A method and system for screening gene sequences of tumor markers

Abstract

The present invention relates to the field of bioinformatics technology, and specifically to a method and system for screening gene sequences of tumor markers, including: obtaining a gene sequence to be analyzed and an original gene sequence of each tumor marker and a gene data block of each original gene sequence at each length; obtaining a division evaluation value of each original gene sequence at each length according to the data similarity and difference between the gene data blocks of the original gene sequence and other original gene sequences of the same tumor marker at the same length; obtaining an optimal length according to the difference in the division evaluation values ​​of all original gene sequences at each length and adjacent lengths; dividing the gene sequence to be analyzed, and performing hash matching on the gene sequence to be analyzed and the division results corresponding to the tumor markers in the database according to the division results, to obtain a gene sequence screening result of the tumor markers of the digestive tract patients. The present invention can adaptively obtain the block length and obtain more accurate gene screening results.

Description

Technical Field

[0001] The present invention relates to the technical field of bioinformatics, and in particular to a method and system for screening gene sequences of tumor markers. Background Art

[0002] When conducting tumor detection, we can extract human tissues and body fluids to obtain genetic products in human metabolism, compare the obtained genetic products with the genetic data of tumor markers in the known gene library, and provide data support for relevant medical staff by comparing the concentrations of different markers in the patient's genes.

[0003] When comparing and matching the gene sequence of the patient to be tested and the gene sequence of the tumor marker, the hash value can be used for annotation and matching, so that rapid gene comparison can be achieved. However, when performing hash value retrieval, due to the diversity of gene sequences, there are relatively small differences in gene sequences during gene transcription. For example, transcription deletion or transcription error causes a small number of bases to change, but the hash value of the gene sequence has a large difference, which may cause mismatches between gene sequences and affect the gene comparison results. Therefore, the gene sequence can be matched in blocks, but the larger or smaller size of the block data may affect the gene comparison results, resulting in less accurate screening results for the gene sequence. Summary of the invention

[0004] In order to solve the technical problem that the prior art does not properly divide the gene sequence into blocks, resulting in inaccurate gene comparison results, and thus inaccurate gene sequence screening results, the purpose of the present invention is to provide a method and system for screening gene sequences of tumor markers. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides a method for screening gene sequences of tumor markers, comprising:

[0006] Obtaining the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively dividing the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length;

[0007] According to the matching of data similarity between each original gene sequence and the gene data blocks of other original gene sequences of the same type of tumor markers at the same length and the differences between the gene data blocks, the division evaluation value of each original gene sequence at each length is obtained;

[0008] The optimal length is obtained according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths;

[0009] The gene sequence to be analyzed is divided by using the optimal length, and the gene sequence to be analyzed is hash matched with the division result corresponding to the tumor marker in the database according to the division result to obtain the gene sequence screening result of the tumor marker of the digestive tract patient.

[0010] Preferably, the step of obtaining the division evaluation value of each original gene sequence at each length according to the matching of data similarity between gene data blocks of each original gene sequence and other original gene sequences at the same length of the same type of tumor marker and the difference between the gene data blocks specifically includes:

[0011] For any tumor marker and any length;

[0012] Determine the global similarity feature value of each gene data block in each original gene sequence according to the similarity between each gene data block in each original gene sequence and each gene data block in each other original gene sequence;

[0013] Screening each gene data block in the original gene sequence based on the global similarity feature value to determine a difference data block;

[0014] According to the maximum similarity between each difference data block in each original gene sequence and the corresponding matching data blocks in other original gene sequences, the division evaluation value of each original gene sequence under any length is obtained.

[0015] Preferably, determining the global similarity feature value of each gene data block in each original gene sequence according to the similarity between each gene data block in each original gene sequence and each gene data block in each other original gene sequence specifically includes:

[0016] Record any gene data block in any original gene sequence as a target data block, and record the gene data block at the same position as the target data block in each original gene sequence other than the any original gene sequence as a reference data block of the target data block; the target data block and the reference data block belong to gene data corresponding to the same type of tumor marker;

[0017] Determine a similarity feature factor between the target data block and each reference data block based on the DTW distance between the target data block and each reference data block;

[0018] Based on the number of corresponding reference data blocks when the similarity feature factor is greater than a preset similarity threshold, a global similarity feature value of the target data block is determined, and the global similarity feature value is a normalized value.

[0019] Preferably, the screening of each gene data block in the original gene sequence based on the global similarity feature value to determine the difference data block specifically includes:

[0020] When the global similarity feature value of the target data block is less than a preset difference threshold, the target data block is a difference data block.

[0021] Preferably, obtaining the division evaluation value of each original gene sequence of any length according to the maximum similarity between each difference data block in each original gene sequence and the corresponding matching data block in other original gene sequences specifically includes:

[0022] In any original gene sequence of any length, the partition characteristic factor of each difference data block is determined based on the negative correlation coefficient of the maximum value of the similarity characteristic factor between each difference data block in the original gene sequence and the corresponding reference data block; and the partition characteristic factors of all the difference data blocks in the original gene sequence are combined to determine the partition evaluation value of any original gene sequence of the said any length.

[0023] Preferably, obtaining the optimal length according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths specifically includes:

[0024] In order of increasing length, the preference level of each length is obtained according to the difference in the partition evaluation values ​​of all original gene sequences between each length and the adjacent length; the minimum length corresponding to the preference level greater than the preset preference threshold is taken as the optimal length.

[0025] Preferably, the step of obtaining the preferred degree of each length according to the difference in the division evaluation values ​​of all original gene sequences between each length and the adjacent lengths specifically includes:

[0026] The average of the partition evaluation values ​​of all original gene sequences at each length is calculated to obtain the partition effect representation value of each length; in the order of increasing length, based on the rate of change of the partition effect representation value between each length and the adjacent previous length, the partition effect slope value of each length is determined;

[0027] For any length, the characteristic evaluation coefficient of the length is determined based on the negative correlation coefficient of the difference in the slope value of the division effect between the length and the adjacent previous length. The preferred degree of the length is obtained according to the characteristic evaluation coefficient and the division effect characterization value of the length. Both the characteristic evaluation coefficient and the division effect characterization value are positively correlated with the preferred degree.

[0028] Preferably, the method of performing hash matching on the gene sequence to be analyzed and the division result corresponding to the tumor marker in the database according to the division result to obtain the gene sequence screening result of the tumor marker of the digestive tract patient specifically includes:

[0029] For any tumor marker, a difference data block corresponding to the minimum value of the global similarity feature value under the optimal length is used as a seed data block, and a hash match is performed based on the seed data block and each data block in the division result of the gene sequence to be analyzed to obtain a matching result between the gene sequence to be analyzed and the any tumor marker;

[0030] Based on the matching results of each tumor marker, the concentration ratio of each tumor marker in the gene sequence to be analyzed is obtained, and the gene sequence screening results of the tumor marker are determined in descending order of concentration.

[0031] Preferably, the matching result between the gene sequence to be analyzed and any one of the tumor markers is specifically:

[0032] When the proportion of data blocks that match the seed data block in the division result of the gene sequence to be analyzed is greater than a preset proportion threshold, the original gene sequence where the seed data block is located is matched with the gene sequence to be analyzed to obtain a matching result of the tumor marker.

[0033] In a second aspect, the present invention provides a gene sequence screening system for tumor markers, comprising:

[0034] A data extraction module is used to obtain the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively divide the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length;

[0035] A segmentation processing module is used to obtain a segmentation evaluation value of each original gene sequence at each length according to the matching of data similarities between each original gene sequence and gene data blocks of other original gene sequences at the same length of the same type of tumor marker and the differences between the gene data blocks;

[0036] A feature evaluation module is used to obtain the optimal length according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths;

[0037] The gene screening module is used to divide the gene sequence to be analyzed by using the optimal length, and perform hash matching on the gene sequence to be analyzed and the division results corresponding to the tumor markers in the database according to the division results, so as to obtain the gene sequence screening results of the tumor markers of the digestive tract patients.

[0038] The embodiments of the present invention have at least the following beneficial effects:

[0039] The present invention first obtains the gene sequence to be analyzed of the patient to be subjected to gene comparison and the original gene sequence in the database, and uses different lengths of values ​​to perform iterative block division operations on the gene information in the database, providing a data basis for subsequent analysis of the division characteristics of different lengths. Then, for the data performance of the gene information of the same type of tumor markers in the database in the block results of different lengths, the similarity and difference of the genes are analyzed, and the division effect of each original gene sequence under each length is quantitatively evaluated, that is, the division evaluation value, wherein the similarity reflects the more common data expression in different gene sequences, and the difference reflects the more special data expression in different gene sequences. Further, for the division evaluation results of all original gene sequences under different lengths, the difference changes of the divisions of different lengths are analyzed in combination with the evaluation results of adjacent lengths to screen out the best choice and realize the process of adaptively determining the optimal length. Finally, the gene sequence to be analyzed is divided by the optimal length, and the gene matching is performed with the division result corresponding to the optimal length in the database, so that a more preferred block result can be obtained, so that the matching result of the gene comparison is also more accurate and more valuable for reference, thereby obtaining a better gene screening result. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of the steps of a method for screening gene sequences of tumor markers provided by the present invention;

[0042] Figure 2 It is a flowchart of the steps of the method for obtaining the division evaluation value of the original gene sequence provided by the present invention;

[0043] Figure 3 It is a flow chart of the steps of the method for obtaining the optimal length provided by the present invention;

[0044] Figure 4 It is a local distribution coordinate diagram of the division evaluation value of the original gene sequence provided by the present invention;

[0045] Figure 5 This is a system block diagram of a tumor marker gene sequence screening system provided by the present invention;

[0046] Figure 6It is a structural schematic diagram of a computer device provided by the present invention. DETAILED DESCRIPTION

[0047] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for screening a gene sequence of a tumor marker proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0049] The specific scheme of the gene sequence screening method and system for tumor markers provided by the present invention is described in detail below with reference to the accompanying drawings.

[0050] See also Figure 1 , which shows a flowchart of a method for screening a gene sequence of a tumor marker provided by an embodiment of the present invention, the method comprising the following steps:

[0051] Step S100, obtaining the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively dividing the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length.

[0052] When a person is suffering from a tumor, the body will secrete corresponding proteins or increase the concentration of corresponding substances. This substance can be called a tumor marker. When synthesizing tumor markers, protein expression is generally performed through gene sequences. By comparing and screening the corresponding tumor marker genes, the performance of the tumor marker gene sequence in the gene can be preliminarily determined. Among them, when performing gene comparison and screening, it is considered that the gene sequence can be divided into blocks for comparison, but when the size of the block is too large, the block cannot play the role of block, and the influence of mutation or error on the hash value still exists. When the size of the block is too small, it is easy to identify the same gene information in multiple places in the gene sequence, which will also affect the accuracy of the gene comparison. The longer the data block obtained, the greater the probability of error in matching the patient's gene sequence, but the shorter the corresponding gene sequence, the worse its uniqueness in the entire library.

[0053] Based on this, this embodiment first obtains the protein expression of the patient to be subjected to gene comparison, and at the same time, performs block processing of different lengths for the gene information of each type of tumor marker in the gene database, providing a data basis for subsequent adaptive analysis of the effects of block division of different lengths.

[0054] Specifically, the gene sequence to be analyzed of the gastrointestinal patients is first obtained, and multiple different gene expressions corresponding to each type of tumor marker are obtained from the database, which are recorded as original gene sequences. That is, the same tumor marker may have multiple different gene expression forms in the database, and thus the same tumor marker corresponds to multiple original gene sequences.

[0055] In this embodiment, the gene sequence in the gene library is iteratively divided into blocks with different lengths, the iteration range of the length is (0, 1000), and the step length of each adjacent length iteration is 5. It can be understood that each length value is an integer, and the length increases in turn according to the iteration step length. In other embodiments, the minimum value of the length can also be the length of the smallest gene unit in the gene sequence in the gene library, that is, the length of the base, and the length is iteratively increased with the initial length to perform the block division operation of different lengths of the original gene sequence.

[0056] It should be noted that, under a certain length, each original gene sequence of each type of tumor marker is divided into blocks to obtain gene data blocks, which provides a data basis for subsequent analysis of the block status of different original gene sequences of the same tumor marker under the same length division results.

[0057] Among them, the specific process of extracting genetic information of digestive tract patients is as follows: obtain colonoscopy and about 10g of preoperative stool specimens through the stool specimen box, and immediately perform a fecal occult blood test. Reagent preparation: add 90 ml of isopropanol to the buffer GFA, add 135 ml and 160 ml of anhydrous ethanol to the deproteinized solution RD and rinse solution PWD respectively, write the configuration time and label it. Pick 0.2g of stool sample and add it to 2ml centrifuge tube A (200 microliters of liquid sample), add 500 microliters, 100 microliters, and 0.25g of buffer SA, SC and grinding beads respectively; shake and mix well, place in a 70℃ metal bath for lysis for 15 minutes, centrifuge the centrifuge tube at 12000rmp for 1 minute to complete the lysis, and aspirate the supernatant into a new 2ml centrifuge tube B. Add 200 μl of buffer SH to centrifuge tube B, shake and mix, place at 4°C for 10 minutes, centrifuge at 12000 rpm for 2 minutes, transfer the supernatant to 2 ml centrifuge tube C, then add 500 μl of buffer GFR, 10 μl of magnetic bead suspension G, shake and mix for 2 minutes. Place centrifuge tube C on the magnetic rack, let it stand for 30 seconds, wait for the magnetic beads to be completely adsorbed to the inner wall, and carefully remove all the liquid. Remove centrifuge tube C and add 700 μl of protein removal solution RD, shake and mix for 3 minutes, place the centrifuge tube on the magnetic rack, let it stand for 30 seconds, wait for the magnetic beads to be completely adsorbed to the inner wall, and carefully remove all the liquid. e. Remove centrifuge tube C and add 700 μl of protein removal solution PWD, shake and mix for 3 minutes, place the centrifuge tube on the magnetic rack, let it stand for 30 seconds, wait for the magnetic beads to be completely adsorbed to the inner wall, and carefully remove all the liquid. Do not remove centrifuge tube C this time, and let it dry at room temperature for 5 minutes. Remove centrifuge tube C, add 80 μl of elution solution TB, shake and mix for 1 minute, and incubate in a 56°C metal bath for 5 minutes. Place centrifuge tube C on the magnetic rack and let it stand for 2 minutes. After the magnetic beads are completely adsorbed to the inner wall, carefully pipette the DNA solution into a new centrifuge tube D.

[0058] Step S200, obtaining a division evaluation value of each original gene sequence at each length according to the matching of data similarities between gene data blocks of each original gene sequence and other original gene sequences at the same length of the same type of tumor marker and the differences between the gene data blocks.

[0059] When screening gene sequences for tumor markers, the gene information of tumor markers in the known gene library can be compared with the gene information of digestive tract patients, and the performance of the hash value comparison base information can be combined to determine the matching of the gene information in the gene information of the patient to be tested. After the original gene sequence is divided according to different lengths, the dynamic time warping algorithm can be used to perform data matching analysis on the gene data blocks at each corresponding position, and the evaluation of the division effect under different lengths can be quantified.

[0060] At the same time, considering that the gene information of the patient to be matched needs to be compared one by one with all the gene information of the same type of tumor markers when performing gene information comparison. The original gene sequences corresponding to the same type of tumor markers may have different unique expression forms. Through block operations of different lengths, the most different gene data blocks in each original gene sequence are screened out as gene expression blocks with unique characteristics or special characteristics. The expression of unique characteristics is used for subsequent gene comparison, which can effectively improve the accuracy of block gene comparison.

[0061] Based on this, in the results of each block division with different lengths, the matching effect is analyzed by analyzing the matching similarity and matching difference between the gene data blocks at corresponding positions in the block division results under the same category, so as to quantify the degree of quality when the gene sequence is divided by different lengths. Figure 2 As shown, the method for obtaining the division evaluation value can be implemented by steps S201 to S203.

[0062] It should be noted that the effect evaluation of the block division operation is to evaluate the division results under each different length value. At the same time, the gene expression of special characteristics or unique characteristics is analyzed and determined for the gene information of the same tumor marker. Therefore, in this embodiment, the process of quantitative analysis and division evaluation values ​​is described based on all original gene sequences corresponding to any tumor marker, and the division results under any length are used as an example for explanation.

[0063] Step S201, determining the global similarity feature value of each gene data block in each original gene sequence according to the similarity between each gene data block in each original gene sequence and each gene data block in each other original gene sequence.

[0064] For any tumor marker and any length of the division result, the position distribution of the gene data blocks in each original gene sequence is the same, and the matching between the gene data blocks corresponding to the same position should also be considered when performing gene feature comparison. Therefore, firstly, feature analysis is performed on the similarity of the gene data blocks in the current division result.

[0065] An example of selecting an original gene sequence of any tumor marker under a division result of any length is used for explanation, and then any gene data block in any original gene sequence is recorded as a target data block, and the gene data block corresponding to the same position as the target data block in each original gene sequence other than the any original gene sequence is recorded as a reference data block of the target data block; the target data block and the reference data block belong to the gene data corresponding to the same type of tumor marker. For example, the i-th gene data block in the a-th original gene sequence is used as the target data block, and the i-th gene data block in each other original gene sequence that belongs to the same division result and the same tumor marker as the a-th original gene sequence is the reference data block of the target data block.

[0066] Then, based on the DTW distance between the target data block and each reference data block, the similarity feature factor between the target data block and each reference data block is determined. The calculation method of the DTW distance is a well-known technology and will not be introduced in detail here. The DTW distance between the target data block and each reference data block reflects the difference in the corresponding matching between the target data block and the reference data block. By performing negative correlation mapping on the calculated DTW distance, the similarity between the target data block and each reference data block can be obtained.

[0067] In this embodiment, the DTW distance between the target data block and each reference data block is subjected to negative correlation normalization processing to obtain the similarity feature factor between the target data block and each reference data block. It should be understood that the negative correlation normalization processing method is a well-known technology, and the implementer can select the calculation method according to the specific implementation scenario. As a specific example, the similarity feature factor can be expressed as , represents the i-th gene data block in the a-th original gene sequence, which is also the target data block; represents the i-th gene data block in the b-th original gene sequence, that is, a reference data block of the target data block, and a≠b; represents the similarity factor between the target data block and a reference data block, max() represents the maximum value function, min() represents the minimum value function, represents the maximum DTW distance between the target data block and the reference data block, represents the minimum DTW distance between the target data block and the reference data block, Indicates the target data block With reference data block The DTW distance between them.

[0068] The smaller the DTW distance value, the larger the value of the similarity feature factor between the corresponding two gene data blocks, indicating that the greater the similarity between the two gene data blocks, the greater the corresponding matching degree. Using the dynamic time warping algorithm for difference analysis can achieve the optimal match between two different original gene sequences, and can effectively avoid the problem that the difference is relatively small when only one unit feature is added or reduced, while the calculation results are relatively different, which improves the accuracy of the data analysis results to a certain extent.

[0069] Finally, based on the number of reference data blocks corresponding to the similarity feature factor being greater than a preset similarity threshold, a global similarity feature value of the target data block is determined, where the global similarity feature value is a normalized value.

[0070] When the value of the similarity feature factor between the target data block and the reference data block is larger, it means that the similarity between the corresponding two gene data blocks is greater. By counting the number of similarities between the target data block and all reference data blocks, the similar performance characteristics of the target data block in the database can be reflected. The higher the similarity ratio, the more consistent the target data block generally is, which further indicates that the target data block is not a gene expression block with special or unique characteristics.

[0071] Specifically, when the similarity feature factor between the target data block and the reference data block is greater than the preset similarity threshold, the number of reference data blocks is counted, which means that the gene similarity between the target data block and the reference data block is relatively large. In this embodiment, the value of the similarity threshold is 0.8. Since the similarity feature factor is a normalized value, the value range of the similarity threshold is (0,1). The closer the value of the similarity threshold is to 1, the stricter the similarity measurement of the target data block gene is. The closer the value of the similarity threshold is to 0, the looser the similarity measurement of the target data block gene is.

[0072] In this embodiment, the number of reference data blocks when all similar feature factors corresponding to the target data block meet the threshold requirement is counted, and the ratio between this number and the total number of all reference data blocks corresponding to the target data block is used as the global similar feature value of the target data block, reflecting the proportion of gene data blocks with a greater degree of similarity with the target data block.

[0073] Step S202: Screen each gene data block in the original gene sequence based on the global similarity feature value to determine a difference data block.

[0074] The larger the global similarity feature value of the target data block, the greater the similarity between the gene information of the target data block and the gene information at the same position in other original gene sequences, and the more likely the target data block is a universal gene expression. The smaller the global similarity feature value of the target data block, the smaller the similarity between the gene information of the target data block and the gene information at the same position in other original gene sequences, and the more likely the target data block is a gene expression with special characteristics.

[0075] The global similarity feature value of each gene data block in each original gene sequence can be obtained in the same way as the global similarity feature value of the target data block, and then the gene data blocks can be screened by the global similarity feature value to determine the gene expression part that may be a special feature, that is, the difference data block.

[0076] Specifically, still taking the target data block as an example, when the global similarity feature value of the target data block is less than the preset difference threshold, the target data block is a difference data block. The difference threshold value is 0.3, and the implementer can set it according to the specific implementation scenario. That is, the global similarity feature value of each gene data block is judged separately. When the threshold requirement is met, the corresponding gene data block is the difference data block. The difference data block represents the gene expression part with special characteristics or difference characteristics in the corresponding original gene sequence.

[0077] Step S203, obtaining a partition evaluation value of each original gene sequence of any length according to the maximum similarity between each difference data block in each original gene sequence and the corresponding matching data blocks in other original gene sequences.

[0078] By analyzing the similarity between all characteristic gene expression parts in an original gene sequence and other original gene sequences, the division of the current length block division result can be effectively reflected. It should be noted that under the same tumor marker, each gene data block in each original gene sequence has a corresponding reference data block, that is, each gene data block represents the gene data block at the same position in other original gene sequences, that is, each difference data block also has a corresponding reference data block.

[0079] Specifically, in any original gene sequence of any length, the partition characteristic factor of each difference data block is determined based on the negative correlation coefficient of the maximum value of the similarity characteristic factor between each difference data block in the original gene sequence and the corresponding reference data block; and the partition characteristic factors of all the difference data blocks in the original gene sequence are combined to determine the partition evaluation value of any original gene sequence of any length.

[0080] As a specific example, this embodiment takes the division result corresponding to any length value as an example for explanation, and takes any original gene sequence as an example for explanation. Then, when the length is d, the division evaluation value of the ath original gene sequence can be expressed as , represents the partition evaluation value of the ath original gene sequence under the partition result of length d, The cth difference data block of a original gene sequences is represented by represents the total number of difference data blocks contained in the a-th original gene sequence under the division result of length d, It represents the maximum value of the similarity feature factor between the cth difference data block in the ath original gene sequence and the corresponding reference data block under the division result of length d.

[0081] The negative correlation coefficient of the maximum similarity between the difference data block and the corresponding reference data block is used It indicates the effectiveness of data matching under the current length, avoiding the situation where a gene data block has obvious differences. In the subsequent iterations, if most of the data in a gene data block is very different from other gene data blocks, this gene data block will appear special. However, special gene data blocks may exist in multiple overlapping gene data block intervals. Therefore, it is necessary to adjust and optimize the division of the overall gene sequence based on the similarity between gene data blocks as a weight. The division evaluation value of the original gene sequence can characterize the performance of the division of the original gene sequence using the current length.

[0082] Step S300, obtaining the optimal length according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths.

[0083] By analyzing the similar gene expressions and special feature expressions between different original gene sequences corresponding to the same tumor marker in the division results corresponding to each length, the division evaluation value can be used to quantify the evaluation of the division effect of different original gene sequences in block processing without using different lengths. The division effect evaluation of all original gene sequences under the same length value can be comprehensively evaluated to globally characterize the effect of block division using the corresponding length. The length with the best division effect can be screened out through the results of the global characterization.

[0084] In this embodiment, the method for obtaining the optimal length is as follows: Figure 3 As shown, it can be implemented by step S301 to step S302.

[0085] Step S301, in order of increasing length, according to the difference change of the partition evaluation value of all original gene sequences between each length and the adjacent length, obtain the preference degree of each length.

[0086] Under a certain length value, each original gene sequence corresponds to a partition evaluation value, such as Figure 4 This is a schematic diagram of the coordinate distribution of the partition evaluation values ​​of part of the original gene sequence under partial length values, that is, some data are selected for exemplary representation. Figure 4 Here, x represents the horizontal axis, which is the value of the length, and y represents the vertical axis, which is the value of the division evaluation value of different original gene sequences in the corresponding length division result.

[0087] In this embodiment, the average of the partition evaluation values ​​of all original gene sequences at each length is calculated to obtain the partition effect representation value of each length, that is, the partition effect representation value comprehensively reflects the performance of the partition effect of the corresponding length.

[0088] In the order of increasing length, the partition effect slope value of each length is determined based on the rate of change of the partition effect characterization value between each length and the adjacent previous length. The value of each length corresponds to a partition effect characterization value, and the method for obtaining the partition effect slope value of each length can be analogous to the slope value of each data point in the two-dimensional coordinate system. The calculation method is a well-known technology. In this embodiment, it is briefly explained as a specific example.

[0089] Specifically, different length values ​​are used as the horizontal coordinates, and the division effect characterization values ​​corresponding to the lengths are used as the vertical coordinates to construct data points corresponding to each length, and then curve fitting is performed on the data points of each length to obtain a fitted division effect curve, and the slope of the data points of each length can be calculated on the division effect curve, which is then used as the length division effect slope value. Among them, methods such as fitting data points and calculating the slope of data points on the curve are well-known technologies and will not be introduced in detail here.

[0090] For any length, the characteristic evaluation coefficient of the length is determined based on the negative correlation coefficient of the difference in the slope value of the division effect between the length and the adjacent previous length. The preferred degree of the length is obtained according to the characteristic evaluation coefficient and the division effect characterization value of the length. Both the characteristic evaluation coefficient and the division effect characterization value are positively correlated with the preferred degree.

[0091] As a specific example, the preference level corresponding to the tth length is It can be expressed as ,in, Indicates the preference of the t-th length, It represents the partition effect characterization value of the t-th length, that is, the mean of the partition evaluation values ​​of all original gene sequences under the t-th length. represents the slope value of the partition effect of the t-th length, It represents the slope value of the partition effect of the t-1th length, represents an exponential function with the natural constant e as the base, and Norm represents a linear normalization function.

[0092] is the characteristic evaluation coefficient of the t-th length, reflecting the difference between the efficiency value of the division effect between the t-th length and the previous length. The smaller the value is, the rate of change of the division effect between the t-1th length and the tth length changes from rapid change to slow change, indicating that the effect of the length value at this time is close to the turning point of the length, and the corresponding characteristic evaluation coefficient value is larger, and the corresponding degree of preference for the current length is greater, and the effect of using this length for the division operation of the gene sequence is better.

[0093] At the same time, the partition effect characterization value comprehensively characterizes the evaluation of the partition results of all original gene sequences under the current length. The larger the value, the greater the preference for the current length, and the better the effect of the gene sequence partition operation using this length. That is, the degree of preference characterizes the accuracy of feature matching of different original gene partition sequences using the corresponding length.

[0094] It should be noted that when analyzing the changes in the division effect during the iterative block operation, it is necessary to analyze the division results under at least a plurality of different length values. That is, in this embodiment, the length that cannot be calculated to be preferred is not considered.

[0095] Step S302: The minimum length corresponding to a preference level greater than a preset preference threshold is taken as the optimal length.

[0096] The larger the value of the preference degree of different lengths, the better the effect of feature comparison of the result of dividing the gene sequence by the corresponding length. When the preference degree is greater than the preset preference threshold, the effect of dividing the corresponding length is better. Considering that the longer the length of the block division is, the more likely it is to have errors in the process of gene comparison using the hash value, the minimum length that meets the threshold requirement is selected as the most preferred length of the division, that is, the optimal length. In this embodiment, the value of the preferred threshold is 0.7, which can be set by the implementer according to the specific implementation scenario, and the value range of the preferred threshold is (0,1).

[0097] Step S400, dividing the gene sequence to be analyzed by using the optimal length, and performing hash matching between the gene sequence to be analyzed and the division results corresponding to the tumor markers in the database according to the division results, so as to obtain the gene sequence screening results of the tumor markers of the digestive tract patients.

[0098] Gene sequences are very large and complex, and directly comparing the full sequence may be very time-consuming and computationally resource-intensive. Segmenting the sequence and generating a hash value can greatly speed up the search and comparison. The hash value length generated by the hash function is fixed and unique, and can be effectively used as an index for quick search and comparison. Segmentation and hash matching make it possible to process different sequence fragments or data blocks in parallel, thereby improving the efficiency and speed of the overall processing. This is particularly important for the processing of large-scale genomic data. The present embodiment iterates the division mode of different lengths, and after feature comparison, adaptively determines a division length that best represents the original gene expression in the current database, and uses the division length to perform feature comparison on the patient gene information to be compared, so as to obtain a more accurate hash matching result.

[0099] Specifically, by using the optimal length to divide the patient's gene sequence to be analyzed into blocks, the gene division result corresponding to the patient can be obtained, including each data block of the gene sequence to be analyzed. Similarly, by using the optimal length to divide each original gene sequence in the database into blocks, each gene data block of the original gene sequence can be obtained, which can be obtained by the above data analysis process.

[0100] Furthermore, the hash value of each data block of the gene sequence to be analyzed and the hash value of each gene data block of the original gene sequence are calculated respectively. The hash value can be used to perform feature comparison and matching operations on each data block in the gene sequence to be analyzed and the gene data block at the same position in each original gene sequence to obtain a matching result. Among them, using hash values ​​for feature comparison and matching is a well-known technology, that is, the same hash values ​​are matched, and different hash values ​​are mismatched, which will not be introduced in detail here.

[0101] Finally, the screening results of tumor markers for gastrointestinal patients can be displayed through matching results. For example, the number of gene sequence matches can be arranged from large to small for each tumor marker. The sorting results can provide certain big data support for relevant doctors.

[0102] More preferably, the data processing of the direct hash value matching process is also relatively large, and a preliminary screening can be performed on the gene expression blocks with special characteristics under the current division results in the database to determine whether the acquired gene sequence needs to be expanded for extended matching.

[0103] Specifically, for any tumor marker, the difference data block corresponding to the minimum value of the global similarity feature value under the optimal length is used as the seed data block, and then the seed data block represents the most special performance of all gene data blocks of the current tumor marker.

[0104] Based on the seed data block and each data block in the division result of the gene sequence to be analyzed, a hash match is performed to obtain a matching result between the gene sequence to be analyzed and any one of the tumor markers. Similarly, data blocks with the same hash value are matched, and data blocks with different hash values ​​are not matched.

[0105] Among them, the method for obtaining the matching result is specifically as follows: when the proportion of data blocks matching the seed data block in the division result of the gene sequence to be analyzed is greater than the preset proportion threshold, the original gene sequence where the seed data block is located is matched with the gene sequence to be analyzed to obtain the matching result of the tumor marker. The value of the proportion threshold is 50%, that is, when the proportion of matched data blocks is greater than 50%, it means that more than half of the special gene expressions are contained in the current patient gene information to be compared. To avoid errors in the comparison, an extended matching operation can be performed, that is, a longer gene sequence is used for matching to determine the matching result. When the proportion of data blocks matching the seed data block in the division result of the sequence to be analyzed is less than the preset proportion threshold, the proportion of the data block can be directly used as the matching result.

[0106] Based on the matching results of each tumor marker, the concentration ratio of each tumor marker in the gene sequence to be analyzed is obtained, and the gene sequence screening results of the tumor marker are determined in descending order of concentration. The concentration ratio can be expressed by the ratio of the number of matched data blocks.

[0107] like Figure 5 As shown, an embodiment of the present invention further provides a gene sequence screening system for tumor markers, the system comprising:

[0108] A data extraction module is used to obtain the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively divide the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length;

[0109] A segmentation processing module is used to obtain a segmentation evaluation value of each original gene sequence at each length according to the matching of data similarities between each original gene sequence and gene data blocks of other original gene sequences at the same length of the same type of tumor marker and the differences between the gene data blocks;

[0110] A feature evaluation module is used to obtain the optimal length according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths;

[0111] The gene screening module is used to divide the gene sequence to be analyzed by using the optimal length, and perform hash matching on the gene sequence to be analyzed and the division results corresponding to the tumor markers in the database according to the division results, so as to obtain the gene sequence screening results of the tumor markers of the digestive tract patients.

[0112] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the gene sequence screening system for tumor markers provided in the above embodiment and the gene sequence screening method for tumor markers are of the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0113] The present application also provides a computer device. Figure 6 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any one of the gene sequence screening methods for tumor markers introduced above.

[0114] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the above-mentioned methods for screening gene sequences of tumor markers.

[0115] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any one of the above-mentioned methods for screening gene sequences of tumor markers.

[0116] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0117] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for screening gene sequences of tumor markers, characterized in that: The method comprises the following steps: Obtaining the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively dividing the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length; According to the matching of data similarity between each original gene sequence and the gene data blocks of other original gene sequences of the same type of tumor markers at the same length and the differences between the gene data blocks, the division evaluation value of each original gene sequence at each length is obtained; The optimal length is obtained according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths; The gene sequence to be analyzed is divided by using the optimal length, and according to the division result, the gene sequence to be analyzed is hash matched with the division result corresponding to the tumor marker in the database to obtain the gene sequence screening result of the tumor marker of the digestive tract patient; The method of obtaining a division evaluation value of each original gene sequence at each length according to the matching of data similarity between gene data blocks of each original gene sequence and other original gene sequences at the same length of the same type of tumor marker and the difference between the gene data blocks specifically includes: For any tumor marker and any length; Determine the global similarity feature value of each gene data block in each original gene sequence according to the similarity between each gene data block in each original gene sequence and each gene data block in each other original gene sequence; Screening each gene data block in the original gene sequence based on the global similarity feature value to determine a difference data block; Obtaining a partition evaluation value for each original gene sequence of any length according to the maximum similarity between each difference data block in each original gene sequence and a corresponding matching data block in other original gene sequences; The optimal length is obtained according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths, specifically including: In the order of increasing length, the degree of preference of each length is obtained according to the difference in the partition evaluation values ​​of all original gene sequences between each length and the adjacent length; the minimum length corresponding to the degree of preference greater than the preset preference threshold is taken as the optimal length; The preferred degree of each length is obtained according to the difference change of the division evaluation values ​​of all original gene sequences between each length and the adjacent length, specifically including: The average of the partition evaluation values ​​of all original gene sequences at each length is calculated to obtain the partition effect representation value of each length; in the order of increasing length, based on the rate of change of the partition effect representation value between each length and the adjacent previous length, the partition effect slope value of each length is determined; For any length, the characteristic evaluation coefficient of the length is determined based on the negative correlation coefficient of the difference in the slope value of the division effect between the length and the adjacent previous length. The preferred degree of the length is obtained according to the characteristic evaluation coefficient and the division effect characterization value of the length. Both the characteristic evaluation coefficient and the division effect characterization value are positively correlated with the preferred degree.

2. The method for screening gene sequences of tumor markers according to claim 1, characterized in that: The step of determining the global similarity feature value of each gene data block in each original gene sequence according to the similarity between each gene data block in each original gene sequence and each gene data block in each other original gene sequence specifically includes: Record any gene data block in any original gene sequence as a target data block, and record the gene data block at the same position as the target data block in each original gene sequence other than the any original gene sequence as a reference data block of the target data block; the target data block and the reference data block belong to gene data corresponding to the same type of tumor marker; Determine a similarity feature factor between the target data block and each reference data block based on the DTW distance between the target data block and each reference data block; Based on the number of corresponding reference data blocks when the similarity feature factor is greater than a preset similarity threshold, a global similarity feature value of the target data block is determined, and the global similarity feature value is a normalized value.

3. The method for screening gene sequences of tumor markers according to claim 2, characterized in that: The step of screening each gene data block in the original gene sequence based on the global similarity feature value to determine the difference data block specifically includes: When the global similarity feature value of the target data block is less than a preset difference threshold, the target data block is a difference data block.

4. The method for screening gene sequences of tumor markers according to claim 2, characterized in that: The step of obtaining the partition evaluation value of each original gene sequence of any length according to the maximum similarity between each difference data block in each original gene sequence and the corresponding matching data block in other original gene sequences specifically includes: In any original gene sequence of any length, the partition characteristic factor of each difference data block is determined based on the negative correlation coefficient of the maximum value of the similarity characteristic factor between each difference data block in the original gene sequence and the corresponding reference data block; and the partition characteristic factors of all the difference data blocks in the original gene sequence are combined to determine the partition evaluation value of any original gene sequence of the said any length.

5. The method for screening gene sequences of tumor markers according to claim 1, characterized in that: The method further comprises: performing hash matching on the gene sequence to be analyzed and the division result corresponding to the tumor marker in the database according to the division result to obtain the gene sequence screening result of the tumor marker of the digestive tract patient. For any tumor marker, a difference data block corresponding to the minimum value of the global similarity feature value under the optimal length is used as a seed data block, and a hash match is performed based on the seed data block and each data block in the division result of the gene sequence to be analyzed to obtain a matching result between the gene sequence to be analyzed and the any tumor marker; Based on the matching results of each tumor marker, the concentration ratio of each tumor marker in the gene sequence to be analyzed is obtained, and the gene sequence screening results of the tumor marker are determined in descending order of concentration.

6. The method for screening gene sequences of tumor markers according to claim 5, characterized in that: The matching result between the gene sequence to be analyzed and any one of the tumor markers is specifically: When the proportion of data blocks that match the seed data block in the division result of the gene sequence to be analyzed is greater than a preset proportion threshold, the original gene sequence where the seed data block is located is matched with the gene sequence to be analyzed to obtain a matching result of the tumor marker.

7. A gene sequence screening system for tumor markers, characterized in that: The system is used to implement the steps of a method for screening a gene sequence of a tumor marker as described in any one of claims 1 to 6, wherein the gene sequence screening system for a tumor marker comprises: A data extraction module is used to obtain the gene sequence to be analyzed of the digestive tract patient and each original gene sequence of each tumor marker in the database, and iteratively divide the original gene sequence using preset different lengths to obtain gene data blocks of each original gene sequence at each length; A segmentation processing module is used to obtain a segmentation evaluation value of each original gene sequence at each length according to the matching of data similarities between each original gene sequence and gene data blocks of other original gene sequences at the same length of the same type of tumor marker and the differences between the gene data blocks; A feature evaluation module is used to obtain the optimal length according to the difference between the partition evaluation values ​​of all original gene sequences at each length and the partition evaluation values ​​of all original gene sequences at adjacent lengths; The gene screening module is used to divide the gene sequence to be analyzed by using the optimal length, and perform hash matching on the gene sequence to be analyzed and the division results corresponding to the tumor markers in the database according to the division results, so as to obtain the gene sequence screening results of the tumor markers of the digestive tract patients.

Images