Method, computing device and storage medium for predicting predetermined disease risk

By obtaining gene sequencing and non-gene data, using regression algorithms to calculate pre-determined disease risk scores, combined with multi-gene and multi-non-gene factor information, the problems of strong invasiveness, poor lag and accuracy in traditional methods are solved, and individuals are sooner , more accurate prediction of predetermined disease risk.

CN113707222BActive Publication Date: 2024-12-06SHIHUA MEDICAL TECH (SUZHOU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110858283.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-28
Publication Date
2024-12-06
Estimated Expiration
2041-07-28

AI Technical Summary

Technical Problem

Traditional methods for predicting the risk of pre-determined diseases have problems such as strong invasiveness, poor lag and accuracy, and it is difficult to achieve an individual's earlier and more accurate prediction of the risk of developing into a pre-determined disease.

Method used

By obtaining gene sequencing data and associated non-gene data for multiple samples to be tested, a weight function of the effect of gene mutations and non-gene data on the phenotype is determined using a regression algorithm, a predetermined disease risk score for the sample to be tested is calculated, and based on Comparison of absolute risks and thresholds predicts disease risk, combining multi-gene and multi-non-gene factor information to maximize the capture of predetermined disease signals.

Benefits of technology

It realizes risk prediction for individuals that develop into predetermined diseases earlier and more accurately, breaks through single-gene dimensions, integrates multi-source information based on systematic medical principles, and improves prediction accuracy and early detection capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113707222B_ABST
    Figure CN113707222B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method, computing device and storage medium for predicting the risk of a predetermined disease. The method includes: generating gene mutation data of multiple genes of each sample to be tested; obtaining multiple non-gene data associated with each sample to be tested; determining a weight function for indicating the influence of gene mutation and non-gene data on the phenotype of each sample to be tested via a regression algorithm; for each sample to be tested, based on the gene mutation, non-gene data and corresponding weights on each gene, calculating the risk score of the subject to be tested for the occurrence of a predetermined disease; and based on the calculated risk score of the subject to be tested for the occurrence of a predetermined disease, determining the absolute risk of the subject to be tested for the occurrence of a predetermined disease within a predetermined time, so as to predict the risk of the predetermined disease of the sample to be tested. The present disclosure can predict the risk of developing a predetermined disease for an individual earlier and more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates generally to biological information processing, and in particular, to methods, computing devices, and storage media for predicting a predetermined disease risk. Background Art

[0002] Even though modern medicine has made great progress, some complex predetermined diseases (such as but not limited to cancer) are still one of the important causes of human death. Cancer originates from a multi-stage process in which normal cells transform into tumor cells. It takes a process for precancerous lesions to develop into malignant tumors, and it is common for clinical manifestations to appear late. If cases of predetermined diseases can be detected and treated early, the mortality rate of cancer patients can be reduced to a certain extent. Therefore, early and accurate prediction of the risk of predetermined diseases (such as cancer) becomes particularly important.

[0003] Traditional solutions for early screening or predicting the risk of a predetermined disease (such as cancer) mainly include: imaging screening, endoscopic screening, tumor marker screening and polygenic risk score (PRS) prediction. For imaging screening, it usually requires the tumor to reach a certain size before it can be effectively detected, so there is a lag. In addition, the ultrasound, X-ray, CT, MRI and other testing methods used in imaging screening are usually accompanied by radiation. For endoscopic screening, the gastroscope, colonoscopy, cystoscope, etc. used have the disadvantages of being highly invasive, prone to discomfort and cross-infection, and the detection range is relatively limited. For tumor marker screening, it has the disadvantages of high false negative rate and false positive rate. The polygenic risk score (PRS) is mainly calculated by calculating the effect size weighted score of multiple single nucleotide polymorphisms (SNPs) to calculate the risk score to identify different levels of risk of the occurrence of a predetermined disease. However, PRS reflects the probability of genetic risk, and the occurrence of most complex diseases (such as cancer) is the result of the interaction between genetic and environmental factors (such as smoking, drinking, air pollution, etc.). Therefore, PRS technology that only considers genetic risk is difficult to accurately predict the risk of an individual developing a predetermined disease.

[0004] In summary, traditional methods for predicting the risk of a predetermined disease have shortcomings such as being highly invasive, having a significant lag, or having poor accuracy, making it difficult to effectively predict the risk of developing a predetermined disease earlier and more accurately for an individual. Summary of the invention

[0005] The present disclosure provides a method, a computing device, and a computer storage medium for predicting the risk of a predetermined disease, which can predict the risk of developing a predetermined disease for an individual earlier and more accurately.

[0006] According to a first aspect of the present disclosure, a method for predicting the risk of a predetermined disease is provided. The method comprises: obtaining gene sequencing data of a plurality of samples to be tested, so as to generate gene mutation data of a plurality of genes of each sample to be tested;

[0007] Acquire multiple non-genetic data associated with each sample to be tested; determine a weight function indicating the effects of gene mutation and non-genetic data on the phenotype of each sample to be tested through a regression algorithm; for each sample to be tested, calculate the risk score of the subject to be tested for the occurrence of a predetermined disease based on the gene mutation data, non-genetic data and corresponding weights on each gene; and based on the calculated risk score of the subject to be tested for the occurrence of the predetermined disease, determine the absolute risk of the subject to be tested for the occurrence of the predetermined disease within a predetermined time, so as to predict the risk of the predetermined disease of the sample to be tested based on a comparison between the absolute risk and a predetermined threshold.

[0008] According to the second aspect of the present invention, a computing device is also provided, which includes: at least one processing unit; at least one memory, which is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the computing device executes the method of the first aspect of the present disclosure.

[0009] According to a third aspect of the present disclosure, a computer-readable storage medium is further provided. The computer-readable storage medium stores machine-executable instructions, which, when executed, enable a machine to perform the method of the first aspect of the present disclosure.

[0010] In some embodiments, the method for predicting a predetermined disease risk also includes: obtaining multiple predetermined omics data associated with each sample to be tested; and normalizing the generated gene mutation data of multiple genes of each sample to be tested, the acquired multiple non-gene data and the multiple predetermined omics data to determine the synergistic effects of the gene mutation, non-gene data and the predetermined omics data on the phenotype of each sample to be tested.

[0011] In some embodiments, determining a weight function for indicating the impact of mutation and non-genetic data on the phenotype of each sample to be tested includes: determining a weight function for the synergistic impact of multiple rare variants and multiple rare variants on the phenotype of each sample to be tested based on a sequence kernel association test algorithm.

[0012] In some embodiments, predicting the risk of a predetermined disease for a sample to be tested based on a comparison between the absolute risk and a predetermined threshold includes: calculating the absolute risk of the subject to be tested developing the predetermined disease within a predetermined time period based on the risk score of the sample to be tested, risk factor distribution data, and the incidence and mortality rate of the predetermined disease in a target population of a predetermined age; determining whether the absolute risk is greater than or equal to a predetermined threshold; in response to determining that the absolute risk is greater than or equal to the predetermined threshold, determining that the subject to be tested meets a high-risk condition for the predetermined disease; and in response to determining that the absolute risk is less than the predetermined threshold, determining that the subject to be tested does not meet the high-risk condition for the predetermined disease.

[0013] In some embodiments, calculating the risk score of the subject to which the sample to be tested belongs for the occurrence of a predetermined disease includes: calculating the risk score of the subject to which the sample to be tested belongs for the occurrence of a predetermined disease based on the weighted sum of the gene mutation data on each gene and the corresponding gene mutation weight, the product of the non-gene data and the corresponding non-gene data weight, and the product of the predetermined omics data and the corresponding omics data weight.

[0014] In some embodiments, the non-genetic data is generated based on at least one of microbial data, cell data, clinical information, immune marker information, and image data of a target area of ​​a subject to which the sample to be tested belongs, associated with the sample to be tested.

[0015] In some embodiments, the predetermined omics data includes at least one of transcriptomics data, proteomics data, and metabolomics data.

[0016] In some embodiments, for each non-genetic data, the non-genetic data sub-weight corresponding to each gene is superimposed to generate the corresponding non-genetic data weight for each non-genetic data; and for each predetermined omics data, the omics data sub-weight corresponding to each gene is superimposed to generate the corresponding omics data weight for each predetermined omics data.

[0017] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the disclosure, nor is it intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a system for predicting a predetermined disease risk according to an embodiment of the present disclosure is shown.

[0019] Figure 2 A flow chart of a method for predicting a predetermined disease risk according to an embodiment of the present disclosure is shown.

[0020] Figure 3A flow chart of a method for determining the influence of a gene mutation, a plurality of acquired non-genetic data, and a plurality of predetermined omics data on a phenotypic effect according to an embodiment of the present disclosure is shown.

[0021] Figure 4 A flow chart of a method for predicting a predetermined disease risk of a sample to be tested according to an embodiment of the present disclosure is shown.

[0022] Figure 5 A schematic diagram showing a method for comparing an absolute risk with a predetermined threshold according to an embodiment of the present disclosure is shown.

[0023] Figure 6 A block diagram of an electronic device suitable for implementing the embodiments of the present disclosure is schematically shown.

[0024] In the various drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0025] The preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0026] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects.

[0027] As mentioned above, traditional methods for early screening or predicting the risk of a predetermined disease (such as but not limited to cancer) mainly include: imaging screening, endoscopic screening, tumor marker screening, and polygenic risk score (PRS) prediction. The above methods have the disadvantages of being highly invasive, significantly lagging, or having poor accuracy. Therefore, traditional methods for early screening or predicting the risk of a predetermined disease are difficult to achieve earlier and more accurate prediction of the risk of developing a predetermined disease for an individual.

[0028] In order to at least partially solve one or more of the above problems and other potential problems, the exemplary embodiments of the present disclosure propose a scheme for predicting the risk of a predetermined disease. In this scheme, gene mutation data of multiple genes of the sample to be tested is generated based on gene sequencing data, and multiple non-gene data associated with the sample to be tested is obtained; then, via a regression algorithm, a weight function for indicating the influence of gene mutation and non-gene data on the phenotype of each sample to be tested is determined. The present disclosure can obtain the synergistic influence of different data sources such as gene mutation data and non-gene data on the phenotype of the sample to be tested. In addition, the present disclosure calculates the risk score of the object to be tested for each sample to be tested based on the gene mutation data, non-gene data on each gene and their corresponding weights; and based on the calculated risk score of the sample to be tested, the absolute risk of the object to be tested within a predetermined time is determined to predict the risk of the predetermined disease of the sample to be tested. The present disclosure can break through the risk prediction of the single gene dimension, but is based on the principle of system medicine, and collects multi-source information such as multi-gene and multi-non-gene factors through a model algorithm to maximize the capture of predetermined disease signals. It should be understood that the occurrence of a predetermined disease is caused by the combined action of multiple genes and multiple pathogenic factors, and through multiple stages of occurrence and development. When the predetermined disease occurs in the early stage, weak predetermined disease signals may occur in different parts of the body and are reflected in different data sources. Therefore, the above method disclosed in the present invention can predict the risk of developing a predetermined disease for an individual subject to be tested earlier and more accurately.

[0029] Figure 1 FIG. 1 is a schematic diagram of a system 100 for predicting a predetermined disease risk according to an embodiment of the present disclosure. Figure 1 As shown, the system 100 includes, for example, a computing device 110, a sequencing device 130, a server 140, a user terminal 150, and a network 160. The computing device 110 can exchange data with the computing device 110, the sequencing device 130, the server 140, and the user terminal 150 through the network 160 in a wired or wireless manner.

[0030] The computing device 110 is, for example, a bioinformatics server, which is used to predict the risk of a predetermined disease. Specifically, the computing device 110 can obtain, for example, gene sequencing data of multiple samples to be tested from the sequencing device 130, and obtain, for example, multiple non-gene data and predetermined omics data associated with each sample to be tested from the server 140 and the user terminal 150. The computing device 110 can also generate gene mutation data of multiple genes of each sample to be tested based on the acquired gene sequencing data; and determine a weight function for indicating the influence of gene mutation and non-gene data on the phenotype of each sample to be tested via a regression algorithm; and for each sample to be tested, based on the gene mutation data, non-gene data and corresponding weights on each gene, calculate the risk score of the subject to be tested for the occurrence of a predetermined disease. The computing device 110 can also determine the absolute risk of the subject to be tested for the occurrence of a predetermined disease within a predetermined time based on the calculated risk score of the subject to be tested for the occurrence of a predetermined disease, so as to predict the risk of the predetermined disease of the sample to be tested.

[0031] In some embodiments, computing device 110 may have one or more processing units, including dedicated processing units such as GPU, FPGA, and ASIC, and general-purpose processing units such as CPU. In addition, one or more virtual machines may also be running on each computing device.

[0032] The computing device 110 includes, for example, a gene mutation data generating unit 112, a non-gene data acquiring unit 114, a weight function determining unit 116, a risk score calculating unit 118 for a sample to be tested, and a predetermined disease risk predicting unit 120. The gene mutation data generating unit 112, the non-gene data acquiring unit 114, the weight function determining unit 116, the risk score calculating unit 118 for a sample to be tested, and the predetermined disease risk predicting unit 120 may be configured on one or more computing devices 110.

[0033] The gene mutation data generating unit 112 is used to obtain gene sequencing data about a plurality of samples to be tested, so as to generate gene mutation data of a plurality of genes of each sample to be tested.

[0034] The non-gene data acquisition unit 114 is used to acquire a plurality of non-gene data associated with each sample to be tested.

[0035] The weight function determination unit 116 is used to determine a weight function indicating the influence of gene mutation data and non-gene data on the phenotype of each sample to be tested through a regression algorithm.

[0036] The test sample risk score calculation unit 118 is used to calculate the risk score of the subject to which the test sample belongs for a predetermined disease based on the gene mutation data, non-gene data and corresponding weights on each gene for each test sample.

[0037] Regarding the predetermined disease risk prediction unit 120, it is used to determine the absolute risk of the subject to which the sample to be tested belongs to developing the predetermined disease within a predetermined time based on the calculated risk score of the subject to which the sample to be tested belongs to develop the predetermined disease, and to predict the predetermined disease risk of the sample to be tested based on the comparison between the absolute risk and a predetermined threshold.

[0038] Regarding the sequencing device 130 , it is used to perform gene sequencing based on a test sample (such as a blood sample or a tissue sample) of the test object, so as to generate gene sequencing data about multiple test samples based on the sequencing results, and send the generated gene sequencing data to the computing device 110 .

[0039] The server 140 is, for example but not limited to, a server of a medical institution, which can send non-genetic data about the user (for example, generated by at least one of microbial data, cell data, clinical information, immune marker information associated with the sample to be tested, and image data of a target area of ​​the object to which the sample to be tested belongs) and predetermined omics data (at least one of transcriptomics data, proteomics data, and metabolomics data) to the computing device 110.

[0040] The user terminal may, for example, send some of the user's non-genetic data, such as age, gender, family history of predetermined diseases, and other information to the computing device 110 .

[0041] The following will be combined Figure 2 A method for predicting a predetermined disease risk according to an embodiment of the present disclosure is described. Figure 2 FIG. 2 is a flowchart of a method 200 for predicting a predetermined disease risk according to an embodiment of the present disclosure. It should be understood that the method 200 may be implemented, for example, in Figure 6 The electronic device 600 described above is executed. Figure 1 The method 200 is executed at the described computing device 110. It should be understood that the method 200 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0042] At step 202 , the computing device 110 obtains gene sequencing data on a plurality of samples to be tested, so as to generate gene mutation data of a plurality of genes of each sample to be tested.

[0043] Gene sequencing data about a plurality of samples to be tested (eg, tissue samples or blood samples) are generated based on, for example, high-throughput sequencing.

[0044] The method of generating gene mutation data of multiple genes of each sample to be tested includes, for example, data preprocessing, data comparison and quality control, variant identification and variant annotation for the acquired gene sequencing data. Tumor gene mutation types include point mutations, insertions, deletions, gene rearrangements, copy number abnormalities and other gene mutations.

[0045] Methods for quality control of gene sequencing data include, for example, quality control based on base call quality scores, number of effective reads after filtering, effective sequencing depth, etc. In some embodiments, in order to improve the quality of generated gene mutations, mutation generation can be repeated twice. For example, after the first generation of gene mutation data, single site, insertion and deletion mutations are extracted, filtered, and basic quality scores are checked. The regenerated gene mutation data is used to predict the risk of a predetermined disease.

[0046] At step 204, the computing device 110 acquires a plurality of non-genetic data associated with each sample to be tested. In some embodiments, in addition to acquiring a plurality of non-genetic data associated with each sample to be tested, the computing device 110 also acquires predetermined omics data associated with each sample to be tested. The non-genetic data is generated based on, for example, at least one of microbial data, cell data, clinical information, immune marker information, and image data of a target area of ​​the subject to which the sample to be tested belongs, associated with the sample to be tested.

[0047] At step 206 , the computing device 110 determines, via a regression algorithm, a weight function for indicating the effects of gene mutations and non-gene data on the phenotype of each sample to be tested.

[0048] It should be understood that the occurrence of a predetermined disease (such as cancer) is usually the result of the combined effects of genetic factors and environmental factors. The following is a regression model for determining the correlation effects of multiple gene variants and non-genetic data on sample phenotypes in combination with formula (1). The regression model is, for example, a logistic regression model.

[0049] logit(Y i =1) = τS i +γ T Z i (1)

[0050] In the above formula (1), i represents the i-th sample, i=1,...,n. S i Represents weighted gene variation data Gi A linear combination of S i =ξ T G i ξ represents the weight, which is an m×1 weight vector, that is, ξ=(ξ 1 ,...,ξ m ) T . G i represents the observed gene mutation on the i-th sample, which can be a rare gene mutation or a common gene mutation. ij represents the jth gene mutation on the i-th sample. j=1,...J. τ represents the coefficient, which is a constant. γ T Represents the non-genetic data Z of the i-th sample i The associated regression coefficient vector. Z i represents the non-genetic data associated with the i-th sample, Z ij Represents the j non-genetic data on the i-th sample.

[0051] The following describes the method for determining the weight function in combination with formulas (2) to (5). 0 :When τ=0, the score statistics can be expressed as.

[0052]

[0053] In the above formula (2), represents the constrained maximum likelihood estimation using γ. U represents the score statistic. By solving the following formula (3), the variance of U can be estimated using the following formulas (4) and (5).

[0054]

[0055]

[0056]

[0057] Under the null hypothesis, the test statistic T = U / V 1 / 2 Approximately follows a standard normal distribution.

[0058] In some embodiments, a method for determining a weight function for indicating the effect of mutation data on a phenotype includes, for example, determining a weight function for the synergistic effect of multiple rare variants and multiple rare variants on the phenotype of each sample to be tested based on a sequence kernel association test algorithm.

[0059] It should be understood that traditional genome-wide association studies usually identify common variants associated with predetermined diseases (e.g., complex diseases) (common variants are, for example, genetic variants with a MAF greater than 5%), but miss the impact of rare variants (rare variants, for example, but not limited to, genetic variants with a MAF less than or equal to 5% or 1%) on complex diseases. This is mainly because GWAS is based on a mixed linear model to test genetic variants one by one, but since the frequency of occurrence of rare variants is very low, the detection efficiency of this GWAS for rare variants is low. Studies have shown that rare variants and common variants act together on the phenotype of the sample to be tested, and there is an association with non-genetic data.

[0060] Regarding the sequence kernel association test (SKAT), it is a type of variance component test. SKAT assumes that the regression coefficient of each genotype has a mean of 0 and a variance of w. j Any distribution of τ (w j is the weight of the pre-given variation j, and τ is the variance component).

[0061] When the null hypothesis is true, τ = 0. A variance component score test can be used. The corresponding variance component score statistics can be expressed as shown in the following formula (6).

[0062]

[0063] In the above formula (6), K = GWG', which represents a weighted linear function, indicating the genetic similarity between individuals. G is an n × p matrix, the value at position (i, j) is the value of gene mutation j on sample i, W = diag(ξ 1 ,...,ξ m ) contains the weights of m mutation sites. is the estimated mean of y under the null hypothesis. Under the null hypothesis, for patients with the predetermined disease, If for continuous values ​​of y, and All are estimated by regression model under the null hypothesis. Under the null hypothesis, Q satisfies a mixed chi-square distribution and can be calculated using the computationally efficient Davies method. ξ m is the pre-given weight of variation m, which reflects the relative contribution of variation m to the variance component score statistics.

[0064] The sequence kernel correlation test can extract weight values ​​from the Beta distribution. The following is an explanation of the weight value ξ in combination with formula (7): m The calculation method of .

[0065]

[0066] In the above formula (7), a1 and a2 are determined according to prior experience. In the sequence kernel association test algorithm, by default, a1 = 1 and a2 = 25. For example, the weights of rare mutations and low-frequency mutations (1% < MAF < 5%). Then, the gene mutation weights corresponding to rare mutations can be determined.

[0067] By adopting the above means, the present disclosure can comprehensively consider the effects of common mutations and rare mutations on the risk of a predetermined disease. Therefore, it can more accurately predict the risk of the predetermined disease. Moreover, by adopting SKAT, the present disclosure can directly fit and adjust the relationship between the phenotype and the gene mutation data within the gene (including common mutations and rare mutations) when non-gene data is adjusted, thereby significantly improving the efficacy of the method for determining the combined effects of rare mutations and common mutations on the phenotype.

[0068] At step 208, the computing device 110 calculates the risk score of the object to which each sample to be tested belongs for developing the predetermined disease based on the gene mutation data, non-gene data, and corresponding weights on each gene.

[0069] Regarding the method for calculating the risk score of the object to which the sample to be tested belongs for developing the predetermined disease, for example, it includes: calculating the risk score of the object to which the sample to be tested belongs for developing the predetermined disease based on the weighted sum of the gene mutation data and the corresponding gene mutation weights on each gene, the product of the non-gene data and the corresponding non-gene data weights, and the product of the predetermined omics data and the corresponding omics data weights. It should be understood that the occurrence of the predetermined disease is caused by the combined action of multiple genes and various pathogenic factors and undergoes multiple stages of occurrence and development. Among them, gene information is manifested as genomics, transcriptomics, proteomics, metabolomics, etc. in different states. By calculating the risk data of the sample to be tested, not only the combined effects of multiple gene mutations and non-gene data on the risk of the predetermined disease in the sequencing technology are considered, but also the combined effects of multiple gene mutations, non-gene factors, and other predetermined omics data on the risk of the predetermined disease are considered. Thereby, it is beneficial to more accurately predict the risk of the predetermined disease.

[0070] The following explains the algorithm for calculating the risk data of the sample to be tested with reference to formula (8). Assume that there are a total of n samples, q non-gene data, and L genes, and there are p l mutation sites on gene l (l = 1,..., L).

[0071] MRS = α 0 + α′ 1 G i1 + α′ 2 G i2 +…+ α′L G iL +β′X i +γ′Z i +∈ i , (8)

[0072] In the above formula (8), α 0 represents the intercept, represents the gene mutation weight for the lth gene. For example, p is found on the lth gene l A gene mutation. ij represents the jth gene mutation in the i-th sample. β=[β 1 ,...,β q ]′ represents the weight of non-genetic data. i Represents the non-genetic data associated with the i-th sample. γ=[γ 1 ,...γ m ]′ represents the weight of the omics data associated with the i-th sample. ij Represents the jth non-genetic data on the i-th sample. MRS represents the risk score for the occurrence of a predetermined disease for the sample to be tested. MRS is a risk score for a predetermined disease based on multiple genes, multiple non-genetic data, and multiple omics.

[0073] The following is an explanation of the non-genetic data weight β = [β 1 ,...,β q ]′ calculation method.

[0074]

[0075] In the above formula (9), q represents the number of non-genetic data. Represents the corresponding non-genetic data weight of the qth non-genetic data. The corresponding non-genetic data weight β q It is generated by superimposing the non-genetic data sub-weights corresponding to each gene for each non-genetic data. It should be understood that, for example, q non-genetic data (such as age, family history of predetermined diseases, microbial data, clinical information, immune marker information, image data of the target area of ​​the object to which the sample to be tested belongs, etc.) are the same for the object to which each sample to be tested belongs. However, for each gene in the L genes, when considering the influence of its co-data (non-genetic data), different non-genetic data weights are generated. Therefore, the non-genetic data weights for the L genes are superimposed to generate q non-genetic data weights associated with the q non-genetic data.

[0076] The following is an explanation of the omics data weight γ = [γ 1 ,...γ m ]′ calculation method.

[0077]

[0078] In the above formula (10), m represents the number of predetermined omics data. Represents the corresponding omics data weight of the mth predetermined omics data. The omics data weight γ m It is generated by superimposing the omics data sub-weights corresponding to each gene on the L genes of the sample to be tested.

[0079] At step 210, the computing device 110 determines the absolute risk of the subject to be tested developing the predetermined disease within a predetermined time based on the calculated risk score of the subject to be tested for the predetermined disease, so as to predict the risk of the predetermined disease of the sample to be tested based on a comparison between the absolute risk and a predetermined threshold.

[0080] The absolute risk indicates the probability that a subject of the sample to be tested who has a certain set of risk factors (including genetic variation data, non-genetic data and their interaction terms) will not develop a predetermined disease at a predetermined age but will develop the predetermined disease within a predetermined time period.

[0081] The predetermined time period is, for example, 5 years, 10 years, 15 years or a lifetime (ie, the life span of the subject to whom the sample to be tested belongs).

[0082] Regarding the method for predicting the risk of a predetermined disease of a sample to be tested, it includes, for example: based on the risk score of the sample to be tested, the risk factor distribution data, the morbidity and mortality rate of the predetermined disease in the target population of a predetermined age, calculating the absolute risk of the subject to be tested to develop the predetermined disease within a predetermined time period; determining whether the absolute risk is greater than or equal to a predetermined threshold; in response to determining that the absolute risk is greater than or equal to the predetermined threshold, determining that the subject to be tested meets the high risk condition for the predetermined disease; and in response to determining that the absolute risk is less than the predetermined threshold, determining that the subject to be tested does not meet the high risk condition for the predetermined disease. The following will be combined with Figure 4 The method for predicting the predetermined disease risk of the sample to be tested is described and will not be repeated here.

[0083] In the above scheme, gene mutation data of multiple genes of the sample to be tested is generated based on gene sequencing data, and multiple non-gene data associated with the sample to be tested are obtained; then, a weight function for indicating the influence of gene mutation and non-gene data on the phenotype of each sample to be tested is determined through a regression algorithm. The present disclosure can obtain the synergistic influence of different data sources such as gene mutation data and non-gene data on the phenotype of the sample to be tested. In addition, the present disclosure calculates the risk score of the object to be tested for each sample to be tested based on the gene mutation, non-gene data on each gene and their corresponding weights; and based on the calculated risk score of the sample to be tested, the absolute risk of the object to be tested within a predetermined time is determined to predict the risk of the predetermined disease of the sample to be tested. The present disclosure can break through the risk prediction of the single gene dimension, but is based on the principle of system medicine, and collects multi-source information such as multi-gene and multi-non-gene factors through a model algorithm to maximize the capture of predetermined disease signals. It should be understood that the occurrence of a predetermined disease is caused by the combined action of multiple genes and multiple pathogenic factors, and the occurrence and development of multiple stages. When the predetermined disease occurs in the early stage, weak predetermined disease signals may occur in different parts of the body and are reflected in different data sources. Therefore, the above method disclosed in the present invention can predict the risk of developing the predetermined disease for the individual subject to be tested earlier and more accurately.

[0084] The following will be combined Figure 3 A method 300 for determining the impact of multiple genes, multiple non-gene data, multiple omics data and phenotypic effects according to an embodiment of the present disclosure is described. Figure 3 FIG. 3 is a flow chart of a method 300 for determining the influence of gene mutation data, a plurality of acquired non-gene data, and a plurality of predetermined omics data on a phenotypic effect according to an embodiment of the present disclosure. It should be understood that the method 300 may be, for example, Figure 6 The electronic device 600 described above is executed. Figure 1 The method 300 is executed at the described computing device 110. It should be understood that the method 300 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0085] At step 302, the computing device 110 acquires a plurality of predetermined omics data associated with each sample to be tested. The predetermined omics data includes, for example but not limited to, at least one of transcriptomics data, proteomics data, and metabolomics data.

[0086] At step 304, the computing device 110 normalizes the generated gene mutation data of multiple genes of each sample to be tested, the obtained multiple non-gene data and multiple predetermined omics data to determine the synergistic effect of the gene mutation, non-gene data and predetermined omics data on the phenotype of each sample to be tested. By adopting the above technical means, the present disclosure can predict the risk of developing a predetermined disease for the individual subject to be tested earlier and more accurately through the combined action of multiple pathogenic factors such as multiple genes and multiple non-gene risks and multiple configuration data.

[0087] The following will be combined Figure 4 and Figure 5 Describes a method for predicting the risk of developing a disease within a predetermined time period according to an embodiment of the present disclosure Figure 4 A flow chart of a method 400 for predicting a predetermined disease risk of a sample to be tested according to an embodiment of the present disclosure is shown. Figure 5 FIG. 4 is a schematic diagram of a method 500 for comparing an absolute risk with a predetermined threshold according to an embodiment of the present disclosure. It should be understood that the method 400 may be used, for example, in Figure 6 The electronic device 600 described above is executed. Figure 1 The method 400 is executed at the described computing device 110. It should be understood that the method 400 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect.

[0088] At step 402, the computing device 110 calculates the absolute risk of the subject of the sample to be tested developing a predetermined disease within a predetermined time period based on the risk score of the sample to be tested, risk factor distribution data, and the incidence and mortality rate of the predetermined disease in the target population of a predetermined age.

[0089] The following is a method for predicting age-specific morbidity rates using formula (11).

[0090]

[0091] In the above formula (11), I(a|Z) represents the probability of disease occurrence at a predetermined age a. a represents the predetermined age. Z=(Z 1 ,…,Z k ) represents risk factors, which include gene variations (e.g., genetic risk factors), non-genetic data (e.g., environmental risk factors), and their interaction terms. In some embodiments, the risk factors also include predetermined omics data. Represents the risk score of the sample to be tested. 0(a) represents the average baseline hazard of a target population of a predetermined age for a predetermined disease, which indicates, for example, the average risk level of a target population of the same gender and age for a predetermined disease outcome. Ea represents the risk factor distribution data, which usually needs to be calculated based on the distribution of risk factor Z in a disease-free population (those who have not died of other causes by age a).

[0092] The following describes a method for determining the absolute risk within a predetermined time period in conjunction with formula (12).

[0093]

[0094] In the above formula (12), m(v|Z) represents the mortality rate at a predetermined age due to other causes. u represents a given age at which it is assumed that the subject still does not have the predetermined disease and will not die from other causes before the given age. R a,a+s represents the absolute risk that the subject of the test will develop the disease within the predetermined time period [a,s+a] at the current age a. The absolute risk within the predetermined time period is determined by the sum of the probabilities of all given ages u developing the disease within the predetermined time period.

[0095] At step 404 , computing device 110 determines whether the absolute risk is greater than or equal to a predetermined threshold.

[0096] like Figure 5As shown, mark 510 indicates the absolute risk curve of breast cancer occurring within 10 years for women between 25 and 70 years old with a risk score of less than 1% for the sample to be tested. Mark 512 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 1-5% for the sample to be tested. Mark 514 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 5-10% for the sample to be tested. Mark 516 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 10-20% for the sample to be tested. Mark 518 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 20-40% for the sample to be tested. Mark 520 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 40-60% for the sample to be tested. Mark 522 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 10-20% for the sample to be tested. Mark 524 indicates the absolute risk curve of breast cancer occurring within 10 years with a risk score of 80-90% for the sample to be tested. Mark 526 indicates an absolute risk curve for breast cancer within 10 years for a risk score of 90-95% for the sample to be tested. Mark 528 indicates an absolute risk curve for breast cancer within 10 years for a risk score of 95-99% for the sample to be tested. Mark 530 indicates an absolute risk curve for breast cancer within 10 years for a risk score greater than 99% for the sample to be tested. Mark 540 indicates a predetermined threshold. The predetermined threshold is, for example, 2.6%.

[0097] At step 406, if the computing device 110 determines that the absolute risk is greater than or equal to the predetermined threshold, it is determined that the subject to which the sample to be tested belongs meets the high risk condition for the predetermined disease. For example, if it is determined that the calculated absolute risk of breast cancer occurring within 10 years for the subject to which the sample to be tested belongs is greater than 2.6%, then the risk of the predetermined disease occurring is determined to be high.

[0098] At step 408, if the computing device 110 determines that the absolute risk is less than the predetermined threshold, it is determined that the subject to which the sample to be tested belongs does not meet the high risk condition for the predetermined disease. That is, if it is determined that the calculated absolute risk of breast cancer occurring within 10 years for the subject to which the sample to be tested belongs is less than 2.6%, it is determined that the risk of occurring the predetermined disease is low.

[0099] Figure 5 The 10-year absolute risk of breast cancer at different ages is indicated, and the age at which women at different risk score levels for the sample to be tested reach a predetermined threshold (eg, 2.6%) is indicated.

[0100] Figure 6 The block diagram of an electronic device 600 suitable for implementing the embodiments of the present disclosure is schematically shown. The device 600 may be a device for implementing the execution Figure 2 , Figure 3 and Figure 4 The apparatus of methods 200, 300 and 400 shown. Figure 6 As shown, the device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 or loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM, various programs and data required for the operation of the device 600 can also be stored. The CPU, ROM, and RAM are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0101] A plurality of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a central processing unit 601 that performs the various methods and processes described above, such as performing methods 200, 300, and 400. For example, in some embodiments, methods 200, 300, and 400 may be implemented as a computer software program, which is stored in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via a ROM and / or a communication unit 609. When the computer program is loaded into the RAM and executed by the CPU, one or more operations of the methods 200, 300, and 400 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to perform one or more actions of methods 200, 300, and 400 by any other appropriate means (e.g., by means of firmware).

[0102] It should be further noted that the present disclosure may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0103] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0104] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0105] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0106] Various aspects of the present disclosure are described herein with reference to the flowchart and / or block diagram of the method, device (system), and computer program product according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0107] These computer-readable program instructions can be provided to a processor in a voice interaction device, a general-purpose computer, a special-purpose computer, or a processing unit of other programmable data processing devices, thereby producing a machine, so that when these instructions are executed by a processing unit of a computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions enable the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0108] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0109] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the equipment, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of this module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0110] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

[0111] The above are only optional embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for predicting a predetermined disease risk, comprising: Obtaining gene sequencing data of multiple samples to be tested so as to generate gene mutation data of multiple genes of each sample to be tested; Acquire a plurality of non-genetic data associated with each sample to be tested, wherein the non-genetic data is generated based on at least one of microbial data, cell data, clinical information, immune marker information, and image data of a target area of ​​a subject to which the sample to be tested belongs, associated with the sample to be tested; Determining a weight function for indicating the effect of gene mutation and non-gene data on the phenotype of each sample to be tested via a regression algorithm, wherein determining a weight function for indicating the effect of mutation and non-gene data on the phenotype of each sample to be tested includes: determining a weight function for the synergistic effect of multiple rare variants and multiple rare variants on the phenotype of each sample to be tested based on a sequence-kernel association test algorithm; For each sample to be tested, based on the gene mutation data, non-gene data and corresponding weights on each gene, the risk score of the subject to which the sample to be tested belongs to developing a predetermined disease is calculated; and Based on the calculated risk score of the subject to be tested for the predetermined disease, determining the absolute risk of the subject to be tested for the predetermined disease within a predetermined time, so as to predict the predetermined disease risk of the sample to be tested based on the comparison between the absolute risk and a predetermined threshold; The method further comprises: Acquire a plurality of predetermined omics data associated with each sample to be tested, wherein the predetermined omics data includes at least one of transcriptomics data, proteomics data and metabolomics data; and The generated gene mutation data of multiple genes of each sample to be tested, the obtained multiple non-gene data and multiple predetermined omics data are normalized to determine the synergistic effects of gene mutation, non-gene data and predetermined omics data on the phenotype of each sample to be tested.

2. The method according to claim 1, wherein predicting the predetermined disease risk of the sample to be tested based on the comparison between the absolute risk and the predetermined threshold comprises: Calculate the absolute risk of the subject to which the sample to be tested will develop the predetermined disease within a predetermined time period based on the risk score of the sample to be tested, the risk factor distribution data, and the incidence and mortality rate of the predetermined disease in the target population of the predetermined age; determining whether the absolute risk is greater than or equal to a predetermined threshold; In response to determining that the absolute risk is greater than or equal to a predetermined threshold, determining that the subject to which the sample to be tested belongs meets a high risk condition for a predetermined disease; as well as In response to determining that the absolute risk is less than a predetermined threshold, it is determined that the subject to which the sample to be tested belongs does not meet a high risk condition for a predetermined disease.

3. The method according to claim 1, wherein calculating the risk score of the subject to be tested for a predetermined disease comprises: Based on the weighted sum of the gene mutation data on each gene and the corresponding gene mutation weight, the product of the non-gene data and the corresponding non-gene data weight, and the product of the predetermined omics data and the corresponding omics data weight, the risk score of the subject to be tested for the occurrence of a predetermined disease is calculated.

4. The method according to claim 3, further comprising: For each non-genetic data, superimpose the non-genetic data sub-weight corresponding to each gene, so as to generate the corresponding non-genetic data weight of each non-genetic data; as well as For each predetermined omics data, the omics data sub-weight corresponding to each gene is superimposed to generate the corresponding omics data weight of each predetermined omics data.

5. A computing device comprising: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the computing device to perform the method according to any one of claims 1 to 4.

6. A computer-readable storage medium having machine-executable instructions stored thereon, which, when executed, cause a machine to perform the method according to any one of claims 1 to 4.