An efficient drug screening method, device, storage medium and electronic equipment

Abstract

The application discloses a high-efficiency drug screening method and device, a storage medium and an electronic device. The method comprises the following steps: obtaining a to-be-screened drug molecule for drug screening; obtaining SMILES format information of the to-be-screened drug molecule; obtaining SMILES format information of a template drug molecule; comparing the template drug molecule with the to-be-screened drug molecule, and obtaining similarity of the template drug molecule and the to-be-screened drug molecule; and screening the to-be-screened drug molecule with similarity greater than a set threshold value as a final screened drug molecule. According to the scheme, the SMILES format information of the to-be-screened drug molecule is compared with the SMILES format information of the template drug molecule, the to-be-screened drug molecule with similarity greater than the set threshold value is determined as the final screened drug molecule, and the automation is realized, so that the influence of subjective factors on the accuracy of the screening result is eliminated, and the efficiency and precision of drug screening are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of accessories for biological sorting equipment, and particularly relates to a high-efficiency drug screening method and device, a storage medium and an electronic device. BACKGROUND

[0002] At present, the accuracy of drug screening is required to be higher and higher in the drug research and development stage. Taking xanthine oxidase as an example, uric acid is the final product of human purine and nucleic acid decomposition metabolism, and the source of uric acid is endogenous uric acid and exogenous uric acid. The endogenous uric acid is mainly synthesized in the liver from glutamic acid, but also from the decomposition of nucleoprotein in the body. The exogenous uric acid is mainly from the intake of seafood and other foods rich in purines. In recent years, with the improvement of people's living standards, a large number of epidemiological studies at home and abroad have shown that the prevalence rate of hyperuricemia / gout is increasing year by year. Xanthine oxidase is a key enzyme in the generation of uric acid in the body, and its main function is to catalyze the generation of uric acid and hypoxanthine from xanthine. In order to treat gout and hyperuricemia, contemporary medicine often treats by inhibiting the expression of xanthine oxidase. At present, allopurinol and non-purine xanthine oxidase inhibitor febuxostat are used as main anti-gout drugs, but both have many side effects, and long-term use can cause great harm to the human body. In 2013, the State Food and Drug Administration issued the Drug Adverse Reaction Information Bulletin, which warned that allopurinol could cause severe drug eruptions. Therefore, it is of great practical significance to develop new low-toxicity and high-efficiency xanthine oxidase inhibitors.

[0003] At present, most of the drug screening methods are based on artificial analysis of structure, analysis of fragments and DNA coding, and the main means of these methods is realized by artificial means. Such method is low in efficiency and slow in speed, and does not meet the trend of high-throughput development today. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a high-efficiency drug screening method, device, storage medium and electronic device to solve the problem of low efficiency and the need for a large amount of manpower and material resources in the prior art drug screening scheme.

[0005] In a first aspect, the technical scheme of the present application provides a high-efficiency drug screening method, comprising:

[0006] obtaining a to-be-screened drug molecule for drug screening;

[0007] obtaining SMILES format information of the to-be-screened drug molecule;

[0008] obtaining SMILES format information of a template drug molecule;

[0009] comparing the template drug molecule with the drug molecule to be screened, and obtaining a similarity between the template drug molecule and the drug molecule to be screened;

[0010] screening the drug molecule to be screened with a similarity greater than a set threshold as a final screened drug molecule.

[0011] In some embodiments of the efficient drug screening method, the comparing the template drug molecule with the drug molecule to be screened, and obtaining a similarity between the template drug molecule and the drug molecule to be screened, comprises:

[0012] comparing the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule as a whole;

[0013] determining the similarity according to the result of the comparison as a whole.

[0014] In some embodiments of the efficient drug screening method, the comparing the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule as a whole, comprises:

[0015] defining a position for each constituent element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule;

[0016] sequentially sliding a set sliding window along the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, and comparing whether the constituent elements in the sliding window are the same;

[0017] setting a first mark at a position where the constituent elements are the same and setting a second mark at a position where the constituent elements are different during the movement of the sliding window;

[0018] taking the proportion of the number of the first marks in the total number of marks as the similarity.

[0019] In some embodiments of the efficient drug screening method, the comparing the template drug molecule with the drug molecule to be screened, and obtaining a similarity between the template drug molecule and the drug molecule to be screened, comprises:

[0020] comparing the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule locally;

[0021] determining the similarity according to the result of the local comparison.

[0022] The high-efficiency drug screening method in some schemes, wherein the SMILES format information of the drug molecule to be screened is locally compared with the SMILES format information of the template drug molecule, comprises:

[0023] The to-be-compared drug molecule module to be screened is cut from the SMILES format information of the drug molecule to be screened;

[0024] The to-be-compared drug molecule module to be screened and each element in the SMILES format information of the template drug molecule are defined positions;

[0025] A set of sliding windows are sequentially slid along the to-be-compared drug molecule module to be screened and the SMILES format information of the template drug molecule, and whether the elements in the sliding windows are the same is compared;

[0026] If there are the same elements in the sliding window, the positions corresponding to the same elements are taken as starting points, the comparison of subsequent elements is performed, and the number of continuous same elements is determined;

[0027] During the sliding of the sliding window, if the number of continuous same elements is the same as the number of elements in the to-be-compared drug molecule module to be screened, the to-be-compared drug molecule module to be screened is taken as a target drug molecule module to be screened, otherwise the starting point position is re-determined;

[0028] The ratio of the number of target drug molecule modules to be screened to the total number of molecular modules is taken as the similarity.

[0029] The high-efficiency drug screening method in some schemes, wherein the template drug molecule is compared with the drug molecule to be screened, and the similarity between the template drug molecule and the drug molecule to be screened is obtained, comprises:

[0030] The SMILES format information of the drug molecule to be screened is compared with the SMILES format information of the template drug molecule in a combination of global comparison and local comparison;

[0031] The similarity is determined according to the results of global comparison and local comparison.

[0032] The high-efficiency drug screening method in some schemes, wherein the SMILES format information of the drug molecule to be screened is compared with the SMILES format information of the template drug molecule in a combination of global comparison and local comparison, comprises:

[0033] The SMILES format information of the drug molecule to be screened is compared with the SMILES format information of the template drug molecule as a whole, and the drug molecule to be screened with a similarity greater than a first set threshold obtained by the overall comparison is selected as a preselected drug molecule;

[0034] The preselected drug molecule is compared with the SMILES format information of the template drug molecule as a whole, and the preselected drug molecule with a similarity greater than a second set threshold obtained by the local comparison is selected as a finally screened drug molecule.

[0035] In a second aspect, the present application provides an efficient drug screening device, comprising:

[0036] A drug molecule to be screened acquisition module is configured to acquire a drug molecule to be screened for drug screening;

[0037] A first information acquisition module is configured to acquire SMILES format information of the drug molecule to be screened;

[0038] A second information acquisition module is configured to acquire SMILES format information of a template drug molecule;

[0039] A comparison module is configured to compare the template drug molecule with the drug molecule to be screened and acquire a similarity of the template drug molecule and the drug molecule to be screened;

[0040] A screening module is configured to screen the drug molecule to be screened with a similarity greater than a set threshold as a finally screened drug molecule.

[0041] In a third aspect, the present application provides a storage medium, wherein the storage medium stores program information, and a computer reads the program information to execute the efficient drug screening method of any one of the first aspect.

[0042] In a fourth aspect, the present application provides an electronic device, comprising at least one processor and at least one memory, wherein the at least one memory stores program instructions, and the at least one processor reads the program instructions in the memory to execute the efficient drug screening method of any one of the first aspect.

[0043] Compared with the prior art, the above-mentioned scheme provided by the embodiments of the present application has the following advantages:

[0044] The high-efficiency drug screening method, device, storage medium and electronic equipment provided by the application, the method comprising: obtaining a drug molecule to be screened for drug screening; obtaining SMILES format information of the drug molecule to be screened; obtaining SMILES format information of a template drug molecule; comparing the template drug molecule with the drug molecule to be screened, and obtaining similarity of the template drug molecule and the drug molecule to be screened; and screening the drug molecule to be screened with similarity greater than a set threshold value as a final screened drug molecule. Through the scheme of the application, the SMILES format information of the drug molecule to be screened is compared with the SMILES format information of the template drug molecule to determine the drug molecule to be screened with similarity greater than a set threshold value as a final screened drug molecule, which can be realized in an automatic manner without relying on human resources, and eliminates the influence of subjective factors on the screening structure accuracy, greatly improving the efficiency and precision of drug screening. BRIEF DESCRIPTION OF DRAWINGS

[0045] The above features and technical advantages of the application will become more apparent and easily understood from the following description of the embodiments thereof, taken in conjunction with the accompanying drawings.

[0046] Figure 1 A flowchart of the high-efficiency drug screening method according to an embodiment of the application;

[0047] Figure 2 A schematic diagram of the operation interface of the high-efficiency drug screening method according to an embodiment of the application;

[0048] Figure 3 A schematic diagram of the display mode of the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule according to an embodiment of the application;

[0049] Figure 4 A structural block diagram of the high-efficiency drug screening device according to an embodiment of the application;

[0050] Figure 5 A schematic diagram of the hardware connection relationship of the electronic device for executing the high-efficiency drug screening method according to an embodiment of the application. EMBODIMENTS

[0051] In order to make the purpose, technical scheme and advantages of the application clearer, the application will be further described in detail below with reference to specific embodiments and the accompanying drawings. The same parts are denoted by the same reference numerals. It should be noted that the words "front", "back", "left", "right", "up" and "down" used in the following description refer to the directions in the drawings. The words "inner" and "outer" refer to the directions towards or away from the geometric center of a particular part.

[0052] This application provides an efficient drug screening method, such as... Figure 1 As shown, it includes:

[0053] S10: Obtain the drug molecules to be screened for drug screening.

[0054] Taking inhibitors that suppress the catalytic activity of xanthine oxidase as an example, this is a key enzyme involved in human metabolism and the main enzyme responsible for the production of uric acid. In practice, expert experience can be used to identify candidate drug molecules that may share similarities with the template drug molecule.

[0055] like Figure 2 The image shows a screenshot of the drug molecule screening program. In the molecule input box, enter the SMILES format of an existing drug molecule. If screening multiple molecules, separate them with commas. Alternatively, use the "From File" button to enter molecule information from a local or online file. Then, select the molecule similarity threshold in the threshold options, with a selectable range of 0-100%, preferably 70%-90%. After determining the screening threshold, you can choose between two screening modes: overall and partial screening. If partial screening is selected, you need to enter the correct pharmacophore information in the pharmacophore module. The overall screening mode compares the overall structure of the drug molecule, accurately identifying molecules with similar structures to the candidate drug molecule from the database. The partial screening mode, also known as the pharmacophore screening mode, accurately analyzes and compares the pharmacophore information of the molecule during the screening process, focusing on a portion of the molecule's structure.

[0056] After all the information is entered correctly, you can click the "Start Search" button to begin filtering. A screening database containing nearly 200 million molecules has been constructed. To improve screening efficiency, the information for these 200 million molecules is stored in over 5,000 tables, with an average of over 40,000 molecules per table. The screening system employs a multi-core processing approach to efficiently handle the massive number of molecular groups, allowing multiple computer cores to be used simultaneously for comparison and screening. Currently, the highest speed is 3,000 molecules per second, and the entire database of 200 million molecules is screened in approximately 20 hours.

[0057] S20: Obtain the SMILES format information of the drug molecule to be screened; obtain the SMILES format information of the template drug molecule.

[0058] like Figure 3 As shown, the top column is the drug molecule to be screened, and the bottom column is the template drug molecule. The SMILES format information of the two can be misaligned. The starting point is determined by identifying the same constituent elements during the comparison process.

[0059] S30: comparing the template drug molecule with the drug molecule to be screened, and obtaining the similarity between the template drug molecule and the drug molecule to be screened.

[0060] S40: screening the drug molecule to be screened with a similarity greater than a set threshold as a final screened drug molecule.

[0061] Further, the screening process will display, for example, the completed screening library, the number of successfully screened molecules, and the molecules that have been screened to meet the requirements, etc. in the interface in real time. The data that is successfully screened and abnormal during the screening comparison process is also recorded in the program. The abnormal data recorded herein refers to the abnormality of the molecular structure stored in the molecular database, such as the occurrence of cracking and the like. The abnormal data will not affect the normal operation of the program, nor will it affect the screening speed. After the program is started, all tables storing molecules, as well as tables being screened and completed screening tables, are displayed in the interface. In the "screening list" module, the molecules that meet the threshold requirements in the completed screening, as well as the similarity information, are displayed in real time. The similar template drug molecules and similar pharmacophore information are also displayed synchronously. When all the molecules are screened, clicking the "export data" button to select the appropriate storage location can export the structure file of the screened molecules, as well as the SMILES format information of the molecules and the similarity information of the molecules in the form of a table file to the appropriate location.

[0062] The above scheme of the embodiment utilizes the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule to compare and determine the drug molecule to be screened with a similarity greater than a set threshold as a final screened drug molecule, which can be realized in an automated manner without relying on human resources, and eliminates the influence of subjective factors on the screening structure accuracy, greatly improving the efficiency and precision of drug screening.

[0063] Further, step S30 in the above scheme includes:

[0064] S311: comparing the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule as a whole;

[0065] S312: determining the similarity according to the overall comparison result.

[0066] In a specific implementation, a position is defined for each component element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule; a sliding window is set, and the component elements in the sliding window are compared in sequence along the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule; during the movement of the sliding window, a first mark is set at a position where the component elements are the same, and a second mark is set at a position where the component elements are different; and the proportion of the number of the first marks in the total number of marks is taken as the similarity.

[0067] Reference Figure 3 , a position is defined for each component element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule in sequence; the component element definition position of the drug molecule to be screened is 1, 2, 3, 4...10, and the component element definition position of the SMILES format information of the template drug molecule is 1-19 according to the same principle; then, the component elements of the SMILES format information of the template drug molecule are moved in a sliding manner from one end in sequence, the position of the first element that is the same as the drug molecule to be screened is found, and then comparison is performed in sequence from this element as a starting point; if the elements at the positions are the same, 1 (i.e., a first mark) is recorded, and if the elements at the positions are different, 0 (i.e., a second mark) is recorded; after the comparison is completed, the number of 1s is counted, and then the proportion of this number in the number of elements of the drug molecule to be screened is calculated to define the similarity.

[0068] In some other schemes, step S30 includes:

[0069] S321: locally aligning the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule.

[0070] S322: determining the similarity according to the local alignment result.

[0071] In a specific implementation, a to-be-compared to-be-screened drug molecule module is segmented from the SMILES format information of the to-be-screened drug molecule; each constituent element in the to-be-compared to-be-screened drug molecule module and the SMILES format information of the template drug molecule is defined in position; a sliding window is set, and the constituent elements in the sliding window are compared in sequence along the to-be-compared to-be-screened drug molecule module and the SMILES format information of the template drug molecule; if there are same constituent elements in the sliding window, the position of the same constituent element is taken as a starting point, and the comparison of subsequent constituent elements is performed to determine the number of continuous same constituent elements; in the process of sliding of the sliding window, if the number of continuous same constituent elements is the same as the number of elements in the to-be-compared to-be-screened drug molecule module, the to-be-compared to-be-screened drug molecule module is taken as a target to-be-screened drug molecule module, otherwise the starting point position is redefined; and a ratio of the number of finally screened drug molecule modules to the total number of drug molecule modules is taken as the similarity.

[0072] Still taking Figure 3 as an example, a part of the to-be-screened drug molecule is taken as a comparison module as the to-be-compared to-be-screened drug molecule module, for example Figure 3 the part marked in the box in the figure, and the rest of the elements can be ignored. Specifically, the same elements in the SMILES format information of the template drug molecule and the to-be-compared to-be-screened drug molecule module are found by the same method as the overall comparison, and then the subsequent element comparison is performed from the starting point. If the elements in the positions are the same, 1 is recorded, and if the elements in the positions are different, 0 is recorded. The difference between the overall comparison mode and the local comparison mode is that: in the overall comparison mode, the same elements can appear discontinuously, for example, the 5th element is the same, but the 6th element is different, which is allowed, but in the local comparison mode, after the comparison starting point is determined, the elements in the continuous positions must be the same, and the number of continuous same elements must be the same as the number of elements of the to-be-compared to-be-screened drug molecule module defined in the template. If the elements in any position are not the same, 0 is recorded. If only one to-be-compared to-be-screened drug molecule module is defined in the to-be-screened drug molecule, and 0 is recorded, the to-be-compared to-be-screened drug molecule module will be discarded. If several to-be-compared to-be-screened drug molecule modules are defined in the template, the ratio of the number of to-be-compared to-be-screened drug molecule modules recorded as 1 to the total number of modules in the template is recorded as the similarity. In the selection of the to-be-compared to-be-screened drug molecule module, the program can select a small molecule pharmacophore as the local comparison module, or the experimenter can define it according to his experience.

[0073] As another solution, the step S30 can also be implemented in the following way:

[0074] S331: The SMILES format information of the drug molecule to be screened is compared with the SMILES format information of the template drug molecule in a combination of global comparison and local comparison.

[0075] S332: The similarity is determined according to the results of global comparison and local comparison.

[0076] Specifically, the SMILES format information of the drug molecule to be screened is first compared with the SMILES format information of the template drug molecule for global comparison, and the drug molecule to be screened with a similarity greater than a first set threshold obtained by global comparison is selected as a preselected drug molecule; the preselected drug molecule is compared with the SMILES format information of the template drug molecule for local comparison, and the preselected drug molecule with a similarity greater than a second set threshold obtained by local comparison is selected as a final screened drug molecule.

[0077] Still taking Figure 3 as an example, first, global comparison is performed, and the comparison method and the determination method of the comparison result are the same as those of the global comparison mode, then the results with a similarity reaching a predetermined threshold in the global comparison results are taken as input files, and then these molecules are compared with the drug molecules to be screened according to the defined modules in the drug molecules to be screened. The comparison method and the determination method of the comparison result are the same as those of the local comparison mode.

[0078] In the above scheme, according to the specific compared molecules and expert experience, the given results of each threshold can be set, and after setting each threshold, the results of comparison are screened according to the threshold, for example, if it is set to 0.9, the molecules with a similarity greater than 90% in the comparison results will be output, and the molecules with a similarity less than 90% will be discarded.

[0079] In the process of screening operation, the above method can also display the running time of the screening process, the number of molecules that have been screened, the number of abnormal molecules among the molecules that have been screened and compared, and the number of molecules that have been normally compared and screened. The standard for judging abnormal molecules is that an element type that does not exist in the drug molecules to be screened appears in the compared molecules or the structure of the compared molecules is abnormal.

[0080] The above scheme of the present application effectively realizes the good effects of fast speed, high accuracy and small energy consumption of computing resources in high-throughput screening of drug molecules by combining template supervision, organic combination of multiple comparison and screening modes, and machine learning assisted by expert experience. The speed of the program for comparing and screening drug molecules is 3000 molecules per second, and the time consumed for the entire screening of a database with a quantity of 200 million molecules is only about 20 hours.

[0081] In practical applications, in order to prove the feasibility of the above method, the applicant takes the marketed drug Febuxostat for treating gout as a template to carry out experimental verification according to the screening process, and obtains a certain number of drug molecules with obvious inhibition of xanthine oxidase expression after several rounds of screening verification. It is verified that the above method has been screened out the molecules with obvious inhibition effect on xanthine oxidase. Therefore, it can be proved that the above method is effective for drug screening, and since most drug molecules are effective by interacting with the target through the pharmacophore, the high-efficiency drug screening method of the application is based on the pharmacophore. Therefore, the method can be effectively applied to the development of small molecule drugs, polypeptide drugs and antibody drugs, and different screening modes or a combination of multiple screening modes can be reasonably used according to the content of the screening.

[0082] The embodiment of the application further provides a high-efficiency drug screening device, as shown in the accompanying drawings, comprising: Figure 4

[0083] The to-be-screened drug molecule acquisition module 10 is configured to acquire to-be-screened drug molecules for drug screening;

[0084] The first information acquisition module 20 is configured to acquire SMILES format information of the to-be-screened drug molecules;

[0085] The second information acquisition module is configured to acquire SMILES format information of the template drug molecules;

[0086] The comparison module 30 is configured to compare the template drug molecules with the to-be-screened drug molecules, and acquire the similarity between the template drug molecules and the to-be-screened drug molecules;

[0087] The screening module 40 is configured to screen the to-be-screened drug molecules with a similarity greater than a set threshold as the final screened drug molecules.

[0088] ​In some embodiments, the comparison module 30 is further configured to compare the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule as a whole, and determine the similarity according to the result of the comparison as a whole. Specifically, a position is defined for each element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, a sliding window is set, and the elements in the sliding window are compared in sequence along the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, a first mark is set for positions where the elements are the same, and a second mark is set for positions where the elements are different, and the similarity is determined as a proportion of the number of the first marks to the total number of the marks.

[0089] In some embodiments, the comparison module 30 is further configured to compare the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule as a whole, and determine the similarity according to the result of the comparison as a whole. Specifically, a position is defined for each element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, a sliding window is set, and the elements in the sliding window are compared in sequence along the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, a first mark is set for positions where the elements are the same, and a second mark is set for positions where the elements are different, and the similarity is determined as a proportion of the number of the first marks to the total number of the marks.

[0090] In some solutions, the comparison module 30 is further configured to compare the SMILES format information of the drug molecule to be screened with the SMILES format information of the template drug molecule in a combination of global comparison and local comparison. The similarity is determined according to the results of the global comparison and the local comparison. Specifically, the SMILES format information of the drug molecule to be screened is first compared with the SMILES format information of the template drug molecule in global comparison, and the drug molecule to be screened with a similarity greater than a first set threshold obtained by global comparison is taken as a preselected drug molecule; the preselected drug molecule is compared with the SMILES format information of the template drug molecule in local comparison, and the preselected drug molecule with a similarity greater than a second set threshold obtained by local comparison is taken as a finally screened drug molecule.

[0091] Some embodiments of the present application provide a storage medium having program information stored therein, and a computer reads the program information to execute the efficient drug screening method proposed in any of the above embodiments.

[0092] Some embodiments of the present application provide an electronic device, such as Figure 5As shown, the electronic device includes at least one processor 51 and at least one memory 52, at least one of the memories 52 stores program information, and at least one of the processors 51 reads the program information and executes the efficient drug screening method described in any of the above method embodiments. The device can also include an input device 53 and an output device 54. The processor 51, the memory 52, the input device 53 and the output device 54 can be communicatively connected. The memory 52, as a non-volatile computer readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The processor 51 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 52, that is, implements the efficient drug screening method provided in any of the above schemes. The memory 52 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the efficient drug screening method, etc. In addition, the memory 52 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 52 can optionally include a memory remotely arranged with respect to the processor 51, and these remote memories can be connected to the device executing the efficient drug screening method through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The input device 53 can receive input user clicks and generate signal inputs related to user settings and functional controls of the efficient drug screening method. The output device 54 can include a display device such as a display screen. When the one or more modules are stored in the memory 52 and are run by the one or more processors 51, the efficient drug screening method in any of the above method embodiments is executed.

[0093] It should be understood by those of ordinary skill in the art that the above is only a specific embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit of the present application shall be included in the protection scope of the present application.

Claims

1. A high throughput drug screening method, characterized by, The method comprises the following steps: acquiring a drug molecule to be screened for drug screening; acquiring SMILES format information of the drug molecule to be screened; acquiring SMILES format information of a template drug molecule; comparing the template drug molecule with the drug molecule to be screened, and acquiring similarity of the template drug molecule and the drug molecule to be screened; screening the drug molecule to be screened with similarity greater than a set threshold as a final screened drug molecule; the comparing the template drug molecule with the drug molecule to be screened, and acquiring similarity of the template drug molecule and the drug molecule to be screened comprises: performing overall alignment of the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, including defining positions of each constituent element in the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, sequentially sliding a set sliding window along the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, and comparing constituent elements in the sliding window; during movement of the sliding window, positions of constituent elements that are the same are marked with a first mark, and positions of constituent elements that are different are marked with a second mark; the similarity is taken as a proportion of the number of the first marks to a total number of marks; determining the similarity according to the overall alignment result.

2. The high throughput drug screening method of claim 1, wherein, the comparing the template drug molecule with the drug molecule to be screened, and acquiring similarity of the template drug molecule and the drug molecule to be screened comprises: performing local alignment of the SMILES format information of the drug molecule to be screened and the SMILES format information of the template drug molecule, including cutting a to-be-aligned drug molecule module from the SMILES format information of the drug molecule to be screened, defining positions of each constituent element in the to-be-aligned drug molecule module and the SMILES format information of the template drug molecule, sequentially sliding a set sliding window along the to-be-aligned drug molecule module and the SMILES format information of the template drug molecule, and comparing constituent elements in the sliding window; if there are same constituent elements in the sliding window, positions corresponding to the same constituent elements are taken as starting points, comparison of subsequent constituent elements is performed, and a number of continuously same constituent elements is determined; during sliding of the sliding window, if the number of continuously same constituent elements is the same as a number of elements in the to-be-aligned drug molecule module, the to-be-aligned drug molecule module is taken as a target to-be-aligned drug molecule module, otherwise the starting point position is re-determined; a ratio of a number of target to-be-aligned drug molecule modules to a total number of molecule modules is taken as the similarity; determining the similarity according to the local alignment result.

3. The high throughput drug screening method of claim 2, wherein, the comparing the template drug molecule with the drug molecule to be screened, and acquiring similarity of the template drug molecule and the drug molecule to be screened comprises: The SMILES format information of the drug molecules to be screened is compared with the SMILES format information of the template drug molecules by combining global comparison and local comparison, including: first, the SMILES format information of the drug molecules to be screened is compared with the SMILES format information of the template drug molecules by global comparison, and the drug molecules to be screened with a similarity greater than a first set threshold obtained by global comparison are selected as preselected drug molecules; the preselected drug molecules are compared with the SMILES format information of the template drug molecules by local comparison, and the preselected drug molecules with a similarity greater than a second set threshold obtained by local comparison are selected as the final screened drug molecules. The similarity is determined according to the results of global comparison and local comparison.

4. A high throughput drug screening device, characterized by, The device for performing the efficient drug screening method of any one of claims 1-3 comprises: a drug molecule to be screened acquisition module configured to acquire drug molecules to be screened for drug screening; a first information acquisition module configured to acquire SMILES format information of the drug molecules to be screened; a second information acquisition module configured to acquire SMILES format information of template drug molecules; a comparison module configured to compare the template drug molecules with the drug molecules to be screened and acquire a similarity of the template drug molecules and the drug molecules to be screened; a screening module configured to screen the drug molecules to be screened with a similarity greater than a set threshold as final screened drug molecules.

5. A storage medium, characterized by The storage medium stores program information, and the computer reads the program information to perform the efficient drug screening method of any one of claims 1-3.

6. An electronic device, comprising: The device comprises at least one processor and at least one memory, and the at least one memory stores program instructions, and the at least one processor reads the program instructions in the memory to perform the efficient drug screening method of any one of claims 1-3.

Images