CN109002689B - T cell data processing method and device - Google Patents

Abstract

Embodiments of the present invention provide a T cell data processing method and device. The T cell data processing method includes: acquiring multiple sets of sample data, each set of sample data includes T cell data sets corresponding to different features; calculating each The T cell receptor statistics of the group T cell data set; the importance of each group of T cell receptor statistics is verified by the cross-validation method, and the importance of the specified number of sample data is screened out. High feature group; build a naive Bayesian recognition network model according to the feature group with high importance.

Description

T cell data processing method and device

technical field

The present invention relates to the field of data processing, in particular, to a T cell data processing method and device.

Background technique

With the development of computer technology, computer technology is used in more and more fields, and the operation efficiency of various fields can be improved through computer technology. In the field of medical technology, there is also a need for more technology to improve efficiency in medical procedures.

SUMMARY OF THE INVENTION

In view of this, the purpose of the embodiments of the present invention is to provide a T cell data processing method and apparatus.

A T cell data processing method provided in an embodiment of the present invention includes:

Acquiring multiple sets of sample data, each set of sample data includes T cell data sets corresponding to different characteristics;

Calculate T cell receptor statistics for each T cell dataset;

The importance of each group of T cell receptor statistics is verified by cross-validation method, and the feature groups with high importance in the specified number of sample data are screened out;

A naive Bayesian recognition network model is constructed according to the feature groups with high importance.

Optionally, after the step of constructing a naive Bayesian recognition network model according to the feature group with high importance, the method further includes:

Calculate the T cell receptor statistics of the data to be judged, and the data to be judged includes the T cell data of the target object;

The T cell receptor statistics of the data to be judged are input into the naive Bayesian identification network model to identify the target disease.

Optionally, T cell receptor statistics are calculated by:

Obtain the VJ family frequency of the T cell data to be calculated, wherein V represents the V gene in the T cell, and J represents the J gene in the T cell;

Calculate the homology within the VJ family according to the T cell data to be calculated;

The T cell receptor statistics of the T cell data to be calculated are calculated according to the VJ family frequency and the homology within the VJ family.

Optionally, the T cell receptor statistic calculated according to the VJ family frequency and the homology within the VJ family to obtain the T cell data to be calculated is expressed as the following expression:

Among them, f represents the VJ family frequency; c represents the homology within the VJ family.

Optionally, the step of calculating the homology within the VJ family according to the T cell data to be calculated includes:

the number of amino acid sequence species in the VJ family for which the T cell data to be calculated was obtained;

Calculate the information entropy of the distance matrix between the amino acid sequence within the VJ family of the T cell data to be calculated and the amino acid sequence;

The product of the number of amino acid species and the information entropy of the distance matrix between amino acid sequences and amino acid sequences within the VJ family is calculated to obtain homology within the VJ family.

Optionally, the step of calculating the information entropy of the distance matrix between amino acids and amino acids in the VJ family of the T cell data to be calculated includes:

All amino acid sequences in the VJ family of the T cell data to be calculated are aligned pairwise;

Use the scoring matrix to score the comparison results of the two amino acid sequences to obtain the distance of each pair of amino acid sequences;

Calculate the distance of all pairs of amino acid sequences to obtain the distance matrix between amino acid sequences and amino acid sequences within the VJ family;

The information entropy of the distance matrix between amino acid sequences within the VJ family is calculated.

Optionally, the scoring matrix is used to score the comparison results of pairs of amino acid sequences, and the scoring rule for obtaining the distance of each pair of amino acid sequences is:

distance(a,a)=0;

distance(a,b)=min(4,4-BLOSUM62(a,b));

Among them, a and b represent different amino acids, respectively.

Optionally, the step of verifying the importance of each group of T cell receptor statistics by a cross-validation method for each group of T cell receptor statistics, and screening out a feature group with high importance in the specified number of sample data, include:

a. After calculating the statistics of each group of T cell receptors by the cross-validation method, according to the importance obtained by the calculation result, and rank each feature in the sample data according to the importance;

b. Select the features of the top-ranked partial groups in the sorting;

Steps a and b are repeated for a set number of times, and a feature group with high importance in a specified number of sample data is selected from the features of the partial groups screened out by the set number of times.

Optionally, the step of verifying the importance of each group of T cell receptor statistics by a cross-validation method for each group of T cell receptor statistics, and screening out a feature group with high importance in the specified number of sample data, include:

After calculating the statistics of each group of T cell receptors by the cross-validation method, according to the importance obtained according to the calculation result, the respective features in the sample data are sorted according to the importance;

A specified number of highly important T cell receptor groups ranked high in the selection sort.

Optionally, the step of verifying the importance of each group of T cell receptor statistics by a cross-validation method for each group of T cell receptor statistics, and screening out a feature group with high importance in the specified number of sample data, include:

The importance of each group of T cell receptor statistics was verified by random forest and cross-validation methods, and the feature groups with high importance in the specified number of sample data were screened.

The embodiment of the present invention also provides a T cell data processing device, including:

an acquisition module, used for acquiring multiple groups of sample data, wherein each group of the sample data includes T cell data sets corresponding to different characteristics;

a first computing module for computing the T cell receptor statistics of each T cell dataset;

The screening module is used to verify the importance of each group of T cell receptor statistics by cross-validation method for each group of T cell receptor statistics, and screen out the feature groups with high importance in the specified number of sample data;

A building module is used to build a naive Bayesian recognition network model according to the feature group with high importance.

Compared with the prior art, the T cell data processing method and device according to the embodiment of the present invention construct a recognition network by calculating and screening multiple sets of detection data to obtain data with relatively high importance. The Naive Bayesian recognition network model can better judge the data that needs to be judged.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the following specific embodiments are given and described in detail in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.

FIG. 1 is a schematic block diagram of an electronic device according to an embodiment of the present invention.

FIG. 2 is a flowchart of a method for processing T cell data according to an embodiment of the present invention.

FIG. 3 is a flowchart of calculating T cell receptor statistics according to the T cell data processing method provided by the embodiment of the present invention.

FIG. 4 is a partial flowchart of the T cell data processing method provided by the embodiment of the present invention

FIG. 5 is a schematic diagram of functional modules of a T cell data processing apparatus according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

As shown in FIG. 1 , it is a schematic block diagram of an electronic device 100 . The electronic device 100 includes a memory 111 , a storage controller 112 , a processor 113 , a peripheral interface 114 , an input and output unit 115 , and a display unit 116 . Those of ordinary skill in the art can understand that the structure shown in FIG. 1 is only for illustration, and does not limit the structure of the electronic device 100 . For example, the electronic device 100 may also include more or fewer components than shown in FIG. 1 , or have a different configuration than that shown in FIG. 1 . The electronic device 100 in this embodiment may be a computing device with image processing capability, such as a personal computer, an image processing server, a vehicle-mounted device, or a mobile electronic device.

The elements of the memory 111 , the storage controller 112 , the processor 113 , the peripheral interface 114 , the input/output unit 115 and the display unit 116 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements may be electrically connected to each other through one or more communication buses or signal lines. The memory 111 stores at least one software function module in the form of software or firmware (Firmware), or a software function module is solidified in an operating system (Operating System, OS) of the electronic device 100 . The processor 113 is used to execute executable modules stored in the memory.

Wherein, the memory 111 may be, but not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM), or Erasable Programmable Read-Only Memory (EPROM), Electrical Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 111 is used to store a program, and the processor 113 executes the program after receiving the execution instruction, and the method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present invention can be applied to processing in the processor 113 , or implemented by the processor 113 .

The processor 113 may be an integrated circuit chip with signal processing capability. The above-mentioned processor 113 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The peripheral interface 114 couples various input/input devices to the processor 113 and the memory 111 . In some embodiments, peripheral interface 114, processor 113, and memory controller 112 may be implemented in a single chip. In other instances, they may be implemented by separate chips.

The input and output unit 115 is used for providing input data to the user. The input and output unit 115 may be, but not limited to, a mouse, a keyboard, and the like.

The display unit 116 provides an interactive interface (eg, a user operation interface) between the electronic device 100 and the user or is used to display image data for the user's reference. In this embodiment, the display unit may be a liquid crystal display or a touch display. In the case of a touch display, it can be a capacitive touch screen or a resistive touch screen that supports single-point and multi-touch operations. Supporting single-point and multi-touch operation means that the touch display can sense the touch operation from one or more positions on the touch display at the same time, and hand over the sensed touch operation to the processor. calculation and processing.

Graves' disease (GD) is an organ-specific autoimmune disease with a prevalence of 0.5%-2% in the population. Graves' ophthalmopathy (GO) is the most common complication of GD. 25%-50% of GD patients will be accompanied by GO during the course of the disease, manifesting as proptosis, pain, and visual impairment. The existing treatment of GO is mainly aimed at patients with moderate to severe activity, giving hormone shocks to suppress immune and inflammatory responses. However, this treatment is not effective for some patients, and there are adverse reactions such as hypertension, infection, and osteoporosis. Therefore, regardless of the disease itself or the treatment method, GO seriously affects the physical and mental health of patients, and optimizing the existing diagnosis and treatment plan has always been a research hotspot in the field.

Orbital fibroblasts are the target cells of GO. Under the traditional diagnostic system, orbital fibroblasts in patients with GO have already been activated and proliferated, and an irreversible tissue remodeling process has been initiated. At this time, hormonal shock can only improve the orbital inflammatory response, but cannot stop or reverse tissue fibrotic remodeling. Therefore, if the occurrence of GO in GD patients can be predicted early, the progression of the disease can be blocked by preventive treatment before the activation and proliferation of orbital fibroblasts, and the occurrence of GO can be fundamentally delayed or even prevented.

In recent years, many GO susceptibility studies have been reported, but no reports have successfully predicted the occurrence of GO. HLA, CTLA-4, TNF, TSHR, TPO, PTPN12, MTHFR (tetramethyltetrahydrofolate), TSLP (thymic stromal lymphopoietin) and other gene polymorphisms may be associated with the occurrence of GO, but due to gene linkage disequilibrium Due to factors such as flaws in experimental design and other factors, these studies did not carry out follow-up prediction-related experiments. High TRAb titers, smoking, or treatment for GD were associated with the occurrence of GO, but lacked a clear causal association and could not be used as a predictor.

An in-depth understanding of the pathogenesis of GO will help to find appropriate levels and angles for prediction and intervention. GO is an autoimmune-mediated inflammatory disease, and orbital tissue is massively infiltrated with mononuclear cells, mainly including CD4+ T cells. GWAS studies have reported that GO susceptibility genes include HLA, CTLA-4 and IL-23R, which are mainly concentrated in the pathways of T cell antigen presentation and activation. The occurrence of GO is that the body breaks the immune tolerance of T cells to self-antigens under the combined action of genetics and the environment, and then antigen-specific T cells conduct specific cross-reactions in the thyroid and orbital tissues to initiate the activation of orbital fibroblasts. T Cell Receptor (TCR) is a molecular structure that T cells specifically recognize and bind to antigenic peptide-MHC, and is an important marker for mediating T cell-specific immune responses. When T cells are stimulated by antigen, there will be significant clonal expansion, and the overall diversity and dominant family of TCR will be significantly shifted. Therefore, TCR plays an important mediating role in the occurrence and progression of GO in GD patients, and the inventor's research believes that GO characteristic TCR can help predict the occurrence of GO in GD patients.

The TCR repertoire contains the sum total of all functionally diverse T cells in an individual, and comprehensively reflects the cellular immune status. TCR is a high-dimensional data that contains information from multiple perspectives such as diversity and clonal expansion, which brings great difficulty to fully reflect its true state. It is conservatively estimated that the TCR diversity in humans is as high as 1012-1015. This diversity is due to rearrangement of the TCR germline gene V/D/J segment during T cell development and nucleotide indels during rearrangement. To facilitate TCR data analysis, 80 Vα and 65 Vβ genes of TCR were divided into 32 Vα and 24 Vβ subfamilies according to V gene homology. Thus, the frequency of TCR VJ families can be calculated from the alignment of the high-throughput sequencing data results. On the other hand, the diversity of TCRs changes continuously with changes in the external environment. When stimulated by antigens or antigenic determinants, T cells will undergo significant clonal proliferation, showing that each TCR subfamily in the TCR VJ family is diverse, but The homology is high and the structural difference is small. Therefore, the VJ family frequency of TCR alone cannot fully describe the true state of TCR, and the VJ family structure and homology of TCR should also be considered. Based on the above research, the present application can conduct processing research on T cell data through the following examples.

Please refer to FIG. 2 , which is a flowchart of a T cell data processing method applied to the electronic device shown in FIG. 1 provided by an embodiment of the present invention. The specific flow shown in FIG. 2 will be described in detail below.

Step S201, acquiring multiple sets of sample data.

In this embodiment, each group of the sample data includes T cell data sets corresponding to different features.

In this embodiment, each group of sample data may be T cell data corresponding to each feature collected for a user or patient. Each feature can be a TCR data set.

In one application scenario, the T cell data processing method in this embodiment is used to construct a data identification network for identifying the prediction of GO likely to occur in GD patients. In this application scenario, the multiple sets of sample data may be T cell data sets corresponding to different characteristics of GD patients. Each sample may carry multiple sets of features, which may include: TRBV12.5_TRBJ2.7, TRBV2_TRBJ2.3, TRBV5.1_TRBJ1.1, TRBV5.1_TRBJ1.2, etc., which will not be described one by one here.

Step S202, calculating the T cell receptor statistics of each group of T cell data sets.

In this embodiment, it can be calculated according to the internal homology of the T cell VJ family and the VJ family frequency in the T cell data set. The T cell receptor statistics can reflect the frequency and internal homology of T cell receptors.

Step S203 , verify the importance of each group of T cell receptor statistics by a cross-validation method, and select feature groups with high importance in the specified number of sample data.

Step S204, constructing a naive Bayesian recognition network model according to the feature group with high importance.

The data of the target user can be identified through the naive Bayesian identification network model.

Further, when the naive Bayesian recognition network model is used to predict the body of the target user, the calculation prediction is performed using the data corresponding to the feature group with high importance of the user.

In the T cell data processing method of the embodiment of the present invention, a recognition network is constructed by using data with relatively high importance obtained by computing and screening multiple sets of detection data, and the constructed Naive Bayesian recognition network model can be more Good judgment on the data that needs to be judged.

In this embodiment, as shown in FIG. 3 , the T cell receptor statistics can be calculated through the following steps.

Step S301, obtaining the VJ family frequency of the T cell data to be calculated.

Wherein, V represents the V gene in the T cell, and J represents the J gene in the T cell.

Step S302, calculating the homology within the VJ family according to the T cell data to be calculated.

Step S303, calculating the T cell receptor statistics of the T cell data to be calculated according to the VJ family frequency and the homology within the VJ family.

Further, the T cell receptor statistic calculated according to the VJ family frequency and the homology within the VJ family to obtain the T cell data to be calculated is expressed as the following expression:

Among them, f represents the VJ family frequency; c represents the homology within the VJ family.

In this embodiment, the step of calculating the homology within the VJ family according to the T cell data to be calculated includes:

the number of amino acid sequence species in the VJ family for which the T cell data to be calculated was obtained;

Calculate the information entropy of the distance matrix between the amino acid sequence within the VJ family of the T cell data to be calculated and the amino acid sequence;

The product of the number of amino acid sequence species and the information entropy of the distance matrix between amino acid sequences and amino acid sequences within the VJ family is calculated to obtain the homology within the VJ family.

Further, the calculation formula of homology within the VJ family can be expressed as:

c=v×e;

Among them, v represents the number of amino acid sequence species in the VJ family, and e represents the information entropy of the distance matrix between the amino acid sequences in the VJ family and the amino acid sequences.

In this embodiment, the step of calculating the information entropy of the distance matrix between the amino acid sequence in the VJ family of the T cell data to be calculated and the amino acid sequence includes:

Aligning all amino acid sequences within the VJ family of the T cell data to be calculated;

Use the scoring matrix to score pairs of amino acid sequences to obtain the distance of each pair of amino acid sequences;

Calculate the distance of all pairs of amino acid sequences to obtain the distance matrix between amino acid sequences and amino acid sequences within the VJ family;

The information entropy of the distance matrix between amino acid sequences within the VJ family is calculated.

Further, the calculation formula of the information entropy of the distance matrix between the amino acid sequence and the amino acid sequence in the VJ family can be expressed as: e=-Σd×log(d).

Wherein, d represents the distance between the amino acid sequence and the amino acid sequence within the VJ family. In one embodiment, the distances between amino acid sequences can be aligned using a weighted Hamming distance. Further, a gap penalty mechanism can be introduced to improve the situation of inconsistent amino acid lengths.

Wherein, the calculation of the distance between the amino acid sequence and the amino acid sequence in the VJ family can be expressed as the following process:

First, all amino acid sequences can be aligned using ClustalW software;

Use the scoring matrix to score the distance between pairs of amino acid sequences. For example, use the BLOSUM62substitution matrix to score pairs of amino acids and amino acids. The scoring rules are as follows:

distance(a,a)=0;

distance(a,b)=min(4,4-BLOSUM62(a,b));

Among them, a and b respectively represent different amino acids. In one example, both gap opening and gapexpansion penalties are set to 8.

In this embodiment, the step S203 includes: verifying the importance of each group of T cell receptor statistics through random forest and cross-validation methods, and screening out a specified number of sample data that are important in high-sex trait group.

In this embodiment, the step S203 includes:

a. After calculating the statistics of each group of T cell receptors by the cross-validation method, according to the importance obtained by the calculation result, and rank each feature in the sample data according to the importance;

b. Select the features of the top-ranked partial groups in the sorting;

Steps a and b are repeated for a set number of times, and a feature group with high importance in a specified number of sample data is selected from the features of the partial groups screened out by the set number of times.

In this embodiment, the top fifty, sixty, seventy and other features can be filtered out each time. It can be known that, as for the selected quantity, those skilled in the art can set it according to requirements. where each feature is a TCR.

In one example, each set of sample data includes T cell data sets corresponding to multiple features. However, not every T-cell dataset of features will play a leading role in the identification of the target disease. Therefore, screening out the features with relatively high importance as the construction of a naive Bayesian recognition network model can reduce the amount of computation and improve the identification efficiency.

Further, after repeating the calculation for many times, a feature group with high importance in a specified number of sample data can be selected from the features appearing in the first fifty, sixty, seventy, etc. numbers. For example, feature A is ranked in the top fifty in each ranking, and feature A can be selected as a feature in a feature group with high importance.

In one embodiment, the feature group with high importance is TCR that has a greater impact on GO (Graves'ophthalmopathy, Graves ophthalmopathy) and GH (Graves'hyperthyroidism, Graves hyperthyroidism). Among them, GO and GH are Graves' disease (GD), which is a complication of organ-specific autoimmune diseases.

In this embodiment, 24 groups of feature groups can be selected after the above screening, namely: TRBV12.5_TRBJ2.7, TRBV2_TRBJ2.3, TRBV5.1_TRBJ1.1, TRBV5.1_TRBJ1.2, TRBV6.5_TRBJ1.5, TRBV7.8_TRBJ2 .7, TRBV7.9_TRBJ2.2, TRBV9_TRBJ1.1, TRBV9_TRBJ2.2, TRBV9_TRBJ2.3, TRBV11.2_TRBJ2.7, TRBV19_TRBJ1.5, TRBV19_TRBJ1.1, TRBV20.1_TRBJ1.3, TRBV6.6_TRBJ1.1, TRBV7 .7, TRBV24.1_TRBJ1.6, TRBV6.1_TRBJ1.5, TRBV10.2_TRBJ2.3, TRBV15_TRBJ1.3, TRBV7.3_TRBJ1.6, TRBV7.3_TRBJ1.6.

Of course, more or less feature groups can be filtered out.

In this embodiment, by filtering out feature groups with relatively high importance as a naive Bayesian recognition network model, it can be more accurate to predict when GO or GH is judged.

In this embodiment, the step S203 includes: after calculating the statistics of each group of T cell receptors by the cross-validation method, according to the importance obtained according to the calculation result, and according to the importance The various features are sorted;

A specified number of highly important T cell receptor groups ranked high in the selection sort.

In this embodiment, the naive Bayesian recognition network model constructed above can also be used to estimate the potential target disease of the user, as shown in FIG. 4 , the method further includes:

Step S401: Calculate the T cell receptor statistics of the data to be determined, where the data to be determined includes the T cell data of the target object.

Step S402 , input the T cell receptor statistics of the data to be determined into the naive Bayesian identification network model to identify the target disease.

In this embodiment, the naive Bayesian recognition network model can be used to classify and predict the data to be judged. Classification prediction can obtain that the data to be judged is GH and GO.

The following shows the results of testing multiple examples using the T cell data processing method in this example:

1) Display of the diagnostic results of 17 patients with GH and GO

GO is 70% correct and GH is 85.7% correct.

2) Prediction results of 7 patients who progressed from GH to GO

The prediction accuracy in the following example is 71.5%.

sample number GH probability GO probability forecast result Real GO happens WL0581 1.46E-02 9.85E-01 GO Yes WL0682 5.68E-01 4.32E-01 GH Yes WL0594 7.14E-03 9.93E-01 GO Yes WL0539 9.98E-01 2.23E-03 GH Yes WL0551 6.02E-06 1.00E+00 GO Yes WL0613 2.42E-01 7.58E-01 GO Yes WL0648 3.88E-08 1.00E+00 GO Yes

The above prediction results in this embodiment are the results obtained by using the naive Bayesian recognition network model for prediction, and the real results are the data obtained by collecting the on-site situation of the corresponding user afterwards.

The above two tables are the results obtained by performing prediction calculations on some instances, and the predicted results may be higher than the above instances in practical applications.

Please refer to FIG. 5 , which is a schematic diagram of functional modules of the T cell data processing apparatus shown in FIG. 1 according to an embodiment of the present invention. The T cell data processing apparatus in this embodiment is used to execute each step in the above method embodiment. The T cell data processing device includes:

an acquisition module 501, configured to acquire multiple groups of sample data, wherein each group of the sample data includes T cell data sets corresponding to different characteristics;

a first calculation module 502, configured to calculate the T cell receptor statistics of each group of T cell data sets;

The screening module 503 is used to verify the importance of each group of T cell receptor statistics by cross-validation method, and screen out the feature groups with high importance in the specified number of sample data;

The building module 504 is configured to build a naive Bayesian recognition network model according to the feature group with high importance.

For other details of this embodiment, further reference may be made to the descriptions in the foregoing method embodiments, which will not be repeated here.

In the T cell data processing device of the embodiment of the present invention, a recognition network is constructed by using data with relatively high importance obtained by calculating and screening multiple sets of detection data, and the constructed Naive Bayesian recognition network model can be more Good judgment on the data that needs to be judged.

In this embodiment, the T cell data processing device further includes:

The second computing module is used to calculate the T cell receptor statistics of the data to be determined, and the data to be determined includes the T cell data of the target object;

The identification module is used for inputting the T cell receptor statistics of the data to be judged into the naive Bayesian identification network model to identify the target disease.

In this embodiment, the first computing module 502 or the second computing module is further used for:

Obtain the VJ family frequency of the T cell data to be calculated, wherein V represents the V gene in the T cell, and J represents the J gene in the T cell;

Calculate the homology within the VJ family according to the T cell data to be calculated;

The T cell receptor statistics of the T cell data to be calculated are calculated according to the VJ family frequency and the homology within the VJ family.

In this embodiment, the second computing module is used for:

Obtain the VJ family frequency of the T cell data to be calculated, wherein V represents the V gene in the T cell, and J represents the J gene in the T cell;

Calculate the homology within the VJ family according to the T cell data to be calculated;

The T cell receptor statistics of the T cell data to be calculated are calculated according to the VJ family frequency and the homology within the VJ family.

In this embodiment, the T cell receptor statistic obtained by calculating the T cell data to be calculated according to the VJ family frequency and the homology within the VJ family is expressed as the following expression:

Among them, f represents the VJ family frequency; c represents the homology within the VJ family.

The first computing module 502 or the second computing module is also used for:

the number of amino acid sequence species in the VJ family for which the T cell data to be calculated was obtained;

Calculate the information entropy of the distance matrix between the amino acid sequence within the VJ family of the T cell data to be calculated and the amino acid sequence;

The product of the number of amino acid species and the information entropy of the distance matrix between amino acid sequences and amino acid sequences within the VJ family is calculated to obtain homology within the VJ family.

The first computing module 502 or the second computing module is also used for:

Aligning all amino acid sequences within the VJ family of the T cell data to be calculated;

Use the scoring matrix to score pairs of amino acids to get the distance of each pair of amino acid sequences

Calculate the distance of all pairs of amino acid sequences to obtain the distance matrix between amino acid sequences and amino acid sequences within the VJ family;

The information entropy of the distance matrix between amino acid sequences within the VJ family is calculated.

The first computing module 502 is also used for:

distance(a,a)=0;

distance(a,b)=min(4,4-BLOSUM62(a,b));

Among them, a and b represent different amino acids, respectively.

In this embodiment, the screening module 503 is also used for:

a. After calculating the statistics of each group of T cell receptors by the cross-validation method, according to the importance obtained by the calculation result, and rank each feature in the sample data according to the importance;

b. Select the features of the top-ranked partial groups in the sorting;

The above two modules a and b are repeated for a set number of times, and a feature group with high importance in the specified number of sample data is selected from the features of the top-ranked partial groups filtered out by the set number of times.

In this embodiment, the screening module 503 is also used for:

The importance of each group of T cell receptor statistics was verified by random forest and cross-validation methods, and the feature groups with high importance in the specified number of sample data were screened.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention. It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (7)

1. A method of T-cell data processing, comprising:

acquiring a plurality of groups of sample data, wherein each group of sample data comprises T cell data sets corresponding to different characteristics;

calculating T cell receptor statistics for each set of T cell datasets: obtaining VJ family frequency of T cell data to be calculated, calculating to obtain internal homology of a VJ family according to the T cell data to be calculated, and calculating to obtain T cell receptor statistic of the T cell data to be calculated according to the VJ family frequency and the internal homology of the VJ family; wherein V represents a V gene in the T cell, J represents a J gene in the T cell, and T cell receptor statistics of the T cell data to be calculated based on the VJ family frequency and homology within the VJ family are represented by the following expression:

wherein f represents a VJ family frequency; c represents homology within the VJ family;

verifying the importance of each group of T cell receptor statistic by a cross-validation method, and screening out a characteristic group with high importance in a specified amount of sample data;

and constructing a naive Bayes recognition network model according to the feature group with high importance.

2. The T-cell data processing method of claim 1, wherein the step of calculating the homology within the VJ family from the T-cell data to be calculated comprises:

obtaining a number of amino acid sequence species in the VJ family of the T cell data to be calculated;

calculating the information entropy of the distance matrix between the amino acid sequences and the VJ family internal amino acid sequences of the T cell data to be calculated;

and calculating the product of the number of the amino acid types and the information entropy of the distance matrix between the amino acid sequences and the amino acid sequences in the VJ family to obtain the homology in the VJ family.

3. The T-cell data processing method according to claim 2, wherein the step of calculating the entropy of the distance matrix between the amino acid sequence and the amino acid sequence within the VJ family of the T-cell data to be calculated comprises:

pairwise alignment of all amino acid sequences within the VJ family of the T cell data to be calculated;

using a scoring matrix to score the comparison result of every two amino acid sequences to obtain the distance between each pair of amino acid sequences;

calculating the distance between every two amino acid sequences to obtain a distance matrix between the amino acid sequences in the VJ family;

calculating the entropy of information of the distance matrix between the amino acid sequences and the amino acid sequences in the VJ family.

4. The method of T-cell data processing according to claim 3, wherein two amino acid sequences are scored using a scoring matrix, and the scoring rule for the distance between each pair of amino acid sequences within the VJ family is:

distance (a, a) is 0;

distance (a, b) ═ min (4,4-BLOSUM62(a, b));

wherein a and b represent different amino acids.

5. The method of T-cell data processing according to claim 1, wherein said step of cross-validating the importance of each T-cell receptor statistic group by each T-cell receptor statistic group and selecting a feature group of high importance among a given number of sample data comprises:

a. after each group of T cell receptor statistics is calculated through the cross-validation method, the importance is obtained according to the calculation result, and all the characteristics in the sample data are ranked according to the importance;

b. selecting the characteristics of the part group which is ranked at the top in the ranking;

and (c) repeating the steps a and b for the set times, and selecting a characteristic group with high importance in the sample data of a specified number from the characteristics of the part group which is screened out from the set times and is ranked at the top.

6. The method of T-cell data processing according to claim 1, wherein said step of cross-validating the importance of each T-cell receptor statistic group by each T-cell receptor statistic group and selecting a feature group of high importance among a given number of sample data comprises:

and verifying the importance of the T cell receptor statistics of each group by a random forest and cross verification method, and screening out a characteristic group with high importance in the sample data of a specified number.

7. A T-cell data processing apparatus, comprising:

the acquisition module is used for acquiring a plurality of groups of sample data, wherein each group of sample data comprises T cell data sets corresponding to different characteristics;

a first calculation module for calculating T cell receptor statistics for each set of T cell datasets: obtaining VJ family frequency of T cell data to be calculated, calculating to obtain internal homology of a VJ family according to the T cell data to be calculated, and calculating to obtain T cell receptor statistic of the T cell data to be calculated according to the VJ family frequency and the internal homology of the VJ family; wherein V represents a V gene in the T cell, J represents a J gene in the T cell, and T cell receptor statistics of the T cell data to be calculated based on the VJ family frequency and homology within the VJ family are represented by the following expression:

wherein f represents a VJ family frequency; c represents homology within the VJ family;

the screening module is used for verifying the importance of each group of T cell receptor statistic by a cross-validation method and screening out a characteristic group with high importance in a specified amount of sample data;

and the construction module is used for constructing a naive Bayes recognition network model according to the feature group with high importance.

Images