design scheme. Background Art
[0002] At present, most drugs on the market exist in the form of crystals, so in drug research and development and production, we will face the choice of drug crystallization experimental schemes. Different experimental schemes, on the one hand, will directly determine whether the drug molecule crystallizes; on the other hand, they will determine the solid form obtained by the crystallization of the drug, such as polymorphs, hydrates, solvates, salt forms and cocrystals. Different solid forms differ in physical and chemical properties, mechanical properties, chemical stability, bioavailability and process feasibility. There are many commonly used experimental schemes, and each method involves multiple experimental parameters. It is very meaningful to screen out reasonable experimental schemes and parameters according to needs.
[0003] The main crystallization experimental schemes currently available are:
[0004] A. Large-scale experimental method traversal screening, that is, for any drug molecule, a large-scale crystallization experiment is carried out using a unified preset multiple experimental methods and experimental parameters to find a solution that can be crystallized.
[0005] The disadvantages are: the experimental plan is not optimized for the specified drug molecule, too many experiments need to be done, and the material, manpower and time costs are too high.
[0006] B. Relying on expert experience, that is, crystallization experiment experts have a deep understanding of the crystallization characteristics of certain molecules through a lot of learning and practice, and can help design personalized experimental plans for specific molecules, so that the ideal crystal form can be obtained through a small number of experiments.
[0007] Its disadvantages are: it is difficult to train crystallization experiment experts with rich experience, it relies too much on personal experience, and it is impossible to design high-throughput plans.
[0008] With regard to the problem that the existing technology has not yet found a way to efficiently, conveniently and cost-effectively screen out reasonable experimental plans and parameters according to actual needs, no effective solution has been proposed so far. Summary of the invention
[0009] The embodiments of the present invention provide a method, device, equipment and storage medium for determining a molecular design scheme, so as to at least solve the technical problem that there is no existing technology for efficiently, conveniently and at low cost screening out reasonable experimental schemes and parameters according to actual needs.
[0010] According to one aspect of an embodiment of the present invention, a method for determining a molecular design scheme is provided, the determination method comprising: obtaining a target molecule to be designed, and calculating a molecular descriptor of the target molecule; determining, based on the molecular descriptor of the target molecule, a distance between the target molecule and each preset molecule in a pre-constructed target chemical space; determining a candidate molecule from each preset molecule based on the distance between the target molecule and each preset molecule; obtaining a design scheme for the candidate molecule; and determining a design scheme for the target molecule based on the design scheme of the candidate molecule.
[0011] Optionally, before obtaining the target molecule to be designed, the method also includes: obtaining multiple preset molecules; determining a molecular descriptor of each of the preset molecules, wherein a molecular descriptor of the preset molecule occupies a position in the multidimensional space; and constructing a target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
[0012] Optionally, the obtaining of multiple preset molecules includes: obtaining design schemes of multiple initial molecules; analyzing the design scheme of each initial molecule to determine the completeness of the design scheme of each initial molecule; and using the initial molecules with complete design schemes as preset molecules.
[0013] Optionally, the parsing the design scheme of each initial molecule to determine the completeness of the design scheme of each initial molecule includes: parsing the design scheme of each initial molecule to obtain a first initial molecule with a complete design scheme and a second initial molecule with an incomplete design scheme; and taking the initial molecule with a complete design scheme as the preset molecule includes: taking the first initial molecule with a complete design scheme as the preset molecule.
[0014] Optionally, the method further includes: completing the design scheme of the second initial molecule, and using the second initial molecule with the completed design scheme as the preset molecule.
[0015] Optionally, determining the molecular descriptor of each of the preset molecules includes: using a preset algorithm to calculate multiple molecular descriptors of each of the preset molecules; and screening the multiple molecular descriptors of each of the preset molecules to obtain a group of molecular descriptors for characterizing the preset molecules.
[0016] Optionally, screening is performed on the multiple molecular descriptors of each of the preset molecules, including: for any molecular descriptor, when there are preset molecules exceeding a first threshold number whose corresponding molecular descriptors have the same value, deleting the molecular descriptor.
[0017] Optionally, screening is performed on the multiple molecular descriptors of each of the preset molecules, including: for any molecular descriptor, when the difference between the value of the molecular descriptor corresponding to a preset molecule and the value of the molecular descriptor corresponding to other preset molecules is lower than a second threshold, deleting the molecular descriptor.
[0018] Optionally, screening is performed on the multiple molecular descriptors of each of the preset molecules, including: for any molecular descriptor, when the value of the molecular descriptor corresponding to a preset molecule is abnormal, deleting the molecular descriptor.
[0019] Optionally, screening is performed on the multiple molecular descriptors of each of the preset molecules, including: for any two molecular descriptors, when a correlation coefficient between the two molecular descriptors calculated based on the values of the two molecular descriptors corresponding to all preset molecules is higher than a third threshold, deleting one of the two molecular descriptors.
[0020] Optionally, screening is performed on the multiple molecular descriptors of each of the preset molecules, including: dimensionality reduction is performed on all the molecular descriptors.
[0021] Optionally, determining the distance between the target molecule and each preset molecule in a pre-constructed target chemical space according to the molecular descriptor of the target molecule includes: determining the position of the target molecule in the pre-constructed target chemical space according to the molecular descriptor of the target molecule; and calculating the distance between the target molecule and each preset molecule according to the position of the target molecule in the target chemical space and the positions of each preset molecule in the target chemical space.
[0022] Optionally, determining the candidate molecule from the preset molecules according to the distance between the target molecule and each preset molecule includes: selecting a preset number or a preset proportion of preset molecules with smaller distances as candidate molecules according to the distance between the target molecule and each preset molecule; or selecting a preset molecule with the smallest distance as a candidate molecule according to the distance between the target molecule and each preset molecule.
[0023] Optionally, when there are multiple candidate molecules, determining the design scheme of the target molecule based on the design schemes of the candidate molecules includes: scoring the design scheme of each candidate molecule according to a preset scoring strategy to obtain a score value for the design scheme of each candidate molecule; and taking the design scheme of the candidate molecule with the highest score as the design scheme of the target molecule.
[0024] Optionally, when there is one candidate molecule and there are multiple design schemes for the candidate molecule, determining the design scheme of the target molecule based on the design scheme of the candidate molecule includes: scoring each set of design schemes of the candidate molecule according to a preset scoring strategy to obtain a score value for each set of design schemes of the candidate molecule; and taking the design scheme with the highest score value as the design scheme of the target molecule.
[0025] According to another aspect of an embodiment of the present invention, a device for determining a molecular design scheme is also provided, the determination device comprising: a first acquisition unit, used to acquire a target molecule to be designed and calculate a molecular descriptor of the target molecule; a first determination unit, used to determine, based on the molecular descriptor of the target molecule, the distance between the target molecule and each preset molecule in a pre-constructed target chemical space; a second determination unit, used to determine a candidate molecule from each preset molecule based on the distance between the target molecule and each preset molecule; a second acquisition unit, used to acquire a design scheme for the candidate molecule; and a third determination unit, used to determine the design scheme for the target molecule based on the design scheme for the candidate molecule.
[0026] Optionally, the determination device also includes: a third acquisition unit, used to acquire multiple preset molecules before the first acquisition unit acquires the target molecule to be designed; a fourth determination unit, used to determine the molecular descriptor of each of the preset molecules, wherein the molecular descriptor of one of the preset molecules occupies a position in the multidimensional space; and a construction unit, used to construct the target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
[0027] Optionally, the third acquisition unit includes: a first acquisition subunit, used to acquire design schemes of multiple initial molecules; a first determination subunit, used to parse the design scheme of each initial molecule and determine the completeness of the design scheme of each initial molecule; and a second determination subunit, used to take the initial molecule with a complete design scheme as a preset molecule.
[0028] Optionally, the first determining subunit includes: a first acquiring module, configured to analyze the design scheme of each initial molecule to obtain a first initial molecule with a complete design scheme and a second initial molecule with an incomplete design scheme.
[0029] Optionally, the second determining subunit includes: a first determining module, configured to use the first initial molecule with a complete design scheme as a preset molecule.
[0030] Optionally, the determining device further includes: a completion unit, configured to complete the design scheme of the second initial molecule, and use the second initial molecule whose design scheme has been completed as the preset molecule.
[0031] Optionally, the fourth determination unit includes: a first calculation subunit, used to calculate multiple molecular descriptors of each of the preset molecules using a preset algorithm; and a screening subunit, used to screen the multiple molecular descriptors of each of the preset molecules to obtain a group of molecular descriptors used to characterize the preset molecules.
[0032] Optionally, the screening subunit includes at least any one of the following: a first processing module, used for deleting any molecular descriptor when there are more than a first threshold number of preset molecules corresponding to the same molecular descriptor value, the molecular descriptor; a second processing module, used for deleting any molecular descriptor when the difference between the value of the molecular descriptor corresponding to a preset molecule and the value of the molecular descriptor corresponding to other preset molecules is lower than a second threshold value; a third processing module, used for deleting any molecular descriptor when the value of the molecular descriptor corresponding to a preset molecule is abnormal; a fourth processing module, used for deleting one of any two molecular descriptors when the correlation coefficient of the two molecular descriptors calculated based on the values of the two molecular descriptors corresponding to all preset molecules is higher than a third threshold value; a fifth processing module, used for performing dimensionality reduction processing on all molecular descriptors.
[0033] Optionally, the first determination unit includes: a third determination subunit, used to determine the position of the target molecule in a pre-constructed target chemical space based on the molecular descriptor of the target molecule; and a second calculation subunit, used to calculate the distance between the target molecule and each preset molecule in the target chemical space based on the position of the target molecule in the target chemical space and the positions of each preset molecule in the target chemical space.
[0034] Optionally, the second determination unit includes at least any one of the following: a first selection subunit, used to select a preset number or a preset proportion of preset molecules with smaller distances as candidate molecules based on the distances between the target molecule and each of the preset molecules; a second selection subunit, used to select the preset molecule with the smallest distance as the candidate molecule based on the distances between the target molecule and each of the preset molecules.
[0035] Optionally, the third determination unit includes: a first scoring subunit, used to score the design scheme of each candidate molecule according to a preset scoring strategy when there are multiple candidate molecules, so as to obtain a score value of the design scheme of each candidate molecule; and a fourth determination subunit, used to use the design scheme of the candidate molecule with the highest score as the design scheme of the target molecule.
[0036] Optionally, the third determination unit includes: a second scoring subunit, used to score each set of design schemes of the candidate molecules according to a preset scoring strategy when there is one candidate molecule and there are multiple sets of design schemes for the candidate molecules, so as to obtain a score value for each set of design schemes of the candidate molecules; and a fifth determination subunit, used to select the design scheme with the highest score as the design scheme of the target molecule.
[0037] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for determining the molecular design scheme.
[0038] According to another aspect of an embodiment of the present invention, an electronic device is provided. The electronic device includes a memory and a processor. The memory stores a program, and the processor is used to execute the program to implement the above-mentioned method for determining a molecular design scheme.
[0039] In an embodiment of the present invention, a target molecule to be designed is obtained and a molecular descriptor of the target molecule is calculated; based on the molecular descriptor of the target molecule, the distance between the target molecule and each preset molecule in a pre-constructed target chemical space is determined; based on the distance between the target molecule and each preset molecule, a candidate molecule is determined from each preset molecule; a design scheme for the candidate molecule is obtained; and based on the design scheme for the candidate molecule, a design scheme for the target molecule is determined.
[0040] At this time, when it is necessary to determine the relevant design scheme of a drug molecule (such as a crystallization experiment scheme, a synthesis experiment scheme, etc.), the molecular descriptor of the target molecule can be calculated, and the position occupied by the molecular descriptor of the target molecule in the target chemical space can be determined at the same time, and based on the Euclidean distance between the positions occupied by the multiple preset molecules and the target molecule in the target chemical space, the candidate molecules whose corresponding design schemes need to be pushed are determined among the multiple preset molecules, and the design schemes of the candidate molecules are pushed, so that the target molecule can be designed accordingly with reference to the design schemes of the candidate molecules. Thus, the technical effect of recommending corresponding design schemes according to the characteristics of the target molecule is achieved efficiently, quickly and at low cost.
[0041] That is, the embodiment of the present application collects design schemes of drug molecules, calculates the molecular descriptors of the drug molecules therein, and constructs the corresponding chemical space using important molecular descriptors. When applied, the molecular descriptors of new molecules are calculated, and the distance between the molecular descriptors of the new molecules and the existing molecular descriptors in the chemical space is calculated; then the corresponding design schemes are recommended in order from the nearest to the farthest distance. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0043] Figure 1 is a flow chart of an optional method for determining a molecular design solution according to an embodiment of the present invention;
[0044] Figure 2 is a schematic diagram of an optional method for determining a molecular design solution according to an embodiment of the present invention;
[0045] Figure 3 is a schematic diagram of an optional target molecule corresponding to bardoxolone methyl according to an embodiment of the present invention;
[0046] Figure 4 is a schematic diagram of a preset molecule corresponding to an optional bardoxolone methyl according to an embodiment of the present invention;
[0047] Figure 5 Schematic diagram of an optional device for determining a molecular design scheme according to an embodiment of the present invention. DETAILED DESCRIPTION
[0048] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0050] According to an embodiment of the present invention, an embodiment of a method for determining a molecular design scheme is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0051] Figure 1 is a method for determining a molecular design solution according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:
[0052] Step S102: obtaining a target molecule to be designed, and calculating a molecular descriptor of the target molecule.
[0053] Step S104: determining the distance between the target molecule and each preset molecule in the pre-constructed target chemical space according to the molecular descriptor of the target molecule.
[0054] Step S106: determining a candidate molecule from the preset molecules according to the distance between the target molecule and the preset molecules.
[0055] Step S108, obtaining a design scheme for the candidate molecule.
[0056] Step S110, determining the design scheme of the target molecule according to the design scheme of the candidate molecule.
[0057] It should be noted that: in the embodiment of the present invention, Figure 2 As shown, before obtaining the target molecule to be designed, the method also includes: obtaining a plurality of preset molecules; determining a molecular descriptor of each of the preset molecules, wherein a molecular descriptor of the preset molecule occupies a position in the multidimensional space; and constructing a target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
[0058] At this time, when it is necessary to determine the relevant crystallization experimental scheme for a certain drug molecule, the molecular descriptor of the target molecule can be calculated, and the position occupied by the molecular descriptor of the target molecule in the target chemical space can be determined at the same time, and based on the Euclidean distance between the positions occupied by the multiple preset molecules and the target molecule in the target chemical space, the candidate molecules whose corresponding design schemes need to be pushed are determined among the multiple preset molecules, and the design schemes of the candidate molecules are pushed, wherein the design schemes at least include the crystallization experimental data of the preset molecules. Thus, the technical effect of efficiently, quickly and low-costly recommending the corresponding crystallization experimental schemes according to the characteristics of the target molecules is achieved.
[0059] That is, the embodiment of the present application collects crystallization experimental data of drug molecules, calculates the molecular descriptors of the drug molecules therein, and constructs the corresponding chemical space using important molecular descriptors. When applied, the molecular descriptors of new molecules are calculated, and the distance between the molecular descriptors of the new molecules and the existing molecular descriptors in the chemical space is calculated; then the corresponding experimental schemes are recommended in order from the closest to the farthest distance.
[0060] The design scheme of the molecule can be represented by the experimental data of the molecule, which may include but is not limited to experimental conditions (including experimental methods, such as volatilization method, dissolution method, etc.; and related experimental parameters, such as temperature, pressure, etc.), and crystal types (such as single crystal, hydrate, solvate and co-crystal, etc.). It is also possible to design experiments to supplement more data from the perspective of molecular diversity to ensure that the experimental data has high coverage.
[0061] In addition, in addition to being applicable to the recommendation of crystallization experimental schemes, the embodiments of the present application can also be applied to the recommendation of other design schemes, such as molecular synthesis experimental design.
[0062] In an optional example, the obtaining of multiple preset molecules includes: obtaining design schemes of multiple initial molecules; parsing the design scheme of each initial molecule to determine the completeness of the design scheme of each initial molecule; and using the initial molecules with complete design schemes as preset molecules.
[0063] In other words, a large amount of experimental data of drug molecules is collected from multiple data sources, and then preset molecules that can construct the target chemical space are determined from the experimental data of a large amount of drug molecules, wherein each preset molecule corresponds to complete crystallization experimental data.
[0064] It should be noted that the above-mentioned multiple data sources can be paper libraries, experimental databases, specific experimental data, etc.
[0065] Furthermore, the parsing of the design scheme of each initial molecule to determine the completeness of the design scheme of each initial molecule includes: parsing the design scheme of each initial molecule to obtain a first initial molecule with a complete design scheme and a second initial molecule with an incomplete design scheme; taking the initial molecule with a complete design scheme as the preset molecule includes: taking the first initial molecule with a complete design scheme as the preset molecule; in addition, the method also includes: completing the design scheme of the second initial molecule, and taking the second initial molecule with the completed design scheme as the preset molecule.
[0066] It should be noted that the design plan at least includes: 1. Experimental conditions, such as methods (such as volatilization method, dissolution method, etc.), related parameters (such as temperature, pressure, etc.); 2. Crystal type, such as single crystal, hydrate, solvate and eutectic, etc.
[0067] In other words, if the design scheme of some initial molecules is incomplete, the design scheme of the initial molecules can be supplemented by designing experiments to ensure that the database established in the embodiment of the present application has high coverage.
[0068] In an optional example, determining the molecular descriptor of each of the preset molecules includes: using a preset algorithm to calculate multiple molecular descriptors of each of the preset molecules; screening the multiple molecular descriptors of each of the preset molecules to obtain a group of molecular descriptors for characterizing the preset molecules.
[0069] In other words, for each preset molecule, a chemical information calculation software (such as RDKit, etc.) can be used to calculate its corresponding molecular descriptor (generally, each preset molecule corresponds to multiple molecular descriptors). At this time, an unsupervised and / or supervised feature engineering method is used to screen and process the multiple molecular descriptors of each of the preset molecules to obtain a set of molecular descriptors for characterizing the preset molecules. At this time, the molecular descriptors for characterizing the preset molecules occupy a data point in the multidimensional space, and the collection of these data points and their coverage constitute the relevant target chemical space.
[0070] Optionally, screening the multiple molecular descriptors of each of the preset molecules includes at least the following processing methods:
[0071] First, for any molecular descriptor, when there are preset molecules exceeding a first threshold number whose values of the molecular descriptors are the same, the molecular descriptor is deleted.
[0072] Second, for any molecular descriptor, when the difference between the value of the molecular descriptor corresponding to a preset molecule and the value of the molecular descriptor corresponding to other preset molecules is lower than a second threshold, the molecular descriptor is deleted.
[0073] It should be noted that the difference can be characterized in various forms, such as variance, standard deviation, standard variance, mean square error, root mean square error, etc.
[0074] Third, for any molecular descriptor, when the value of the molecular descriptor corresponding to a preset molecule is abnormal, the molecular descriptor is deleted;
[0075] Fourthly, for any two molecular descriptors, when a correlation coefficient between the two molecular descriptors calculated based on the values of the two molecular descriptors corresponding to all preset molecules is higher than a third threshold, one of the two molecular descriptors is deleted.
[0076] Fifth, perform dimensionality reduction on all molecular descriptors.
[0077] It should be noted that the dimensionality reduction of molecular descriptors is to eliminate irrelevant and redundant information and reduce the number of variables; irrelevant information refers to molecular descriptors that are irrelevant to the design scheme, such as the number of atoms, atom types that are not contained in all molecules, etc.; redundant information refers to two or more molecular descriptors with similar meanings, such as molecular mass and heavy atom mass, and only one of them can be retained.
[0078] For example: if 90% of the samples (drug molecules) have the same value for the same molecular descriptor, the molecular descriptor will be deleted; if the relative standard deviation / relative standard variance of any molecular descriptor calculated across all samples is too low (such as less than 0.05), the molecular descriptor will be deleted; if an abnormal value (such as NaN or infinity) appears in a molecular descriptor, the molecular descriptor will be deleted; if the correlation coefficient between two molecular descriptors is too high (such as greater than 0.9), any one of the two molecular descriptors will be deleted.
[0079] In an optional example, determining the distance between the target molecule and each preset molecule in a pre-constructed target chemical space based on the molecular descriptor of the target molecule includes: determining the position of the target molecule in the pre-constructed target chemical space based on the molecular descriptor of the target molecule; and calculating the distance between the target molecule and each preset molecule based on the position of the target molecule in the target chemical space and the positions of each preset molecule in the target chemical space.
[0080] Furthermore, determining the candidate molecule from the preset molecules according to the distance between the target molecule and each of the preset molecules includes: selecting a preset number or a preset proportion of preset molecules with a smaller distance as candidate molecules according to the distance between the target molecule and each of the preset molecules; or selecting a preset molecule with the smallest distance as a candidate molecule according to the distance between the target molecule and each of the preset molecules.
[0081] It should be noted that the distance between the target molecule and each of the preset molecules may be a Euclidean distance.
[0082] In an optional example, when there are multiple candidate molecules, determining the design scheme of the target molecule based on the design schemes of the candidate molecules includes: scoring the design scheme of each candidate molecule according to a preset scoring strategy to obtain a score value of the design scheme of each candidate molecule; and using the design scheme of the candidate molecule with the highest score as the design scheme of the target molecule. In addition, when there is one candidate molecule and there are multiple sets of design schemes for the candidate molecules, determining the design scheme of the target molecule based on the design schemes of the candidate molecules includes: scoring each set of design schemes of the candidate molecules according to a preset scoring strategy to obtain a score value of each set of design schemes of the candidate molecules; and using the design scheme with the highest score as the design scheme of the target molecule.
[0083] When it is necessary to obtain a crystallization scheme for a target molecule, the preset scoring strategy for scoring the design schemes of the candidate molecules can be characterized by at least one information such as crystallinity, crystallization time, crystallization rate, etc. For example, a design scheme with a high crystallinity has a higher score than a design scheme with a low crystallinity, and a design scheme with a fast crystallization rate has a higher score than a design scheme with a low crystallization rate.
[0084] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, it will be described below in conjunction with specific embodiments.
[0085] Taking Bardoxolone methyl as an example, the staff input the target molecule, such as Figure 3 As shown; at this time, the 10 preset molecules closest to the target molecule are found in the target chemical space, such as Figure 4 As shown; finally, the design schemes of the 10 preset molecules are pushed in sequence according to the calculated distance to obtain the reference data of the crystallization experiment of methyl bardoxolone.
[0086] In summary, the embodiments of the present application achieve the following technical effects: 1. The reasonable crystallization experimental scheme is recommended quickly and high throughput can be achieved; 2. On the premise of achieving the crystallization goal, the number of experiments is reduced and costs are saved; 3. Only basic molecular information needs to be provided without further operations, which is easy to use.
[0087] According to another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for determining the molecular design scheme.
[0088] According to yet another embodiment of the present invention, there is provided an electronic device, which includes a memory and a processor, wherein the memory stores a program, and the processor is used to execute the program to implement the above-mentioned method for determining a molecular design scheme.
[0089] According to another embodiment of the present invention, an embodiment of a device for determining a molecular design scheme is also provided. It should be noted that the device for determining a molecular design scheme can be used to execute the method for determining a molecular design scheme in the embodiment of the present invention, and the method for determining a molecular design scheme in the embodiment of the present invention can be executed in the device for determining a molecular design scheme.
[0090] Figure 5 is a schematic diagram of a device for determining a molecular design scheme according to an embodiment of the present invention, such as Figure 5 As shown, the device may include: a first acquisition unit 51, used to acquire the target molecule to be designed and calculate the molecular descriptor of the target molecule; a first determination unit 53, used to determine the distance between the target molecule and each preset molecule in a pre-constructed target chemical space according to the molecular descriptor of the target molecule; a second determination unit 55, used to determine a candidate molecule from each preset molecule according to the distance between the target molecule and each preset molecule; a second acquisition unit 57, used to acquire a design scheme for the candidate molecule; and a third determination unit 59, used to determine the design scheme for the target molecule according to the design scheme for the candidate molecule.
[0091] Optionally, the determination device also includes: a third acquisition unit, used to acquire multiple preset molecules before the first acquisition unit 51 acquires the target molecule to be designed; a fourth determination unit, used to determine the molecular descriptor of each of the preset molecules, wherein the molecular descriptor of one of the preset molecules occupies a position in the multidimensional space; and a construction unit, used to construct the target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
[0092] Optionally, the third acquisition unit includes: a first acquisition subunit, used to acquire design schemes of multiple initial molecules; a first determination subunit, used to parse the design scheme of each initial molecule and determine the completeness of the design scheme of each initial molecule; and a second determination subunit, used to take the initial molecule with a complete design scheme as a preset molecule.
[0093] Optionally, the first determining subunit includes: a first acquiring module, configured to analyze the design scheme of each initial molecule to obtain a first initial molecule with a complete design scheme and a second initial molecule with an incomplete design scheme.
[0094] Optionally, the second determining subunit includes: a first determining module, configured to use the first initial molecule with a complete design scheme as a preset molecule.
[0095] Optionally, the determining device further includes: a completion unit, configured to complete the design scheme of the second initial molecule, and use the second initial molecule whose design scheme has been completed as the preset molecule.
[0096] Optionally, the fourth determination unit includes: a first calculation subunit, used to calculate multiple molecular descriptors of each of the preset molecules using a preset algorithm; and a screening subunit, used to screen the multiple molecular descriptors of each of the preset molecules to obtain a group of molecular descriptors used to characterize the preset molecules.
[0097] Optionally, the screening subunit includes at least any one of the following: a first processing module, used for deleting any molecular descriptor when there are more than a first threshold number of preset molecules corresponding to the same molecular descriptor value, the molecular descriptor; a second processing module, used for deleting any molecular descriptor when the difference between the value of the molecular descriptor corresponding to a preset molecule and the value of the molecular descriptor corresponding to other preset molecules is lower than a second threshold value; a third processing module, used for deleting any molecular descriptor when the value of the molecular descriptor corresponding to a preset molecule is abnormal; a fourth processing module, used for deleting one of any two molecular descriptors when the correlation coefficient of the two molecular descriptors calculated based on the values of the two molecular descriptors corresponding to all preset molecules is higher than a third threshold value; a fifth processing module, used for performing dimensionality reduction processing on all molecular descriptors.
[0098] Optionally, the first determination unit 53 includes: a third determination subunit, used to determine the position of the target molecule in a pre-constructed target chemical space based on the molecular descriptor of the target molecule; and a second calculation subunit, used to calculate the distance between the target molecule and each preset molecule in the target chemical space based on the position of the target molecule in the target chemical space and the positions of each preset molecule in the target chemical space.
[0099] Optionally, the second determination unit 55 includes at least any of the following: a first selection subunit, used to select a preset number or a preset proportion of preset molecules with smaller distances as candidate molecules based on the distances between the target molecule and each of the preset molecules; a second selection subunit, used to select the preset molecule with the smallest distance as the candidate molecule based on the distances between the target molecule and each of the preset molecules.
[0100] Optionally, the third determination unit 59 includes: a first scoring subunit, used to score the design scheme of each candidate molecule according to a preset scoring strategy when there are multiple candidate molecules, so as to obtain a score value of the design scheme of each candidate molecule; and a fourth determination subunit, used to use the design scheme of the candidate molecule with the highest score as the design scheme of the target molecule.
[0101] Optionally, the third determination unit 59 includes: a second scoring subunit, used to score each set of design schemes of the candidate molecules according to a preset scoring strategy when there is one candidate molecule and there are multiple sets of design schemes for the candidate molecules, so as to obtain a score value for each set of design schemes of the candidate molecules; and a fifth determination subunit, used to select the design scheme with the highest score as the design scheme of the target molecule.
[0102] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0103] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0104] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0106] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0108] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for determining a molecular design scheme, characterized in that: include: Obtaining a target molecule to be designed, and calculating a molecular descriptor of the target molecule; Determining the distance between the target molecule and each preset molecule in a pre-constructed target chemical space according to the molecular descriptor of the target molecule; Determining a candidate molecule from each of the preset molecules according to the distance between the target molecule and each of the preset molecules; Obtaining a design scheme for the candidate molecule; Determining a design scheme for the target molecule according to the design scheme for the candidate molecule; Before obtaining the target molecule to be designed, obtaining a plurality of preset molecules; Determine a molecular descriptor of each of the preset molecules, wherein a molecular descriptor of the preset molecule occupies a position in the multidimensional space; and construct a target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
2. The method according to claim 1, characterized in that: The obtaining of a plurality of preset molecules comprises: Obtaining design solutions for multiple initial molecules; Analyze the design scheme of each initial molecule to determine the completeness of the design scheme of each initial molecule; The initial molecule with the complete design scheme is used as the preset molecule.
3. The method according to claim 2, characterized in that The step of analyzing the design scheme of each initial molecule to determine the integrity of the design scheme of each initial molecule includes: analyzing the design scheme of each initial molecule to obtain a first initial molecule with a complete design scheme and a second initial molecule with an incomplete design scheme; The taking the initial molecule with a complete design scheme as the preset molecule includes: taking the first initial molecule with a complete design scheme as the preset molecule.
4. The method according to claim 3, characterized in that The method further comprises: The design scheme of the second initial molecule is completed, and the second initial molecule whose design scheme has been completed is used as the preset molecule.
5. The method according to claim 1, characterized in that The determining of the molecular descriptor of each of the preset molecules comprises: Calculating multiple molecular descriptors of each of the preset molecules using a preset algorithm; A plurality of molecular descriptors of each of the preset molecules are screened to obtain a group of molecular descriptors for characterizing the preset molecules.
6. The method according to claim 5, characterized in that Screening the multiple molecular descriptors of each of the preset molecules includes: For any molecular descriptor, when there are more than a first threshold number of preset molecules corresponding to the same molecular descriptor value, the molecular descriptor is deleted; and / or, For any molecular descriptor, when the difference between the value of the molecular descriptor corresponding to a preset molecule and the value of the molecular descriptor corresponding to other preset molecules is lower than a second threshold, the molecular descriptor is deleted; and / or, For any molecular descriptor, when the value of the molecular descriptor corresponding to a preset molecule is abnormal, the molecular descriptor is deleted; and / or, For any two molecular descriptors, when a correlation coefficient of the two molecular descriptors calculated based on the values of the two molecular descriptors corresponding to all preset molecules is higher than a third threshold, deleting one of the two molecular descriptors; and / or, All molecular descriptors were subjected to dimensionality reduction.
7. The method according to any one of claims 1 to 6, characterized in that: Determining the distance between the target molecule and each preset molecule in the pre-constructed target chemical space according to the molecular descriptor of the target molecule includes: Determining the position of the target molecule in a pre-constructed target chemical space according to the molecular descriptor of the target molecule; According to the position of the target molecule in the target chemical space and the position of each preset molecule in the target chemical space, the distance between the target molecule and each preset molecule is calculated.
8. The method according to any one of claims 1 to 6, characterized in that: The step of determining a candidate molecule from each of the preset molecules according to the distance between the target molecule and each of the preset molecules comprises: According to the distance between the target molecule and each of the preset molecules, a preset number or a preset proportion of preset molecules with a smaller distance are selected as candidate molecules; or, According to the distance between the target molecule and each of the preset molecules, the preset molecule with the shortest distance is selected as the candidate molecule.
9. The method according to any one of claims 1 to 6, characterized in that: When there are multiple candidate molecules, determining the design scheme of the target molecule according to the design scheme of the candidate molecules includes: Scoring the design scheme of each candidate molecule according to a preset scoring strategy to obtain a score value of the design scheme of each candidate molecule; The design solution of the candidate molecule with the highest score is used as the design solution of the target molecule.
10. The method according to any one of claims 1 to 6, characterized in that: When there is one candidate molecule and there are multiple design schemes for the candidate molecule, determining the design scheme for the target molecule according to the design scheme for the candidate molecule includes: Scoring each set of design solutions for the candidate molecules according to a preset scoring strategy to obtain a score value for each set of design solutions for the candidate molecules; The design solution with the highest score is taken as the design solution for the target molecule.
11. A device for determining a molecular design scheme, characterized in that: The device comprises: A first acquisition unit, used for acquiring a target molecule to be designed and calculating a molecular descriptor of the target molecule; A first determining unit, configured to determine the distance between the target molecule and each preset molecule in a pre-constructed target chemical space according to the molecular descriptor of the target molecule; A second determining unit, configured to determine a candidate molecule from each of the preset molecules according to the distance between the target molecule and each of the preset molecules; A second acquisition unit, used to acquire a design scheme of the candidate molecule; A third determining unit, configured to determine a design scheme for the target molecule according to the design scheme for the candidate molecule; The third acquisition unit is used to acquire multiple preset molecules before the first acquisition unit acquires the target molecule to be designed; the fourth determination unit is used to determine the molecular descriptor of each of the preset molecules, wherein the molecular descriptor of one of the preset molecules occupies a position in the multidimensional space; the construction unit is used to construct the target chemical space based on the position occupied by the molecular descriptor of each of the preset molecules in the multidimensional space.
12. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a program, and the processor is used to execute the program to implement the method for determining a molecular design scheme according to any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for determining a molecular design scheme according to any one of claims 1 to 10.