Methods, apparatus, equipment, and storage media for determining the CT value of PCR instruments

Abstract

This application relates to the field of biomedical technology, and provides a method, apparatus, device, and storage medium for determining the CT value of a PCR instrument, which can accurately determine the CT value. In this application, the original fluorescence intensity values ​​at different cycle numbers described by the original CT curve are input into a baseline processing model to obtain the baseline slope and baseline intercept of the original CT curve output by the baseline processing model; based on the baseline determined by the baseline slope and baseline intercept, and the original CT curve, a corrected CT curve is obtained, and the CT value of the PCR instrument is determined on the corrected CT curve.

Description

Technical Field

[0001] This application relates to the field of biomedical technology, and in particular to a method, apparatus, computer device, storage medium, and computer program product for determining the CT value of a PCR instrument. Background Technology

[0002] Real-time fluorescence quantitative PCR (qPCR), also known as real-time quantitative PCR, involves adding a fluorescent dye to the PCR reaction system. As the PCR reaction proceeds, the PCR products accumulate, and the intensity of the fluorescence signal increases proportionally. By monitoring the accumulation of the fluorescence signal, the entire PCR process can be detected in real time.

[0003] To monitor PCR reaction efficiency, the number of cycles required for the fluorescence intensity of the amplified product to reach a set fluorescence threshold can be monitored during PCR amplification. The fewer the number of cycles required to reach the set fluorescence threshold, the higher the efficiency; the more the number of cycles required to reach the set fluorescence threshold, the lower the efficiency. The number of cycles required to reach the set fluorescence threshold is generally referred to as the CT value.

[0004] When determining CT values, the baseline is typically subtracted from the original CT curve, and the CT value is then determined from the resulting CT curve. The baseline is usually determined by the user based on experience; if the baseline determined by the user is inaccurate, it will affect the accuracy of the CT values. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, storage medium, and computer program product for determining the CT value of a PCR instrument to address the above-mentioned technical problems.

[0006] This application provides a method for determining the CT value of a PCR instrument, the method comprising:

[0007] Obtain the original CT curve;

[0008] The original fluorescence intensity values ​​described by the original CT curve at different cycle numbers are input into the baseline processing model to obtain the baseline slope and baseline intercept of the original CT curve output by the baseline processing model.

[0009] Based on the baseline determined by the baseline slope and baseline intercept, and the original CT curve, a corrected CT curve is obtained, and the CT value of the PCR instrument is determined on the corrected CT curve.

[0010] This application provides a device for determining the CT value of a PCR instrument, the device comprising:

[0011] The curve acquisition module is used to acquire the original CT curve;

[0012] The model prediction module is used to input the original fluorescence intensity values ​​under different cycle numbers described by the original CT curve into the baseline processing model to obtain the baseline slope and baseline intercept of the original CT curve output by the baseline processing model.

[0013] The curve correction module is used to obtain a corrected CT curve based on the baseline determined by the baseline slope and baseline intercept, and the original CT curve.

[0014] A CT value determination module is used to determine the CT value of the PCR instrument on the calibration CT curve.

[0015] This application provides a computer device, including a memory and a processor, wherein the memory stores a computer program and the processor executes the above-described method.

[0016] This application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor using the methods described above.

[0017] This application provides a computer program product having a computer program stored thereon, the computer program being executed by a processor using the above-described method.

[0018] In this application, the original fluorescence intensity values ​​described by the original CT curve at different cycle numbers are input into the baseline processing model, so that the baseline processing model can take into account the global shape of the original CT curve. Based on the global shape of the original CT curve, the appropriate baseline slope and baseline intercept are predicted, and then the appropriate baseline is obtained. Then, the appropriate baseline is subtracted from the original CT curve to obtain the accurate CT value. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the CT curve in one embodiment;

[0020] Figure 2a This is a schematic diagram of the original CT curve and baseline in one embodiment;

[0021] Figure 2b This is a schematic diagram of calibrating the CT curve in one embodiment;

[0022] Figure 3 This is a flowchart illustrating a method for determining the CT value of a PCR instrument in one embodiment;

[0023] Figure 4 This is a schematic diagram of the labeled interface in one embodiment;

[0024] Figure 5This is a structural block diagram of a device for determining the CT value of a PCR instrument in one embodiment;

[0025] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0027] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0028] The following describes some of the contents involved in this application:

[0029] In the process of quantitative real-time PCR, a fluorescence intensity value can be collected after each cycle. The collected fluorescence intensity value can be called the raw fluorescence intensity value. Based on the raw fluorescence intensity values ​​collected at each cycle number, a CT curve can be obtained. This CT curve can be called the original CT curve. The horizontal axis of the original CT curve represents the cycle number, and the vertical axis represents the raw fluorescence intensity value.

[0030] The baseline refers to the signal level during the first few cycles of PCR (typically 3-15 cycles); the change in fluorescence signal is minimal during this stage. A low baseline signal corresponds to the background or noise of the PCR reaction.

[0031] CT curves as follows Figure 1 As shown, the CT curve can be divided into three stages: the fluorescence background signal stage (baseline stage), the fluorescence signal exponential amplification stage, and the plateau stage. In the fluorescence background signal stage, the amplified fluorescence signal is masked by the background fluorescence signal, making it impossible to determine changes in product quantity. In the plateau stage, the amplification product no longer increases exponentially, and there is no linear relationship between the final PCR product quantity and the initial template quantity; therefore, the initial DNA copy number cannot be calculated based on the final PCR product quantity. Only in the fluorescence signal exponential amplification stage is there a linear relationship between the logarithm of the PCR product quantity and the initial template quantity.

[0032] Fluorescence threshold: A value set manually on the CT curve. It can be set at any position in the exponential amplification phase of the fluorescence signal, but the default value of the fluorescence threshold is generally 10 times the standard deviation of the fluorescence signal in the first 3-15 cycles of the PCR reaction.

[0033] CT value: The number of cycles required for the fluorescence intensity of the amplified product to reach the set fluorescence threshold during PCR amplification.

[0034] Baseline determination is a challenging problem in this field. The baseline is a straight line, and it can be determined by the baseline slope and the baseline intercept. The baseline slope and the baseline intercept are generally calculated from the first 3-15 cycles. Then, based on the baseline slope and the baseline intercept, the fluorescence intensity baseline values ​​corresponding to all cycles (usually 40 cycles) are calculated, and these fluorescence intensity baseline values ​​are subtracted one-to-one from the original CT curve.

[0035] The baseline intercept is crucial, determining the vertical shift of the baseline. The baseline slope is also important; if the slope calculation is flawed early on, the deviation will increase as the baseline extends through more cycles. (Refer to...) Figure 2a In the figure, straight lines a, b, and c represent three baselines, and curve d represents the original CT curve. Subtracting the baseline from the original CT curve is: the original fluorescence intensity value of the original CT curve for each cycle minus its baseline fluorescence intensity value, which is equivalent to subtracting the 40 dots on the curve from the 40 asterisks on the straight line.

[0036] The data from the first 3-15 cycles fluctuated significantly, influenced by both the PCR instrument and the reagents. An inaccurate baseline will affect the corrected CT curve obtained after subtracting the baseline from the original CT curve, leading to inaccurate CT values ​​and thus false positives or false negatives. (Refer to...) Figure 2b In the figure, curves da, db, and dc are the corrected CT curves obtained by subtracting baselines a, b, and c from the original CT curve d. The horizontal line e in the figure corresponds to the fluorescence threshold. It can be seen that if the baseline is too large, the fluorescence intensity correction value obtained by subtracting the baseline fluorescence intensity value from the original fluorescence intensity value will be too small. If the fluorescence threshold of the horizontal line e in the figure is taken as the standard, then the corrected CT curve da has false negatives, and the corrected CT curves db and dc have false positives. That is, a baseline that is too large or too small directly causes false positives or false negatives.

[0037] Based on this, this application provides a method for determining the CT value of a PCR instrument, which can globally consider the morphology of the original CT curve and determine a suitable baseline for the original CT curve. This method can be executed by a computer device, and the method includes... Figure 3 The steps shown are as follows:

[0038] Step S301: Obtain the original CT curve.

[0039] In the process of quantitative real-time PCR, a fluorescence intensity value is collected after each cycle. The collected fluorescence intensity value can be called the raw fluorescence intensity value. Then, the raw fluorescence intensity value corresponding to each cycle number is obtained. The curve obtained based on the raw fluorescence intensity value corresponding to each cycle number can be called the raw CT curve.

[0040] Step S302: Input the original fluorescence intensity values ​​under different cycle numbers described by the original CT curve into the baseline processing model to obtain the baseline slope and baseline intercept of the original CT curve output by the baseline processing model.

[0041] The fluorescence intensity at each cycle number described by the original CT curve is original and reflects the global shape of the original CT curve. Therefore, the baseline processing model can take into account the global shape of the original CT curve, thereby determining an appropriate baseline slope and baseline intercept for the original CT curve.

[0042] Step S303: Based on the baseline determined by the baseline slope and baseline intercept, and the original CT curve, a corrected CT curve is obtained, and the CT value of the PCR instrument is determined on the corrected CT curve.

[0043] In this step, based on the baseline intercept b and the baseline slope k, the equation for the baseline can be obtained as y = k × x + b. x is the cycle number, and y is the baseline fluorescence intensity value.

[0044] After obtaining the baseline and the original CT curve, the baseline can be subtracted from the original CT curve to obtain the corrected CT curve. Specifically, the original fluorescence intensity value on the original CT curve for each cycle number is subtracted from the baseline fluorescence intensity value on the baseline to obtain the fluorescence intensity correction value corresponding to each cycle number; the corrected CT curve is formed based on the fluorescence intensity correction value corresponding to each cycle number.

[0045] For example, when the cycle number is 20, the original fluorescence intensity value corresponding to cycle number 20 on the original CT curve is subtracted from the baseline fluorescence intensity value corresponding to cycle number 20 to obtain the fluorescence intensity correction value corresponding to cycle number 20. Following this method, fluorescence intensity correction values ​​corresponding to each cycle number can be obtained. Based on the fluorescence intensity correction values ​​corresponding to each cycle number, a corrected CT curve is formed, such as... Figure 2b The corrected CT curves are shown.

[0046] In the above embodiments, the original fluorescence intensity values ​​described by the original CT curve at different cycle numbers are input into the baseline processing model, so that the baseline processing model can consider the global shape of the original CT curve. Based on the global shape of the original CT curve, the appropriate baseline slope and baseline intercept are predicted, and then the appropriate baseline is obtained. Then, the appropriate baseline is subtracted from the original CT curve to obtain the accurate CT value.

[0047] In one embodiment, the step of obtaining training samples for the baseline processing model includes: obtaining multiple test raw CT curves, and labeling the baseline slope and baseline intercept of each test raw CT curve; obtaining training samples based on the original fluorescence intensity values ​​at different cycle numbers described by each test raw CT curve, and the baseline slope and baseline intercept obtained by labeling each test raw CT curve.

[0048] The annotation interface is as follows: Figure 4 As shown, when annotating the baseline slope and baseline intercept of each test raw CT curve, the global shape of the test raw CT curve is considered. During annotation, the overall shape of the test raw CT curve can be observed. Figure 4 The shape of the baseline (straight line) and curve (the line corresponding to the asterisk) is used to determine whether to modify the baseline slope and baseline intercept, and then the annotation is completed. The modified values ​​can be automatically recorded.

[0049] After an original test CT curve is labeled, the original fluorescence intensity values ​​at different cycle numbers described by the original test CT curve, as well as the labeled baseline slope and baseline intercept, form a training sample; since there are multiple original test CT curves, multiple training samples can be used.

[0050] Furthermore, after obtaining multiple training samples, the step of obtaining a baseline processing model using the training samples includes: inputting the original fluorescence intensity values ​​under different cycle numbers described by each original CT curve of the test into the neural network; adjusting the parameters of the neural network with the goal of minimizing the difference between the baseline slope output by the neural network and the corresponding labeled baseline slope, and with the goal of minimizing the difference between the baseline intercept output by the neural network and the corresponding labeled baseline intercept; and using the neural network with adjusted parameters as the baseline processing model.

[0051] In other words, the input data is the original fluorescence intensity described by each test original CT curve in the training sample at different cycle numbers, and the standard data for output data is the baseline slope and baseline intercept obtained from the annotation in the training sample.

[0052] Specifically, after obtaining multiple training samples and forming a dataset, the dataset can be divided into a training set and a test set, and the baseline slope and baseline intercept can be trained separately using neural network training.

[0053] • This embodiment can use a 3-layer neural network, with 1 input layer, 1 hidden layer, and 1 output layer, and 421 trainable parameters;

[0054] The first layer of the neural network has 41 units, which are the 40 CT values ​​and 1 bias value input.

[0055] • The second layer has 11 units, including 1 bias value;

[0056] The third layer has only one output unit;

[0057] • Training the baseline intercept is relatively simple, mainly depending on the initial few raw data points; the first and second layers use the ReLU activation function, while the second and third layers may not use an activation function.

[0058] • Training the baseline slope is relatively complex. The first layer to the second layer uses the activation function "sigmoid", and the second layer to the third layer uses the activation function "tanh".

[0059] • Optimize the use of "adam" and use the mean squared error loss function.

[0060] In the above embodiments, a better baseline slope and baseline intercept are obtained through annotation, thereby improving the prediction accuracy of the baseline processing model. Furthermore, during the training process, the original fluorescence intensity values ​​described by the original CT curve at different cycle numbers are input into the neural network. The parameters of the neural network are adjusted with the goal of minimizing the difference between the baseline slope output by the neural network and the corresponding labeled baseline slope, and minimizing the difference between the baseline intercept output by the neural network and the corresponding labeled baseline intercept. This results in the baseline processing model, which has the ability to predict the baseline slope and baseline intercept based on the global shape of the original CT curve.

[0061] In one embodiment, the step of determining the CT value of a PCR instrument on a calibration CT curve may specifically include: if there is a fluorescence intensity correction value on the calibration CT curve that is equal to the fluorescence threshold, taking the cycle number corresponding to the fluorescence intensity correction value on the calibration CT curve that is equal to the fluorescence threshold as the CT value of the PCR instrument.

[0062] If there is no fluorescence intensity correction value equal to the fluorescence threshold on the calibration CT curve, determine the first fluorescence intensity correction value greater than the fluorescence threshold on the calibration CT curve in ascending order of cycle number; take the cycle number corresponding to the first fluorescence intensity correction value greater than the fluorescence threshold on the calibration CT curve as the target cycle number; determine the CT value of the PCR instrument between the target cycle number and the cycle number preceding the target cycle number.

[0063] For example, if there is no fluorescence intensity correction value equal to the fluorescence threshold on the calibrated CT curve, if the first fluorescence intensity correction value greater than the fluorescence threshold on the calibrated CT curve is determined to be i in ascending order of cycle number, since the fluorescence intensity correction value on the calibrated CT curve is greater than the fluorescence threshold at the i-th cycle number, the cycle number to reach the fluorescence threshold should be between the (i-1)-th cycle number and the i-th cycle number. Therefore, in this embodiment, the CT value is determined between the (i-1)-th cycle number and the i-th cycle number.

[0064] Furthermore, interpolation can be used to determine the number of cycles required to reach the fluorescence threshold, thereby obtaining a more accurate CT value. Specifically, the curve segment in the corrected CT curve corresponding to the target number of cycles and the previous cycle number is taken as a coarsely divided curve segment; linear interpolation is performed on the coarsely divided curve segment to obtain a finely divided curve segment; the point on the finely divided curve segment whose fluorescence intensity correction value is the fluorescence threshold is determined, and the number of cycles at the point on the finely divided curve segment is taken as the CT value of the PCR instrument.

[0065] For example, when the target cycle number is the i-th cycle number, a curve segment on the corrected CT curve corresponding to the (i-1)-th and i-th cycle numbers can be determined, and this curve segment is called the coarsely divided curve segment. After obtaining the coarsely divided curve segment, linear interpolation can be performed on it, with an interpolation precision of 100 divisions. The curve segment obtained after interpolation is called the finely divided curve segment. In the finely divided curve segment, the horizontal axis represents the finely divided cycle number, and the vertical axis represents the finely divided fluorescence intensity correction value.

[0066] Next, determine the point on the finely divided curve segment where the fluorescence correction value is the fluorescence threshold. If the point is the j-th point on the finely divided curve segment, then the cycle number of the point on the finely divided curve segment is i-1+(j×0.01), and i-1+(j×0.01) is used as the CT value of the PCR instrument.

[0067] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0068] In one embodiment, such as Figure 5 As shown, a device for determining the CT value of a PCR instrument is provided, comprising:

[0069] Curve acquisition module 501 is used to acquire the original CT curve;

[0070] The model prediction module 502 is used to input the original fluorescence intensity values ​​under different cycle numbers described by the original CT curve into the baseline processing model to obtain the baseline slope and baseline intercept of the original CT curve output by the baseline processing model.

[0071] The curve correction module 503 is used to obtain a corrected CT curve based on the baseline determined by the baseline slope and the baseline intercept, and the original CT curve.

[0072] The CT value determination module 504 is used to determine the CT value of the PCR instrument on the calibration CT curve.

[0073] In one embodiment, the device further includes a training sample module for acquiring multiple original test CT curves, annotating the baseline slope and baseline intercept of each original test CT curve, and obtaining training samples based on the original fluorescence intensity values ​​at different cycle numbers described by each original test CT curve, and the baseline slope and baseline intercept obtained by annotating each original test CT curve.

[0074] In one embodiment, the device further includes a model training module for inputting the original fluorescence intensity values ​​at different cycle numbers described by each original CT curve into a neural network; adjusting the parameters of the neural network with the goal of minimizing the difference between the baseline slope output by the neural network and the corresponding labeled baseline slope, and with the goal of minimizing the difference between the baseline intercept output by the neural network and the corresponding labeled baseline intercept; and using the parameter-adjusted neural network as a baseline processing model.

[0075] In one embodiment, the curve correction module is further configured to obtain a baseline based on the baseline slope and the baseline intercept; subtract the baseline fluorescence intensity value from the original fluorescence intensity value on the original CT curve for each cycle number to obtain a fluorescence intensity correction value corresponding to each cycle number; and form a corrected CT curve based on the fluorescence intensity correction value corresponding to each cycle number.

[0076] In one embodiment, the CT value determination module is further configured to, when there is no fluorescence intensity correction value equal to the fluorescence threshold on the calibration CT curve, determine the first fluorescence intensity correction value greater than the fluorescence threshold on the calibration CT curve in ascending order of cycle number; take the cycle number corresponding to the first fluorescence intensity correction value greater than the fluorescence threshold on the calibration CT curve as the target cycle number; and determine the CT value of the PCR instrument between the target cycle number and the cycle number preceding the target cycle number.

[0077] In one embodiment, the CT value determination module is further configured to: take the curve segment in the corrected CT curve corresponding to the target cycle number and the previous cycle number of the target cycle number as a coarsely divided curve segment; perform linear interpolation on the coarsely divided curve segment to obtain a finely divided curve segment; determine the point on the finely divided curve segment whose fluorescence intensity correction value is the fluorescence threshold; and take the cycle number of the point on the finely divided curve segment as the CT value of the PCR instrument.

[0078] Specific limitations regarding the device for determining the CT value of a PCR instrument can be found in the limitations of the method for determining the CT value of a PCR instrument described above, and will not be repeated here. Each module in the aforementioned device for determining the CT value of a PCR instrument can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or they can be stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0079] In one embodiment, a computer device is provided, the internal structure of which can be shown as follows: Figure 6As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores CT value data for determining PCR instruments. The network interface communicates with external terminals via a network connection. The computer device also includes input / output interfaces, which are connection circuits between the processor and external devices for exchanging information; they are connected to the processor via a bus and are referred to as I / O interfaces. When the computer program is executed by the processor, it implements a method for determining the CT value of a PCR instrument.

[0080] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0081] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the various method embodiments described above.

[0082] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments described above.

[0083] In one embodiment, a computer program product is provided having a computer program stored thereon, the computer program being executed by a processor of the steps described in the various method embodiments above.

[0084] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0085] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] The above embodiments are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of determining a CT value of a PCR instrument, the method comprising: The method comprises: obtaining an original CT curve; inputting the original values of the fluorescence intensity at different cycle numbers described by the original CT curve into a baseline processing model to obtain a baseline slope and a baseline intercept of the original CT curve output by the baseline processing model; determining a baseline according to the baseline slope and the baseline intercept, and obtaining a corrected CT curve according to the original CT curve, and determining a CT value of a PCR instrument on the corrected CT curve; wherein the step of obtaining a training sample for the baseline processing model comprises: obtaining a plurality of test original CT curves, labeling the baseline slope and the baseline intercept of each test original CT curve; obtaining the training sample according to the original values of the fluorescence intensity at different cycle numbers described by each test original CT curve, and the baseline slope and the baseline intercept labeled for each test original CT curve; the training sample is used for parameter adjustment of a neural network to obtain the baseline processing model.

2. The method of claim 1, wherein, The method further comprises: inputting the original values of the fluorescence intensity at different cycle numbers described by each test original CT curve into a neural network; minimizing the difference between the baseline slope output by the neural network and the corresponding labeled baseline slope, and minimizing the difference between the baseline intercept output by the neural network and the corresponding labeled baseline intercept, to adjust the parameters of the neural network; the neural network after parameter adjustment is used as the baseline processing model.

3. The method of claim 1, wherein, According to the baseline determined according to the baseline slope and the baseline intercept, and the original CT curve, a corrected CT curve is obtained, which comprises: obtaining a baseline according to the baseline slope and the baseline intercept; subtracting the baseline value of the fluorescence intensity on the baseline from the original value of the fluorescence intensity at each cycle number on the original CT curve to obtain the corrected value of the fluorescence intensity corresponding to each cycle number; forming a corrected CT curve according to the corrected value of the fluorescence intensity corresponding to each cycle number.

4. The method of claim 1, wherein, Determining a CT value of a PCR instrument on the corrected CT curve comprises: in the case that there is no corrected value of the fluorescence intensity equal to the fluorescence threshold on the corrected CT curve, determining the first corrected value of the fluorescence intensity greater than the fluorescence threshold on the corrected CT curve in the order of cycle number from small to large; taking the cycle number corresponding to the first corrected value of the fluorescence intensity greater than the fluorescence threshold on the corrected CT curve as a target cycle number; determining the CT value of the PCR instrument between the target cycle number and the last cycle number of the target cycle number.

5. The method of claim 4, wherein, Determining the CT value between the target cycle number and the last cycle number of the target cycle number comprises: taking the curve segment corresponding to the target cycle number and the last cycle number of the target cycle number in the corrected CT curve as a coarse division curve segment; performing linear interpolation processing on the coarse division curve segment to obtain a fine division curve segment; determining the point on the fine division curve segment at which the corrected value of the fluorescence intensity is the fluorescence threshold, and taking the cycle number of the point on the fine division curve segment as the CT value of the PCR instrument.

6. An apparatus for determining CT values of a PCR instrument, the apparatus comprising: The device comprises: a curve obtaining module configured to obtain an original CT curve; a model prediction module, configured to input the raw values of the fluorescence intensity at different cycle numbers described by the original CT curve into a baseline processing model to obtain a baseline slope and a baseline intercept of the baseline processing model output for the original CT curve; a curve correction module, configured to determine a baseline according to the baseline slope and the baseline intercept and the original CT curve to obtain a corrected CT curve; a CT value determination module, configured to determine a CT value of a PCR instrument on the corrected CT curve; a training sample module, configured to obtain a plurality of test original CT curves, label a baseline slope and a baseline intercept for each test original CT curve, and obtain training samples according to the raw values of the fluorescence intensity at different cycle numbers described by each test original CT curve and the baseline slope and the baseline intercept labeled for each test original CT curve, wherein the training samples are used to adjust parameters of a neural network to obtain the baseline processing model.

7. The apparatus of claim 6, wherein, The device further comprises: a model training module, configured to input the raw values of the fluorescence intensity at different cycle numbers described by each test original CT curve into the neural network, and adjust parameters of the neural network by minimizing a difference between a baseline slope output by the neural network and a corresponding labeled baseline slope and by minimizing a difference between a baseline intercept output by the neural network and a corresponding labeled baseline intercept, and use the neural network with the adjusted parameters as the baseline processing model.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor implements the method in any one of claims 1 to 5 when executing the computer program.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 5. The computer program is executed by the processor to implement the method in any one of claims 1 to 5.

Images