A method for assisting photoelectric combined detection of nucleic acid protein based on machine learning

Abstract

The present application relates to the technical field of biological detection, and particularly relates to a method for detecting nucleic acid protein based on machine learning and photoelectric combined detection. The present application firstly connects a photoelectric combined detection nucleic acid protein device with a test system; adds a nucleic acid protein sample to be detected into a sample pool in the photoelectric combined detection nucleic acid protein device, obtains D 测 and 测 ; then carries out data processing on D 测 and G 测 , obtains characteristic values of normalized electric sensing unit signal response and light sensing unit signal response; trains a machine learning model, obtains classification surface I and classification surface II; finally, takes the characteristic values of normalized electric sensing unit signal response and light sensing unit signal response as input and substitutes into the classification surface I and the classification surface II, realizes the interpretation result of the nucleic acid protein sample to be detected. The method can solve the problems of single signal collection, low clinical accuracy and insufficient reliability of the existing molecular detection technology.

Description

Technical Field

[0001] This invention relates to the field of biodetection technology, and in particular to a method for detecting nucleic acid proteins based on machine learning-assisted photoelectric co-detection. Background Technology

[0002] With the accelerating pace of digital healthcare, the development of rapid and high-precision nucleic acid and protein detection methods is essential. In recent years, molecular detection methods have demonstrated numerous advantages, including low cost, fast response, and ease of operation. However, existing molecular detection methods, including electrochemical sensors, mass spectrometers, surface Raman enhanced sensors, transistor sensors, and immunochromatographic sensors, generally monitor a single signal response and employ a single judgment mode. This presents numerous challenges when dealing with untreated clinical samples, such as significant loss of sensitivity, low detection accuracy, and complex signal judgment modes. Therefore, there is an urgent need to develop efficient and sensitive multi-signal sensors to achieve accurate and reliable nucleic acid and protein detection. Summary of the Invention

[0003] To address the problems of existing molecular detection methods, such as "single signal acquisition, low clinical accuracy, and insufficient reliability," the purpose of this invention is to provide a method for detecting nucleic acid proteins based on machine learning-assisted photoelectric co-detection.

[0004] Machine learning is a data mining process that uses algorithms and is now widely used in materials design, artificial intelligence, clinical analysis, and other fields. In sensor detection applications, by selecting appropriate machine learning parameters and algorithms, accurate decision-making and classification can be achieved for input data. Furthermore, through mathematical dimensionality enhancement and visualization, machine learning can compare and analyze the responses of multiple signals, ultimately enabling the precise detection of nucleic acid and protein clinical samples using a combined photoelectric sensor.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] This invention provides a method for detecting nucleic acid proteins based on machine learning-assisted photoelectric co-detection, comprising the following steps:

[0007] (S1) Connect the photoelectric combined detection device for nucleic acid and protein to the testing system;

[0008] (S2) Add the nucleic acid protein sample to be tested into the sample pool of the photoelectric combined detection nucleic acid protein device, and obtain the signal response D of the electrical sensing unit. 测 The signal response G of the optical sensing unit 测 ;

[0009] (S3) The signal response D of the inductive unit obtained in step (S2) 测 The signal response G of the optical sensing unit 测Data processing is performed to obtain the characteristic values ​​of the normalized signal response of the electrical sensing unit and the signal response of the optical sensing unit.

[0010] (S4) Train the machine learning model to obtain Classification Surface I and Classification Surface II;

[0011] (S5) Using the characteristic values ​​of the normalized electrical sensing unit signal response and optical sensing unit signal response obtained in step (S3) as inputs and substituting them into the classification surface I and classification surface II obtained in step (S4), the interpretation results of the nucleic acid protein test sample are realized.

[0012] In one embodiment of the present invention, in step (S1), the testing system includes an electrical testing system and an optical testing system;

[0013] The optical testing system is a non-contact optical testing system, which is selected from one of an electrochemiluminescence analyzer, a laser confocal microscope, or a Raman spectrometer.

[0014] In one embodiment of the present invention, the electrical sensing unit of the photoelectric combined detection device for nucleic acid proteins is connected to the electrical testing system, and the optical sensing unit is connected to the optical testing system.

[0015] In one embodiment of the present invention, the source electrode of the electrical sensing unit is connected to the positive electrode of the electrical testing system, and the drain electrode of the electrical sensing unit is connected to the negative electrode of the electrical testing system.

[0016] In one embodiment of the present invention, in step (S2), the nucleic acid protein is selected from one of the nucleic acid proteins of influenza virus, coronavirus, group B streptococcus, chlamydia, mycoplasma, bacteria or rickettsia.

[0017] In one embodiment of the present invention, in step (S2), the signal response D of the inductive unit... 测 This represents the steady-state current after the electrical testing system has stabilized.

[0018] In one embodiment of the present invention, in step (S2), the signal response G of the optical sensing unit... 测 This is the photon count after the optical testing system has stabilized.

[0019] In one embodiment of the present invention, in step (S3), the Z-score algorithm is used in the data processing.

[0020] In one embodiment of the present invention, in step (S4), the process of training the machine learning model uses one of the following algorithms: partial least squares, support vector machine, K-nearest neighbor, or logistic regression.

[0021] In one embodiment of the present invention, the process of training a machine learning model uses a logistic regression algorithm.

[0022] In one embodiment of the present invention, in step (S5), the interpretation result of the nucleic acid protein sample to be tested is as follows:

[0023] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response belong to the classification surface I, it is determined to be detected / positive, that is, the nucleic acid protein sample to be tested contains the pathogen to be tested.

[0024] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I, but belong to classification surface II, it is determined to be detected / positive, that is, the nucleic acid protein sample to be tested contains nucleic acid protein.

[0025] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I and do not belong to classification surface II, they are determined to be in the gray area, and steps (S2) to (S5) are repeated.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] This invention combines a front-end photoelectric detection device for nucleic acid proteins with a back-end machine learning mathematical model. Through optimization of the classification algorithm, it overcomes the problem of low clinical detection accuracy caused by the single signal recognition in existing molecular detection methods, providing a new direction for the practical application of molecular detection in complex clinical samples. The machine learning-based auxiliary algorithm constructs classification surfaces for different nucleic acid proteins, providing a foundation for accurate sensor diagnosis, with a detection accuracy greater than 96.3%, and has potential socio-economic value. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the photoelectric combined detection device for nucleic acid proteins in Example 1;

[0029] Figure 2 This is a flowchart of the method for detecting nucleic acid proteins based on machine learning-assisted photoelectric co-detection, as described in Example 2.

[0030] Figure 3 To obtain the signal response D of the inductive unit in Example 2 测 Resulting image;

[0031] Figure 4 In Example 2, the signal response G of the optical sensing unit is obtained. 测 Resulting image;

[0032] Figure 5 This is a schematic diagram of the results of machine learning-assisted photoelectric joint detection of rhinovirus in Example 2;

[0033] Figure 6 This is a schematic diagram of the results of machine learning-assisted photoelectric combined detection of Mycobacterium tuberculosis in Example 3;

[0034] Figure 7 This is a schematic diagram of the results of machine learning-assisted photoelectric joint detection of Group B Streptococcus in Example 4;

[0035] Figure 8 This is a schematic diagram of the detection results of the photoelectric combined detection device for nucleic acid proteins in Example 5 using different dimensional classification methods;

[0036] The following are the labels in the figure: 1. Insulating substrate; 2. Source; 3. Drain; 4. First connecting molecule; 5. Second connecting molecule; 6. Gate; 7. Sample cell; 8. Biological probe; 9. Two-dimensional sensitive material. Detailed Implementation

[0037] This invention provides a method for detecting nucleic acid proteins based on machine learning-assisted photoelectric co-detection, comprising the following steps:

[0038] (S1) Connect the photoelectric combined detection device for nucleic acid and protein to the testing system;

[0039] (S2) Add the nucleic acid protein sample to be tested into the sample pool of the photoelectric combined detection nucleic acid protein device, and obtain the signal response D of the electrical sensing unit. 测 The signal response G of the optical sensing unit 测 ;

[0040] (S3) The signal response D of the inductive unit obtained in step (S2) 测 The signal response G of the optical sensing unit 测 Data processing is performed to obtain the characteristic values ​​of the normalized signal response of the electrical sensing unit and the signal response of the optical sensing unit.

[0041] (S4) Train the machine learning model to obtain Classification Surface I and Classification Surface II;

[0042] (S5) Using the characteristic values ​​of the normalized electrical sensing unit signal response and optical sensing unit signal response obtained in step (S3) as inputs and substituting them into the classification surface I and classification surface II obtained in step (S4), the interpretation results of the nucleic acid protein test sample are realized.

[0043] In one embodiment of the present invention, in step (S1), the testing system includes an electrical testing system and an optical testing system;

[0044] The optical testing system is a non-contact optical testing system, which is selected from one of an electrochemiluminescence analyzer, a laser confocal microscope, or a Raman spectrometer.

[0045] In one embodiment of the present invention, the electrical sensing unit of the photoelectric combined detection device for nucleic acid proteins is connected to the electrical testing system, and the optical sensing unit is connected to the optical testing system.

[0046] In one embodiment of the present invention, the source electrode of the electrical sensing unit is connected to the positive electrode of the electrical testing system, and the drain electrode of the electrical sensing unit is connected to the negative electrode of the electrical testing system.

[0047] In one embodiment of the present invention, in step (S2), the nucleic acid protein is selected from one of the nucleic acid proteins of influenza virus, coronavirus, group B streptococcus, chlamydia, mycoplasma, bacteria or rickettsia.

[0048] In one embodiment of the present invention, in step (S2), the signal response D of the inductive unit... 测 This represents the steady-state current after the electrical testing system has stabilized.

[0049] In one embodiment of the present invention, in step (S2), the signal response G of the optical sensing unit... 测 This is the photon count after the optical testing system has stabilized.

[0050] In one embodiment of the present invention, in step (S3), the Z-score algorithm is used in the data processing.

[0051] In one embodiment of the present invention, in step (S4), the process of training the machine learning model uses one of the following algorithms: partial least squares, support vector machine, K-nearest neighbor, or logistic regression.

[0052] In one embodiment of the present invention, the process of training a machine learning model uses a logistic regression algorithm.

[0053] In one embodiment of the present invention, in step (S5), the interpretation result of the nucleic acid protein sample to be tested is as follows:

[0054] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response belong to the classification surface I, it is determined to be detected / positive, that is, the nucleic acid protein sample to be tested contains nucleic acid protein.

[0055] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I, but belong to classification surface II, it is determined that no detection / negative, that is, the nucleic acid protein sample to be tested does not contain nucleic acid protein.

[0056] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I and do not belong to classification surface II, they are determined to be in the gray area, and steps (S2) to (S5) are repeated.

[0057] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0058] The following testing methods are not for the purpose of disease diagnosis, but simply to determine the presence or absence of rhinovirus (HRV), mycobacterium (TB), group B streptococcus (GBS), SARS-CoV-2, and influenza A virus (H1N1) in the sample to be tested.

[0059] The rhinovirus (HRV) test samples used in the detection method of this invention include nasal swabs and pharyngeal swabs; the Zygomycosis (TB) test samples are lower respiratory tract samples (deep cough sputum, bronchoalveolar lavage fluid, bronchoalveolar lavage fluid) and serum samples; and the Group B Streptococcus (GBS) test samples are lower vaginal and anal swabs. The specific methods for obtaining these samples are as follows:

[0060] (a) Nasal and pharyngeal swabs: The specific steps for collecting and processing the samples to be tested should be obtained in accordance with the "National Influenza Surveillance Technical Guidelines (2017 Edition)" issued by the Chinese Center for Disease Control and Prevention, the "Technical Specifications for 10-in-1 Pooled Nucleic Acid Testing for COVID-19" issued by the National Health Commission of the People's Republic of China, and the "Technical Guidelines for Dilution Pooled Sample Testing for COVID-19 Nucleic Acid Screening" issued by the National Health Commission of the People's Republic of China.

[0061] (b) Deep cough sputum: After the patient coughs deeply, the sputum is collected in a 50 ml screw-top plastic tube containing 3 ml of sampling solution;

[0062] (c) Bronchoalveolar lavage fluid: Insert the collector tip into the trachea through the nostril or endotracheal intubation (about 30 cm deep), inject 5 ml of normal saline, turn on negative pressure, rotate the collector tip and slowly withdraw it. Collect the extracted mucus and rinse the collector once with the sampling solution (a pediatric catheter connected to a 50 ml syringe can also be used for collection).

[0063] (d) Bronchoalveolar lavage fluid: After local anesthesia, the fiberoptic bronchoscope is inserted through the mouth or nose into the pharynx into the bronchus of the right middle lobe or the lingular segment of the left lung. The tip of the bronchoscope is inserted into the opening of the bronchial branch. Sterile saline is slowly added through the tracheal biopsy hole, 30-50 ml each time, with a total volume of 100-250 ml, and should not exceed 300 ml.

[0064] (e) Lower vaginal and anal swabs: Without using a vaginal speculum, a swab is used to collect a sample from the lower 1 / 3 of the vagina, and then the same swab is used to collect a sample from the rectum through the rectal sphincter. For specific methods, refer to the expert consensus on prevention of perinatal group B streptococcal disease (China) of the Chinese Society of Perinatal Medicine and the Obstetrics Group of the Chinese Society of Obstetrics and Gynecology [J] (Chinese Journal of Perinatal Medicine, 2021, 24, 561).

[0065] Example 1

[0066] This embodiment provides a photoelectric combined detection device for nucleic acid proteins, such as... Figure 1 As shown, the photoelectric combined detection device for nucleic acid proteins includes an insulating substrate 1, a source electrode 2, a drain electrode 3, connecting molecules (a first connecting molecule 4 and a second connecting molecule 5), a gate electrode 6, a sample cell 7, a biological probe 8, and a two-dimensional sensitive material 9. The source electrode 2, drain electrode 3, and gate electrode 6 are located above the insulating substrate 1, with the source electrode 2 and drain electrode 3 arranged in parallel and the gate electrode 6 located opposite the source electrode 2 and drain electrode 3. The sample cell 7 is disposed above the source electrode 2, drain electrode 3, and gate electrode 6. The two-dimensional sensitive material 9 is located at the bottom of the source electrode 2 and drain electrode 3 near their end faces and on the upper surface of the insulating substrate 1. The first connecting molecule 4 with a luminescent group is disposed above the two-dimensional sensitive material 9. The second connecting molecule 5 is connected to the end of the gate electrode 6. The upper surface of the connecting molecules (the first connecting molecule 4 and the second connecting molecule 5) is connected to the biological probe 8. On one hand, the insulating substrate 1, source electrode 2, drain electrode 3, gate electrode 6, first connecting molecule 4, biological probe 8, and two-dimensional sensitive material 9 constitute an electrosensing unit; on the other hand, the insulating substrate 1, second connecting molecule 5, biological probe 8, and two-dimensional sensitive material 9 constitute an optical sensing unit.

[0067] Among them, the insulating substrate 1 is a plastic film with a light transmittance greater than 90%, and the plastic film is selected from one or more of polyester resin, polyimide or polymethyl methacrylate; the source electrode 2 is a gold source electrode, the drain electrode 3 is a gold drain electrode, and the gate electrode 6 is a gold gate electrode; the first connecting molecule 4 is selected from one of gold nanoparticles or carbon quantum dots; the second connecting molecule 5 is selected from one of coupling activators or gold nanoparticles; the biological probe 8 is selected from one of antibody molecules, nucleic acid probes or antigen molecules; and the two-dimensional sensitive material 9 is a two-dimensional sensitive material film obtained by chemical deposition, mechanical exfoliation or liquid phase exfoliation.

[0068] Example 2

[0069] This embodiment provides a method for detecting nucleic acid proteins using machine learning-assisted photoelectric co-detection.

[0070] In this embodiment, the nucleic acid protein is HRV, and the specific steps are as follows (e.g. Figure 2 As shown):

[0071] (S10) Construction of a transistor-integrated optoelectronic sensing system:

[0072] (S101) A metal electrode (50 nanometer gold) is fabricated on a PI film with a thickness of 2 mm / micrometer using printed electronics technology. The electrode includes a gold gate, a gold source, and a gold drain, wherein the gold source is the current input terminal and the gold drain is the current output terminal.

[0073] (S102) Spin-coat 8 wt.% polymethyl methacrylate (PMMA) onto a two-dimensional sensitive material grown on a metal substrate. Transfer the two-dimensional sensitive material / PMMA film to a quartz substrate with metal electrodes using an electrochemical method and connect it between the gold source electrode and the gold drain electrode. After soaking in acetone for 2 hours, wash with isopropanol and deionized water respectively. Use photolithography to etch the two-dimensional sensitive material / PMMA film into a 150×20 micrometer rectangular shape to obtain the device to be modified.

[0074] (S103) Modify the gold gate region on the device to be modified with a second linker molecule: Soak the gold gate in a solution of 50 micrograms per milliliter of Staphylococcus aureus for 1 hour to modify the gold nanoparticles.

[0075] Modify the channel region of the two-dimensional sensitive material with a first linker molecule containing a luminescent group: Immerse the two-dimensional sensitive material / PMMA film in a PASE solution of 5 mmol / L for 2 hours; then immerse it in a solution of 25 mmol / L anthocyanin fluorescent dye (Cy3 dye, CAS#146368-13-0) in the dark for 2 hours.

[0076] (S104) The gold nanoparticles and two-dimensional sensitive material / PMMA film on the device to be modified were immersed in 5 μg / mL MPT64 antibody solution for 6 hours, and then washed with 1×PBS buffer solution to obtain the pretreatment device.

[0077] (S105) Mix type 194 polydimethylsiloxane (PDMS) at a ratio of 194A:194B = 1:10 (wt.%), remove air under vacuum, and bake at 70°C for 30 minutes to obtain PDMS. Punch holes in the PDMS to obtain sample cells and place them on top of the pretreatment device to obtain the device for photoelectric joint detection of nucleic acid proteins.

[0078] (S20) Connect the gold source electrode, gold gate electrode, and gold drain electrode in the photoelectric joint detection nucleic acid protein device obtained in step (S10) to the electrical testing system via alligator clips, wherein the gold source electrode is connected to the positive terminal of the electrical testing system and the gold drain electrode is connected to the negative terminal of the electrical testing system; connect the photosensitive unit to the 20× optical path (laser beam 532 nm) of the laser confocal microscope; add the HRV sample to be tested into the sample cell and obtain the signal response D of the electrical sensing unit. 测 ( Figure 3 The signal response G of the optical sensing unit 测 ( Figure 4 ).

[0079] (S30) Use the Z-Score algorithm of SPSS27 to analyze the acquired signal response D of the inductive unit. 测 The signal response G of the optical sensing unit 测 Perform data processing;

[0080] (S40) After step (S30) is completed, feature extraction is performed on the signal response of the electrical sensing unit and the signal response of the optical sensing unit to obtain the feature values ​​of the normalized signal response of the electrical sensing unit and the signal response of the optical sensing unit.

[0081] (S50) Using Python 3.1 to train a logistic regression algorithm, modeling the data based on the normalized eigenvalues ​​of the electrical sensing unit signal response and the optical sensing unit signal response obtained in step (S40), to obtain classification surface I and classification surface II. Figure 5 );

[0082] (S60) Substitute the eigenvalues ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response into the classification surface I;

[0083] Interpretation result:

[0084] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response belong to the classification surface I, it is determined to be detected / positive, that is, the sample to be tested contains HRV.

[0085] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I, but belong to classification surface II, it is determined that the sample is not detected / negative, that is, the sample to be tested does not contain HRV.

[0086] When the characteristic values ​​of the normalized electrical sensing unit signal response and the optical sensing unit signal response do not belong to classification surface I and do not belong to classification surface II, they are determined to be in the gray area, and steps (S20) to (S50) are repeated.

[0087] The method described in this embodiment achieves an accuracy rate of 99.8% for HRV detection.

[0088] In this embodiment, the HRV sample to be tested was provided by the Public Health Clinical Center affiliated with Fudan University, and its HRV concentration was calibrated to 11 copies per milliliter. The biological probes used in this embodiment include: HRV monoclonal antibody (60299-1-1g, Proteintech), HRV polyclonal antibody (10831-1-AP, Proteintech), and HRV nucleic acid probe (SEQ ID NO.1: 5'-TCCTCCGGCCCCTGAATGYGGCTA-3').

[0089] Example 3

[0090] This embodiment provides a method for detecting nucleic acid proteins using machine learning-assisted photoelectric co-detection.

[0091] In this embodiment, the nucleic acid protein is TB; the difference between this embodiment and Embodiment 2 is:

[0092] In step (S101), the insulating substrate used in this embodiment is a polyester resin film (1000 micrometers thick);

[0093] In step (S103), the TB antibodies used in this embodiment are anti-MPT64 (Abcam, ab193435) and anti-CFP10 (Invitrogen, MA5-18220);

[0094] In step (S20), the specimens to be tested in this embodiment are 173 TB clinical samples. The specific test results are as follows: Figure 6 As shown:

[0095] The machine learning-assisted photoelectric joint detection of TB achieves an accuracy of 98.9%, demonstrating excellent detection performance and showcasing the value of the method described in this invention.

[0096] Example 4

[0097] This embodiment provides a method for detecting nucleic acid proteins using machine learning-assisted photoelectric co-detection.

[0098] In this embodiment, the nucleic acid protein is GBS; the difference between this embodiment and Embodiment 2 is:

[0099] In step (S101), the insulating substrate used in this embodiment is a polymethyl methacrylate film (1000 micrometers thick);

[0100] In step (S103), the GBS nucleic acid probe sequence used in this embodiment is: 5'-GGTGCATTGTTATTTTCACCA-3' (SEQ ID NO.2);

[0101] In step (S20), the samples to be tested in this embodiment are 169 GBS clinical samples. The specific test results are as follows: Figure 7 As shown:

[0102] The machine learning-assisted optoelectronic joint detection of GBS achieves an accuracy of 96.3%, demonstrating excellent detection performance and showcasing the value of the method described in this invention.

[0103] Example 5

[0104] This embodiment provides a method for detecting nucleic acid proteins using a photoelectric combined detection device and a different dimensional classification method.

[0105] In this embodiment, the nucleic acid proteins are HRV, TB, and GBS; the difference between this embodiment and Embodiment 2 is:

[0106] In step (S103), the TB antibodies used in this embodiment are anti-MPT64 (Abcam, ab193435) and anti-CFP10 (Invitrogen, MA5-18220), and the GBS nucleic acid probe sequence used is: 5'-GGTGCATTGTTATTTTCACCA-3' (SEQ ID NO.2);

[0107] In step (S20), the samples to be tested in this embodiment are 159 HRV clinical samples, 173 TB clinical samples and 169 GBS clinical samples;

[0108] In step (S50), this embodiment uses algorithms of different dimensions (1D, 2D, and 3D) to classify the detection results, thereby evaluating the detection accuracy. Specific test results are as follows: Figure 8 As shown:

[0109] The accuracy of the machine learning-assisted photoelectric joint detection of nucleic acid proteins based on the 3D algorithm is greater than 96.3%, while the detection accuracy of the low-dimensional algorithm is even lower (less than 82% for the 1D algorithm and less than 95% for the 2D algorithm). This demonstrates the excellent detection performance of the detection method of the present invention and reflects the value of the method described in the present invention.

[0110] Example 6

[0111] This embodiment provides a method for detecting nucleic acid proteins using machine learning-assisted photoelectric co-detection.

[0112] In this embodiment, the nucleic acid protein is the novel coronavirus; the difference between this embodiment and Embodiment 2 is:

[0113] In step (S101), the insulating substrate used in this embodiment is a polymethyl methacrylate film (1000 micrometers thick);

[0114] In step (S103), the COVID-19 antibodies used in this embodiment include SARS-CoV-2 Spike S1 antibody (40150-R007, SinoBiological) and CR3022 antibody (ab273073, Abcam), and the COVID-19 nucleic acid probe sequence used is 5'-CCATAACCTTTCCACATACCGCAGACGG-3' (SEQ ID NO.3).

[0115] In step (S20), the samples to be tested in this embodiment are 17 clinical samples of COVID-19. The specific test results are shown in Table 1:

[0116] Table 1

[0117]

[0118]

[0119] In this embodiment, the overall accuracy rate of machine learning-assisted photoelectric combined detection of 17 SARS-CoV-2 samples in clinical testing was 100%.

[0120] Example 7

[0121] Machine learning-assisted photoelectric joint detection of influenza A virus (H1N1) is performed according to the method described in the specific implementation method. The difference between this embodiment and Embodiment 2 is:

[0122] In step (S103), the H1N1 nucleic acid probe sequences used in this embodiment are 5'-TTTTTGTCCTCGCTC-3' (H1N1-1: SEQ ID NO.4) and 5'-TTTTTACACAAATCCTAAAATTCCC-3' (H1N1-2: SEQ ID NO.5).

[0123] In step (S20), the samples to be tested in this embodiment are 21 H1N1 clinical samples. The specific test results are shown in Table 1:

[0124] Table 2

[0125]

[0126]

[0127] In this embodiment, the overall accuracy of machine learning-assisted photoelectric combined detection of H1N1 in the clinical testing of 21 COVID-19 samples was 100%.

[0128] The above description of the embodiments is provided to enable those skilled in the art to understand and use the invention. It will be apparent to those skilled in the art that various modifications can be made to these embodiments, and the general principles described herein can be applied to other embodiments without inventive effort. Therefore, the present invention is not limited to the above embodiments, and any improvements and modifications made by those skilled in the art based on the interpretation of the present invention, without departing from the scope of the invention, should be within the protection scope of the present invention.

Claims

1. A method for assisting photoelectric combined detection of nucleic acid protein based on machine learning, characterized in that, The method comprises the following steps: (S1) connecting the photoelectric combined nucleic acid protein detection device to a test system; (S2) adding the nucleic acid protein sample to be tested into the sample pool of the photoelectric combined nucleic acid protein detection device, obtaining the signal response D of the electrical sensing unit 测 and the signal response G of the optical sensing unit 测 ; (S3) The signal response D of the inductive unit obtained in step (S2) 测 The signal response G of the optical sensing unit 测 Data processing is performed to obtain the characteristic values ​​of the normalized signal response of the electrical sensing unit and the signal response of the optical sensing unit. (S4) training a machine learning model to obtain a classification surface I and a classification surface II; (S5) taking the characteristic values of the normalized electric sensor unit signal response and the optical sensor unit signal response obtained in step (S3) as input and substituting them into the classification surface I and the classification surface II obtained in step (S4) to realize the interpretation result of the nucleic acid protein sample to be tested; In step (S5), the interpretation result of the nucleic acid protein sample to be tested is as follows: When the characteristic values of the normalized electric sensor unit signal response and the optical sensor unit signal response belong to the classification surface I, it is determined that the detection is positive, that is, the nucleic acid protein sample to be tested contains nucleic acid protein; When the characteristic values of the normalized electric sensor unit signal response and the optical sensor unit signal response do not belong to the classification surface I and belong to the classification surface II, it is determined that the detection is negative, that is, the nucleic acid protein sample to be tested does not contain nucleic acid protein; When the characteristic values of the normalized electric sensor unit signal response and the optical sensor unit signal response do not belong to the classification surface I and do not belong to the classification surface II, it is determined that the sample is in a gray area, and steps (S2)-(S5) are repeated.

2. The method of claim 1, wherein the method is assisted by machine learning. In step (S1), the test system comprises an electrical test system and an optical test system.

3. The method of claim 2, wherein the method is assisted by machine learning. The electric sensor unit of the photoelectric combined nucleic acid protein detection device is connected to the electrical test system, and the optical sensor unit is connected to the optical test system.

4. The method of claim 1, wherein the method is assisted by machine learning. In step (S2), the nucleic acid protein is selected from one of the nucleic acid proteins of influenza virus, coronavirus, group B streptococcus, chlamydia, mycoplasma, bacteria or rickettsia.

5. The method of claim 1, wherein the method is assisted by machine learning. In step (S2), the signal response D of the electrical sensing unit 测 is the steady-state current corresponding to the stable state of the electrical test system.

6. The method of claim 1, wherein the method is assisted by machine learning. In step (S2), the signal response G of the light sensing unit 测 The photon counts corresponding to the stable optical test system.

7. The method of claim 1, wherein the method is assisted by machine learning. In step (S3), the Z-score algorithm is used in the data processing process.

8. The method of claim 1, wherein the method is assisted by machine learning. In step (S4), one of the partial least squares method, the support vector machine algorithm, the K nearest neighbor algorithm or the logistic regression algorithm is used in the training process of the machine learning model.

9. The method of claim 8, wherein the method is assisted by machine learning. The logistic regression algorithm is used in the training process of the machine learning model.

Images