Method and apparatus for screening old drugs for potential therapeutic effects on specific cancer types

Abstract

The application discloses a method and device for screening drugs with potential therapeutic effects on specific cancer types from old drugs, and finds potential drug target genes by researching essential genes in a certain disease state, and then designs and screens drugs aiming at the target genes. The application proposes a method for evaluating the specific necessity of genes in specific cancer types, and based on the method, proposes a method for determining ideal target points of the cancer types, and in combination with existing drug / compound-target point action information and the current research and development state of the drugs / compounds, proposes a strategy for screening existing drugs / compounds with potential therapeutic effects in specific cancer types.

Description

Technical Field

[0001] This invention relates to the field of biotechnology, and in particular to a method and apparatus for screening drugs from existing drugs that have potential therapeutic effects on specific cancer types. Background Technology

[0002] Essential genes are those that are necessary for the survival and development of an organism. These genes play a vital role in the life process of an organism, and if these genes mutate or are lost, it may lead to the death or developmental abnormalities of the organism.

[0003] In the fields of biotechnology and bioinformatics, researchers often utilize essential genes to identify new drug targets or to study the mechanisms of disease. For example, by studying essential genes in a particular disease state, researchers can identify potential drug targets and then design and screen drugs targeting these genes.

[0004] A study published in *Nature* by FMBehan et al., titled "Prioritization of cancertherapeutic targets using CRISPR-Cas9 screens," reported the essentiality of 7470 genes in 325 cell lines belonging to 32 cancer types, with several other cell lines not classified. Therefore, by studying essential genes in these cancer cell lines, we can identify potential drug target genes for specific cancer types, and then design and screen drugs targeting these genes.

[0005] Designing new drugs is a lengthy and challenging process, while screening existing drugs / compounds is relatively simpler, and essential genes are also used in the screening of existing drugs for repurposing. Drug repurposing, also known as drug repositioning or drug reuse, refers to using already marketed drugs for the treatment of new diseases. Because the drugs involved in drug repurposing have already passed clinical trials and proven safe, they can enter later stages of clinical trials more quickly or be used directly on patients, saving significant research and development time and costs. Current drug repurposing technologies require experimental verification and screening from a large drug library one by one, a large task with a long cycle.

[0006] Therefore, it is necessary to provide a method and apparatus for screening existing drugs that have potential therapeutic effects on specific cancer types. This method can be used to screen existing drugs for potential therapeutic effects and then verify them experimentally, thereby shortening the screening time and reducing the workload and time cost. Summary of the Invention

[0007] The purpose of this invention is to provide a method and apparatus for screening drugs with potential therapeutic effects on specific cancer types from existing drugs. It proposes for the first time a method for evaluating the specific necessity of a gene in a specific cancer type. When the value of n is larger and the value of m is smaller, that is, the more a gene is required in a cell line of a certain cancer type and the less required in cell lines of other cancer types, the stronger the specific necessity of that gene for that cancer type, and the greater the likelihood that the gene is a specific ideal target for that cancer type. Screening drugs with potential therapeutic effects on specific cancer types from existing drugs based on specific necessity can shorten screening time and reduce workload and time costs.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] In a first aspect of the present invention, a method is provided for screening drugs from existing drugs that have potential therapeutic effects against a specific type of cancer, the method comprising:

[0010] Based on the necessity of multiple target genes in cell lines of a specific cancer type, the ratio of the number of cell lines required for each gene in a specific cancer type to the total number of cell lines of that specific cancer type is obtained, denoted as n.

[0011] Based on the necessity of multiple target genes in multiple cancer cell lines, the ratio of the number of cell lines required for each gene in multiple cancer cell lines to the total number of cell lines in multiple cancer cell lines is obtained and denoted as m.

[0012] From the plurality of genes, a first screening is performed according to the requirement that n>0.5 and n≥m to obtain the first candidate gene;

[0013] Based on existing drug / compound-target interaction information, a second screening is performed to search for genes that interact with drugs / compounds in the existing drug / compound library, thereby obtaining a second candidate gene;

[0014] Remove genes with n>0.9 and m>0.9 from the second candidate genes, and sort the genes by n / m from largest to smallest to obtain the target gene;

[0015] Based on the drug / compound target action information associated with the target gene, as well as the research and development status and existing action information of the associated drug / compound, existing drugs with potential therapeutic effects on specific cancer types are screened.

[0016] In a second aspect of the present invention, an apparatus is provided for screening drugs from existing drugs that have potential therapeutic effects against a specific type of cancer, the apparatus comprising:

[0017] A module for obtaining the value of n is used to calculate the ratio of the number of cell lines required for each gene in a specific cancer type to the total number of cell lines for that specific cancer type.

[0018] The module for obtaining the m value is used to calculate the ratio of the number of cell lines required for each gene in multiple cancer cell lines to the total number of cell lines in multiple cancer cell lines.

[0019] The module for obtaining the first candidate gene is used to perform a first screening from the plurality of genes according to the requirement that n>0.5 and n≥m, to obtain the first candidate gene;

[0020] The module for obtaining the second candidate gene searches for genes that interact with drugs / compounds in the existing drug / compound library based on existing drug / compound target interaction information to perform a second screening and obtain the second candidate gene.

[0021] The module for obtaining the target gene removes genes with n>0.9 and m>0.9 from the second candidate genes, and sorts the genes by their n / m values ​​from largest to smallest to select the top ten genes to obtain the target gene.

[0022] A module for obtaining existing drugs with potential therapeutic effects on specific cancer types is used to screen existing drugs with potential therapeutic effects on specific cancer types based on the drug / compound-target action information associated with the target gene and the research and development status and existing action information of the associated drug / compound.

[0023] In a third aspect of the present invention, an apparatus is provided for screening drugs from existing drugs that have potential therapeutic effects against a specific type of cancer, the apparatus comprising:

[0024] A processor and a memory, the memory being coupled to the processor, the memory storing instructions that are used when the instructions are executed by the processor.

[0025] In a fourth aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, characterized in that the computer program uses the steps when executed by a processor.

[0026] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0027] The method and apparatus for screening existing drugs with potential therapeutic effects on specific cancer types provided in this invention comprehensively consider the overall specificity and necessity of the target in a specific cancer type to obtain the target gene. Then, based on the drug / compound-target interaction information associated with the target gene, as well as the research and development status and existing activity information of the associated drug / compound, existing drugs with potential therapeutic effects on specific cancer types are screened. This proposes a new method for finding cancer treatment drugs from marketed drugs used to treat other diseases. In screening existing drugs for repurposing, this invention simultaneously considers the current research and development status of the drug / compound, avoiding the inclusion of drugs withdrawn from the market due to excessive toxic side effects. Since the drugs for repurposing have already passed clinical trials and proven safe, they can enter later stages of clinical trials or be directly used by patients more quickly, significantly saving time and costs. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 The ROC curve of the SVM model constructed in the method for screening drugs with potential therapeutic effects on specific cancer types provided by the present invention. Detailed Implementation

[0030] The following detailed description of the embodiments and examples will illustrate the present invention in more detail, thereby making the advantages and various effects of the embodiments more clearly apparent. Those skilled in the art should understand that these detailed embodiments and examples are for illustrative purposes only and are not intended to limit the scope of the present invention.

[0031] Throughout this specification, unless otherwise specified, the terminology used herein should be understood as having the meaning commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments of this invention pertain. In the event of any conflict, this specification shall prevail.

[0032] Unless otherwise specified, all raw materials, reagents, instruments and equipment used in the embodiments of the present invention can be purchased from the market or prepared by existing methods.

[0033] The following will describe in detail a method and apparatus for screening drugs from existing drugs that have potential therapeutic effects on specific cancer types, in conjunction with embodiments, comparative examples and experimental data.

[0034] Example 1: A method for screening existing drugs that have potential therapeutic effects against specific cancer types.

[0035] In the screening example of repurposing existing drugs for lung adenocarcinoma, the single-target-based screening strategy mentioned in this invention was used.

[0036] Taking lung adenocarcinoma as an example, the method for screening drugs with potential therapeutic effects against lung adenocarcinoma from existing drugs includes the following specific steps:

[0037] First, it is necessary to identify potential ideal drug targets for lung adenocarcinoma by evaluating the specific necessity of genes in specific cancer types.

[0038] Step S1: Obtain the ratio of the number of cell lines required for each of the 7470 genes (obtained from the literature "Prioritization of cancer therapeutic targets using CRISPR-Cas9 screens.") to the total number of cell lines of said lung adenocarcinoma, denoted as n;

[0039] The literature “Prioritization of cancer therapeutic targets using CRISPR-Cas9 screens” describes a total of 325 cell lines and 7470 genes for 32 cancer types.

[0040] The number of cell lines required for each gene in a specific cancer type is explained below: For example, there are 20 cell lines for lung adenocarcinoma, specifically A549, HCC-78, HOP-62, LXF-289, NCI-H1355, NCI-H1568, NCI-H1650, NCI-H1755, NCI-H1944, NCI-H1975, NCI-H1993, NCI-H2087, NCI-H23, NCI-H3122, NCI-H322M, NCI-H358, NCI-H650, PC-14, SW1573, and VMRC-LCD (described in the literature "Prioritization of cancer therapeutic targets using CRISPR-Cas9 screens"). Based on the literature, 7470 genes were screened to determine which genes are required in the above cell lines.

[0041] The word "essential" here means that the gene is essential for the cell line's growth and proliferation; if the gene is knocked out or reduced, the cell line cannot survive.

[0042] Whether each of the 7470 genes is essential in different cell lines is described in the literature "Prioritization of cancer therapeutic targets using CRISPR-Cas9 screens."

[0043] That is, n is the number of cell lines required for each gene in a lung adenocarcinoma cell line divided by the total number of lung adenocarcinoma cell lines, 20.

[0044] Step S2: Obtain the ratio of the number of cell lines required for each of the 7470 genes in 325 cell lines of 32 cancer types, including lung adenocarcinoma, to the total number of cell lines of 325 for the 32 cancer types, and denote it as m;

[0045] That is, m is the number of cell lines required for each gene in 325 cell lines divided by 325;

[0046] Step S3: Perform a first screening from the multiple genes according to the requirement that n>0.5 and n≥m to obtain the first candidate genes; specifically, 643 genes that meet the requirements are obtained.

[0047] Step S4: Based on the existing drug / compound-target interaction information, search among the 10373 drugs / compounds for drugs / compounds that interact with these 643 genes. Filter out genes that do not interact with any of the 10373 drugs / compounds to obtain 33 qualified second candidate genes.

[0048] Specific drug / compound target information can be found in the literature "Therapeutic target database update 2022: facilitating drug discovery with enriched comparative data of targeted agents" by Y. Zhou et al. published in *Nucleic Acids Research*, and "Integration of the Drug-Gene Interaction Database (DGIdb 4.0) with open crowdsource efforts" by S. Freshour et al.

[0049] Step S5: Remove genes with n>0.9 and m>0.9 from the second candidate genes, and sort them in descending order according to the ratio of n / m to select the top ten genes to obtain the target gene;

[0050] In other implementations, the top five genes are selected as target genes. If too few genes are selected, the number of existing drugs / compounds associated with the target genes will be too small, making it impossible to select suitable drugs / compounds for subsequent experimental verification. If too many genes are selected, the number of existing drugs / compounds associated with the target genes will be too large, resulting in a large workload for subsequent experimental verification.

[0051] As a specific implementation method, among these 33 genes, genes with both n and m values ​​being large (>0.9) are removed, and genes are selected according to the principle of sorting from largest to smallest n / m value (i.e., prioritizing the selection of genes with larger n values ​​and smaller m values), resulting in 8 genes. The n, m, and e (i.e. n / m) values ​​of these 8 genes are shown in Table 1.

[0052] Table 1 - n, m, and e values ​​of 8 potential ideal drug target genes screened in lung adenocarcinoma

[0053]

[0054] Step S6: Based on the drug / compound-target action information associated with the target gene, as well as the research and development status and existing action information of the associated drug / compound, screen out existing drugs that have potential therapeutic effects on specific cancer types.

[0055] Based on the drug / compound target information associated with these eight genes, combined with the drug / compound's development status and existing information on its effects (information from the aforementioned publications in *Nucleic Acids Research*, "Therapeutic target database update 2022: facilitating drug discovery with enriched comparative data of targeted agents," and S. Freshour et al., "Integration of the Drug-Gene Interaction Database (DGIdb 4.0) with open crowdsource efforts"), we screened out more than twenty existing drugs with potential therapeutic effects against lung adenocarcinoma. The specific names of these drugs and their pubchem_cid, pubchem_sid, chebi_id, and chembl_id are shown in Table 2.

[0056] Table 2 - Existing drugs with potential therapeutic effects in lung adenocarcinoma a

[0057]

[0058] a The drugs marked in bold have previously been used to treat certain types of tumors.

[0059] The IDs listed in Table 2 provide more information about the drug molecules in the corresponding databases PubChem, ChEBI (Chemical Entities of Biological Interest), and ChEMBL. Regarding the pubchem_sids listed in Table 2, each drug may have multiple pubchem_sids depending on the researchers' published articles; only one is listed in the table. Data gaps in Table 2 are due to some drugs / compounds not being included in their respective databases. Whether the drugs listed in Table 2 are effective against lung adenocarcinoma requires further extensive experimental validation. However, it is worth noting that many of these twenty-plus drugs have been used to treat other types of cancer. For example, Everolimus is an inhibitor of the mammalian target mTOR kinase, used to treat various types of malignant tumors; Regorafenib is used to treat metastatic colorectal cancer, hepatocellular carcinoma, and unresectable, locally advanced, or metastatic gastrointestinal stromal tumors; and Trametinib is used to treat specific types of melanoma, non-small cell lung cancer, and thyroid cancer. These results indirectly demonstrate the feasibility of the drug repurposing screening strategy based on essential genes in this invention.

[0060] Example 2: Apparatus for screening drugs from existing drugs that have potential therapeutic effects on specific cancer types.

[0061] Based on the results of Example 1, this invention provides an apparatus for screening drugs from existing drugs that have potential therapeutic effects against specific cancer types, the apparatus comprising:

[0062] A module for obtaining the value of n is used to calculate the ratio of the number of cell lines required for each gene in a specific cancer type to the total number of cell lines for that specific cancer type.

[0063] The module that obtains the m value is used to calculate the ratio of the number of cell lines required for each gene in other cancer cell lines to the total number of cell lines in other cancer cell lines.

[0064] The module for obtaining the first candidate gene is used to perform a first screening from the plurality of genes according to the requirement that n>0.5 and n≥m, to obtain the first candidate gene;

[0065] The module for obtaining the second candidate gene searches for genes that interact with drugs / compounds in the existing drug / compound library based on existing drug / compound target interaction information to perform a second screening and obtain the second candidate gene.

[0066] The module for obtaining the target gene removes genes with n>0.9 and m>0.9 from the second candidate genes, and sorts the genes in descending order according to the ratio of n / m to select the top ten genes to obtain the target gene.

[0067] A module for obtaining existing drugs with potential therapeutic effects on specific cancer types is used to screen existing drugs with potential therapeutic effects on specific cancer types based on the drug / compound-target action information associated with the target gene and the research and development status and existing action information of the associated drug / compound.

[0068] Example 3: Apparatus for screening drugs from existing drugs that have potential therapeutic effects on specific cancer types.

[0069] This invention provides an apparatus for screening drugs from existing drugs that have potential therapeutic effects against specific cancer types, the apparatus comprising:

[0070] A processor and a memory, the memory being coupled to the processor, the memory storing instructions that, when executed by the processor, use the steps described in Example 1.

[0071] Example 4: Computer-readable storage medium

[0072] This invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of Embodiment 1 and / or the method of Embodiment 2.

[0073] Of course, the computer-executable instructions provided in the embodiments of the present invention are not limited to the method operations described above, but can also perform related operations in the methods provided in any embodiment of the present invention.

[0074] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0075] It is worth noting that the various units and modules included in the above embodiments are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0076] Experimental Example 1: ROC curve evaluation of the method of the present invention

[0077] Information on the effects of 1254 drugs was collected. A positive result was defined as having an anti-cancer effect, and a negative result as not having one. "Having an anti-cancer effect" was used as the label for positive samples. The m and n values ​​of the corresponding gene, the drug development status score, and the drug-target interaction score were used as feature inputs to construct a Support Vector Machine (SVM) model. SVM is a commonly used supervised learning method for binary and multi-class classification problems. Its main idea is to find an optimal hyperplane in the feature space that separates samples of different classes while maximizing the margin between the two classes. During model training, cross-validation was used to select the training and test sets. Specifically, Stratified KFold was used for hierarchical k-fold cross-validation, dividing the dataset into 10 parts. Nine parts were selected as the training set each time, and the remaining part was used as the test set. A Gaussian radial basis function (RBF) kernel was selected. In determining the regularization parameter C of the SVM and the variance gamma parameter of the RBF kernel function, a grid search was used. For each pair of C and gamma values, the model was trained and evaluated, and the average values ​​of the relevant evaluation metrics were recorded. By trying different values ​​of C and gamma multiple times, the performance of the model under different parameter combinations was obtained, thus selecting the optimal parameter combination.

[0078] The ROC curve of the SVM model constructed above is shown in Figure 1 . Figure 1 The abscissa is False Positive Rate (FPR), and the ordinate is True Positive Rate (TPR). The ROC curve can evaluate the classification effect of one or more indicators on two types of samples (in this example, drugs with anticancer-related effects and drugs without anticancer-related effects). AUC (Area under Curve) is the area under the ROC curve, ranging between 0.1 and 1. As a numerical value, it can intuitively evaluate the prediction accuracy of the model; the larger the AUC value, the higher the prediction accuracy. If 0.5 < AUC < 1, it indicates that the classification model is superior to random guessing. Figure 1 The AUC in is 0.65, indicating that the method of the present invention is superior to random selection when screening drugs with anticancer-related effects. In addition, since there is a high probability that unrecognized anticancer drugs are contained in the negative samples, the AUC of this model is actually underestimated.

[0079] Finally, it should also be noted that the term "comprise", "include" or any other variants thereof is intended to cover non-exclusive inclusion, so that a process, method, article or apparatus comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus.

[0080] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic inventive concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0081] Obviously, those skilled in the art can make various modifications and variations to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations to the embodiments of the present invention fall within the scope of the claims of the embodiments of the present invention and their equivalent technologies, the embodiments of the present invention are also intended to include these modifications and variations.

Claims

1. A method for screening drugs from existing drugs that have potential therapeutic effects against specific cancer types, characterized in that, The method includes: Based on the necessity of multiple genes in cell lines of a specific cancer type, the ratio of the number of cell lines required for each of the multiple genes in a specific cancer type to the total number of cell lines of the specific cancer type is obtained and denoted as n. Based on the necessity of the multiple genes in multiple cancer cell lines, the ratio of the number of cell lines required for each of the multiple genes in the multiple cancer cell lines to the total number of cell lines in the multiple cancer cell lines is obtained, denoted as m; the necessity is interpreted as: for a cell line, the gene is essential for its proliferation and growth, and the cell line cannot survive if the gene is knocked out or reduced. From the plurality of genes, a first screening is performed according to the requirement that n>0.5 and n≥m to obtain the first candidate gene; Based on existing drug / compound-target interaction information, a second screening is conducted to find genes in the first candidate genes that interact with drugs / compounds in the existing drug / compound library, thereby obtaining a second candidate gene; Remove genes with n>0.9 and m>0.9 from the second candidate genes, and sort them in descending order according to the ratio of n / m to select the top ten genes to obtain the target gene; Based on the drug / compound target action information associated with the target gene, as well as the research and development status and existing action information of the associated drug / compound, existing drugs with potential therapeutic effects on the specific cancer type are screened.

2. An apparatus for screening drugs from existing drugs that have potential therapeutic effects against specific cancer types, characterized in that, The device includes: A module for obtaining the value of n is used to calculate the ratio of the number of cell lines required for each gene in a specific cancer type to the total number of cell lines for that specific cancer type. The module for obtaining the m value is used to calculate the ratio of the number of cell lines required for each of the multiple genes in multiple cancer cell lines to the total number of cell lines in the multiple cancer cell lines; the term "required" is interpreted as: for a cell line, the gene is essential for its proliferation and growth, and knocking out or reducing the gene will prevent the cell line from surviving. The module for obtaining the first candidate gene is used to perform a first screening from the plurality of genes according to the requirement that n>0.5 and n≥m, to obtain the first candidate gene; The module for obtaining the second candidate gene searches for genes in the first candidate gene that interact with drugs / compounds in the existing drug / compound library based on existing drug / compound-target interaction information, and performs a second screening to obtain the second candidate gene. The module for obtaining the target gene removes genes with n>0.9 and m>0.9 from the second candidate genes, and sorts the genes by their n / m values ​​from largest to smallest to select the top ten genes to obtain the target gene. A module for obtaining existing drugs with potential therapeutic effects on the specific cancer type is used to screen existing drugs with potential therapeutic effects on the specific cancer type based on the drug / compound-target action information associated with the target gene and the research and development status and existing action information of the associated drug / compound.

3. An apparatus for screening drugs from existing drugs that have potential therapeutic effects against specific cancer types, characterized in that, The device includes: A processor and a memory, the memory being coupled to the processor, the memory storing instructions that, when executed by the processor, employ the steps of the method of claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it uses the steps of the method of claim 1.

5. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method of claim 1.

Images