Data analysis method and apparatus, electronic device and storage medium

By automatically determining the data type and selecting suitable analysis methods, the automated analysis of multi-omic data is achieved, and the problems of low data analysis efficiency and insufficient user-friendliness in the existing technology are solved, and intuitive data display is provided, suitable for codeless capabilities. User use.

WO2024229951A1PCT designated stage expired Publication Date: 2024-11-14NANJING PINSHENG MEDICAL TECH CO LTD +2
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/103876
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-10
Filing Date
2023-06-29
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

In the prior art, data analysis is inefficient, and users need to use multiple software to obtain complete analysis results. The multi-omics data analysis method is complex to use and lack user-friendly automated integration and mapping tools.

Method used

Provide a data analysis method and device to automatically determine the data type and select suitable analysis methods by obtaining proteomics, metabolomics, lipomics and clinical information data, so as to achieve integrated automatic analysis from data to charts.

Benefits of technology

It greatly reduces the time and difficulty of multi-omics data analysis, reduces user learning costs, provides an intuitive data display form, is suitable for users without code capabilities, and improves data analysis efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023103876_14112024_PF_FP_ABST
    Figure CN2023103876_14112024_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed in the present invention are a data analysis method and apparatus, an electronic device and a storage medium. The method comprises: acquiring data to be analyzed, said data comprising at least two of proteomics data, metabonomics data, lipidomics data and clinical information; determining the data type of each piece of data among the data to be analyzed, and determining a data analysis method on the basis of the data type of each piece of data among said data; and analyzing said data on the basis of the data analysis method so as to obtain an analysis result chart. The described technical solution automatically determines a data analysis method and then automatically analyzes, according to the automatically determined data analysis method, data to be analyzed so as to obtain an analysis result chart, thereby achieving integrated automatic analysis from data to charts, and improving data analysis efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Data analysis method, device, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on May 10, 2023, with application number 202310518291.2 and invention name “Data Analysis Method, Device, Electronic Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present invention relates to the field of data processing technology, and in particular to a data analysis method, device, electronic device and storage medium. Background Art

[0003] With the development of big data technology, data centered on health care is increasing rapidly. As the amount and types of data increase, how to process multi-omics data efficiently and conveniently has become a new challenge.

[0004] The current data analysis software has relatively simple functions, and users need to use multiple software to obtain complete analysis results.

[0005] In the process of realizing the present invention, the inventors discovered that there are at least the following technical problems in the prior art: the prior art solution has the problem of low data analysis efficiency.

[0006] Summary of the Invention

[0007] The present invention provides a data analysis method, device, electronic device and storage medium to improve the efficiency of data analysis.

[0008] According to one aspect of the present invention, there is provided a data analysis method, comprising:

[0009] Acquiring data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information;

[0010] Determining the data type of each data in the data to be analyzed, and determining a data analysis method based on the data type of each data in the data to be analyzed;

[0011] The data to be analyzed is analyzed based on the data analysis method to obtain the analysis result chart.

[0012] According to another aspect of the present invention, there is provided a data analysis device, comprising:

[0013] An analysis data acquisition module, configured to acquire data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information;

[0014] An analysis method determination module is used to determine the data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed;

[0015] The result chart determination module is used to analyze the data to be analyzed based on the data analysis method to obtain the analysis result chart.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor;

[0018] and a memory communicatively coupled to the at least one processor;

[0019] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the data analysis method of any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data analysis method of any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention obtains data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data and clinical information, thereby achieving the acquisition of multiple combinations of data, and then determining the data type of each data in the data to be analyzed, determining the data analysis method based on the data type of each data in the data to be analyzed, achieving automatic determination of the data analysis method, and then analyzing the data to be analyzed based on the automatically determined data analysis method to obtain analysis result charts, thereby achieving integrated automatic analysis from data to charts, thereby improving data analysis efficiency.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0024] FIG1 is a flow chart of a data analysis method provided according to a first embodiment of the present invention;

[0025] FIG2 is a flow chart of a data analysis method provided according to a second embodiment of the present invention;

[0026] FIG3 is a flow chart of a data analysis method provided according to a third embodiment of the present invention;

[0027] FIG4 is a flow chart of a data analysis method provided according to a fourth embodiment of the present invention;

[0028] FIG5 is a schematic structural diagram of a data analysis device provided according to a fifth embodiment of the present invention;

[0029] FIG6 is a schematic diagram of the structure of an electronic device for implementing the data analysis method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0032] Before introducing specific embodiments, the following provides a detailed introduction to the background technology of the present invention. Prior art multi-omics data analysis methods often require numerous adjustable parameters and extensive statistical background. Furthermore, most multi-omics data analysis methods lack user-friendly interfaces and are still limited to developer languages ​​such as Python and R. Users are required to install adapters and adjust the code based on the data, placing high demands on their computer skills.

[0033] Using a single multi-omics analysis method requires significant learning and manual data processing time. Implementing multiple multi-omics analysis methods and analyzing, comparing, and contrasting existing data from multiple perspectives is even more challenging. Specifically, different omics data require different analysis methods. Experimenters without coding skills need to learn how to use numerous websites, but may only obtain basic charts. Furthermore, some omics data analysis methods can only be performed by downloading sample code and adjusting the sample code and various parameters based on their own data, making them inaccessible to those without coding skills.

[0034] It can be seen that the current multi-omics data analysis lacks a set of user-friendly, one-click analysis tools that can combine different data types, automate data integration, adapt to multiple multi-omics calculation methods, and generate simultaneous graphs.

[0035] The present invention provides a data analysis method, device, electronic device and storage medium for comprehensive processing of multi-omics and clinical information, which reduces the considerable time spent on manual processing of proteomics data, metabolomics data, lipidomics data and clinical information, greatly reduces the analysis difficulty and threshold of multi-omics and multi-analysis methods, does not require users to have a computer science or statistics background, can be used with one click, and through a rich graphical display form, more intuitive understanding and comparison of data analysis results.

[0036] Example 1

[0037] FIG1 is a flow chart of a data analysis method provided in Example 1 of the present invention. This embodiment is applicable to the case of automatically analyzing multi-omics data. The method can be executed by a data analysis device, which can be implemented in the form of hardware and / or software and can be configured in a computer terminal, server, or other device. As shown in FIG1 , the method includes:

[0038] S110 , obtaining data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information.

[0039] In this embodiment, the data to be analyzed refers to the data to be subjected to multi-omics data analysis, which may include but is not limited to at least two of proteomics data, metabolomics data, lipidomics data and clinical information. In other words, if there is no clinical information, two or more omics data need to be entered by default; if there is clinical information, one or more omics data can be entered.

[0040] Specifically, each omics data in the data to be analyzed can be obtained from the corresponding database or external input, and the clinical information in the data to be analyzed can be obtained from the preset storage location of the electronic device or other devices connected to the electronic device. For example, the electronic device can be an electronic computer in a hospital.

[0041] S120: Determine the data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed.

[0042] In this embodiment, the data type is used to characterize the type of each data in the data to be analyzed, and may include a proteomics data type, a metabolomics data type, a lipidomics data type, and a clinical information type.

[0043] It should be noted that by determining the data type of each data in the data to be analyzed, the composition of the data to be analyzed can be determined, so that a data analysis method suitable for the data to be analyzed can be selected later. For example, if a protein input file is detected, it indicates that the data to be analyzed contains data of the proteomics data type, where the protein input file contains information such as protein accession numbers; if a metabolomics input file is detected, it indicates that the data to be analyzed contains data of the metabolomics data type, where the metabolomics input file contains information such as name and compound ID.

[0044] For example, if proteomics data input is detected, the data to be analyzed is determined to contain data of the proteomics data type, and the variable corresponding to the proteomics data is assigned TRUE. If proteomics data input is not detected, the data to be analyzed is determined to contain no data of the proteomics data type, and the variable corresponding to the proteomics data is assigned FALSE. The detection process for other omics data and clinical information is the same as that for proteomics data, and will not be repeated here. After the data type of each data in the data to be analyzed is detected, a data analysis method suitable for the data to be analyzed can be selected according to the data type of each data to perform targeted analysis on the data.

[0045] S130: Analyze the data to be analyzed based on the data analysis method to obtain an analysis result chart.

[0046] In this embodiment, the analysis result chart refers to a visualization chart converted from the analyzed data, which provides a more intuitive display of the analyzed data. For example, the analysis result chart can be a network diagram, a line chart, a bar chart, a dot chart, etc. The analysis result chart can be displayed in a static diagram and / or a dynamic interactive diagram, wherein the dynamic interactive diagram can be an offline HTML interactive network diagram.

[0047] Specifically, the data to be analyzed may be analyzed by one or more of an association analysis method, a cluster analysis method, an enrichment analysis method, and a MOFA analysis method to obtain one or more analysis result charts and display them.

[0048] It should be noted that the data analysis method provided in this embodiment reduces the time spent on manual processing of proteomic, metabolomic, lipidomic and clinical data, and the data analysis method can be used with one click, and users do not need to have coding skills, which reduces the analysis difficulty and threshold of multi-omics analysis methods, and can display analysis result charts, allowing users to more intuitively understand and compare analysis data.

[0049] The technical solution of the embodiment of the present invention obtains data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data and clinical information, thereby achieving the acquisition of multiple combinations of data, and then determining the data type of each data in the data to be analyzed, determining the data analysis method based on the data type of each data in the data to be analyzed, achieving automatic determination of the data analysis method, and then analyzing the data to be analyzed based on the automatically determined data analysis method to obtain analysis result charts, thereby achieving integrated automatic analysis from data to charts, thereby improving data analysis efficiency.

[0050] Example 2

[0051] Figure 2 is a flow chart of a data analysis method provided in Example 2 of the present invention. The method of this embodiment can be combined with the various optional schemes in the data analysis method provided in the above embodiments. The data analysis method provided in this embodiment has been further optimized. In some embodiments, the acquisition of the data to be analyzed includes: acquiring omics data and / or clinical information; performing data processing on the omics data by a pre-configured omics data processing method to obtain omics processing data, wherein the omics data processing method includes one or more of a two-tailed Student's T test, multiple test correction, and one-way analysis of variance; performing clinical indicator significance analysis on the clinical information to obtain clinical analysis information; merging the omics processing data with the clinical analysis information to obtain data to be analyzed.

[0052] As shown in FIG2 , the method includes:

[0053] S210: Acquire omics data and / or clinical information.

[0054] In this embodiment, the omics data may include but are not limited to proteomics quantitative files, metabolomics quantitative files, and lipidomics quantitative files.

[0055] For example, a proteomics quantitative analysis file can be a peptide quantitative analysis result text file output by search software such as Proteome Discoverer, MaxQuant, Spectronaut, or DIA-NN. A metabolomics quantitative analysis file can be a file output by CD (Compound Discoverer) or MS-DIAL search software. A lipidomics quantitative analysis file can be a file output by lipid search software.

[0056] In this embodiment, the clinical information may be data in a tabular form. For example, the first column of the clinical information may be a sample identifier, the second column may be a sample group, and the remaining columns may be clinical indicator columns.

[0057] S220. Process the omics data using a pre-configured omics data processing method to obtain omics-processed data, wherein the omics data processing method includes one or more of a two-tailed Student's T test, multiple test correction, and one-way analysis of variance.

[0058] For example, a two-tailed Student's T-test can be performed on a single omics data set to obtain a P value (P value), which can then be corrected using the Benjamini & Hochberg (BH) multiple testing correction method to obtain a Q value (Q value). The P value is a parameter used to determine the results of a hypothesis test, and the Q value is the result after the P value is verified. If the omics data consists of more than two groups, a one-way analysis of variance is used to determine significance and the BH correction method is used for correction to obtain the omics processed data.

[0059] S230: Perform clinical indicator significance analysis on the clinical information to obtain clinical analysis information.

[0060] For example, a two-tailed Student's T test may be performed between each two comparison groups for each clinical indicator in the clinical information to compare whether the difference in the mean values ​​of the two groups is significant, thereby obtaining clinical analysis information.

[0061] In some embodiments, analysis of variance (ANOVA) may be performed on the clinical information to test the significance of the clinical indicators, and an Excel table may be generated for comparison and review.

[0062] S240: Merge the omics-processed data with the clinical analysis information to obtain data to be analyzed.

[0063] After the omics data processing and clinical information processing are completed, the omics processed data can be merged with the clinical analysis information to obtain the data to be analyzed.

[0064] S250: Determine the data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed.

[0065] S260: Analyze the data to be analyzed based on the data analysis method to obtain an analysis result chart.

[0066] The technical solution of the embodiment of the present invention obtains omics data and / or clinical information, and then processes the omics data through a pre-configured omics data processing method to obtain omics processed data, wherein the omics data processing method includes one or more of a two-tailed Student's T test, multiple test correction and one-way analysis of variance, and then performs clinical indicator significance analysis on the clinical information to obtain clinical analysis information, and merges the omics processed data with the clinical analysis information to obtain data to be analyzed so that the data can be subsequently analyzed.

[0067] Example 3

[0068] FIG3 is a flow chart of a data analysis method provided in Example 3 of the present invention. The method of this embodiment can be combined with the various optional schemes in the data analysis method provided in the above embodiments. The data analysis method provided in this embodiment has been further optimized. In some embodiments, the data analysis method includes one or more of an association analysis method, a cluster analysis method, an enrichment analysis method, and a MOFA analysis method.

[0069] As shown in FIG3 , the method includes:

[0070] S310 , obtaining data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information.

[0071] S320. Determine the data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed, wherein the data analysis method includes one or more of an association analysis method, a cluster analysis method, an enrichment analysis method, and a MOFA analysis method.

[0072] In this embodiment, association analysis methods can be used to mine molecular data relationships across different omics. Cluster analysis methods can be used to identify co-expressed molecules and regulatory relationships between molecules across data sets. Enrichment analysis methods can be used to perform distribution analysis on the data to be analyzed. MOFA analysis methods can be used to integrate the data to be analyzed.

[0073] S330: Analyze the data to be analyzed based on the data analysis method to obtain an analysis result chart.

[0074] It should be noted that the above-mentioned data analysis method can generate a record file during the analysis of the data to be analyzed to make the analysis process traceable; in some embodiments, the data processing intermediate files and operating parameters can also be retained to facilitate subsequent analysis and modification of the analysis result charts; in some embodiments, Excel tables and a variety of illustrated visual results can also be obtained through each data analysis method for users to quickly call.

[0075] Based on the above embodiments, in some embodiments, the data to be analyzed is analyzed based on a data analysis method to obtain an analysis result chart, including: analyzing the data to be analyzed based on an association analysis method to obtain an analysis result chart, wherein the association analysis method includes one or more of an interaction network analysis method, a bidirectional orthogonal partial least squares method, and a correlation determination method.

[0076] In this embodiment, the interaction network refers to a network that can characterize the interaction state between metabolism, lipids and proteins. Specifically, the molecules of each group identified can be searched from the relationship library, the biological connection can be extracted, and then a dynamic network diagram in HTML format can be generated. It should be noted that if there is a reaction relationship between protein and metabolism or lipid, a line will exist between the two points in the network diagram, thereby showing the interaction relationship. In the network diagram, blue circles can be used to represent metabolism and yellow circles to represent proteins. The larger the circle, the more molecules associated with it.

[0077] Bidirectional orthogonal partial least squares (O2PLS) can explore the internal connections between the two omics data from a holistic perspective, determine the degree of association between the two omics data, and identify the main proteins, metabolites, or lipids that cause this association. It should be noted that after bidirectional orthogonal partial least squares analysis, each omics can be divided into a joint part (the part with common changes in the two omics), an orthogonal part (the part that is unrelated in the two omics), and a noise part (some redundant information). The coefficients of the joint part obtained by O2PLS analysis can be used to draw a loading diagram to assist in interpreting the analysis results. At the same time, based on the input omics data type, an example diagram of the proportion of each part of the two omics will be automatically generated. The two omics loading diagrams can be merged into the same diagram, distinguished by different colors and shapes, for a more intuitive and convenient display.

[0078] Correlation determination involves performing a univariate linear fit on clinical and omics data to determine the proportion of the regression relationship explained by a single independent variable. This method of correlation analysis can generate a chord diagram. Wider lines indicate a higher correlation, with blue representing a negative correlation and red representing a positive correlation. In addition to chord diagrams, R value density plots can be generated by integrating all clinical information based on the distribution of R values.

[0079] Based on the above embodiments, in some embodiments, the data to be analyzed is analyzed based on a data analysis method to obtain an analysis result chart, including: analyzing the data to be analyzed based on a cluster analysis method to obtain an analysis result chart, wherein the cluster analysis method includes one or more of the Mfuzz multi-omics analysis method and the WGCNA analysis method.

[0080] In this embodiment, the Mfuzz multi-omics analysis method can determine the consistent change trend of multiple omics, provide data support for subsequent enrichment analysis and multi-omics correlation analysis, and discover the biological functions performed by a single class.

[0081] Specifically, the quantitative data for differentially expressed molecules across all comparison groups in the data to be analyzed are unioned. The median of the quantitative values ​​within each group is calculated based on sample grouping. The median is then selected for a coefficient of variation greater than 0.1, which serves as the input data for expression pattern clustering. First, the sample groups in the input data are sorted by time series or by degree of processing. The Fuzzy C-Means Clustering (FCM) algorithm is then used to automatically classify the grouped data. By optimizing the objective function, the membership of each group's molecules to all cluster centers is determined, thereby determining the class of the molecules within the group. Based on the given class, the expression trends of the molecules within the group are grouped. Molecules within the same class with the same expression trends are assigned a membership value, representing the probability of their belonging to that class. Molecules with the same trend are then classified. Proteins, metabolic molecules, and lipid molecules with the same trend are grouped together. The classification results are saved and visualized using a combination of heatmaps and line charts, with membership values ​​represented by gradient colors.

[0082] Furthermore, different omics data can be separated, grouping information can be recorded, and corresponding enrichment analysis can be performed on each class in the single omics to characterize the biological processes involved under the same expression trend. Different display formats such as bubble charts, heat maps, and line charts can be used.

[0083] It should be noted that the Mfuzz method can be used for clustering, so as to divide the molecules of various omics into a custom number of clusters with the same trend. After the division is completed, the bubble chart and the corresponding enrichment result table can be obtained according to the results after the enrichment analysis. The enrichment analysis includes a variety of different analysis methods, which are not limited here. The heat map can include a variety of different heat maps. For example, the heat map can include a first heat map and a second heat map. The first heat map can be obtained according to the Mfuzz results, and the second heat map can be obtained according to the ratio of different comparison groups to the baseline. The line graph is related to the Mfuzz display. Unlike the enrichment analysis of the marked positions, the single-omics separate enrichment is still used here, that is, only the Mfuzz method is used to mark the clusters, and then each omics and clinical data will be separated and processed separately. In some embodiments, the single-omics enrichment method can be added to the subsequent enrichment analysis for subsequent data analysis.

[0084] In order to facilitate the study of the relationship between various omics in a single class and thus discover the connection between upstream and downstream in the biological process, after the person / spearman correlation calculation was performed on multiple omics data belonging to the same cluster group, the results were plotted using the interactive multi-omics interaction network analysis method.

[0085] The WGCNA analysis method is an analysis method applied to the gene expression patterns of multiple samples. It clusters genes with similar expression patterns and analyzes the relationship between modules and specific traits or phenotypes. In this example, the WGCNA analysis method was used to identify whether there is co-expression between various protein molecules and metabolites, cluster them into the same module, identify key molecules within them, and visualize the analysis results.

[0086] On the basis of the above embodiments, optionally, the data to be analyzed is analyzed based on a data analysis method to obtain an analysis result chart, including: analyzing the data to be analyzed based on an enrichment analysis method to obtain an analysis result chart, wherein the enrichment analysis method includes one or more of a single-omics enrichment method, a multi-omics co-enrichment method, and a gene set enrichment analysis.

[0087] In this embodiment, the single-omics enrichment method refers to a method of performing enrichment analysis on each single-omics separately.

[0088] Multi-omics co-enrichment methods use detected proteins, metabolites, and lipid molecules as background and differential molecules as foreground. Specifically, hypergeometric distribution can be used This method examines the significance of a specific functional class within a set of differentially expressed molecules. Through discrete distribution significance analysis, enrichment analysis, and false positive analysis, we identify protein metabolic functional categories that are significantly associated with the experimental objectives and have a low false positive rate. Here, N is the number of molecules with pathway annotations; n is the number of differentially expressed molecules within N; M is the number of proteins annotated to a specific pathway among all molecules; and m is the number of differentially expressed molecules annotated to a specific pathway. The significance of the enrichment results is expressed as a p-value. The p-value is corrected using the BH method to obtain a p.adjust value. Pathways meeting this threshold of p.adjust < 0.05 are then selected as significantly enriched. Bubble charts and bar graphs are used for visualization.

[0089] In this example, the Gene Set Enrichment Analysis (GSEA) specifically involves ranking the differential expression levels of molecules in two samples, and then determining whether the database used for GSEA tends to cluster at the top or bottom of the ordered list, thereby determining whether the group of molecules is statistically significant between the two comparison groups.

[0090] Based on the above embodiments, in some embodiments, the data to be analyzed is analyzed based on a data analysis method to obtain an analysis result chart, including: analyzing the data to be analyzed based on a MOFA analysis method to obtain an analysis result chart.

[0091] In this embodiment, MOFA is a multi-omics data integration method based on the Bayesian group factor analysis framework, which uses lower-dimensional latent factors to show the overall variability of each omics molecular feature. This method is applicable to a wide range of data types, such as discrete, continuous, and binary, and can be used for both large and small sample data. It can be used for missing value estimation and provides new ideas for multi-omics data mining from a factor perspective. It also has a wide range of downstream analysis methods and rich mapping methods, including variance decomposition, feature weight checking, enrichment analysis, sample cluster analysis, latent factor visualization, molecular correlation heat maps with high contribution in factors, correlation network diagrams, expression calorimetry, and so on.

[0092] In some embodiments, the database may include, but is not limited to, a multi-omics co-enrichment database, a KEGG-based biological response relationship database, and a multi-omics database suitable for GSEA analysis.

[0093] Among them, the multi-omics co-enrichment database is a multi-omics database based on the Fisher exact test enrichment method. This database realizes the co-enrichment of multiple omics data. The enrichment results can be compared with the single-omics enrichment results, which is more conducive to discovering the molecular mechanism of biological functions. The database based on the biological reaction relationship of KEGG can be used to extract protein, metabolism, and lipid reaction relationships, establish a multi-omics reaction relationship library, and use the database based on the biological reaction relationship of KEGG to draw a multi-omics reaction network diagram and determine the regulatory relationship between omics. The multi-omics database suitable for GSEA analysis is a multi-omics database used for GSEA analysis method, which is typeset and stored in gmt format and gmx format.

[0094] The technical solution of the embodiment of the present invention analyzes the data to be analyzed through one or more of the association analysis method, cluster analysis method, enrichment analysis method and MOFA analysis method to obtain analysis result charts, realizes automatic generation of charts, and thus improves data analysis efficiency.

[0095] Example 4

[0096] FIG4 is a flow chart of a data analysis method provided in Example 4 of the present invention. The method of this embodiment can be combined with the various optional schemes in the data analysis method provided in the above embodiment. The data analysis method provided in this embodiment has been further optimized. In some embodiments, the data analysis method is determined based on the data type of each data in the data to be analyzed, including: if the data type includes the data type of multiple omics data, then the data analysis method is determined to be a multi-omics data analysis method; if the data type includes clinical information and the data type of a single omics data, then the data analysis method is determined to be a data fitting analysis method; if the data type includes clinical information and the data type of multiple omics data, then the data analysis method is determined to be a multi-omics data analysis method and / or a data fitting analysis method; accordingly, the data to be analyzed is analyzed based on the data analysis method to obtain an analysis result chart, including: analyzing the data to be analyzed based on the multi-omics data analysis method and / or the data fitting analysis method to obtain an analysis result chart.

[0097] As shown in FIG4 , the method includes:

[0098] S410: Acquire data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information.

[0099] S420. Determine the data type of each data in the data to be analyzed. If the data type includes the data type of multiple omics data, determine that the data analysis method is a multi-omics data analysis method; if the data type includes clinical information and the data type of a single omics data, determine that the data analysis method is a data fitting analysis method; if the data type includes clinical information and the data type of multiple omics data, determine that the data analysis method is a multi-omics data analysis method and / or a data fitting analysis method.

[0100] In this embodiment, a multi-omics data analysis method refers to a method for analyzing and processing multiple omics data. Exemplarily, the multi-omics data analysis method may include, but is not limited to, the Mfuzz multi-omics analysis method, bidirectional orthogonal partial least squares, and the like. A data fitting analysis method refers to a method for fitting clinical information and omics data. Exemplarily, the data fitting analysis method may include, but is not limited to, correlation determination methods and WGCNA analysis methods.

[0101] S430 , analyzing the data to be analyzed based on the multi-omics data analysis method and / or the data fitting analysis method to obtain an analysis result chart.

[0102] Exemplarily, if the data type includes clinical information and data types of multiple omics data, the data analysis method is determined to be the Mfuzz multi-omics analysis method, bidirectional orthogonal partial least squares, correlation determination method and WGCNA analysis method; then, based on the Mfuzz multi-omics analysis method, bidirectional orthogonal partial least squares, correlation determination method and WGCNA analysis method, the data to be analyzed are analyzed respectively to obtain analysis result charts corresponding to each analysis method.

[0103] The technical solution of the embodiment of the present invention determines the data analysis method according to the data type of each data in the data to be analyzed, realizes the automatic determination of the data analysis method, and provides a guarantee for realizing automated data analysis.

[0104] Example 5

[0105] FIG5 is a schematic diagram of the structure of a data analysis device provided in Example 5 of the present invention. As shown in FIG5 , the device includes:

[0106] An analysis data acquisition module 510 is configured to acquire data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information;

[0107] An analysis method determination module 520 is configured to determine a data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed;

[0108] The result chart determination module 530 is configured to analyze the data to be analyzed based on the data analysis method to obtain an analysis result chart.

[0109] The technical solution of the embodiment of the present invention obtains data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data and clinical information, thereby achieving the acquisition of multiple combinations of data, and then determining the data type of each data in the data to be analyzed, determining the data analysis method based on the data type of each data in the data to be analyzed, achieving automatic determination of the data analysis method, and then analyzing the data to be analyzed based on the automatically determined data analysis method to obtain analysis result charts, thereby achieving integrated automatic analysis from data to charts, thereby improving data analysis efficiency.

[0110] In some embodiments, the analysis data acquisition module 510 is further configured to:

[0111] Access to omics data and / or clinical information;

[0112] Processing the omics data using a pre-configured omics data processing method to obtain omics processed data, wherein the omics data processing method includes one or more of a two-tailed Student's T test, multiple test correction, and one-way analysis of variance;

[0113] Performing clinical indicator significance analysis on the clinical information to obtain clinical analysis information;

[0114] The omics processed data is combined with the clinical analysis information to obtain data to be analyzed.

[0115] In some embodiments, the data analysis method includes one or more of an association analysis method, a cluster analysis method, an enrichment analysis method, and a MOFA analysis method.

[0116] In some embodiments, the result chart determination module 530 is further configured to:

[0117] The data to be analyzed is analyzed based on the association analysis method to obtain an analysis result chart, wherein the association analysis method includes one or more of an interaction network analysis method, a bidirectional orthogonal partial least squares method, and a correlation determination method.

[0118] In some embodiments, the result chart determination module 530 is further configured to:

[0119] The data to be analyzed is analyzed based on the cluster analysis method to obtain an analysis result chart, wherein the cluster analysis method includes one or more of the Mfuzz multi-omics analysis method and the WGCNA analysis method.

[0120] In some embodiments, the result chart determination module 530 is further configured to:

[0121] The data to be analyzed are analyzed based on the enrichment analysis method to obtain an analysis result chart, wherein the enrichment analysis method includes one or more of a single-omics enrichment method, a multi-omics co-enrichment method, and a gene set enrichment analysis.

[0122] In some embodiments, the result chart determination module 530 is further configured to:

[0123] The data to be analyzed is analyzed based on the MOFA analysis method to obtain an analysis result chart.

[0124] In some embodiments, the analysis method determination module 520 is further configured to:

[0125] If the data type includes data types of multiple omics data, determining the data analysis method as a multi-omics data analysis method;

[0126] If the data types include clinical information and single-omics data types, the data analysis method is determined to be a data fitting analysis method;

[0127] If the data type includes clinical information and a plurality of omics data types, determining the data analysis method to be a multi-omics data analysis method and / or a data fitting analysis method;

[0128] Accordingly, the result chart determination module 530 is further configured to:

[0129] The data to be analyzed are analyzed based on the multi-omics data analysis method and / or the data fitting analysis method to obtain an analysis result chart.

[0130] The data analysis device provided in the embodiment of the present invention can execute the data analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0131] Example 6

[0132] FIG6 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0133] As shown in FIG6 , the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, that is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An I / O interface 15 is also connected to the bus 14.

[0134] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0135] The processor 11 may be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a data analysis method, which includes:

[0136] Acquiring data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information;

[0137] Determining the data type of each data in the data to be analyzed, and determining a data analysis method based on the data type of each data in the data to be analyzed;

[0138] The data to be analyzed is analyzed based on the data analysis method to obtain an analysis result chart.

[0139] In some embodiments, the data analysis method may be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data analysis method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data analysis method in any other appropriate manner (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0144] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0145] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0146] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0147] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A data analysis method, characterized in that: include: Acquiring data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data, and clinical information; Determine the data type of each data in the data to be analyzed, and determine the data analysis method based on the data type of each data in the data to be analyzed; The data to be analyzed is analyzed based on the data analysis method to obtain an analysis result chart.

2. The method according to claim 1, characterized in that The obtaining of the data to be analyzed includes: Access to omics data and / or clinical information; Processing the omics data by a pre-configured omics data processing method to obtain omics processed data, wherein the omics data processing method includes one or more of a two-tailed Student's T test, multiple test correction, and one-way analysis of variance; Performing clinical indicator significance analysis on the clinical information to obtain clinical analysis information; The omics processing data is combined with the clinical analysis information to obtain data to be analyzed.

3. The method according to claim 1, characterized in that The data analysis method includes one or more of an association analysis method, a cluster analysis method, an enrichment analysis method and a MOFA analysis method.

4. The method according to claim 3, characterized in that The step of analyzing the data to be analyzed based on the data analysis method to obtain an analysis result chart includes: The data to be analyzed are analyzed based on the association analysis method to obtain an analysis result chart, wherein the association analysis method includes one or more of an interaction network analysis method, a bidirectional orthogonal partial least squares method, and a correlation determination method.

5. The method according to claim 3, characterized in that: The step of analyzing the data to be analyzed based on the data analysis method to obtain an analysis result chart includes: The data to be analyzed are analyzed based on the cluster analysis method to obtain an analysis result chart, wherein the cluster analysis method includes one or more of the Mfuzz multi-omics analysis method and the WGCNA analysis method.

6. The method according to claim 3, characterized in that The step of analyzing the data to be analyzed based on the data analysis method to obtain an analysis result chart includes: The data to be analyzed are analyzed based on the enrichment analysis method to obtain an analysis result chart, wherein the enrichment analysis method includes one or more of a single-omics enrichment method, a multi-omics co-enrichment method, and a gene set enrichment analysis.

7. The method according to claim 3, characterized in that The step of analyzing the data to be analyzed based on the data analysis method to obtain an analysis result chart includes: The data to be analyzed is analyzed based on the MOFA analysis method to obtain an analysis result chart.

8. The method according to claim 1, characterized in that The determining of the data analysis method based on the data type of each data in the data to be analyzed includes: If the data type includes data types of multiple omics data, determining the data analysis method to be a multi-omics data analysis method; If the data types include clinical information and data types of single-omics data, determining the data analysis method as a data fitting analysis method; If the data type includes clinical information and data types of multiple omics data, determining the data analysis method to be a multi-omics data analysis method and / or a data fitting analysis method; Correspondingly, the data to be analyzed is analyzed based on the data analysis method to obtain an analysis result chart, including: The data to be analyzed are analyzed based on the multi-omics data analysis method and / or the data fitting analysis method to obtain an analysis result chart.

9. A data analysis device, characterized in that: include: An analysis data acquisition module, used to acquire data to be analyzed, wherein the data to be analyzed includes at least two of proteomics data, metabolomics data, lipidomics data and clinical information; An analysis method determination module, used to determine the data type of each data in the data to be analyzed, and determine a data analysis method based on the data type of each data in the data to be analyzed; The result chart determination module is used to analyze the data to be analyzed based on the data analysis method to obtain an analysis result chart.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data analysis method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the data analysis method according to any one of claims 1 to 8 when executed.

Citation Information

Patent Citations

  • Chest enhanced CT image processing method based on traditional radiomics

    CN113706435A

  • Integrated, molecular, omics, immunotherapy, metabolic, epigenetic, and clinical database

    CN114023403A

  • Multi-omics data integration analysis method and online interactive comprehensive analysis platform

    CN114203259A

  • Application of urine protein in diagnosis of metabolic liver disease

    CN114280300A

  • Data analysis method and device, electronic equipment and storage medium

    CN116230247A