Data screening system for pharmacological analysis of heat stroke traditional Chinese medicine

Abstract

The invention relates to the technical field of medical data processing, in particular to a data screening system for pharmacological analysis of traditional Chinese medicines for heat stroke, comprising: an information acquisition module comprising a time sequence retrieval unit for retrieving inner-layer camouflage information in a plurality of databases to be retrieved; the screening module is used for screening out a target spot from the feature data, the KEGG path analysis unit is used for determining a plurality of signal paths by performing target enrichment analysis on the characteristic data; the comparison and recognition unit is connected with the KEGG path analysis unit and is used for marking the characteristic data which does not form the signal paths as disguise information; the verification analysis module is used for determining a core target spot and a core target compound from the target spots; the accuracy of pharmacological evaluation of the traditional Chinese medicine based on the heat stroke is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional Chinese medicine medical data processing, and particularly to a data screening system for traditional Chinese medicine pharmacological analysis of heat stroke. Background Art

[0002] Exertional heat stroke (EHS) is a life-threatening disease caused by high-temperature environments, posing significant health risks. Qing-Shu-Yi-Qi Decoction (QSYQD) is a traditional Chinese medicine (TCM) formula renowned for clearing summer heat, replenishing qi, and protecting intestinal function. However, experimental evidence regarding its role in EHS prevention and insights into its mechanisms are limited.

[0003] Traditional Chinese medicine (TCM), based on its unique theoretical framework, has a rich history and extensive clinical experience in preventing and treating EHS (Li et al., 2023). TCM emphasizes the importance of disease prevention, focusing on maintaining balance and harmony within the body to avoid diseases before they occur. This approach combines lifestyle adjustments, dietary therapy, and the use of herbal formulas to strengthen the body's resistance to external and internal factors that may cause diseases.

[0004] Chinese Patent Publication No.: CN115762774A discloses a heat stroke warning method, system, and storage medium, which relate to the technical field of monitoring devices. It solves the problem that the person in charge on-site is highly likely to delay the discovery of the corresponding heat stroke symptoms of the trainees due to personal negligence, delaying the timely diagnosis and treatment of the corresponding personnel. It includes: analyzing and determining the heat index of the training schedule period according to the correspondence between environmental temperature and humidity information and the heat index; analyzing and determining the trainees whose heat index exceeds the maximum heat index that can be tolerated according to the heat index of the training schedule period analyzed and determined and the correspondence between the training intensity of the trainees and the maximum heat index that can be tolerated; and sending the trainees whose heat index exceeds the maximum heat index that can be tolerated and the training schedule period as notification information to the terminal held by the general person in charge. Thus, the heat stroke warning method, system, and storage medium have problems of decreased accuracy of traditional Chinese medicine pharmacological evaluation and decreased precision of information screening due to the overgeneralized retrieval information in the process of traditional Chinese medicine pharmacological analysis and the negative feedback effect between some target information. Summary of the Invention

[0005] Therefore, the present invention provides a data screening system for traditional Chinese medicine pharmacological analysis of heat stroke to overcome the problems of decreased accuracy of traditional Chinese medicine pharmacological evaluation and decreased precision of information screening in the prior art due to the overgeneralized retrieval information in the process of traditional Chinese medicine pharmacological analysis and the negative feedback effect between some target information.

[0006] To achieve the above object, the present invention provides a data screening system for traditional Chinese medicine pharmacological analysis of heat stroke, including:

[0007] An information collection module for collecting characteristic data, including a time-series retrieval unit for retrieving inner-layer camouflage information in a number of databases to be retrieved.

[0008] A screening module connected to the information collection module for screening target targets from the characteristic data, including a KEGG pathway analysis unit for determining a number of signal pathways by performing target enrichment analysis on the characteristic data, and a comparison and recognition unit connected to the KEGG pathway analysis unit for marking characteristic data that has not formed the signal pathway as camouflage information.

[0009] Wherein, the edit distance of the visual color of the intersection point of the KEGG pathway analysis unit is determined according to the number of intersection lines of the intersection point.

[0010] A verification and analysis module connected to the information collection module and the screening module respectively for determining core targets and core target compounds from the target targets, and determining a retrieval anomaly processing method according to the information content ratio of the camouflage information, including adjusting the pharmacodynamic classification granularity of the pathway according to the linear fitting degree between the antagonistic amplitude of the target group and the number of pathway connections of the target group.

[0011] Or, determining whether to run the time-series retrieval unit according to the information entropy of the camouflage information.

[0012] Further, the screening module further includes a duplicate elimination unit connected to the comparison and recognition unit for screening duplicate information in the characteristic data.

[0013] Further, the KEGG pathway analysis unit is further configured to obtain the number of intersection lines of the intersection point, and increase the edit distance of the visual color of the intersection point when the number of intersection lines is greater than a preset first number.

[0014] Further, the edit distance of the visual color of the intersection point is positively correlated with the number of intersection lines, and the edit distance of the visual color of the intersection point is the minimum edit distance between a single intersection point and an adjacent intersection point that is camouflage information.

[0015] Further, the camouflage information is characteristic data that has not formed the signal pathway.

[0016] Further, the inner-layer camouflage information is the corresponding target information retrieved by the time-series retrieval unit in a database other than the current database to be retrieved according to the chronological development order of heat stroke.

[0017] Further, the verification and analysis module is also used to determine the accuracy of the retrieval according to the information volume ratio of the camouflage information, where

[0018] If the information volume ratio of the camouflage information is greater than or equal to a preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is lower than the allowable range and executes the retrieval anomaly handling method;

[0019] If the information volume ratio of the camouflage information is less than the preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is within the allowable range.

[0020] Further, the verification and analysis module is also used to obtain the linear fitting degree between the antagonistic amplitude of several target groups of the camouflage information and the number of pathway connections of the target group under the condition that the information volume ratio of the camouflage information is greater than or equal to a preset first ratio and less than or equal to a preset second ratio.

[0021] If the linear fitting degree is greater than or equal to a preset fitting degree, the verification and analysis module controls the KEGG pathway analysis unit to reduce the pharmacodynamic classification granularity of the pathway.

[0022] Further, the pharmacodynamic classification granularity of the pathway is negatively correlated with the linear fitting degree.

[0023] Further, the verification and analysis module is also used to obtain the information entropy of the camouflage information under the condition that the information volume ratio of the camouflage information is greater than or equal to a preset second ratio, and control the time-series retrieval unit to operate under the condition that the information entropy is greater than a preset information entropy.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows. By setting a time-series retrieval unit, a comparison and recognition unit, a KEGG pathway analysis unit, and a verification and analysis module, the present invention screens the camouflage information in the feature data to mark the information in the feature data that has no actual pharmacological association with the disease symptoms, achieving accurate recognition of the camouflage information. By determining whether to perform time-series retrieval according to the information entropy of the camouflage information, the influence of the increase in camouflage information caused by the inaccurate retrieval content due to the overly general retrieval terms is reduced. And by determining the pharmacodynamic classification granularity of the pathway according to the linear fitting degree between the antagonistic amplitude of the target group and the number of pathway connections of the target group, the interaction between the connected pathways of the target interferes with the cancellation effect between the targets, reducing the influence on the accuracy of target recognition, and improving the accuracy of traditional Chinese medicine pharmacological analysis.

[0025] Furthermore, the system of the present invention determines the edit distance of the visual color of the intersection point according to the number of intersecting lines of the intersection point. When the number of intersecting lines of the intersection point is too large, it indicates that the intersection point is relatively close to the core. Therefore, adjusting the edit distance can reduce the impact of errors in the position of the core point, which may lead to errors in the screening of the core point.

[0026] Furthermore, the system of the present invention retrieves the inner-layer camouflage information through the timing retrieval unit. When the generalization of the retrieval term is too strong, there is too much irrelevant or camouflage information in the retrieved information. By retrieving the inner-layer camouflage information, the impact of the increase in irrelevant information caused by the relatively general retrieval term on the accuracy of data collection is overcome, and the accuracy of traditional Chinese medicine pharmacology analysis is further improved.

[0027] Furthermore, when the linear fitting degree between the antagonistic amplitude of several target groups of the camouflage information and the number of pathway connections of the target group is too large, it indicates that the degree of interaction between the pathways between the targets masks the offset effect between the targets. Therefore, by reducing the pharmacodynamic classification granularity of the pathway, the impact of the interaction between the pathways on the accuracy of target screening is weakened, and the accuracy of traditional Chinese medicine pharmacology analysis is further improved.

[0028] Furthermore, the system of the present invention collects target information by setting a timing retrieval unit, which overcomes the problem that it is difficult to retrieve the corresponding specific target when the retrieved content is relatively general, resulting in a large amount of camouflage information and insufficient accuracy of data collection, and realizes the improvement of the accuracy of traditional Chinese medicine pharmacology analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is the overall structural block diagram of the data screening system for traditional Chinese medicine pharmacology analysis of heat stroke in the embodiment of the present invention;

[0030] Figure 2 It is the specific structural block diagram of the screening module of the data screening system for traditional Chinese medicine pharmacology analysis of heat stroke in the embodiment of the present invention;

[0031] [[ID=2z]] Figure 3 It is the connection structural block diagram of the specific structure of the screening module of the data screening system for traditional Chinese medicine pharmacology analysis of heat stroke in the embodiment of the present invention, which is respectively connected to the information collection module and the verification and analysis module. DETAILED DESCRIPTION OF THE INVENTION

[0032] In order to make the objectives and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0033] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0034] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0035] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0036] Please refer to Figure 1 、 Figure 2 and Figure 3 as shown, which are respectively the overall structural block diagram of the data screening system for the pharmacological analysis of traditional Chinese medicine for heat stroke, the specific structural block diagram of the screening module, and the connection structural block diagram in which the specific structure of the screening module is respectively connected to the information collection module and the verification and analysis module. An embodiment of the present invention provides a data screening system for the pharmacological analysis of traditional Chinese medicine for heat stroke, including:

[0037] An information collection module for collecting characteristic data, including a time-series retrieval unit for retrieving the inner-layer camouflage information in a number of databases to be retrieved;

[0038] A screening module connected to the information collection module for screening target targets from the characteristic data, including a KEGG pathway analysis unit for determining a number of signal pathways by performing target enrichment analysis on the characteristic data and a comparison and recognition unit connected to the KEGG pathway analysis unit for marking the characteristic data that has not formed the signal pathway as camouflage information;

[0039] Among them, the edit distance of the visual color of the intersection point of the KEGG pathway analysis unit is determined according to the number of intersection lines of the intersection point;

[0040] A verification and analysis module, which is respectively connected to the information collection module and the screening module, is used to determine core target points and core target compounds from the target points, and determine a retrieval anomaly handling method according to the information volume ratio of the camouflage information, including adjusting the pharmacodynamic classification granularity of the pathway according to the linear fitting degree between the antagonistic amplitude of the target point group and the number of pathway connections in the target point group,

[0041] or determine whether to run the time-series retrieval unit according to the information entropy of the camouflage information.

[0042] Specifically, the verification model is an AI model, which trains a classification model on the gene expression patterns in the KEGG pathway to predict disease pathways; those skilled in the art can understand that the AI model is a conventional technical means well-known to those skilled in the art, and its training process is also a conventional technical means. Therefore, under the condition that the data to be trained is the gene expression feature information in the KEGG pathway, the AI model and the training process will not be elaborated.

[0043] Specifically, the gene expression feature information includes differentially expressed genes, the change trend of gene expression levels over time, the association between gene expression and protein expression such as heat shock protein HSP70, metabolite levels, epigenetic modifications, and statistical significance indicators such as p-value / FDR, and the gene coverage of the KEGG pathway.

[0044] Specifically, the screening module further includes a GPU connected to the verification model to drive the verification model for training and operation.

[0045] Specifically, the types of feature data include but are not limited to the pathophysiological characteristics of heat stroke such as body temperature, pharmacodynamic indicators such as body temperature recovery time, metabolism and toxicity such as puerarin bioavailability, traditional Chinese medicine ingredients, target points and pathways, and multi-omics integration such as gene loci.

[0046] Target points and pathways include that heat stroke can cause damage to the blood-brain barrier, and traditional Chinese medicine may repair the barrier function by regulating tight junction proteins (such as Claudin-5, Occludin) or inhibiting inflammatory factors (such as TNF-α, IL-6), heat stroke triggers microglial activation and the release of pro-inflammatory factors, and traditional Chinese medicine may reduce brain neuroinflammation by inhibiting signal pathways such as NF-κB, MAPK, and high temperature causes neuronal apoptosis (such as Bax / Bcl-2 imbalance), and traditional Chinese medicine may reduce cell death by activating the PI3K / Akt or inhibiting the Caspase-3 pathway, and traditional Chinese medicine may restore brain energy supply by dilating cerebral blood vessels (such as the nitric oxide pathway) or promoting glucose metabolism (such as AMPK activation).

[0047] Specifically, Salvia miltiorrhiza (tanshinone) inhibits brain inflammation and oxidative stress; Coptis chinensis (berberine): regulates the permeability of the blood-brain barrier; Panax ginseng (ginsenoside Rg1) enhances mitochondrial function and reduces neuronal apoptosis.

[0048] Specifically, the contrast recognition unit recognizes the camouflage information, continues to recognize the camouflage information during the next batch of information screening process after the recognition is completed, and uses the duplicate elimination unit to eliminate the camouflage information and duplicate information.

[0049] Specifically, when the first batch of camouflage information is recognized by the timing retrieval unit, the timing retrieval unit is also used for retrieval according to the actual situation during the next batch of information screening and acquisition process.

[0050] Specifically, the verification and analysis module is also used to mark a target target as a core target under the condition that the central feature parameter of a single target target is greater than or equal to a preset feature parameter.

[0051] Specifically, the central feature parameter of a single target target is the sum of the product of the degree centrality of the target target and the degree centrality weight coefficient and the product of the betweenness centrality of the target target and the betweenness centrality weight coefficient.

[0052] Wherein, the sum of the degree centrality weight coefficient and the betweenness centrality weight coefficient is 1.

[0053] Those skilled in the art can understand that the values of the degree centrality weight coefficient and the betweenness centrality weight coefficient can be adaptively set according to the characteristics of the target target. A preferred embodiment is given. The preferred embodiment of the degree centrality weight coefficient is 0.6, and the preferred embodiment of the betweenness centrality weight coefficient is 0.4.

[0054] Specifically, the core target compound is a compound with the function of combating heat stroke among the core targets.

[0055] Specifically, the information acquisition module further includes a data acquisition unit connected to the timing retrieval unit.

[0056] In implementation, the optional implementation methods of the data acquisition unit include crawlers, ETL, and custom scripts or programs; the preferred embodiment of the data acquisition unit in the traditional Chinese medicine pharmacological evaluation and analysis system for heat stroke information is ETL with batch processing capabilities. Those skilled in the art can make adaptive replacements and adjustments to the data acquisition unit according to the actual data type or data volume in actual practice.

[0057] Specifically, several alternative embodiments of the databases to be retrieved include the GeneCards database (https: / / www.genecards.org), OMIM (https: / / www.omim.org / ), the DisGeNET database (https: / / www.disgenet.org / ), and the DrugBank database (https: / / go.drugbank.com / ).

[0058] Those skilled in the art can understand that the targets are the biomolecules and related pathways through which traditional Chinese medicines exert their effects on diseases. These biomolecules include biological macromolecules such as proteins (such as enzymes, receptors, ion channels), nucleic acids (DNA, RNA), etc. After entering the human body, traditional Chinese medicines will bind to these specific molecules or receptors, thereby exerting their pharmacological effects. Due to the complexity and diversity of the components of traditional Chinese medicines, their targets can be a single molecule or the interaction of multiple molecules.

[0059] In implementation, the present invention sets up a time-series retrieval unit, a comparison and recognition unit, a KEGG pathway analysis unit, and a verification and analysis module. By screening the camouflage information in the feature data, the information in the feature data that has no actual pharmacological association with the disease symptoms is marked, realizing the accurate recognition of the camouflage information. By determining whether to perform time-series retrieval according to the information entropy of the camouflage information, the influence of the increase in camouflage information caused by the inaccuracy of the retrieved content due to overly general retrieval terms is reduced. And by determining the pharmacological effect classification granularity of the pathway according to the linear fitting degree between the antagonistic amplitude of the target group and the number of pathway connections of the target group, the interaction between the connected pathways of the targets interferes with the offset effect between the targets, reducing the influence on the accuracy of target recognition, and realizing the improvement of the accuracy of traditional Chinese medicine pharmacological analysis.

[0060] Specifically, the screening module further includes a duplicate removal unit connected to the comparison and recognition unit for screening duplicate information in the feature data.

[0061] Specifically, the KEGG pathway analysis unit is further used to obtain the number of cross lines of the intersection point, and increase the edit distance of the visual color of the intersection point under the condition that the number of cross lines is greater than a preset first number.

[0062] Specifically, the KEGG pathway analysis unit is software well-known to those skilled in the art for performing pathway enrichment analysis, so its specific functions and operation methods will not be elaborated here.

[0063] Specifically, the KEGG pathway analysis unit is further used to obtain the number of cross lines of the intersection point, and increase the edit distance of the visual color of the intersection point under the condition that the number of cross lines is greater than a preset first number.

[0064] In implementation, the system according to the present invention determines the edit distance of the visual color of the intersection based on the number of intersecting lines of the intersection. When the number of intersecting lines of the intersection is excessive, it indicates that the intersection is relatively close to the core. Adjusting the edit distance can reduce the impact of errors in the screening of the core points caused by incorrect positions of the core points.

[0065] Optionally, the preset first quantity has an optional range of [6, 12].

[0066] Preferably, a preferred embodiment of the preset first quantity is 10.

[0067] Specifically, the meaning of the edit distance is the minimum number of color adjustment times / number of colors for adjusting the visual color of the intersection to the visual color of an adjacent intersection. Those skilled in the art can understand that the calculation process of the edit distance is a conventional technical means familiar to those skilled in the art. Therefore, the calculation process of the edit distance will not be elaborated herein.

[0068] In implementation, when the number of intersecting lines of the intersection exceeds the preset first quantity by within 5 lines, the edit distance of the visual color of the intersection is adjusted to 1.2 times the current edit distance. When the number of intersecting lines of the intersection exceeds the preset first quantity by each additional line, the edit distance of the visual color of the intersection is increased by 1 time. For example, if the number of intersecting lines of the intersection is 12 and the current edit distance is 10 times, then the edit distance of the visual color of the intersection is adjusted to 12 times.

[0069] Specifically, Cytoscape software version 3.8.2 can be used to visualize and beautify the pathway.

[0070] Specifically, the edit distance of the visual color of the intersection is positively correlated with the number of intersecting lines, and the edit distance of the visual color of the intersection is the minimum edit distance between a single intersection and an adjacent intersection for camouflage information.

[0071] Specifically, the camouflage information is characteristic data that does not form the signal pathway.

[0072] Specifically, the inner layer camouflage information is the corresponding target information retrieved by the timing retrieval unit from a database other than the current database to be retrieved in the chronological development order of heat stroke.

[0073] In implementation, the system of the present invention retrieves the inner-layer camouflage information through a timing retrieval unit. When the generalization of the retrieval term is too strong, there is too much irrelevant or camouflage information in the retrieved information. By retrieving the inner-layer camouflage information, the influence of the increase in irrelevant information caused by the relatively general retrieval term on the accuracy of data collection is overcome, and the accuracy of traditional Chinese medicine pharmacological analysis is further improved.

[0074] Specifically, the verification and analysis module is also used to determine the accuracy of the retrieval according to the information volume ratio of the camouflage information, where

[0075] if the information volume ratio of the camouflage information is greater than or equal to a preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is lower than the allowable range and executes the retrieval exception handling method;

[0076] if the information volume ratio of the camouflage information is less than the preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is within the allowable range.

[0077] Specifically, the information volume ratio of the camouflage information is the ratio of the byte volume of the camouflage information to the total byte volume of all the information retrieved currently.

[0078] Optionally, the optional range of the preset first ratio is [0.1, 0.3].

[0079] Preferably, the preferred embodiment of the preset first ratio is 0.2.

[0080] Those skilled in the art can understand that the selection range of the preset first ratio and the setting of the embodiment are the ranges adopted in the process of screening heatstroke information for heatstroke and conducting traditional Chinese medicine pharmacological evaluation and analysis. Those skilled in the art can adaptively adjust the preset first ratio according to the actual situation.

[0081] Specifically, the verification and analysis module is also used to obtain the linear fitting degree between the antagonistic amplitude of several target groups of the camouflage information and the number of pathway connections of the target groups under the condition that the information volume ratio of the camouflage information is greater than or equal to the preset first ratio and less than or equal to the preset second ratio.

[0082] If the linear fitting degree is greater than or equal to the preset fitting degree, the verification and analysis module controls the KEGG pathway analysis unit to reduce the pharmacological classification granularity of the pathway.

[0083] Specifically, the preset first ratio is less than the preset second ratio.

[0084] Optionally, the optional range of the preset second ratio is [0.4, 0.6].

[0085] Preferably, the preferred embodiment of the preset second ratio is 0.5.

[0086] Specifically, taking the antagonistic amplitude of several target groups of the camouflage information as the ordinate and the number of pathway connections of the target group as the abscissa, the data of several groups of coordinate points constitute the collected sample data, so as to calculate the linear fitting degree between the two.

[0087] Those skilled in the art can understand that the calculation process of the linear fitting degree between the antagonistic amplitude of several target groups of the camouflage information and the number of pathway connections of the target group is a conventional technical means well-known to those skilled in the art. Therefore, the calculation process of the linear fitting degree will not be elaborated here.

[0088] Specifically, the pharmacodynamic classification granularity of the pathway is the degree of fineness of the pharmacodynamic classification of the pathway, and the pharmacodynamic classification granularity of the pathway can be the number of levels of the pharmacodynamic action intensity.

[0089] Specifically, the pharmacodynamic classification granularity of the pathway is negatively correlated with the linear fitting degree.

[0090] In implementation, those skilled in the art can set the decreasing method of the gradient according to the actual value of the linear fitting degree exceeding the preset fitting degree to adaptively reduce the pharmacodynamic classification granularity of the pathway. There is no limitation on this, as long as the pharmacodynamic classification granularity of the pathway is negatively correlated with the linear fitting degree, that is, the greater the linear fitting degree, the greater the reduced pharmacodynamic classification granularity. There is no limitation on the setting of the gradient, and those skilled in the art can make adaptive settings according to the actual situation.

[0091] In implementation, when the linear fitting degree between the antagonistic amplitude of several target groups of the camouflage information and the number of pathway connections of the target group is too large in the system of the present invention, it indicates that the degree of interaction between the pathways among the targets masks the offset effect between the targets. Therefore, by reducing the pharmacodynamic classification granularity of the pathway, the influence of the interaction between the pathways on the accuracy of target screening is weakened, and further the improvement of the accuracy of traditional Chinese medicine pharmacological analysis is realized.

[0092] Specifically, the verification and analysis module is further configured to obtain the information entropy of the camouflage information under the condition that the information ratio of the camouflage information is greater than or equal to a preset second ratio, and control the timing retrieval unit to operate under the condition that the information entropy is greater than the preset information entropy.

[0093] Optionally, the optional range of the information entropy of the camouflage information is [500MB, 1500MB].

[0094] Preferably, the preferred embodiment of the information entropy of the camouflage information is 1000MB.

[0095] In implementation, the system of the present invention collects target information by setting a timing retrieval unit, overcoming the problem that when the retrieved content is relatively general, it is difficult to retrieve the corresponding specific target, resulting in a large number of disguised information, thus leading to insufficient accuracy of data collection, and achieving an improvement in the accuracy of traditional Chinese medicine pharmacological analysis.

[0096] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A data screening system for the pharmacological analysis of traditional Chinese medicine for heat stroke, characterized in that Including: An information collection module for collecting feature data, including a time-series retrieval unit for retrieving inner-layer camouflage information in a number of databases to be retrieved; A screening module connected to the information collection module for screening target targets from the feature data, including a KEGG pathway analysis unit for determining a number of signal pathways by performing target enrichment analysis on the feature data, a comparison and recognition unit connected to the KEGG pathway analysis unit for marking the feature data that has not formed the signal pathway as camouflage information, and a verification model connected to the KEGG pathway analysis unit for verifying the accuracy of the number of signal pathways according to the feature data; Among them, the edit distance of the visual color of the intersection point of the KEGG pathway analysis unit is determined according to the number of intersection lines of the intersection point; A verification and analysis module is respectively connected to the information collection module and the screening module for determining core targets and core target compounds from the target targets, and determining a retrieval anomaly handling method according to the information volume ratio of the camouflage information, including adjusting the pharmacodynamic classification granularity of the pathway according to the linear fitting degree between the antagonistic amplitude of the target group and the number of pathway connections of the target group, Or, determining whether to run the time-series retrieval unit according to the information entropy of the camouflage information.

2. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 1, wherein The screening module further includes a duplicate elimination unit connected to the comparison and recognition unit for screening duplicate information in the feature data.

3. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 2, wherein, The KEGG pathway analysis unit is further used to obtain the number of intersection lines of the intersection point, and increase the edit distance of the visual color of the intersection point under the condition that the number of intersection lines is greater than a preset first number.

4. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 3, wherein The edit distance of the visual color of the intersection point is positively correlated with the number of intersection lines, and the edit distance of the visual color of the intersection point is the minimum edit distance between a single intersection point and an adjacent intersection point of the non-camouflage information.

5. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 4, wherein The camouflage information is feature data that has not formed the signal pathway.

6. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 5, characterized in that, The inner-layer camouflage information is the corresponding target information retrieved by the time-series retrieval unit in a database other than the current database to be retrieved according to the chronological development order of heat stroke.

7. The data screening system for traditional Chinese medicine pharmacological analysis of heat stroke according to claim 6, characterized in that, The verification and analysis module is further used to determine the accuracy of the retrieval according to the information volume ratio of the camouflage information, where If the information volume ratio of the camouflage information is greater than or equal to a preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is lower than the allowable range and executes the retrieval anomaly handling method; If the information volume ratio of the camouflage information is less than the preset first ratio, the verification and analysis module determines that the accuracy of the retrieval is within the allowable range.

8. The traditional Chinese medicine pharmacological evaluation and analysis system based on feature data screening according to claim 7, wherein, The verification and analysis module is further used to obtain the linear fitting degree between the antagonistic amplitude of a number of target groups of the camouflage information and the number of pathway connections of the target group under the condition that the information volume ratio of the camouflage information is greater than or equal to a preset first ratio and less than or equal to a preset second ratio, If the linear fitting degree is greater than or equal to a preset fitting degree, the verification and analysis module controls the KEGG pathway analysis unit to reduce the pharmacodynamic classification granularity of the pathway.

9. The traditional Chinese medicine pharmacological evaluation and analysis system based on feature data screening according to claim 8, characterized in that, The pharmacodynamic classification granularity of the pathway is negatively correlated with the linear fitting degree.

10. The traditional Chinese medicine pharmacological evaluation and analysis system based on feature data screening according to claim 9, characterized in that, The verification and analysis module is further configured to obtain the information entropy of the camouflage information under the condition that the information volume ratio of the camouflage information is greater than or equal to a preset second ratio, and control the operation of the timing retrieval unit under the condition that the information entropy is greater than a preset information entropy.

Images