Extraction method of bladder cancer stem cell biomarker

Abstract

The invention belongs to the technical field of cell extraction, and provides a bladder cancer stem cell biomarker extraction method, which comprises: in the historical extraction of bladder cancer stem cell biomarkers, obtaining a plurality of biomarker concentrations of each operation, then according to the biomarker concentrations, carrying out effective degree evaluation on each operation, constructing a historical feature library according to an evaluation result, performing extraction stability analysis on a plurality of biomarkers in the historical feature library to obtain a stability analysis result, and constructing a stable extraction feature library according to the stability analysis result, so that the extraction stability of the biomarkers is comprehensively analyzed from two dimensions of extraction times and extraction concentration; accurate data support is provided for screening and extracting biomarkers with high stability and bringing the biomarkers into a stable extraction feature library, the reliable stable extraction feature library is constructed, and more stable and accurate biomarker features are provided for subsequent application such as research and diagnosis.

Description

Technical Field

[0001] The present invention belongs to the technical field of cell extraction, and specifically relates to a method for extracting biomarkers of bladder cancer stem cells. Background Art

[0002] Bladder cancer stem cells play an important role in the occurrence, development, invasion, metastasis and drug resistance of bladder cancer. Therefore, the extraction and research of biomarkers of bladder cancer stem cells are of great significance, and biomarkers of bladder cancer stem cells are key molecules for identifying and separating bladder cancer stem cells.

[0003] In the prior art, the extraction of biomarkers in bladder cancer stem cells is usually carried out by extracting features. However, the existing feature extraction methods are not summarized and screened according to historical data to obtain a high-precision and stable extraction feature library. Therefore, the concentration of biomarkers is obtained, and the extraction effectiveness is evaluated by comparing with the preset concentration. The biomarkers are integrated and sorted according to the proportion of effective extraction times to construct a historical feature library. A historical extraction period is set, and the extraction reference values are sorted from small to large to construct a stable extraction feature library, providing relatively accurate data support for screening biomarkers with higher extraction stability and incorporating them into the stable extraction feature library. A historical determination period is set, and the effective determination stability values are sorted from small to large to construct a high-precision extraction feature library. Finally, by comparing the stable extraction feature library with the high-precision extraction feature library, a high-precision and stable extraction feature library is constructed, thus not only solving the problem of unstable determination accuracy and improving the determination accuracy of bladder cancer stem cells, but also comprehensively considering the performance of biomarkers in both high-precision extraction and stable extraction, solving the limitation problem of single-dimensional screening, and providing better biomarker resources for the research of bladder cancer stem cells.

[0004] Therefore, the present invention provides a method for extracting biomarkers of bladder cancer stem cells. Summary of the Invention

[0005] In order to make up for the deficiencies of the prior art and solve at least one technical problem proposed in the background art.

[0006] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0007] A method for extracting biomarkers of bladder cancer stem cells, comprising:

[0008] Obtaining the supernatant of biomarkers in each historical extraction to obtain the biomarker concentration, and effectively evaluating each extraction, and constructing a historical feature library according to the evaluation results;

[0009] Within the historical extraction period, according to the extraction results of biomarkers in the historical feature library, screening out stable extraction features, and constructing a stable extraction feature library based on the stable extraction features;

[0010] During the historical determination period, according to the determination results of biomarkers in the historical feature library, high-precision features are screened out, and based on the high-precision features, a high-precision extraction feature library is constructed;

[0011] Compare the features in the high-precision extraction feature library with those in the stable extraction feature library to obtain high-precision stable features and features to be marked, and respectively construct a high-precision stable extraction feature library according to the high-precision stable features and the features to be marked.

[0012] As a further solution of the present invention: the acquisition of biomarker concentration is as follows:

[0013] Detect the supernatant of the biomarker by high-performance liquid chromatography to obtain the biomarker concentration.

[0014] As a further solution of the present invention: the construction of the historical feature library is carried out as follows:

[0015] If the biomarker concentration is greater than or equal to the preset extraction concentration, it is recorded as a historical effective extraction;

[0016] Sort according to the proportion of the number of historical effective extractions in the total number of historical extractions from large to small to construct a historical feature library.

[0017] As a further solution of the present invention: the acquisition process of extracting stable features is as follows:

[0018] Divide the historical extraction period into several historical extraction time periods;

[0019] Obtain the proportion of the number of effective extractions in the total number of extractions within the historical extraction time period, and input it into the Manhattan distance calculation model, and output to obtain the effective number stability value;

[0020] Obtain the biomarker concentration corresponding to the historical effective extraction within the historical extraction time period, and input it into the extraction concentration stability model, and output to obtain the effective concentration stability value;

[0021] Input the effective number stability value and the effective concentration stability value into the geometric product model, and output to obtain the extraction reference value;

[0022] If the extraction reference value is greater than or equal to the extraction reference value threshold, the biomarker is recorded as an extraction stable feature.

[0023] As a further solution of the present invention: the construction process of the stable extraction feature library is as follows:

[0024] Sort all the extraction stable features from small to large according to the corresponding extraction reference values to obtain a stable extraction feature library.

[0025] As a further solution of the present invention: The acquisition method of high-precision features is as follows:

[0026] Divide the historical determination period into several historical determination time periods;

[0027] Obtain the ratio of the number of valid determinations to the total number of historical determinations within the historical determination time period, and input it into the Manhattan distance calculation model to output the effective determination stability value;

[0028] If the effective determination stability value is less than or equal to the effective determination stability threshold, record the biomarker as a high-precision feature.

[0029] As a further solution of the present invention: The construction process of the high-precision extraction feature library is as follows:

[0030] Sort the high-precision features in ascending order according to the corresponding effective determination stability values to construct a high-precision extraction feature library.

[0031] As a further solution of the present invention: The acquisition process of high-precision stable features and features to be marked is as follows:

[0032] Extract the same biomarkers in the high-precision extraction feature library and the stable extraction feature library and record them as the same features;

[0033] Respectively obtain the rankings of the same features in the high-precision extraction feature library and the stable extraction feature library. If the ranking numbers are both small in the high-precision extraction feature library and the stable extraction feature library, mark the same features as high-precision stable features;

[0034] If the ranking number is relatively high in one of the high-precision extraction feature library or the stable extraction feature library, mark the same features as features to be marked.

[0035] As a further solution of the present invention: Construct a high-precision stable extraction feature library according to the high-precision stable features, and the execution process is as follows:

[0036] Sum up the rankings of the high-precision stable features in the high-precision extraction feature library and the stable extraction feature library, and sort them in ascending order to construct a high-precision stable extraction feature library.

[0037] As a further solution of the present invention: Construct a high-precision stable extraction feature library according to the features to be marked, and the execution process is as follows:

[0038] If the ranking number of the feature to be marked is relatively low in the high-precision extraction feature library and relatively high in the stable extraction feature library, calculate the ratio of the ranking number of the feature to be marked in the stable extraction feature library to the total number of features in the stable extraction feature library to obtain the stable extraction coefficient;

[0039] Compare the stability extraction coefficients corresponding to the features to be marked in terms of magnitude, and add them to the high-precision and stable extraction feature library in ascending order;

[0040] If the ranking number of the feature to be marked is relatively high in the high-precision extraction feature library and relatively low in the stability extraction feature library, then calculate the ratio of the ranking number of the feature to be marked in the high-precision extraction feature library to the total number of features in the high-precision extraction feature library to obtain the high-precision extraction coefficient;

[0041] Compare the high-precision extraction coefficients corresponding to the features to be marked in terms of magnitude, and add them to the high-precision and stable extraction feature library in ascending order.

[0042] The beneficial effects of the present invention are as follows:

[0043] 1. In the historical extraction of bladder cancer stem cell biomarkers of the present invention, a number of biomarker concentrations for each operation are obtained, and then based on the biomarker concentrations, the effectiveness of each operation is evaluated. According to the evaluation results, a historical feature library is constructed, and the extraction stability of multiple biomarkers in the historical feature library is analyzed to obtain a stable analysis result. And based on the stable analysis result, a stability extraction feature library is constructed. Therefore, the extraction stability of biomarkers is comprehensively analyzed from two dimensions of the number of extractions and the extraction concentration, providing relatively accurate data support for screening biomarkers with higher extraction stability and incorporating them into the stability extraction feature library, and constructing a reliable stability extraction feature library, providing more stable and accurate biomarker features for subsequent research, diagnosis and other applications;

[0044] 2. The present invention uses the Manhattan distance calculation model to obtain the effective determination stability value based on the historical effective determination times of biomarkers, and accordingly screens high-precision features to construct a high-precision extraction feature library. Then, the high-precision extraction feature library is compared with the stability extraction feature library, and high-precision and stable features, features to be marked, and non-high-precision and stable features are divided according to the coincidence of biomarkers and their rankings in the two libraries. For the features to be marked, by comparing the magnitudes of the high-precision extraction coefficients and the stability extraction coefficients respectively, a high-precision and stable extraction feature library is constructed, thus not only solving the problem of unstable determination accuracy and improving the accuracy of bladder cancer stem cell determination, but also comprehensively considering the performance of biomarkers in both high-precision extraction and stable extraction, solving the limitation problem of single-dimensional screening, and providing better biomarker resources for bladder cancer stem cell research. Brief Description of the Drawings

[0045] The present invention will be further described below with reference to the accompanying drawings.

[0046] Figure 1 is a flowchart of a method for extracting bladder cancer stem cell biomarkers of the present invention. Detailed Embodiments

[0047] In order to make the technical means, creative features, achieved objectives and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0048] Example 1

[0049] As Figure 1 shown, a method for extracting a biomarker of bladder cancer stem cells according to an embodiment of the present invention includes:

[0050] Step 1: In the historical extraction of biomarkers of bladder cancer stem cells, obtain the concentrations of several biomarkers for each operation, and then evaluate the effectiveness of each operation according to the biomarker concentrations. According to the evaluation results, construct a historical feature library;

[0051] It should be noted that the biomarkers of bladder cancer stem cells include but are not limited to protein biomarkers, nucleic acid biomarkers, and glycan biomarkers;

[0052] In Step 1, taking the protein biomarker as an example, the process of obtaining the biomarker concentration for each operation is as follows:

[0053] Exemplarily, use cell lysate to break bladder cancer stem cells, release the intracellular proteins, then remove cell debris by centrifugation to obtain the supernatant of the biomarker, and detect it by high performance liquid chromatography to obtain the biomarker concentration;

[0054] Among them, the detection process of high performance liquid chromatography: inject the supernatant into the HPLC system, the mobile phase carries the sample through the chromatographic column, and different proteins are separated according to their different partition coefficients between the stationary phase and the mobile phase. Detect the elution peaks of the target biomarker through an ultraviolet detector, a fluorescence detector, etc., and calculate the biomarker concentration by comparing the peak area or peak height with the standard product;

[0055] The process of evaluating the effectiveness of each operation is as follows:

[0056] If the biomarker concentration is greater than or equal to the preset extraction concentration, it means that the biomarker extraction is successful, and the historical extraction operation is recorded as a historical effective extraction;

[0057] If the biomarker concentration is less than the preset extraction concentration, it means that the biomarker extraction fails, and the historical extraction operation is recorded as a historical ineffective extraction;

[0058] The process of constructing the historical feature library is as follows:

[0059] Integrate and sort the biomarkers corresponding to the historical effective extractions according to the proportion of the historical effective extraction times in the total historical extraction times to obtain the historical feature library;

[0060] Those skilled in the art can understand that the concentration of biomarkers is the basis for accurate detection and subsequent research applications of biomarkers. If the detected concentration of biomarkers is relatively low, it may not be accurately recognized by existing detection methods or equipment. Taking bladder cancer as an example, the concentration of some specific biomarkers in cancer tissues or patient body fluids is significantly higher than that in normal tissues or healthy populations. Therefore, when extracting biomarkers for disease diagnosis or research, if the detected concentration after extraction can reflect this difference (the concentration in cancer tissues or patient body fluids is significantly higher than that in normal tissues or healthy populations) and is consistent with the known disease state, it can be used as the basis for successful extraction;

[0061] Step 2: Based on multiple biomarkers in the historical feature library, obtain the stable results of bladder cancer stem cell feature extraction each time. According to the stable results of bladder cancer stem cell feature extraction, screen out the stable extraction features and construct a stable extraction feature library;

[0062] In some instances, set a historical extraction cycle and divide the historical extraction cycle into several historical extraction time periods;

[0063] Arbitrarily select a biomarker, obtain the historical effective extraction times of the biomarker within the historical extraction time period, and calculate the ratio with the total historical extraction times to obtain the extraction effective value;

[0064] It should be noted that the total historical extraction times is the sum of the historical effective extraction times and the historical ineffective extraction times within the historical extraction time period;

[0065] Input the extraction effective values corresponding to all historical extraction time periods within the historical extraction cycle into the Manhattan distance calculation model, and output to obtain the effective times stability value;

[0066] Among them, the Manhattan distance calculation model is:

[0067] It can be understood that D t is the effective times stability value, n represents the total number of historical extraction time periods. Since each historical extraction time period corresponds to an extraction effective value, represents the extraction effective value corresponding to the i-th historical extraction time period, represents the extraction effective value corresponding to the (i - 1)-th historical extraction time period;

[0068] The reason for using the Manhattan distance calculation model is as follows: The Manhattan distance calculation model is essentially a method for calculating the distance between two points in Euclidean space. Now, the effective extraction times in different historical extraction periods are regarded as the coordinate values of two points respectively, and the distance between them is calculated by the Manhattan distance method. This distance reflects the deviation degree of the effective extraction times in adjacent historical extraction periods. The smaller the distance, the closer the effective extraction times in adjacent historical extraction periods are, and the better the extraction effect is.

[0069] Obtain the biomarker concentrations corresponding to the historical effective extractions and sort them according to the time series to obtain the effective extraction concentration sequence.

[0070] Specifically, sorting according to the time series is to compare the historical extraction periods where the historical effective extractions are located. If the historical extraction time is earlier, the biomarker concentration corresponding to the historical effective extraction is ranked higher in the effective extraction concentration sequence; if the historical extraction time is later, the biomarker concentration corresponding to the historical effective extraction is ranked lower in the effective extraction concentration sequence.

[0071] Input the biomarker concentrations in the effective extraction concentration sequence into the extraction concentration stability model respectively, and output to obtain the effective concentration stability value.

[0072] The specific execution process is as follows:

[0073] A1. Combine the biomarker concentrations at adjacent times in the effective extraction concentration sequence to obtain multiple concentration stability groups.

[0074] A2. Input the multiple concentration stability groups into the extraction concentration stability model as follows: and output to obtain the effective concentration stability value D C ;

[0075] It can be understood that D C represents the effective concentration stability value, m represents the total number of concentration stability groups, respectively represent the biomarker concentrations in the j-th group, C Y represents the preset extraction concentration.

[0076] It can be understood that the extraction concentration stability model is improved based on the principle of the Manhattan distance calculation model. Its purpose is mainly to evaluate the deviation degree between the biomarker concentrations during multiple historical effective extractions, so as to reflect whether the biomarker extraction is stable from the biomarker concentration, that is, as the basis for evaluating the stability degree of biomarker extraction in the historical feature library.

[0077] Input the effective number stability value and the effective concentration stability value into the geometric product model, and output to obtain the extraction reference value.

[0078] It can be understood that the role of the geometric product model is as follows: The essential principle of the geometric product model is based on the properties of multiplication operations and can reflect the interaction and comprehensive influence among multiple factors. Therefore, if the stable value of the effective number and the stable value of the effective concentration are smaller, the extracted reference value after multiplication is smaller, indicating that the extraction of biomarkers is more stable. If the stable value of the effective number and the stable value of the effective concentration are larger, the extracted reference value after multiplication is larger, indicating that the extraction of biomarkers is less stable, reflecting the influence of the combined action of two factors (the stable value of the effective number and the stable value of the effective concentration) on the overall evaluation and avoiding the problem of only focusing on a single factor and ignoring the overall synergistic effect;

[0079] More specifically, the meaning represented by the extracted reference value is as follows: By comprehensively considering the stable value of the effective number and the stable value of the effective concentration of the biomarker in the historical extraction process, it is used to comprehensively evaluate the extraction stability of the biomarker. On the one hand, the stable value of the effective number reflects the deviation degree of the effective extraction times of the biomarker in different historical extraction periods, reflecting the stability of the extraction operation in terms of the number of times. On the other hand, the stable value of the effective concentration evaluates the deviation degree between the concentrations of the biomarker during multiple historical effective extractions, reflecting the extraction stability from the concentration perspective. Thus, the stable analysis results obtained through the extraction stability analysis of multiple biomarkers provide relatively accurate data support for screening biomarkers with higher extraction stability and including them in the stable extraction feature library;

[0080] Compare the extracted reference value with the extracted reference value threshold, and the process is as follows:

[0081] If the extracted reference value is greater than or equal to the extracted reference value threshold, it indicates that the stability degree of the biomarker in the extraction process is relatively high both in terms of the extraction times and the extraction concentration, and a characteristic reference signal is generated;

[0082] If the extracted reference value is less than the extracted reference value threshold, it indicates that the stability degree of the biomarker in the extraction process is relatively low both in terms of the extraction times and the extraction concentration, and a characteristic reference signal is generated;

[0083] Mark the biomarker that generates the characteristic reference signal as an extraction stable feature;

[0084] Sort all the extraction stable features in ascending order according to the corresponding extracted reference values to obtain a stable extraction feature library;

[0085] The specific implementation plan of the embodiment of the present invention is as follows: In the historical extraction of bladder cancer stem cell biomarkers, a number of biomarker concentrations for each operation are obtained. Then, according to the biomarker concentrations, the effectiveness of each operation is evaluated. Based on the evaluation results, a historical feature library is constructed. The extraction stability of multiple biomarkers in the historical feature library is analyzed to obtain a stability analysis result. And according to the stability analysis result, a stable extraction feature library is constructed. Therefore, the extraction stability of biomarkers is comprehensively analyzed from two dimensions of the extraction times and extraction concentrations, providing relatively accurate data support for screening biomarkers with higher extraction stability and incorporating them into the stable extraction feature library, and constructing a reliable stable extraction feature library, providing more stable and accurate biomarker features for subsequent research, diagnosis and other applications.

[0086] Example 2

[0087] As Figure 1 shown, on the basis of Example 1, the extraction method of a bladder cancer stem cell biomarker described in the embodiment of the present invention further includes:

[0088] Step 3: According to multiple biomarkers in the historical feature library, obtain the accuracy results of each determination of bladder cancer stem cells. According to the stable results of the accuracy determination of bladder cancer stem cells, high-precision features are screened out and a high-precision extraction feature library is constructed;

[0089] In some embodiments, a historical determination period is set, and the historical determination period is divided into several historical determination time periods with equal time;

[0090] Arbitrarily select a biomarker, obtain the historical effective determination times of the biomarker within the historical determination time period, and calculate the ratio with the total historical determination times to obtain a determination effective value;

[0091] It should be noted that the total historical determination times is the sum of the historical effective determination times and historical ineffective determination times within the historical determination time period;

[0092] Input the determination effective values corresponding to all historical determination time periods within the historical determination period into the Manhattan distance calculation model, and output to obtain an effective determination stability value;

[0093] Among them, the Manhattan distance calculation model is:

[0094] It can be understood that D p represents the effective determination stability value, q represents the total number of historical determination time periods, is the determination effective value corresponding to the rth historical extraction time period, is the determination effective value corresponding to the (r - 1)th historical extraction time period;

[0095] The reason for using the Manhattan distance calculation model is as follows: The Manhattan distance calculation model is essentially a method for calculating the distance between two points in Euclidean space. Now, the effective determination times within different historical determination periods are regarded as the coordinate values of two points respectively, and the distance between them is calculated by the Manhattan distance method. This distance reflects the degree of deviation of the determination times within adjacent historical determination periods. The smaller the distance, the closer the determination times within adjacent historical determination periods are, and the better the extraction effect;

[0096] More specifically, the meaning represented by the effective determination stability value is: the stability degree of the effective determination values of biomarkers within different historical determination periods. Since the effective determination times within different historical determination periods are regarded as the coordinate values of points, and the deviation degree of the determination times within adjacent periods is measured by calculating the Manhattan distance between them, the effective determination stability value actually comprehensively reflects the stability of the determination results of biomarkers in each historical determination period throughout the historical determination cycle. Specifically, the more stable the determination results of the analyzed biomarker in different periods, the more stable the accuracy result of the determination of bladder cancer stem cells, and the more conducive to screening out high-precision features and constructing a high-precision extraction feature library;

[0097] Compare the effective determination stability value with the effective determination stability threshold, and the process is as follows:

[0098] If the effective determination stability value is less than or equal to the effective determination stability threshold, it indicates that the determination of bladder cancer stem cells based on biomarkers within the historical determination cycle is relatively stable, and the analyzed biomarker is recorded as a high-precision feature;

[0099] If the effective determination stability value is greater than the effective determination stability threshold, it indicates that the determination of bladder cancer stem cells based on biomarkers within the historical determination cycle is relatively unstable, and the analyzed biomarker is recorded as a determination unstable biomarker;

[0100] Sort the high-precision features in ascending order according to the corresponding effective determination stability values, and construct a high-precision extraction feature library;

[0101] Example Three

[0102] As Figure 1 shown, a method for extracting a biomarker of bladder cancer stem cells according to an embodiment of the present invention further includes the following steps:

[0103] Step Four: Compare the high-precision extraction feature library with the stable extraction feature library to obtain high-precision stable features and to-be-labeled features, and respectively construct a high-precision stable extraction feature library according to the high-precision stable features and the to-be-labeled features;

[0104] In some embodiments, the process of performing a biomarker coincidence comparison between the high-precision extraction feature library and the stable extraction feature library is as follows:

[0105] Extract the same biomarkers in the high-precision extraction feature library and the stable extraction feature library, and record them as the same features;

[0106] Extract the non-identical biomarkers in the high-precision extraction feature library and the stable extraction feature library, and record them as different features;

[0107] Based on the same features, obtain the rankings corresponding to the same features in the high-precision extraction feature library and the stable extraction feature library respectively. If the ranking numbers are both small in the high-precision extraction feature library and the stable extraction feature library, mark the same features as high-precision stable features;

[0108] Sum up the rankings corresponding to the high-precision stable features in the high-precision extraction feature library and the stable extraction feature library, and sort them in ascending order to construct a high-precision stable extraction feature library;

[0109] If the ranking number is higher in one of the high-precision extraction feature library or the stable extraction feature library, mark the same features as features to be marked;

[0110] If the ranking numbers are both large in the high-precision extraction feature library and the stable extraction feature library, mark the same features as non-high-precision stable features;

[0111] Based on the features to be marked, if the ranking number is lower in the high-precision extraction feature library and higher in the stable extraction feature library, calculate the ratio of the ranking number of the feature to be marked in the stable extraction feature library to the total number of features in the stable extraction feature library to obtain a stable extraction coefficient;

[0112] Compare the stable extraction coefficients corresponding to the features to be marked, and add them to the high-precision stable extraction feature library in ascending order;

[0113] If the ranking number is higher in the high-precision extraction feature library and lower in the stable extraction feature library, calculate the ratio of the ranking number of the feature to be marked in the high-precision extraction feature library to the total number of features in the high-precision extraction feature library to obtain a high-precision extraction coefficient;

[0114] Compare the high-precision extraction coefficients corresponding to the features to be marked, and add them to the high-precision stable extraction feature library in ascending order;

[0115] The specific implementation scheme of the embodiment of the present invention is as follows: the effective determination stability value is obtained according to the historical effective determination times of biomarkers through the Manhattan distance calculation model, and high-precision features are screened based on this to construct a high-precision extraction feature library. Then, the high-precision extraction feature library is compared with the stable extraction feature library, and high-precision stable features, to-be-labeled features, and non-high-precision stable features are divided according to the coincidence of biomarkers and their rankings in the two libraries. For the to-be-labeled features, a high-precision stable extraction feature library is constructed by comparing the magnitudes of the high-precision extraction coefficients and the stable extraction coefficients respectively. Thus, not only the problem of unstable determination accuracy is solved, and the determination accuracy of bladder cancer stem cells is improved, but also the performance of biomarkers in both high-precision extraction and stable extraction is comprehensively considered, and the limitation problem of single-dimensional screening is solved, providing a better biomarker resource for the research of bladder cancer stem cells.

[0116] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and all these changes and improvements fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. A method for extracting biomarkers of bladder cancer stem cells, characterized in that: Including: Obtain the supernatant of the biomarker in each historical extraction to obtain the biomarker concentration, and conduct an effective evaluation of each extraction. According to the evaluation results, construct a historical feature library. During the historical extraction period, based on the extraction results of the biomarker in the historical feature library, screen out the stable extraction features, and based on the stable extraction features, construct a stable extraction feature library. During the historical determination period, based on the determination results of the biomarker in the historical feature library, screen out the high-precision features, and based on the high-precision features, construct a high-precision extraction feature library. Compare the features in the high-precision extraction feature library with those in the stable extraction feature library to obtain the high-precision stable features and the features to be marked, and respectively construct a high-precision stable extraction feature library according to the high-precision stable features and the features to be marked.

2. The extraction method of a bladder cancer stem cell biomarker according to claim 1, wherein: The acquisition of the biomarker concentration is as follows: Detect the supernatant of the biomarker by high-performance liquid chromatography to obtain the biomarker concentration.

3. The extraction method of a bladder cancer stem cell biomarker according to claim 2, characterized in that: The process of constructing the historical feature library is as follows: If the biomarker concentration is greater than or equal to the preset extraction concentration, it is recorded as a historical effective extraction. Sort according to the proportion of the number of historical effective extractions in the total number of historical extractions from large to small to construct a historical feature library.

4. The extraction method of a bladder cancer stem cell biomarker according to claim 1, wherein: The acquisition process of the stable extraction features is as follows: Divide the historical extraction period into several historical extraction time periods. Obtain the proportion of the number of effective extractions in the total number of extractions within the historical extraction time period and input it into the Manhattan distance calculation model to output the effective number stability value. Obtain the biomarker concentration corresponding to the historical effective extraction within the historical extraction time period and input it into the extraction concentration stability model to output the effective concentration stability value. Input the effective number stability value and the effective concentration stability value into the geometric product model to output the extraction reference value. If the extraction reference value is greater than or equal to the extraction reference value threshold, the biomarker is recorded as a stable extraction feature.

5. The extraction method of a bladder cancer stem cell biomarker according to claim 4, wherein: The construction process of the stable extraction feature library is as follows: Sort all the stable extraction features in ascending order according to the corresponding extraction reference values to obtain a stable extraction feature library.

6. The extraction method of a bladder cancer stem cell biomarker according to claim 1, wherein: The method for obtaining high-precision features is as follows: Divide the historical determination period into several historical determination time periods. Obtain the ratio of the number of effective determinations in the historical determination time period to the total number of historical determinations and input it into the Manhattan distance calculation model to output the effective determination stability value. If the effective determination stability value is less than or equal to the effective determination stability threshold, the biomarker is recorded as a high-precision feature.

7. The extraction method of a bladder cancer stem cell biomarker according to claim 1, characterized in that: The construction process of the high-precision extraction feature library is as follows: Sort the high-precision features in ascending order according to the corresponding effective determination stability values to construct a high-precision extraction feature library.

8. The extraction method of a bladder cancer stem cell biomarker according to claim 7, characterized in that: The acquisition process of the high-precision stable features and the features to be marked is as follows: Extract the same biomarkers in the high-precision extraction feature library and the stable extraction feature library and record them as the same features. Respectively obtain the rankings of the same features in the high-precision extraction feature library and the stable extraction feature library. If the ranking numbers are both small in the high-precision extraction feature library and the stable extraction feature library, mark the same features as high-precision stable features. If the ranking number is high in one of the high-precision extraction feature library or the stable extraction feature library, mark the same features as the features to be marked.

9. The extraction method of a bladder cancer stem cell biomarker according to claim 1, characterized in that: According to the high-precision and high-stability features, construct a high-precision and high-stability extraction feature library, and the execution process is as follows: Sum up the rankings of the high-precision and high-stability features in the high-precision extraction feature library and the stable extraction feature library, sort them in ascending order, and construct the high-precision and high-stability extraction feature library.

10. The extraction method of a bladder cancer stem cell biomarker according to claim 1, characterized in that: Construct a high-precision and high-stability extraction feature library according to the features to be marked, and the execution process is as follows: If the ranking number of the feature to be marked is relatively low in the high-precision extraction feature library and relatively high in the stable extraction feature library, then calculate the ratio of the ranking number of the feature to be marked in the stable extraction feature library to the total number of features in the stable extraction feature library to obtain the stable extraction coefficient; Compare the stable extraction coefficients corresponding to the features to be marked, and add them to the high-precision and high-stability extraction feature library in ascending order; If the ranking number of the feature to be marked is relatively high in the high-precision extraction feature library and relatively low in the stable extraction feature library, then calculate the ratio of the ranking number of the feature to be marked in the high-precision extraction feature library to the total number of features in the high-precision extraction feature library to obtain the high-precision extraction coefficient; Compare the high-precision extraction coefficients corresponding to the features to be marked, and add them to the high-precision and high-stability extraction feature library in ascending order.

Images