A method for tracing the origin of endangered wildlife and products thereof based on machine learning and DNA fingerprinting and application thereof

Abstract

The application discloses a kind of endangered wild animals and its product geographical tracing method based on machine learning and DNA imprinting and application thereof, it is related to wild animal and product geographical tracing technical field.The method includes applying machine learning method to known geographical coordinates sample and establishing linear regression model, and the sample of unknown geographical coordinates is traced according to linear regression model two parts of content.The application discloses a kind of endangered wild animals and its product geographical tracing method based on machine learning and DNA imprinting and application thereof, by dimension reduction, the large amount of genetic markers obtained by original sequencing is simplified into a group of simplified features that cannot be directly compared, and each feature contains the geographical origin information of individual in sample;On this basis, linear regression model is established by training simplified features, which greatly reduces the training cost;The principal component with maximum variance is mapped to the geographical coordinates of individual, and the effect of tracing the geographical origin of individual is achieved through linear regression model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographical tracing of wild animals and their products, and particularly relates to a method for tracing endangered wild animals and their products based on machine learning and DNA imprinting and application thereof. BACKGROUND

[0002] Illegal trade of wild animals not only disrupts international trade markets, but also is an important reason for the endangerment and extinction of wild animals (Schneider, 2012). In addition, wild animals may carry pathogenic bacteria, viruses, and parasites, causing animal diseases. If the carried disease is a zoonosis, it will seriously threaten human health (White & Razgour, 2020). Therefore, tracing the origin of wild animals and their products, especially the geographical origin, can not only monitor the origin of wild animals and their products, but also reveal the routes of illegal trade of wild animals, providing technical support for the tracing and protection of wild animals.

[0003] Previous studies have used mitochondrial haplotype network or genetic geographical lineage to trace wild animals and their products (Ogden & Linacre, 2015). However, such tracing is based on background samples to identify the close relatives of the samples, which can only distinguish the attribution of the samples, and cannot accurately estimate the geographical coordinates of the samples. The accuracy and precision depend on the background information of known samples. For wild animals and their products with wide distribution and multiple circulation places, the accuracy and precision of these methods cannot meet the current needs of geographical tracing.

[0004] In recent years, the development of molecular tracing technology based on machine learning and population genetics has provided more scientific technical support for such research (Qin et al., 2022a; Qin et al., 2022b; Qin & Gaggiotti, 2022). By clarifying the geographical genetic structure of the potential source population of the sample, it will help to reveal the source, flow route and endangering mechanism of the sample.

[0005] Kernel local Fisher discriminant analysis of principal components (KLFDAPC) is a nonlinear supervised machine learning method, which has the same principle as principal component discriminant analysis (DAPC), but uses kernel local Fisher discriminant analysis (KLFDA) instead of LDA (Fisher linear discriminant analysis) in the original method.

[0006] DAPC is a hybrid dimensionality reduction statistical technique that combines LDA and PCA (principal component analysis). It effectively compensates for PCA's limitation of only characterizing the total variance of a sample. This multivariate statistical method divides the sample variance into two components: between-group and within-group, which can maximize the differentiation between different groups. However, DAPC is more suitable for linear association analysis and has poor statistical performance for nonlinear associations.

[0007] KLFDAPC uses KLFDA instead of LDA to help overcome these limitations. By introducing a kernel function, KLFDA effectively extends linear discriminant analysis to nonlinear discriminant analysis. This combination of linear, nonlinear, and principal component analysis can be applied to more complex genetic scenarios, more effectively detecting the geographic genetic structure of populations and predicting the geographic origins of individuals. Summary of the Invention

[0008] To solve the above problems, the present invention provides a geographical tracing method for endangered wild animals and their products based on machine learning and DNA imprinting and its application, develops a geographical tracing model for endangered animals and their products based on machine learning and DNA imprinting, and provides new theories and new and excellent technologies for the exploration and monitoring of endangered wild animals and plants.

[0009] To achieve the above objectives, the present invention provides a method for geographically tracing endangered wild animals and their products based on machine learning and DNA imprinting, comprising the following steps:

[0010] S1. Use KLFDAPC to trace the samples and establish a linear regression model;

[0011] The process of tracing the source and establishing a linear regression model includes:

[0012] S11, sampling and sequencing to obtain the whole genome sequence of the sample;

[0013] S12, aligning the whole genome sequence obtained by sequencing in step S1 to the reference genome and detecting mutations, merging the mutation detection files of each sample and setting parameter filtering to obtain high-quality mutation sites;

[0014] S13. Using 0, 1, and 2 as the coding genotypes, perform KLFDAPC analysis on the individual × genotype matrix to trace the origin, including:

[0015] S131, use PCA to reduce the dimension of the individual × genotype matrix to obtain principal components PCs containing geographic location information in the genotype;

[0016] S132, perform KLFDA analysis on the first 20 to 50 standardized PCs to further extract nonlinear features in the principal components;

[0017] S133, using Procrustes analysis to calculate the correlation between the first two principal components KLFDAPC1 and KLFDAPC2 and the geographic coordinates of the sampling points, establishing a transformation between the principal components and the geographic coordinates through translation, rotation, and scaling, and establishing a linear regression model between the transformed principal components and latitude and longitude;

[0018] S2. Apply linear regression model to trace the origin of samples with unknown geographical coordinates.

[0019] Preferably, during the sequencing process of step S11, tissues that are difficult to grind and have low nucleic acid content are removed from the sample. After the tissue is removed, it is quickly frozen in liquid nitrogen, stored at -80°C, and transported on dry ice. Repeated freezing and thawing should be avoided during sample delivery.

[0020] Preferably, in the filtering process of step S12, filtering is performed with minimum allele frequency MAF>0.05 and deletion rate ≤0.2.

[0021] Preferably, in step S13, 012 represent homozygous, heterozygous and homozygous minor alleles of the locus, respectively.

[0022] Preferably, the process of tracing the samples of unknown geographic coordinates in step S2 includes: inputting the samples KLFDAPC1 and KLFDAPC2 of unknown geographic coordinates into a linear regression model, decoding the output of the linear regression model as the geographic coordinates corresponding to KLFDAPC1 and KLFDAPC2, and mapping the geographic coordinates onto a map for tracing.

[0023] The present invention provides a method for geographically tracing endangered wild animals and their products based on machine learning and DNA imprinting, and its application, which has the following beneficial effects:

[0024] (1) By reducing the dimensionality of the original sequencing data, the large number of genetic markers obtained are simplified into a set of genetic features that cannot be directly compared. At the same time, each feature contains the geographical origin information of the individuals in the sample.

[0025] (2) Establishing a linear regression model through genetic feature training greatly reduces training costs;

[0026] (3) The genetic characteristics with the largest variance are mapped to the geographic coordinates of the individual, and the effect of tracing the individual's geographic origin is achieved through a linear regression model.

[0027] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A in the middle is the distinction of population structure by the first 16 principal components of PCA, B is the first 4 principal component diagram, C is the gradient change of the first two genetic characteristics along longitude, and D is the gradient change of the first two genetic characteristics along latitude;

[0029] Figure 2 is the correlation between the reduced-dimensional genetic characteristics and geographic coordinates; A is the relationship between KLFDAPC1 and longitude on the projected map and its gradient distribution on the geographic coordinates, and B is the relationship between KLFDAPC2 and latitude on the projected map and its gradient distribution on the geographic coordinates;

[0030] Figure 3 is the projection of the individual on the real map, where A is the KLFDAPC tracing result and B is the PCA tracing result;

[0031] Figure 4 Projection of the KLFDAPC traceability results on a real map for individuals with unknown geographical locations. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar numbers throughout represent the same or similar elements or elements with the same or similar functions.

[0033] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0034] Example 1

[0035] A method for tracing the geographic origins of endangered wild animals and their products based on machine learning and DNA imprinting was used to infer the geographic origins of the forest musk deer. A total of 274 samples were sequenced in this example, including 59 from the Tp farm in the southernmost part of Shaanxi Province, 192 from the Q1 farm in southern Shaanxi and north of the Qinling Mountains, and 23 from the WS farm in northern Sichuan Province. The origins were the Tapa Mountains, the central Qinling Mountains, and the western Sichuan Plateau, respectively.

[0036] These farms are typical examples of musk deer farming. The three farms are independent and do not cross-breed with each other. Musk deer from the same farms share similar breeding conditions. The 274 samples were randomly collected from adult males aged 2.5-6.5 years from each farm. Sample collection was conducted with permission from the forestry department and in compliance with China's National Wildlife Protection Law.

[0037] The method specifically includes the following steps:

[0038] S1. KLFDAPC was used to trace the origin of 274 musk deer samples and a linear regression model was established.

[0039] S11. First, sequence the training set of musk deer samples, removing tissues that are difficult to grind and have low nucleic acid content. After removal, quickly freeze the tissues in liquid nitrogen, store at -80°C, and transport them on dry ice. Avoid repeated freeze-thaw cycles.

[0040] S12. Align the sequenced simplified genome to the reference genome and detect single nucleotide polymorphisms (SNPs). Merge the variant detection files for each sample and filter for a minimum allele frequency < 0.05 and a deletion rate < 0.2 to identify high-quality SNP sites.

[0041] S13. Genotypes are coded as 012, indicating homozygous, heterozygous, and homozygous minor alleles, respectively. KLFDAPC analysis was performed on the individual × genotype matrix to trace the origin.

[0042] S131. PCA is used to reduce the dimensionality and obtain the principal components (PCs) containing the geographical location information in the genotype. The PCA results are as follows: Figure 1 As shown in a and b.

[0043] The results show the degree of differentiation between the three musk deer populations on PC1-PC16. Both results indicate that the first two principal components of PCA can clearly divide the samples into three groups, while the remaining principal components are not very effective in distinguishing different populations. This shows that the first two principal components contain the vast majority of the individual geographic location information, retaining the most useful information while reducing the dimensionality, providing support for the subsequent use of the first two principal components for geographical tracing.

[0044] S132. Perform KLFDA analysis on the first 20 to 50 standardized PCs to further extract nonlinear features in the principal components. The principal components (KLFDAPCs) now contain not only the decisive geographic location information but also retain the linear and nonlinear associations between samples.

[0045] S133. Use Procrustes analysis to calculate the correlation between the first two principal components (KLFDAPC1 and KLFDAPC2) and the geographic coordinates of the sampling points. Compare and calculate the geometric similarity between KLFDAPCs and the actual geographic locations of the samples by translation, rotation and scaling, and plot the first two principal component axes after rotation. The results are shown in Figure 1. Figure 1 As shown in c and d, c is longitude and d is latitude.

[0046] The variance explanation (PVE) of the first two principal components after Proctor transformation was 42.6% and 3.84%, respectively, which were higher than the corresponding PCA results. They also showed longitude and latitude gradients, indicating that the dimensionality-reduced genetic signature had a better explanation for longitude.

[0047] S134. Perform linear regression on KLFDAPC1 and KLFDAPC2 with the sample longitude and latitude to establish a corresponding relationship between the dimensionality reduction features and the longitude and latitude, thereby realizing the mapping of PC on the real map.

[0048] Figure 2 The linear correlation between the KLFDAPCs after the general transformation and the geographic longitude and latitude coordinates is shown, Y = aX + b, Y is the longitude and latitude coordinates, and X is the KLFDAPC genetic characteristic value. The correlation coefficient (R 2 ) reached 75% and 73% respectively, indicating that the principal components after the Pu-type transformation have a high geometric correlation with the longitude and latitude and a certain linear correlation. At the same time, R 2 It also ensures the accuracy of geographical location of traceability to a certain extent. Considering that the actual traceability is generally carried out at the national or regional level, the R 2 To a certain extent, it can also effectively ensure the application of traceability in actual scenarios.

[0049] Figure 2 It also shows the gradient distribution of the first two principal components in geographic coordinates. Figure 2 A in the middle shows the relationship between KLFDAPC1 and longitude on the projected map. The results show that KLFDAPC1 is positively correlated with the longitude of the three source farms. Figure 2 Figure B shows the relationship between KLFDAPC2 and latitude on the projected map. Here, KLFDAPC2 well illustrates the latitude correlation between Ql and the other two farms, but for WS and Tp farms, it is not well represented, probably because their latitudes are not much different.

[0050] The above results show that the geographical location information contained in the principal components can be used to trace the geographical origin of wild animals. However, both the KLFDAPCs and the PCs contain this information, so the effects of the two in tracing were compared. The KLFDAPCs and the PCs were subjected to principal component conversion and linear correlation, and the coincidence of the projections of the two on the map and the principal component correlation coefficient were compared to illustrate the tracing effect.

[0051] The final individual tracing results are shown in Figure 3 The results show that, whether directly mapped by the PCs or mapped by the KLFDAPCs after KLFDA analysis, the sample points of the results are well matched with the geographical coordinates from the Ql and WS farm individuals, but for the tracing of the Tp farm, the KLFDAPC results are more matched.

[0052] In particular, for the KLFDAPC results, the geometric similarity of the first two reduced dimension features with the geographical coordinates reached 0.8486, which is higher than 0.7355 of the PCs method. This is also well demonstrated in the figure on the tracing of the individuals from the Tp farm.

[0053] S2. Verify the trained linear regression model.

[0054] The model constructed by the above KLFDAPC results covers the geographical genetic structure of the population sampling site. For the obtained unknown samples, after simplified genome sequencing, the sequencing data is input into the KLFDAPC model to predict the geographical genetic feature value, and the output value of the genetic feature decoded linear regression model is the geographical coordinates corresponding to the genetic feature, which is mapped to the map to trace the origin of the individual. Figure 4

[0055] An example is taken to obtain the simplified genomes of 5 individuals from different sources, input the 5 simplified genomes into the KLFDAPC to obtain the predicted genetic geographical genetic feature values, and input the feature values into the previously constructed linear model to obtain the geographical coordinates of the individuals.

[0056] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application and not to limit them, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements also cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.​

Claims

1. A method for geographical tracing of endangered wild animals and their products based on machine learning and DNA imprinting, characterized in that: The steps include: S1. Apply KLFDAPC to deduce the genetic geographic structure of the samples and establish a linear regression model, including: S11, sampling and sequencing to obtain a simplified genome sequence of the sample; S12, aligning the simplified genome sequence obtained by sequencing in step S1 to the reference genome and detecting mutations, merging the mutation detection files of each sample and setting parameter filtering to obtain high-quality mutation sites; S13. Code genotypes as 0, 1, and 2 and perform KLFDAPC analysis on the individual × genotype matrix, including: S131, use PCA to reduce the dimension of the individual × genotype matrix to obtain principal components PCs containing geographic location information in the genotype; S132, perform KLFDA analysis on the first 20 to 50 standardized PCs to further extract nonlinear features in the principal components; S133, using Procrustes analysis to calculate the correlation between the first two principal components KLFDAPC1 and KLFDAPC2 and the geographic coordinates of the sampling points, establishing a transformation between the principal components and the geographic coordinates through translation, rotation, and scaling, and establishing a linear regression model between the transformed principal components and latitude and longitude; In step S13, 0, 1, and 2 represent homozygous, heterozygous, and homozygous minor alleles of the locus, respectively; S2. Apply linear regression model to trace the origin of samples with unknown geographical coordinates.

2. The method for geographically tracing endangered wild animals and their products based on machine learning and DNA imprinting according to claim 1, characterized in that: During the sequencing process of step S11, tissues that are difficult to grind and have low nucleic acid content are removed from the sample. After the tissue is removed, it is quickly frozen in liquid nitrogen, stored at -80°C, and transported on dry ice. Repeated freezing and thawing should be avoided during sample delivery.

3. The method for geographically tracing endangered wild animals and their products based on machine learning and DNA imprinting according to claim 1, characterized in that: During the filtering process of step S12, filtering was performed with minimum allele frequency (MAF) > 0.05 and deletion rate ≤ 0.

2.

4. The method for geographical tracing of endangered wild animals and their products based on machine learning and DNA imprinting according to claim 1, characterized in that: Step S2: The process of tracing the source of samples with unknown geographical coordinates includes: The samples KLFDAPC1 and KLFDAPC2 with unknown geographic coordinates are input into the linear regression model. The output of the decoded linear regression model is the geographic coordinates corresponding to KLFDAPC1 and KLFDAPC2. The geographic coordinates can be mapped onto the map for traceability.

5. An application of the method for geographical tracing of endangered wild animals and their products based on machine learning and DNA imprinting as claimed in any one of claims 1 to 4, characterized in that: Apply KLFDAPC to the geographical traceability of endangered wild animals and their products.

Images