An intelligent system and method for rapid determination of antibody affinity

Abstract

The present invention relates to the field of biotechnology, and in particular to an intelligent system and method for rapid determination of antibody affinity. The content includes: conducting experimental preparations and setting frequencies, monitoring the antibody-target binding reaction in real time, and calculating the initial discrete signal; performing adaptive modulation processing on the initial discrete signal to obtain a discrete signal; processing the discrete signal at different frequencies to obtain a preliminary antibody affinity and make corrections, displaying the obtained final antibody affinity as a measurement result, and generating an experimental report. It solves the problem that the traditional antibody affinity determination method is sensitive to noise when processing low-intensity signals, resulting in unstable signal extraction; usually relies on a global optimization algorithm, which takes a long time to calculate and has low efficiency; lacks intelligence and adaptive capabilities, and cannot dynamically adjust the processing flow according to the experimental conditions, making it difficult to cope with the diverse needs under different experimental conditions, limiting the adaptability in complex biological reactions.

Description

Technical Field

[0001] The present invention relates to the field of biotechnology, and in particular to an intelligent system and method for rapid antibody affinity determination. Background Art

[0002] Antibody affinity determination technology has important application value in the biomedical and pharmaceutical fields, especially in drug development, immune research and clinical diagnosis, the interaction between antibodies and target molecules needs to be accurately measured. Traditional antibody affinity determination methods mainly rely on surface plasmon resonance (SPR) and biolayer interferometry (BLI). The technology can monitor the kinetics of antibody binding to the target in real time, and has high sensitivity and accuracy, and is widely used in antibody screening, drug discovery and other fields. However, with the increase in research needs and the increase in the complexity of biological reactions, the limitations of the technology have gradually emerged, especially in the study of high-throughput screening and weak binding reactions, facing greater challenges.

[0003] Therefore, traditional antibody affinity determination methods have many limitations in antibody affinity determination: first, traditional antibody affinity determination methods such as surface plasmon resonance (SPR) and bio-layer interferometry (BLI) are sensitive to noise when processing low-intensity signals, resulting in unstable signal extraction, especially when the antibody binds weakly to the target, and it is difficult to accurately reflect the kinetic characteristics of the antibody-target binding; second, the calculation process is complex and usually relies on global optimization algorithms, which takes a long time to calculate, especially in high-throughput screening scenarios, and the efficiency is low; finally, it lacks intelligence and adaptive capabilities, and cannot dynamically adjust the processing flow according to experimental conditions, making it difficult to cope with the diverse needs under different experimental conditions, limiting its adaptability in complex biological reactions. Summary of the invention

[0004] The present invention provides an intelligent system and method for rapid antibody affinity determination, so as to solve the problems that traditional antibody affinity determination methods such as surface plasmon resonance (SPR) and biolayer interferometry (BLI) are sensitive to noise when processing low-intensity signals, resulting in unstable signal extraction, especially when the antibody binds weakly to the target, it is difficult to accurately reflect the kinetic characteristics of the antibody-target binding; the calculation process is complex, usually relying on a global optimization algorithm, and the calculation is time-consuming, especially in high-throughput screening scenarios, the efficiency is low; lack of intelligence and self-adaptation capabilities, unable to dynamically adjust the processing flow according to experimental conditions, difficult to cope with the diversity requirements under different experimental conditions, and limiting the adaptability in complex biological reactions.

[0005] The intelligent system and method for rapid antibody affinity determination of the present invention specifically include the following technical solutions:

[0006] An intelligent method for rapid antibody affinity determination comprises the following steps:

[0007] S1: Perform experimental preparation, set the frequency, collect antibody-target binding signals, monitor the antibody-target binding reaction in real time, calculate the initial discrete signal, perform adaptive modulation processing on the initial discrete signal, and obtain a discrete signal;

[0008] S2: Through the intelligent discrete random mapping algorithm, the discrete signals at different frequencies are processed to obtain the preliminary antibody affinity; the preliminary antibody affinity is corrected to obtain the final antibody affinity; the final antibody affinity is displayed as the measurement result, and an experimental report is generated.

[0009] Preferably, the S1 specifically includes:

[0010] The antibody-target binding signal at each frequency is discretized into time segments, and the initial discrete signal is calculated by introducing the sinusoidal modulation term and the time-related nonlinear factor through the initial discrete signal formula; the initial discrete signal formula is as follows:

[0011]

[0012] in, is the initial discrete signal of the kth time segment at the i-th frequency; i is the index variable of the frequency; A i is the initial amplitude of the antibody-target binding signal; i is the signal attenuation coefficient at the ith frequency; t k is the time point corresponding to the kth time segment; k is the index variable of the time segment; sin(ω i t k ) is the sinusoidal modulation term; ω i is the sinusoidal modulation frequency, which represents the frequency of sinusoidal modulation applied to the antibody-target binding signal at the i-th frequency; is a time-dependent nonlinear factor; is the noise term, which represents the Gaussian noise of the kth time segment at the ith frequency.

[0013] Preferably, the S1 specifically includes:

[0014] Nonlinear modulation terms and nonlinear exponential enhancement terms are introduced to perform adaptive modulation processing on the initial discrete signal, dynamically adjust the periodic change and intensity of the initial discrete signal, and obtain a discrete signal.

[0015] Preferably, the S2 specifically includes:

[0016] In the implementation process of the intelligent discrete random mapping algorithm, logarithmic, absolute value and exponential operations are introduced based on discrete signals at different frequencies to construct the objective function; the objective function formula of the intelligent discrete random mapping algorithm is as follows:

[0017]

[0018] Where L(X) is the objective function; X is the antibody affinity; N is the total number of frequencies used in the discrete signal; i is the index variable of the frequency; K is the total number of time segments at each frequency; k is the index variable of the time segment; is the discrete signal of the kth time segment at the ith frequency; a i is the index used to adjust the nonlinear change of antibody affinity at the i-th frequency; B i is the initial value of antibody-target binding capacity at the ith frequency; C i is the kinetic constant at the ith frequency.

[0019] Preferably, the S2 specifically includes:

[0020] An improved gradient descent method is introduced to calculate the gradient of the objective function through exponential terms and logarithmic terms.

[0021] Preferably, the S2 specifically includes:

[0022] Based on the gradient of the objective function, a gradient smoothing parameter is introduced to update the antibody affinity and obtain the antibody affinity after iteration; an iteration threshold is set, and when the absolute value difference of the antibody affinity before and after iteration is less than the iteration threshold, the iteration is stopped to obtain the preliminary antibody affinity.

[0023] Preferably, the S2 specifically includes:

[0024] Through the nonlinear correction function, the hyperbolic tangent function, logarithmic function and exponential function are introduced to correct the preliminary antibody affinity and obtain the final antibody affinity.

[0025] An intelligent system for rapid determination of antibody affinity, comprising the following parts:

[0026] Initial signal acquisition module, signal modulation and enhancement module, antibody affinity estimation module, antibody affinity correction module, result display and report generation module;

[0027] The initial signal acquisition module performs preliminary preparations for the experiment, sets the number and intensity of frequencies, monitors the antibody-target binding reaction in real time through the initial discrete signal formula, obtains and outputs the initial discrete signal, and uses the initial discrete signal as basic data for subsequent processing; the initial signal acquisition module is connected to the signal modulation and enhancement module by means of data transmission;

[0028] The signal modulation and enhancement module receives the initial discrete signal, performs adaptive modulation processing on the initial discrete signal, obtains a discrete signal and outputs it; the signal modulation and enhancement module is connected to the antibody affinity estimation module by means of data transmission;

[0029] The antibody affinity estimation module receives discrete signals, constructs and minimizes the objective function through an intelligent discrete random mapping algorithm, estimates and outputs the preliminary antibody affinity; the antibody affinity estimation module is connected to the antibody affinity correction module through data transmission;

[0030] The antibody affinity correction module receives the preliminary antibody affinity, applies a nonlinear correction function, and corrects the preliminary antibody affinity by combining a hyperbolic tangent function, a logarithmic function, and an exponential function to obtain and output the final antibody affinity; the antibody affinity correction module is connected to the result display and report generation module by means of data transmission;

[0031] The result display and report generation module receives the final antibody affinity, uses the final antibody affinity data as the measurement result and displays it, and generates an experimental report at the same time.

[0032] The beneficial effects of the technical solution of the present invention are:

[0033] 1. The present invention reflects the complex dynamic changes of the antibody-target binding process by introducing sinusoidal modulation terms and time-dependent nonlinear factors, so that even when the antibody-target binding is weak or there is noise interference, the signal characteristics can still be accurately captured, significantly improving the accuracy of antibody affinity determination.

[0034] 2. The present invention uses an intelligent discrete random mapping algorithm (IDSM) and an improved gradient descent method to quickly minimize the objective function and optimize the calculation process of antibody affinity. Compared with traditional global optimization algorithms, the present invention reduces the computational complexity and speeds up the estimation of antibody affinity. It is particularly suitable for rapid processing of large-scale data in high-throughput screening scenarios, and solves the problems of long time consumption and low efficiency of traditional algorithms.

[0035] 3. The present invention corrects the preliminary antibody affinity through a nonlinear correction function, so that the intelligent system for rapid antibody affinity determination can automatically adjust the signal processing and antibody affinity estimation process according to the experimental conditions, can adapt to different experimental conditions and complex biological reactions, and meet the diverse needs of antibody affinity determination in different experimental scenarios, with higher robustness and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1This is a structural diagram of an intelligent system for rapid antibody affinity determination according to the present invention;

[0037] Figure 2 The present invention is a flowchart of an intelligent method for rapid determination of antibody affinity. DETAILED DESCRIPTION

[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] The specific scheme of an intelligent system and method for rapid antibody affinity determination provided by the present invention is described in detail below with reference to the accompanying drawings.

[0041] See attached Figure 1 , which shows a structure diagram of an intelligent system for rapid antibody affinity determination provided by an embodiment of the present invention, the system includes the following parts:

[0042] Initial signal acquisition module, signal modulation and enhancement module, antibody affinity estimation module, antibody affinity correction module, result display and report generation module;

[0043] The initial signal acquisition module performs preliminary preparations for the experiment, sets the number and intensity of frequencies, monitors the antibody-target binding reaction in real time through the initial discrete signal formula, obtains and outputs the initial discrete signal, and uses the initial discrete signal as basic data for subsequent processing; the initial signal acquisition module is connected to the signal modulation and enhancement module by means of data transmission;

[0044] The signal modulation and enhancement module receives the initial discrete signal, performs adaptive modulation processing on the initial discrete signal through an adaptive modulation formula, obtains a discrete signal and outputs it; the signal modulation and enhancement module is connected to the antibody affinity estimation module through data transmission;

[0045] The antibody affinity estimation module receives discrete signals, constructs and minimizes the objective function through an intelligent discrete random mapping algorithm, estimates and outputs the preliminary antibody affinity; the antibody affinity estimation module is connected to the antibody affinity correction module through data transmission;

[0046] The antibody affinity correction module receives the preliminary antibody affinity, applies a nonlinear correction function, and corrects the preliminary antibody affinity by combining a hyperbolic tangent function, a logarithmic function, and an exponential function to obtain and output the final antibody affinity; the antibody affinity correction module is connected to the result display and report generation module by means of data transmission;

[0047] The result display and report generation module receives the final antibody affinity, takes the final antibody affinity data as the measurement result and displays it, and generates a detailed experimental report. According to the needs of the specific implementation scenario, it selects to record the parameters in the antibody affinity measurement process, such as the experiment date and time and ambient temperature, the preliminary antibody affinity estimation value, the number of iterations, the final antibody affinity, etc., for easy viewing and archiving.

[0048] See attached Figure 2 , which shows a flow chart of an intelligent method for rapid antibody affinity determination provided by an embodiment of the present invention, the method comprising the following steps:

[0049] S1: Perform experimental preparation, set the frequency, collect antibody-target binding signals, monitor the antibody-target binding reaction in real time, calculate the initial discrete signal, perform adaptive modulation processing on the initial discrete signal, and obtain a discrete signal;

[0050] First, carry out experimental preparation work, including the preparation of antibodies and targets and the optimization of experimental conditions. Specifically, ensure that the antibodies and target molecules have been purified and prepared to meet the experimental requirements, select the appropriate antibody concentration, and modify or label the target so that the interaction between the antibody and the target can be accurately detected; optimize experimental conditions, such as temperature, pH value and ionic strength, to ensure that the antibody and target can bind in a suitable environment to obtain a reaction signal, and select the test detection equipment according to the specific implementation scenario and calibrate it to ensure the sensitivity and accuracy of signal detection. The experimental preparation work is a technical means well known to those skilled in the art and will not be elaborated here;

[0051] Next, according to the specific implementation scenario, combined with the previous experimental design and data analysis, the frequency is set to ensure that the selected frequency range can fully cover the kinetic characteristics of the antibody-target binding process. By setting the number and intensity of frequencies, antibody-target binding signals can be collected at multiple different frequencies to monitor the antibody-target binding reaction in real time, such as low frequency for capturing slow reactions and high frequency for capturing fast kinetic changes;

[0052] Discretize the antibody-target binding signal at each frequency into multiple time segments, and calculate the initial discrete signal using the initial discrete signal formula to reflect the changes in the antibody-target binding signal at different time points and frequencies, providing an accurate kinetic data basis for subsequent estimation of antibody affinity;

[0053] The initial discrete signal formula is as follows:

[0054]

[0055] in, is the initial discrete signal of the kth time segment at the i-th frequency; i is the frequency index variable, which is used to indicate the i-th frequency used when collecting antibody-target binding signals; A i is the initial amplitude of the antibody-target binding signal, which indicates the signal intensity at the beginning of the antibody-target binding reaction at the ith frequency. It is the initial parameter set in the experiment and is set according to the specific implementation scenario using the expert experience method; i is the signal attenuation coefficient at the ith frequency, describing the rate at which the antibody-target binding signal decays over time at the ith frequency. It is used to control the exponential decay rate of the antibody-target binding reaction and is obtained through experimental fitting; t k is the time point corresponding to the kth time segment, and the time segment is set according to the specific implementation scenario; k is the index variable of the time segment; sin(ω i t k ) is a sinusoidal modulation term, which is used to reflect the periodic changes of the antibody-target binding signal; ω i is the sinusoidal modulation frequency, which indicates the frequency of sinusoidal modulation applied to the antibody-target binding signal at the i-th frequency, and is used to enhance the periodicity of the signal and is set according to the specific implementation scenario; is a time-dependent nonlinear factor used to adjust the evolution of the initial discrete signal over time; is the noise term, which represents the Gaussian noise of the kth time segment at the ith frequency, set to obey the mean of 0 and the variance of Gaussian noise;

[0056] The initial discrete signal formula reflects the complex dynamic changes of the antibody-target binding process by introducing sinusoidal modulation terms and time-related nonlinear factors. Sinusoidal modulation enhances the periodic response of the antibody-target binding signal and helps capture different kinetic characteristics, while the nonlinear factor makes the antibody-target binding signal more sensitive to time changes and improves the feature extraction capability under weak signal or noise interference;

[0057] Next, the initial discrete signal is adaptively modulated using the signal attenuation coefficient and the sinusoidal modulation frequency to obtain a discrete signal. Through adaptive modulation processing, the weight of the discrete signal in the key time segment is enhanced, and the ability of the discrete signal to capture changes in antibody affinity is effectively improved. The key time segment is a time segment that is relatively long during the experiment, has significant changes, or has a greater impact on the estimation of antibody affinity;

[0058] The adaptive modulation formula is as follows:

[0059]

[0060] in, is the discrete signal of the kth time segment at the ith frequency; i is the signal attenuation coefficient at the ith frequency; t k is the time point corresponding to the kth time segment; ω i is the sinusoidal modulation frequency at the ith frequency; log(1+sin(ω i t k )·t k ) is a nonlinear modulation term, which is used to smooth the periodic changes in the initial discrete signal to dynamically adjust the change effect of the initial discrete signal and make the initial discrete signal processing more stable; It is a nonlinear exponential enhancement term, which is used to dynamically adjust the strength of the initial discrete signal and further enhance the responsiveness of the signal;

[0061] The adaptive modulation formula dynamically adjusts the periodic changes and strength of the initial discrete signal by introducing nonlinear modulation terms and nonlinear exponential enhancement terms. The nonlinear modulation term can smooth the periodic changes in the initial discrete signal, reduce the impact of noise, and make the processing process more stable; the nonlinear exponential enhancement term is used to enhance the strength of the initial discrete signal, amplify the response of the effective signal, and improve the robustness and processing accuracy of the discrete signal;

[0062] Compared with the initial discrete signal, the discrete signal obtained by adaptive modulation processing can more sensitively reflect the subtle characteristics of the antibody-target binding reaction, reduce noise interference, and help improve the accuracy and stability of subsequent antibody affinity estimation.

[0063] S2: Through the intelligent discrete random mapping algorithm, the discrete signals at different frequencies are processed to obtain the preliminary antibody affinity; the preliminary antibody affinity is corrected to obtain the final antibody affinity; the final antibody affinity is displayed as the measurement result, and an experimental report is generated.

[0064] Discrete signals at different frequencies were processed by the intelligent discrete random mapping algorithm (IDSM) to obtain preliminary antibody affinities.

[0065] The intelligent discrete random mapping algorithm constructs an objective function based on discrete signals at different frequencies, and quickly and accurately estimates antibody affinity by minimizing the objective function. The antibody affinity represents the strength of the binding between the antibody and the target molecule, which is quantified using the dissociation constant. The smaller the antibody affinity (dissociation constant) value, the tighter the binding between the antibody and the target, and the higher the stability of the interaction. The larger the antibody affinity value, the weaker the binding between the antibody and the target, and the lower the stability.

[0066] The objective function formula of the intelligent discrete random mapping algorithm is as follows:

[0067]

[0068] Among them, L(X) is the objective function; X is the antibody affinity, which is a scalar reflecting the binding strength between the antibody and the target molecule; N is the total number of frequencies used in the discrete signal, that is, the number of frequencies used in the experiment; i is the index variable of the frequency; K is the total number of time segments at each frequency; k is the index variable of the time segment; is the discrete signal of the kth time segment at the ith frequency; a i is the index used to adjust the nonlinear change of antibody affinity at the i-th frequency, obtained by experimental fitting; R i is the initial value of the antibody-target binding capacity at the ith frequency, obtained by experimental fitting; C i is the kinetic constant at the i-th frequency, which represents the speed or affinity kinetic characteristics of the antibody-target binding reaction and is obtained by experimental fitting;

[0069] The objective function introduces logarithmic and absolute value operations, making the calculation of antibody affinity insensitive to noise, and the introduction of exponential operations increases nonlinearity, making the intelligent discrete random mapping algorithm more robust for antibody affinity calculation under different experimental conditions;

[0070] The antibody affinity is updated by the improved gradient descent method to minimize the objective function. The specific implementation process of the improved gradient descent method is: first calculate the gradient of the objective function, and the gradient formula is as follows:

[0071]

[0072] in, is the gradient of the objective function L(X) with respect to the antibody affinity X, which is used to optimize the antibody affinity; It is the exponential term in the gradient formula, which is used to realize the nonlinear amplification of the discrete signal error; It is the logarithmic term in the gradient formula, which is used to smooth the discrete signal error;

[0073] Then, the antibody affinity is updated by the gradient descent formula to obtain the iterated antibody affinity. The specific update formula is as follows:

[0074]

[0075] in, is the antibody affinity after iteration, that is, the antibody affinity value updated by the gradient descent algorithm; X is the antibody affinity before iteration; the initial value of antibody affinity is obtained by experimental fitting based on the antibody-target binding reaction curve in the previous experiment. The process of obtaining the initial value of antibody affinity is a prior art and will not be described here; α is the learning rate, which is used to control the gradient update step size; β is the gradient smoothing parameter, which is used to adjust the gradient update amplitude; Used to control the gradient update speed to smooth the gradient value of the objective function; α and β are obtained through experimental tuning;

[0076] The gradient calculation formula introduces an exponential term to nonlinearly amplify the discrete signal error, so that significant errors under high noise conditions are given greater weights, and small errors are smoothed by logarithmic terms to ensure the stability of the calculation; the update formula of the antibody affinity adjusts the gradient nonlinearly and uses the gradient smoothing parameter to control the size of the update step to avoid the gradient of the objective function being too large or too small, thereby ensuring numerical stability and rapid convergence during the optimization process;

[0077] The iteration threshold is set according to the specific implementation scenario. When the absolute value difference of the antibody affinity before and after the iteration is less than the iteration threshold, it indicates that the calculation has converged, and the iteration is stopped to obtain the preliminary antibody affinity.

[0078] Furthermore, in order to further improve the accuracy, the preliminary antibody affinity was corrected using a nonlinear correction function to obtain the final antibody affinity;

[0079] The specific calculation formula of the nonlinear correction function is as follows:

[0080]

[0081] Among them, Y is the corrected antibody affinity, i.e., the final antibody affinity; is the preliminary antibody affinity; tanh is the hyperbolic tangent function, which is used to perform nonlinear correction on the antibody affinity; γ is the correction amplitude adjustment coefficient; δ is a constant to prevent it from being zero, which is set to 10 -6 ; μ is the nonlinear adjustment coefficient, which is used to control the smoothness of the antibody affinity correction; θ is the correction center point, which is used to adjust the center position of the correction; the correction amplitude adjustment coefficient γ, the nonlinear adjustment coefficient μ and the correction center point θ are set according to the specific implementation scenario;

[0082] The nonlinear correction function corrects the initial antibody affinity by combining the hyperbolic tangent function, the logarithmic function and the exponential function, so that the antibody affinity can be optimized adaptively, thereby improving the robustness of the antibody affinity;

[0083] The final antibody affinity obtained after nonlinear correction is displayed as the antibody affinity measurement result. Based on the antibody affinity measurement results, users can perform antibody screening, evaluate the binding efficiency of antibodies and targets, or apply the antibody affinity measurement results to drug development, clinical diagnosis and other fields; at the same time, a detailed experimental report is generated. According to the needs of the specific implementation scenario, you can choose to record the parameters in the antibody affinity measurement process, such as the experimental date and time and ambient temperature, preliminary antibody affinity estimation value, number of iterations, final antibody affinity, etc., for easy viewing and archiving.

[0084] In summary, an intelligent system and method for rapid determination of antibody affinity have been completed.

[0085] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0087] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent method for rapid determination of antibody affinity, characterized in that: The following steps are involved: S 1: Perform experimental preparation, set the frequency, collect antibody-target binding signals, monitor the antibody-target binding reaction in real time, calculate the initial discrete signal; perform adaptive modulation processing on the initial discrete signal to obtain a discrete signal; S2: The discrete signals at different frequencies are processed by intelligent discrete random mapping algorithm to obtain preliminary antibody affinity; The preliminary antibody affinity is corrected to obtain the final antibody affinity; The final antibody affinity is presented as the assay result and an experimental report is generated.

2. The intelligent method for rapid antibody affinity determination according to claim 1, characterized in that: The S1 specifically includes: The antibody-target binding signal at each frequency is discretized into time segments, and the initial discrete signal is calculated by introducing the sinusoidal modulation term and the time-related nonlinear factor through the initial discrete signal formula; the initial discrete signal formula is as follows: in, is the initial discrete signal of the kth time segment at the i-th frequency; i is the index variable of the frequency; A i is the initial amplitude of the antibody target binding signal; i is the signal attenuation coefficient at the ith frequency; t k is the time point corresponding to the kth time segment; k is the index variable of the time segment; sin(ω i t k ) is the sinusoidal modulation term; ω i is the sinusoidal modulation frequency, which represents the frequency of sinusoidal modulation applied to the antibody-target binding signal at the i-th frequency; is a time-dependent nonlinear factor; is the noise term, which represents the Gaussian noise of the kth time segment at the ith frequency.

3. The intelligent method for rapid antibody affinity determination according to claim 2, characterized in that: The S1 specifically includes: Nonlinear modulation terms and nonlinear exponential enhancement terms are introduced to perform adaptive modulation processing on the initial discrete signal, dynamically adjust the periodic change and intensity of the initial discrete signal, and obtain a discrete signal.

4. The intelligent method for rapid antibody affinity determination according to claim 1, characterized in that: The S2 specifically includes: In the implementation process of the intelligent discrete random mapping algorithm, logarithmic, absolute value and exponential operations are introduced based on discrete signals at different frequencies to construct the objective function; the objective function formula of the intelligent discrete random mapping algorithm is as follows: Where L(X) is the objective function; X is the antibody affinity; N is the total number of frequencies used in the discrete signal; i is the index variable of the frequency; K is the total number of time slices at each frequency; k is the index variable of the time slice; is the discrete signal of the kth time segment at the ith frequency; a i is the index used to adjust the nonlinear change of antibody affinity at the i-th frequency; B i is the initial value of antibody-target binding capacity at the ith frequency; C i is the kinetic constant at the ith frequency.

5. The intelligent method for rapid antibody affinity determination according to claim 4, characterized in that: The S2 specifically includes: An improved gradient descent method is introduced to calculate the gradient of the objective function through exponential terms and logarithmic terms.

6. The intelligent method for rapid antibody affinity determination according to claim 5, characterized in that: The S2 specifically includes: Based on the gradient of the objective function, a gradient smoothing parameter is introduced to update the antibody affinity and obtain the antibody affinity after iteration; an iteration threshold is set, and when the absolute value difference of the antibody affinity before and after iteration is less than the iteration threshold, the iteration is stopped to obtain the preliminary antibody affinity.

7. The intelligent method for rapid antibody affinity determination according to claim 6, characterized in that: The S2 specifically includes: The initial antibody affinity was corrected through nonlinear correction functions, introducing hyperbolic tangent function, logarithmic function and exponential function to obtain the final antibody affinity.

8. An intelligent system for rapid antibody affinity determination, applied to the intelligent method for rapid antibody affinity determination as claimed in claim 1, characterized in that: Includes the following parts: Initial signal acquisition module, signal modulation and enhancement module, antibody affinity estimation module, antibody affinity correction module, result display and report generation module; The initial signal acquisition module performs preliminary preparations for the experiment, sets the number and intensity of frequencies, monitors the antibody-target binding reaction in real time through the initial discrete signal formula, obtains and outputs the initial discrete signal, and uses the initial discrete signal as basic data for subsequent processing; the initial signal acquisition module is connected to the signal modulation and enhancement module by means of data transmission; The signal modulation and enhancement module receives the initial discrete signal, performs adaptive modulation processing on the initial discrete signal, obtains a discrete signal and outputs it; The signal modulation and enhancement module is connected to the antibody affinity estimation module by means of data transmission; The antibody affinity estimation module receives discrete signals, constructs and minimizes the objective function through an intelligent discrete random mapping algorithm, estimates the preliminary antibody affinity and outputs it; The antibody affinity estimation module is connected to the antibody affinity correction module by means of data transmission; The antibody affinity correction module receives the preliminary antibody affinity, applies a nonlinear correction function, and corrects the preliminary antibody affinity by combining a hyperbolic tangent function, a logarithmic function, and an exponential function to obtain and output the final antibody affinity; The antibody affinity correction module is connected to the result display and report generation module by means of data transmission; The result display and report generation module receives the final antibody affinity, uses the final antibody affinity data as the measurement result and displays it, and generates an experimental report at the same time.

Images