CN112509704A - Acute coronary syndrome early warning method and device based on metabonomics data - Google Patents
Acute coronary syndrome early warning method and device based on metabonomics data Download PDFInfo
- Publication number
- CN112509704A CN112509704A CN202110157589.6A CN202110157589A CN112509704A CN 112509704 A CN112509704 A CN 112509704A CN 202110157589 A CN202110157589 A CN 202110157589A CN 112509704 A CN112509704 A CN 112509704A
- Authority
- CN
- China
- Prior art keywords
- acute coronary
- coronary syndrome
- early warning
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/04—Preparation or injection of sample to be analysed
- G01N30/06—Preparation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention discloses an acute coronary syndrome early warning method and device based on metabonomics data, wherein the method comprises the following steps: obtaining metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual; screening out differential metabolite data; according to the different metabolite data, machine learning is carried out on the LightGBM model to obtain an acute coronary syndrome early warning model, and the acute coronary syndrome early warning model comprises the following components: a plurality of biomarkers for diagnosing acute coronary syndrome; and according to the acute coronary syndrome early warning model, acquiring an index value of the biological individual to be diagnosed corresponding to each biomarker, judging whether the index value of each biomarker exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to a judgment result. The invention can perform early warning on the acute coronary syndrome of the patient according to the metabolite data of the patient, and realize non-invasive early warning.
Description
Technical Field
The invention relates to the field of machine learning application, in particular to an acute coronary syndrome early warning method and device based on metabonomics data.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
Coronary heart disease (CAD), also known as Coronary atherosclerotic heart disease, is a metabolic disorder that is a combination of genes and the environment and has become one of the leading causes of death in developed and developing countries. CAD can be divided into different categories according to its clinical symptoms, arterial obstruction and degree of myocardial damage: stable coronary heart disease (sCAD), unstable angina pectoris (UA), and Acute Myocardial Infarction (AMI), where UA and AMI are also known as Acute Coronary Syndrome (ACS). ACS is mostly caused by sudden intraluminal thrombosis AS a result of Atherosclerotic (AS) plaque rupture or erosion. Atherosclerosis belongs to a lipid-driven inflammatory disease of an artery intima, the level of oxidized low-density lipoprotein (LDL) is increased due to risk factors such as hyperlipidemia and high cholesterol, so that the artery intima is damaged, mononuclear cells on intima skin phagocytize lipid to form foam cells, and atherosclerotic lesion, namely lipid stripes, is formed, then lesion is generated under the action of various growth factors and proinflammatory mediators, fibrous plaque is formed, and rupture occurs when the plaque is unstable, so that acute thrombosis is caused. Due to the dynamics and complexity of coronary heart disease, the mechanisms of formation, development and displacement of inflammatory unstable plaques remain unclear, and therefore identification of biomarkers of rupture of coronary artery plaques in ACS patients is crucial to prevent their transition from stable to unstable states and to prevent thrombosis.
At present, genomics research has been successful in identifying genetic variation affecting major risk factors such as cholesterol level, but it is still necessary to find new specific susceptibility genes, drug action targets and biomarkers for predicting ACS risk to increase the understanding of medical staff on the pathological mechanism of ACS. The existing coronary heart disease diagnosis method has the defects of poor sensitivity and specificity, invasiveness and the like, and is difficult to realize the early diagnosis of ACS.
Metabonomics is a new omics technology which appears after genomics, transcriptomics and proteomics and becomes a powerful tool for researching metabolic processes, identifying biomarkers and disclosing metabolic mechanisms, so that a dynamic regulation and control network of coronary heart disease is deeply excavated by using metabonomics means, the basis of key signal paths is explored, molecular markers are searched, an early diagnosis and treatment method of coronary heart disease is established, and the metabonomics has important significance for reducing the incidence rate and the fatality rate of the coronary heart disease.
With the progress of metabonomic analysis instruments and analysis methods, the number of detected metabolites in biological samples is increasing, and the data volume is also becoming huge. Therefore, how to fully consider the metabolic characteristics of the acute coronary syndrome patient and determine a model for early warning the acute coronary syndrome according to metabolite data is a technical problem to be solved urgently at present.
Disclosure of Invention
The embodiment of the invention provides an acute coronary syndrome early warning method based on metabonomics data, which is used for solving the technical problem that the prior art can not realize the early warning of the acute coronary syndrome based on metabolite data, and comprises the following steps: obtaining metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual; screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals; according to the different metabolite data, machine learning is carried out on the LightGBM model to obtain an acute coronary syndrome early warning model, wherein the acute coronary syndrome early warning model comprises the following components: a plurality of biomarkers for diagnosing acute coronary syndrome; and according to the acute coronary syndrome early warning model, acquiring an index value of the biological individual to be diagnosed corresponding to each biomarker, judging whether the index value of the biological individual to be diagnosed corresponding to each biomarker exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to a judgment result.
The embodiment of the invention also provides an acute coronary syndrome early warning device based on metabonomics data, which is used for solving the technical problem that the prior art can not realize the early warning of the acute coronary syndrome based on metabolite data, and comprises the following components: the metabolite data acquisition module is used for acquiring metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual; the differential metabolite screening module is used for screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals; the model learning module is used for performing machine learning on the LightGBM model according to the different metabolite data to obtain an acute coronary syndrome early warning model, wherein the acute coronary syndrome early warning model comprises: a plurality of biomarkers for diagnosing acute coronary syndrome; and the acute coronary syndrome early warning module is used for acquiring the index value of each biomarker corresponding to the biological individual to be diagnosed according to the acute coronary syndrome early warning model, judging whether the index value of each biomarker corresponding to the biological individual to be diagnosed exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to the judgment result.
The embodiment of the invention also provides computer equipment for solving the technical problem that the prior art can not realize the early warning of the acute coronary syndrome based on the metabolite data, the computer equipment comprises a memory, a processor and a computer program which is stored on the memory and can be operated on the processor, and the processor realizes the early warning method of the acute coronary syndrome based on the metabonomic data when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which is used for solving the technical problem that the prior art cannot realize the early warning of the acute coronary syndrome based on the metabolite data, and the computer readable storage medium stores a computer program for executing the acute coronary syndrome early warning method based on the metabonomics data.
In the embodiment of the invention, after the metabolite data of the normal coronary artery organism individual and the acute coronary syndrome organism individual are obtained, the differential metabolite data are screened out according to the metabolite data of the normal coronary artery organism individual and the acute coronary syndrome organism individual, then the LightGBM model is subjected to machine learning according to the screened out differential metabolite data, an acute coronary syndrome early warning model containing multiple biomarkers is obtained, so that the index value of each biomarker corresponding to the organism individual to be diagnosed is collected based on the acute coronary syndrome early warning model, whether the index value of each biomarker corresponding to the organism individual to be diagnosed exceeds a preset normal value range is judged, and corresponding early warning information is output according to the judgment result.
The embodiment of the invention can provide a non-invasive early warning method for acute coronary syndrome, and the early warning of the acute coronary syndrome is carried out on a patient according to the metabolite data of the patient.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart of an acute coronary syndrome early warning method based on metabonomics data according to an embodiment of the present invention;
FIG. 2 is a flow chart of machine learning provided in an embodiment of the present invention;
FIG. 3 is a flow chart of metabolite data acquisition provided in an embodiment of the present invention;
fig. 4 is an AUROC graph of an acute coronary syndrome early warning model provided in an embodiment of the present invention;
fig. 5 is a schematic diagram of an acute coronary syndrome early warning result based on metabonomics data provided in an embodiment of the present invention;
fig. 6 is a schematic diagram of an acute coronary syndrome early warning device based on metabonomics data according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an alternative acute coronary syndrome early warning device based on metabonomics data according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a computer device provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment of the invention provides an acute coronary syndrome early warning method based on metabonomics data, and fig. 1 is a flow chart of the acute coronary syndrome early warning method based on metabonomics data provided by the embodiment of the invention, and as shown in fig. 1, the method comprises the following steps:
s101, obtaining metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual.
The normal coronary organism individuals refer to people who do not suffer from the acute coronary syndrome (i.e., normal people); the biological individual of the acute coronary syndrome refers to a population (namely a patient) suffering from the acute coronary syndrome; the metabolite data in the present embodiment refers to data of various biological metabolites obtained by analyzing a plasma sample of a subject.
S102, screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals.
It should be noted that by analyzing the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals, one or more metabolites with differences can be screened.
S103, according to the different metabolite data, machine learning is carried out on the LightGBM model to obtain an acute coronary syndrome early warning model, wherein the acute coronary syndrome early warning model comprises the following components: a plurality of biomarkers for diagnosing acute coronary syndrome.
It should be noted that the acute coronary syndrome early warning model refers to a model which is obtained by training a machine learning model and can early warn acute coronary syndrome according to metabolite data.
In specific implementation, different machine learning algorithms, such as linear regression, random forest, etc., may be used according to experimental conditions, biological sample differences, and applicable conditions. In the embodiment of the invention, a light GBM (light Gradient Boosting machine) model is selected for machine learning training, and the model has the advantages of higher training efficiency, low memory usage, higher accuracy, support of parallelization learning, capability of processing large-scale data and the like.
And S104, acquiring the index value of each biomarker corresponding to the biological individual to be diagnosed according to the acute coronary syndrome early warning model, judging whether the index value of each biomarker corresponding to the biological individual to be diagnosed exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to the judgment result.
The biological subject to be diagnosed refers to a population unknown to have acute coronary syndrome. According to the acute coronary syndrome early warning method based on metabonomics data provided by the embodiment of the invention, the acute coronary syndrome early warning information of the biological individual to be diagnosed can be output in any form of characters, voice and the like.
According to the acute coronary syndrome early warning method based on metabonomics data provided by the embodiment of the invention, the obtained acute coronary syndrome early warning comprises the following biomarkers: 2-hydroxybutyric acid, dihydropyrimidine, succinic acid, 2, 3-dihydroxybutyric acid, salicylic acid, lysine, rhamnol-1, 4-lactone, dopaquinone, aconitic acid, N-acetyl-L-phenylalanine, hydroxyethyllysine, pantothenic acid, 3-hydroxy-L-kynurenine, N-formylkynurenine, glucose-6-phosphate, pretyrosine, 6-phospho-2-dehydrogluconic acid, retinoic acid, clopidogrel carboxylic acid, leukotriene B4, galactose, 7 alpha-hydroxycholesterol, 4-phosphopantysteine.
As shown in fig. 2, the acute coronary syndrome early warning method based on metabonomics data provided in the embodiment of the present invention may further implement training of an acute coronary syndrome early warning model by the following steps:
s201, dividing the differential metabolite data into training data and testing data according to a preset proportion;
s202, training the LightGBM model according to the training data to obtain an acute coronary syndrome early warning model;
and S203, verifying the trained acute coronary syndrome early warning model according to the test data.
In particular implementation, 70% of the data in the metabolomics data sample can be used as training data, and 30% of the data can be used as test data.
It should be noted that in the acute coronary syndrome early warning method based on metabonomic data provided in the embodiment of the present invention, in the process of performing machine learning on the LightGBM model, the GridSearchCV algorithm and the Hyperopt algorithm may be used to adjust model parameters.
In an embodiment, as shown in fig. 3, the acute coronary syndrome early warning method based on metabonomics data provided in the embodiment of the present invention can further obtain metabolite data of the normal coronary artery organism individual and the acute coronary syndrome organism individual by the following steps:
s301, collecting plasma samples of normal coronary artery biological individuals and acute coronary syndrome biological individuals;
s302, analyzing plasma samples of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals by using a liquid chromatography-mass spectrometry combined analysis method to obtain metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals.
In the embodiment of the invention, the plasma samples of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals are analyzed by using a liquid chromatography-mass spectrometry combined analysis method, and the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals can be obtained.
In an embodiment, the acute coronary syndrome early warning method based on metabonomics data provided in the embodiment of the present invention may further include: and determining the importance degree of different biomarkers in the acute coronary syndrome early warning model by adopting a Boruta algorithm.
It should be noted that the goal of Boruta is to select all feature sets related to dependent variables, rather than selecting a feature set that minimizes the cost function of a model for a particular model. The significance of the Boruta algorithm is that the influence factors of dependent variables can be more comprehensively understood, so that feature selection can be performed better and more efficiently. Boruta is a feature selection package in python, and after the package is installed, the historical information of relative abundance of differential metabolites is input, so that important features suitable for modeling can be obtained. The specific algorithm steps are as follows: (1) creating shadow features (shadow feature), namely randomly disordering the sequence of each real feature R to obtain a shadow feature matrix S, and splicing the shadow feature matrix S behind the real features to form a new feature matrix N = [ R, S ]; (2) training a model by using the new feature matrix N as input to obtain real features and shadow features; (3) taking the maximum value of the shadow features, recording one-time hit when the value in the real features is larger than the maximum value; (4) accumulating hits using the true features recorded in (3), with the tag feature being significant or insignificant; (5) the insignificant features are deleted and (1) - (4) are repeated until all features are marked.
The acute coronary syndrome early warning method based on metabonomics data provided by the embodiment of the invention can comprise the following steps of:
firstly, metabonomics sample pretreatment: blood samples were collected and plasma was centrifuged within one hour and immediately stored in a-80 ℃ freezer. For sample pretreatment, 100. mu.l of plasma was precisely pipetted into a 10 ml glass tube, 20. mu.l of a mixing standard was added, 3ml of MeOH/MTBE (1:1, V/V) was added to precipitate proteins, the mixture was vortexed at 2500 rpm for 5min, then centrifuged at 4200 rpm at 4 ℃ for 10min, and the supernatant was pipetted into another glass tube. 3ml of MTBE and 1.2 ml of H are added2O, vortexed at 2500 rpm for 15min, 4200 rpm, centrifuged at 4 ℃ for 10min, the lower aqueous phase was transferred to a 2 ml EP tube, dried with nitrogen, and 100. mu.L ACN: H was added2O (2: 98, V/V) redissolving, vortexing the redissolved sample at 2500 rpm for 5min, centrifuging at 4 ℃ and 12500 for 5min, separating supernatant, filtering by a 96-well plate, and then injecting sample for analysis.
Secondly, LC-HRMS analysis conditions: performing metabonomic data acquisition by using a liquid chromatography-mass spectrometry combined analysis method, wherein a Waters acquisition UPLC HSS T3 chromatographic column (2.1 × 100 mm, 1.8 μm) is selected as the chromatographic column; the sample injection amount is 10 mu L; the column temperature was 35 ℃; the flow rate was 0.25 ml/min. Mobile phase A: H2O (0.1% formic acid); and the mobile phase B is ACN. The mobile phase gradients are shown in table 1 and the mass spectrometry conditions are shown in table 2.
TABLE 1 gradient of mobile phase
TABLE 2 Mass Spectrometry conditions
Thirdly, metabonomics data processing and differential metabolite screening: and (3) leading the original data obtained by LC-HRMS analysis into Progenetics QI for peak identification, peak alignment and data normalization to obtain a two-dimensional data matrix containing information such as mass-to-charge ratio, retention time, original peak area and normalized peak area, and performing data quality evaluation by adopting a QC sample. The data after quality control is based onMummichogThe metabonomics processing method of the metabolic pathway mapping of the algorithm is used for quickly matching molecular weight information and detected ion information in a metabolite database with proper mass-to-charge ratio tolerance, carrying out high-throughput temporary labeling on metabolites and directly mapping the metabolites into a metabolic pathway based on a KEGG database, and modularly analyzing differences among groups through the overall change of the metabolic pathway and the correlation of metabolic reactions, thereby efficiently finding and identifying reliable biomarkers with biological significance. And identifying the structure of the metabolite of the differential metabolite obtained by the primary identification by using an LC-MS/MS technology, and comparing the metabolite of the obtained standard substance with the standard substance to further confirm the structure. For metabolites whose structure cannot be determined because of low abundance or no inclusion in the secondary database and no availability of standards, preliminary identification results are temporarily employed. And then establishing a model for the finally obtained differential metabolite abundance information for prediction.
Fourthly, building a prediction model and carrying out model verification by using external data based on a LightGBM machine learning algorithm:
(1) feature selection was performed using the Boruta algorithm.
(2) GridSearchCV (grid search) adjusting parameters, namely adjusting the parameters in sequence according to the step length in a specified parameter range, training a learner by using the adjusted parameters, and finding the parameter with the highest precision on the verification set from all the parameters, which is a loop and comparison process.
(3) Modeling a LightGBM; LightGBM is a model which is stronger and faster than Xgboost, has great improvement in performance, and has the advantages compared with the traditional algorithm: the method has the advantages of higher training efficiency, low memory use, higher accuracy, support of parallelization learning and capability of processing large-scale data.
(4) Selecting important features in the model, and modeling again;
(5) and the Hyperopt is a tool for adjusting the parameters through Bayesian optimization, and the method has higher speed and better effect. In addition, the Hyperopt is combined with the MongoDB to carry out distributed parameter adjustment, so that relatively excellent parameters can be quickly found;
(6) LightGBM modeling prediction;
(7) and (3) acquiring a batch of external data which never participate in modeling, using the constructed model for predicting the batch of data, and judging whether the prediction model is good or bad through AUROC.
And fifthly, obtaining an acute coronary syndrome early warning model aiming at normal people based on the algorithm, wherein the marker information adopted by the model is shown in the table 3.
TABLE 3 biomarker signature
In Table 3, "+" indicates that the protein has passed through LC-MS2Identified metabolites; "#" represents the identified metabolite compared to the standard substance; the other is primary mass spectrum identification.
Fig. 4 shows AUROC graphs of the early warning model of acute coronary syndrome, and as shown in fig. 4, AUROC of training data is 0.98491, and AUROC of test data is 0.97166. Figure 5 shows a number of acute coronary syndrome biomarkers and their degree of importance screened from metabolomic data.
The following describes an embodiment of the present invention with reference to a specific example:
clinical grouping criteria: according to the clinical characteristics of coronary atherosclerotic heart disease, participants were divided into 2 groups including ST-elevation acute myocardial infarction (STEMI, unstable plaque rupture group, myocardial necrosis); non-ST elevation acute myocardial infarction (NSTEMI, unstable plaque partial rupture group, myocardial minor necrosis) and unstable angina (UAP, plaque endangered rupture or pre-rupture unstable group, myocardial minor necrosis), i.e., ACS group, N = 102; ② normal control group without atherosclerotic plaque, namely normal coronary artery array group, NCA, N = 93. On the basis of clinical information collection, blood samples of all groups of people are collected, and metabonomics analysis is carried out after plasma is obtained through centrifugation.
(1) Study subjects:
and (3) inclusion standard: stable coronary heart disease (old myocardial infarction, PCI history, stable angina or "healthy person" without clinical ischemic symptoms, with coronary stenosis >50% found by CT/contrast imaging).
Exclusion criteria:
1) myocardial infarction type 2-5 as diagnosed by the international general myocardial infarction definition;
2) severe heart failure/cardiogenic shock (Killip grade >2 or NYHA grade > 2);
3) mechanical complications (perforation of the ventricular septum, rupture of the free wall, rupture of the papillary muscle, etc.);
4) sudden cardiac arrest and/or cardiopulmonary resuscitation after the onset;
5) any antibiotic taken orally or intravenously within 3 months is more than or equal to 1 week;
6) acute Coronary Syndrome (ACS) or coronary revascularization (including PCI and CABG) within 3 months;
7) trauma or surgery within 3 months;
8) history of cerebrovascular disease (including cerebral infarction or cerebral hemorrhage) within 3 months;
9) bleeding of the upper or lower digestive tract within 3 months;
10) clear infection (including digestive tract, respiratory tract, body surface infection, etc.) within 3 months;
11) chronic intestinal diseases (e.g., Crohn's disease, ulcerative colitis, etc.);
12) any tumor;
13) rheumatic immune diseases;
14) chronic kidney disease, including after kidney transplantation.
(2) Study enrollment and case information collection procedure
1) Informed consent;
2) inclusion/exclusion criteria;
3) patient lifestyle questionnaires clinical data;
4) on the basis of clinical information collection, blood and fresh or properly frozen excrement of all groups of people are collected for omics analysis.
(3) The clinical study was performed in compliance with the requirements of the declaration of Helsinki of the world medical society and the relevant national regulations, and all clinical patients participating in the experiment signed the informed consent form of the subject.
(II) the implementation method comprises the following steps:
(1) clinical sample collection and pretreatment: metabolomics data was collected for 195 participants (biological individuals). The collected metabolomics data were divided into the following two groups according to diagnostic guidelines and exclusion criteria: NCA group (N = 93), ACS group (N = 102).
Blood samples of each participant in the morning and with a fasting time of more than 10 hours are collected, and relevant clinical routine biomarker detection is completed by a hospital, wherein all detection is performed according to an international standard method. After the test, the samples were collected in tubes containing heparin sodium, cooled to 4 ℃, centrifuged to take plasma (1,350 rpm, centrifugation for 12 minutes) within 1 hour, aliquoted and stored in a refrigerator at-80 ℃.
Sample pretreatment before metabonomics analysis is carried out on the collected sample, and the pretreatment comprises the following steps:
mu.l of plasma was pipetted precisely into a 10 ml glass tube, 20. mu.l of the mix was added, 3ml of MeOH/MTBE (1:1, V/V) was added to precipitate the proteins, vortexed at 2500 rpm for 5min, then centrifuged at 4200 rpm at 4 ℃ for 10min, and the supernatant was pipetted into another glass tube. 3ml of MTBE and 1.2 ml of H are added2O, vortexed at 2500 rpm for 15min, 4200 rpm, centrifuged at 4 ℃ for 10min, the lower aqueous phase was transferred to a 2 ml EP tube and blown dry with nitrogenThen, 100. mu.L of ACN: H was added2O (2: 98, V/V) redissolving, vortexing the redissolved sample at 2500 rpm for 5min, centrifuging at 4 ℃ and 12500 for 5min, separating supernatant, filtering by a 96-well plate, and then injecting sample for analysis.
(2) LC-HRMS analysis conditions: performing metabonomic data acquisition by using a liquid chromatography-mass spectrometry combined analysis method, wherein a liquid chromatography system selects a Waters two-dimensional ACQUITY UPLC system which comprises a binary ultrahigh pressure gradient pump, a quaternary ultrahigh pressure gradient pump, an online degasser, an autosampler, a column incubator, a 4-40 ℃ incubator, a diode array detector and an evaporative light scattering detector, and is provided with empower (TM) workstation software, and the chromatographic column selects a Waters ACQUITY UPLC HSS T3 chromatographic column (2.1 x 100 mm, 1.8 mu m); the sample injection amount is 10 mu L; the column temperature was 35 ℃; the flow rate was 0.25 ml/min. Mobile phase A: H2O (0.1% formic acid); and the mobile phase B is ACN. The mobile phase gradient is shown in table 4.
TABLE 4 gradient of mobile phase
After liquid phase analysis, a Q-Orbitrap high resolution mass spectrometer (Q-exact type) is adopted to carry out mass spectrum detection on the measured sample in a full scan acquisition mode, and the mass spectrum detection device is provided with an Xcaliibur 3.0 data acquisition system, and the detailed parameter settings are shown in Table 5.
Table 5 set parameter information
(3) Metabonomic data processing and differential metabolite screening:
and (3) leading the original data obtained by LC-MS analysis into Progenetics QI for peak identification, peak alignment and data normalization to obtain a two-dimensional data matrix containing information such as mass-to-charge ratio, retention time, original peak area and normalized peak area, and performing data quality evaluation by adopting a QC sample. The data after quality control is based onMummichogMetabolic pathway mapping for algorithmsThe metabolomics processing method of (1), setting an appropriate mass-to-nuclear ratio tolerance: (<5 ppm) and addition of ion species, obtained on high resolution mass spectral datam/z(mass-to-charge ratio, namely the ratio of proton number/charge number) is subjected to high-flux temporary labeling to obtain metabolite information, and then channel analysis and module analysis are carried out by combining with channel databases such as KEGG, UCSD BiGG and the like. Finally obtaining 12 metabolic pathways with obvious changes, including phenylalanine metabolism, tryptophan metabolism, arachidonic acid metabolism, tyrosine metabolism, valine, biosynthesis of leucine and isoleucine, TCA cycle and the like, and carrying out t test on metabolites in the pathways to obtain the differential metabolites with obvious changes. And identifying the structure of the metabolite of the differential metabolite obtained by the primary identification by using an LC-MS/MS technology, and comparing the metabolite of the obtained standard substance with the standard substance to further confirm the structure. For metabolites whose structure cannot be determined because of low abundance or no inclusion in the secondary database and no availability of standards, preliminary identification results are temporarily employed. 49 differential metabolites were finally obtained.
(4) Establishing a prediction model by adopting a machine learning method: and (3) randomly dividing the differential metabolite data into a training set and a testing set by adopting a LightGBM machine learning method modeling and a ten-by-ten cross validation method. Feature selection is first performed using the Boruta algorithm. And continuously adjusting parameters by GridSearchCV (grid search) and Hyperopt, and selecting the optimal parameters. And (3) acquiring a batch of external data which never participate in modeling, using the constructed model for predicting the batch of data, and judging whether the prediction model is good or bad through AUROC. The importance of a feature is expressed in its contribution to the model. All analyses were performed using the Sciket-leann package by Python.
As can be seen from the above, the acute coronary syndrome early warning method based on metabonomics data provided in the embodiment of the present invention, aiming at the problems of poor sensitivity and specificity, invasiveness and difficulty in implementing early diagnosis of ACS (acute coronary syndrome), is implemented by obtaining metabonomics data of normal coronary arteries and patients with acute coronary syndrome by using an LC-HRMS (high resolution moving Picture) technology, screening differential metabolites, and then screening biomarkers that can be used for predicting and monitoring acute coronary syndrome from complex and tedious biological big data based on a machine learning method, and can provide a noninvasive screening and early warning means to make up for the blank of clinical early warning of acute coronary syndrome. Based on metabonomic biological big data, the machine learning method is used for screening the biomarkers, so that the biomarkers obtained by screening are more reliable.
Based on the same inventive concept, the embodiment of the invention also provides an acute coronary syndrome early warning device based on metabonomics data, such as the following embodiment. Because the principle of solving the problems of the device is similar to the acute coronary syndrome early warning method based on the metabonomics data, the implementation of the device can be referred to the implementation of the acute coronary syndrome early warning method based on the metabonomics data, and repeated parts are not repeated.
Fig. 6 is a schematic diagram of an acute coronary syndrome early warning device based on metabonomics data according to an embodiment of the present invention, as shown in fig. 6, the device includes: the system comprises a metabolite data acquisition module 61, a differential metabolite screening module 62, a model learning module 63 and an acute coronary syndrome early warning module 64.
The metabolite data acquisition module 61 is used for acquiring metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual; the differential metabolite screening module 62 is used for screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals; and the model learning module 63 is configured to perform machine learning on the LightGBM model according to the differential metabolite data to obtain an acute coronary syndrome early warning model, where the acute coronary syndrome early warning model includes: a plurality of biomarkers for diagnosing acute coronary syndrome; and the acute coronary syndrome early warning module 64 is configured to obtain an index value of each biomarker corresponding to the biological individual to be diagnosed according to the acute coronary syndrome early warning model, determine whether the index value of each biomarker corresponding to the biological individual to be diagnosed exceeds a preset normal value range, and output acute coronary syndrome early warning information of the biological individual to be diagnosed according to a determination result.
Optionally, the metabolite data acquiring module 61 is further configured to: obtaining plasma samples of normal coronary artery biological individuals and acute coronary syndrome biological individuals; analyzing plasma samples of normal coronary artery biological individuals and acute coronary syndrome biological individuals by using a liquid chromatography-mass spectrometry combined analysis method to obtain metabolite data of the normal coronary artery biological individuals and the acute coronary syndrome biological individuals.
In an embodiment, in the acute coronary syndrome early warning apparatus based on metabonomic data provided in the embodiment of the present invention, the model learning module 63 is further configured to adjust model parameters by using a GridSearchCV algorithm and a Hyperopt algorithm in a process of performing machine learning on the LightGBM model.
In an embodiment, as shown in fig. 7, in the acute coronary syndrome early warning apparatus based on metabonomics data provided in the embodiment of the present invention, the model learning module 63 specifically includes: a sample data partitioning module 631, a model training module 632, and a model verification module 633.
The sample data dividing module 631 is configured to divide the differential metabolite data into training data and test data according to a preset ratio; the model training module 632 is configured to train the LightGBM model according to the training data to obtain an acute coronary syndrome early warning model; and the model verification module 633 is used for verifying the trained acute coronary syndrome early warning model according to the test data.
In one embodiment, as shown in fig. 7, the acute coronary syndrome early warning device based on metabonomics data provided in the embodiment of the present invention further includes: and the biomarker analysis module 65 is used for determining the importance degree of different biomarkers in the acute coronary syndrome early warning model by adopting a Boruta algorithm.
Based on the same inventive concept, a computer device is further provided in the embodiments of the present invention to solve the technical problem that the prior art cannot implement the early warning of acute coronary syndrome based on metabolite data, fig. 8 is a schematic diagram of a computer device provided in the embodiments of the present invention, as shown in fig. 8, the computer device 80 includes a memory 801, a processor 802, and a computer program stored on the memory 801 and operable on the processor 802, and the processor 802 implements the above-mentioned acute coronary syndrome early warning method based on metabonomic data when executing the computer program.
Based on the same inventive concept, the embodiment of the present invention further provides a computer-readable storage medium, so as to solve the technical problem that the prior art cannot realize the early warning of the acute coronary syndrome based on the metabolite data, and the computer-readable storage medium stores a computer program for executing the above-mentioned acute coronary syndrome early warning method based on the metabonomics data.
To sum up, the embodiments of the present invention provide an acute coronary syndrome early warning method, an apparatus, a computer device, and a computer readable storage medium based on metabonomics data, after metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual are obtained, differential metabolite data are screened according to the metabolite data of the normal coronary artery organism individual and the acute coronary syndrome organism individual, and then machine learning is performed on a LightGBM model according to the screened differential metabolite data, so as to obtain an acute coronary syndrome early warning model including multiple biomarkers, so as to collect an index value of each biomarker corresponding to a to-be-diagnosed organism individual based on the acute coronary syndrome early warning model, and determine whether the index value of each biomarker corresponding to the to-be-diagnosed organism individual exceeds a preset normal value range, and outputting corresponding early warning information according to the judgment result.
The embodiment of the invention can provide a noninvasive screening method for the biomarkers of the acute coronary syndrome, and the early warning of the acute coronary syndrome is carried out on the patient according to the metabolite data of the patient.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An acute coronary syndrome early warning method based on metabonomics data is characterized by comprising the following steps:
obtaining metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual;
screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals;
according to the different metabolite data, machine learning is carried out on the LightGBM model to obtain an acute coronary syndrome early warning model, wherein the acute coronary syndrome early warning model comprises the following components: a plurality of biomarkers for diagnosing acute coronary syndrome;
and according to the acute coronary syndrome early warning model, acquiring an index value of each biomarker corresponding to the biological individual to be diagnosed, judging whether the index value of each biomarker corresponding to the biological individual to be diagnosed exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to a judgment result.
2. The method of claim 1, wherein performing machine learning of the LightGBM model based on the differential metabolite data to obtain an acute coronary syndrome pre-warning model comprises:
dividing the differential metabolite data into training data and testing data according to a preset proportion;
training a LightGBM model according to the training data to obtain an acute coronary syndrome early warning model;
and verifying the trained acute coronary syndrome early warning model according to the test data.
3. The method of claim 2, wherein model parameters are adjusted using GridSearchCV algorithm and Hyperopt algorithm in the machine learning of the LightGBM model.
4. The method of claim 1, wherein obtaining metabolite data of the normal coronary organism and the acute coronary syndrome organism comprises:
collecting plasma samples of normal coronary artery organism individuals and acute coronary syndrome organism individuals;
analyzing plasma samples of normal coronary artery biological individuals and acute coronary syndrome biological individuals by using a liquid chromatography-mass spectrometry combined analysis method to obtain metabolite data of the normal coronary artery biological individuals and the acute coronary syndrome biological individuals.
5. The method of claim 1, wherein the method further comprises:
and determining the importance degree of different biomarkers in the acute coronary syndrome early warning model by adopting a Boruta algorithm.
6. The method of any one of claims 1 to 5, wherein the acute coronary syndrome pre-warning model comprises the following biomarkers: 2-hydroxybutyric acid, dihydropyrimidine, succinic acid, 2, 3-dihydroxybutyric acid, salicylic acid, lysine, rhamnol-1, 4-lactone, dopaquinone, aconitic acid, N-acetyl-L-phenylalanine, hydroxyethyllysine, pantothenic acid, 3-hydroxy-L-kynurenine, N-formylkynurenine, glucose-6-phosphate, pretyrosine, 6-phospho-2-dehydrogluconic acid, retinoic acid, clopidogrel carboxylic acid, leukotriene B4, galactose, 7 alpha-hydroxycholesterol, 4-phosphopantysteine.
7. An acute coronary syndrome early warning device based on metabonomics data, which is characterized by comprising:
the metabolite data acquisition module is used for acquiring metabolite data of a normal coronary artery organism individual and an acute coronary syndrome organism individual;
the differential metabolite screening module is used for screening out differential metabolite data according to the metabolite data of the normal coronary artery organism individuals and the acute coronary syndrome organism individuals;
the model learning module is used for performing machine learning on the LightGBM model according to the differential metabolite data to obtain an acute coronary syndrome early warning model, wherein the acute coronary syndrome early warning model comprises: a plurality of biomarkers for diagnosing acute coronary syndrome;
and the acute coronary syndrome early warning module is used for acquiring the index value of each biomarker corresponding to the biological individual to be diagnosed according to the acute coronary syndrome early warning model, judging whether the index value of each biomarker corresponding to the biological individual to be diagnosed exceeds a preset normal value range, and outputting the acute coronary syndrome early warning information of the biological individual to be diagnosed according to a judgment result.
8. The apparatus of claim 7, wherein the apparatus further comprises:
the sample data dividing module is used for dividing the differential metabolite data into training data and test data according to a preset proportion;
the model training module is used for training the LightGBM model according to the training data to obtain an acute coronary syndrome early warning model;
and the model verification module is used for verifying the trained acute coronary syndrome early warning model according to the test data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the metabonomic data based acute coronary syndrome warning method of any of claims 1 to 6.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the metabonomic data-based acute coronary syndrome warning method of any one of claims 1 to 6.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157589.6A CN112509704A (en) | 2021-02-05 | 2021-02-05 | Acute coronary syndrome early warning method and device based on metabonomics data |
| PCT/CN2022/075246 WO2022166935A1 (en) | 2021-02-05 | 2022-01-30 | Cardiovascular disease incidence risk assessment marker based on metabolomic data and application thereof |
| CN202280002121.2A CN114938659A (en) | 2021-02-05 | 2022-01-30 | Cardiovascular disease onset risk assessment marker based on metabonomics data and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157589.6A CN112509704A (en) | 2021-02-05 | 2021-02-05 | Acute coronary syndrome early warning method and device based on metabonomics data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112509704A true CN112509704A (en) | 2021-03-16 |
Family
ID=74952722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110157589.6A Pending CN112509704A (en) | 2021-02-05 | 2021-02-05 | Acute coronary syndrome early warning method and device based on metabonomics data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112509704A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113113131A (en) * | 2021-03-24 | 2021-07-13 | 南京途博科技有限公司 | Method for generating death risk prediction model, terminal and computer storage medium |
| CN113539478A (en) * | 2021-06-24 | 2021-10-22 | 山西医科大学 | Metabolic omics-based deep vein thrombosis prediction model establishing method |
| WO2022166935A1 (en) * | 2021-02-05 | 2022-08-11 | 中国医学科学院阜外医院 | Cardiovascular disease incidence risk assessment marker based on metabolomic data and application thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109884302A (en) * | 2019-03-14 | 2019-06-14 | 北京博远精准医疗科技有限公司 | Lung cancer early diagnosis marker and its application based on metabolism group and artificial intelligence technology |
| CN110598836A (en) * | 2019-10-12 | 2019-12-20 | 中国科学院成都生物研究所 | Metabonomics analysis method based on improved particle swarm optimization algorithm |
| CN111289736A (en) * | 2020-02-03 | 2020-06-16 | 北京大学 | Slow obstructive pulmonary early diagnosis marker based on metabonomics and application thereof |
| CN111312399A (en) * | 2020-02-24 | 2020-06-19 | 南京鼓楼医院 | Method for establishing model for early prediction of gestational diabetes |
-
2021
- 2021-02-05 CN CN202110157589.6A patent/CN112509704A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109884302A (en) * | 2019-03-14 | 2019-06-14 | 北京博远精准医疗科技有限公司 | Lung cancer early diagnosis marker and its application based on metabolism group and artificial intelligence technology |
| CN110598836A (en) * | 2019-10-12 | 2019-12-20 | 中国科学院成都生物研究所 | Metabonomics analysis method based on improved particle swarm optimization algorithm |
| CN111289736A (en) * | 2020-02-03 | 2020-06-16 | 北京大学 | Slow obstructive pulmonary early diagnosis marker based on metabonomics and application thereof |
| CN111312399A (en) * | 2020-02-24 | 2020-06-19 | 南京鼓楼医院 | Method for establishing model for early prediction of gestational diabetes |
Non-Patent Citations (3)
| Title |
|---|
| JIA LI,ET AL.: "Succinate accumulation impairs cardiac pyruvate dehydrogenase activity through GRP91-dependent and independent signaling pathways:Therapeutic effects of ginsenoside Rb1", 《BBA - MOLECULAR BASIS OF DISEASE》 * |
| 苏比娜: "基于 UPLC-MS 方法检测分析急性冠脉综合征患者血浆代谢组学特点", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 陈朴，陈斌: "代谢组学和机器学习模型用于人体亚健康状态的预测", 《中国营养学会第十三届全国营养科学大会暨全球华人营养科学家大会》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022166935A1 (en) * | 2021-02-05 | 2022-08-11 | 中国医学科学院阜外医院 | Cardiovascular disease incidence risk assessment marker based on metabolomic data and application thereof |
| CN113113131A (en) * | 2021-03-24 | 2021-07-13 | 南京途博科技有限公司 | Method for generating death risk prediction model, terminal and computer storage medium |
| CN113113131B (en) * | 2021-03-24 | 2024-02-13 | 南京途博科技有限公司 | Method, terminal and computer storage medium for generating death risk prediction model |
| CN113539478A (en) * | 2021-06-24 | 2021-10-22 | 山西医科大学 | Metabolic omics-based deep vein thrombosis prediction model establishing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Mass spectrometry-based metabolomics in health and medical science: A systematic review | |
| CN112509704A (en) | Acute coronary syndrome early warning method and device based on metabonomics data | |
| Pereira et al. | Metabolomics as a tool for the early diagnosis and prognosis of diabetic kidney disease | |
| CN112509695A (en) | Acute coronary syndrome early warning method and device for stable coronary heart disease patient | |
| CN112505199A (en) | Stable coronary heart disease early warning method and device based on metabonomics data | |
| KLUPCZY—SKA et al. | Metabolomics in medical sciences ń trends, challenges and perspectives | |
| US11940453B2 (en) | Ceramides and their use in diagnosing CVD | |
| Nikolic et al. | Metabolomics in hypertension | |
| A Nagana Gowda et al. | Biomarker discovery and translation in metabolomics | |
| Barderas et al. | Metabolomic profiling for identification of novel potential biomarkers in cardiovascular diseases | |
| Ciborowski et al. | Metabolomics with LC-QTOF-MS permits the prediction of disease stage in aortic abdominal aneurysm based on plasma metabolic fingerprint | |
| Tiedt et al. | Circulating metabolites differentiate acute ischemic stroke from stroke mimics | |
| Kaluarachchi et al. | A comparison of human serum and plasma metabolites using untargeted 1 H NMR spectroscopy and UPLC-MS | |
| US20100173346A1 (en) | Methods for detecting coronary artery disease | |
| Michelhaugh et al. | Finding a needle in a haystack: proteomics in heart failure | |
| Barba et al. | Metabolomics and heart diseases: from basic to clinical approach | |
| Ding et al. | Mass spectrometry-based metabolomics for clinical study: Recent progresses and applications | |
| Ricard-Blum et al. | Omic approaches to decipher the molecular mechanisms of fibrosis, and design new anti-fibrotic strategies | |
| Barderas et al. | Vascular proteomics | |
| ES2642186T3 (en) | Diagnosis of multiple sclerosis | |
| CN114938659A (en) | Cardiovascular disease onset risk assessment marker based on metabonomics data and application | |
| Lindon et al. | The development of metabolic phenotyping—a historical perspective | |
| CN110068624B (en) | Biomarker for predicting vascular restenosis and detection kit | |
| US20170227528A1 (en) | Biomarker compositions specific to coronary heart disease patients and uses thereof | |
| Julià et al. | Metabolomics in rheumatic diseases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210316 |