HGT tumor marker screening method and device, computer equipment and storage medium

Abstract

The invention relates to an HGT tumor marker screening method and device, computer equipment and a storage medium. The method comprises the following steps: extracting microorganisms of a to-be-screened object as target microorganisms; obtaining a gene sequence of the target microorganism as a target gene sequence; obtaining a first HGT event from the target gene sequence; the first HGT event is subjected to normalization, and a normalized first HGT event is obtained; performing reliability verification on the normalized first HGT event to obtain a second HGT event; and according to the second HGT event and a standard HGT event, obtaining the HGT tumor marker probability of the to-be-screened object. The HGT tumor marker probability of the to-be-screened object can be obtained through the HGT event, and the cost is low.

Description

Technical Field

[0001] The present invention relates to the field of biomedicine, and in particular to a method, device, computer equipment and storage medium for screening HGT tumor markers. Background Art

[0002] Colorectal cancer (CRC) develops slowly and is considered the second eradicable tumor because of its relatively clear pathogenesis and early detection through screening. However, colorectal cancer develops slowly and its early manifestations are atypical, so it is easy to be confused with other gastrointestinal diseases, and the opportunity for early diagnosis is missed.

[0003] The existing colorectal cancer screening method usually uses tumor markers to indirectly determine the probability of colorectal cancer, and there are roughly the following types of tumor marker screening. The first is colonoscopy, which is an invasive examination that may cause perforation or mucosal tissue damage, and has a high rate of missed diagnosis. The second is intestinal cell DNA analysis in feces. Since intestinal cells are extracted from feces, the process requirements are high, and the extraction environment is prone to damage to intestinal cells, and the sensitivity to some tumors is poor, so the accuracy rate is not high.

[0004] It can be seen that the accuracy of screening for tumor markers for colorectal cancer in the existing technology is still not high. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present invention provides a screening method, device, computer equipment and storage medium for HGT tumor markers.

[0006] In a first aspect, the present invention provides a method for screening HGT tumor markers, the method comprising:

[0007] extracting microorganisms of the object to be screened as target microorganisms;

[0008] obtaining a gene sequence of the target microorganism as a target gene sequence;

[0009] Obtaining a first HGT event from the target gene sequence;

[0010] Normalizing the first HGT event to obtain a normalized first HGT event;

[0011] Performing reliability verification on the normalized first HGT event to obtain a second HGT event;

[0012] According to the second HGT event and the standard HGT event, the HGT tumor marker probability of the object to be screened is obtained.

[0013] Optionally, normalizing the first HGT event to obtain a normalized first HGT event includes:

[0014] According to the target gene sequence, obtaining a likelihood function of a first HGT event;

[0015] According to the standard gene sequence, obtaining a priori function of the standard HGT event;

[0016] According to the likelihood function of the first HGT event and the prior function of the standard HGT event, the posterior probability of the first HGT event is obtained, and the posterior probability of the first HGT event is used as the normalized first HGT event.

[0017] Optionally, obtaining the posterior probability of the first HGT event according to the likelihood function of the first HGT event and the prior function of the standard HGT event is performed in the following manner:

[0018]

[0019]

[0020]

[0021]

[0022] Among them, P(dara|θ) is the likelihood function of the first HGT event, g is the total number of the target gene sequences, m is the total number of the first HGT event, θ is the probability of the first HGT event, f(θ|a, b) is the prior function of the standard HGT event, B(a, b) is the probability function of a and b, a and b are fixed parameters, and P(θ|data) is the posterior probability of the first HGT event.

[0023] Optionally, the reliability verification of the normalized first HGT event to obtain the second HGT event is performed according to the following method;

[0024]

[0025] α=a+m

[0026] β=b+gm

[0027] Wherein, P(σ) is the second HGT event, α and β are intermediate parameters, g is the total number of target gene sequences, m is the total number of first HGT events, and B(α, β) is the probability function of α and β.

[0028] Optionally, obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event includes:

[0029] Inputting the second HGT event into the HGT model to obtain the HGT tumor marker probability of the subject to be screened;

[0030] Before obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event, the method further includes:

[0031] Construct an initial probability model;

[0032] Acquire a training sample and a validation sample, wherein the training sample includes a training HGT event and a training sample probability, and the validation sample includes a validation HGT event and a validation sample probability;

[0033] According to the standard HGT event, obtaining differential HGT from the training samples;

[0034] Obtaining a difference sample corresponding to the difference HGT;

[0035] Training the initial probability model according to the difference samples to obtain a model to be verified;

[0036] Verifying the model to be verified according to the verification sample;

[0037] The model to be verified that has passed the verification is used as the HGT model.

[0038] Optionally, the training samples include training HGT events and training sample probabilities, and the verification samples include verification HGT events and verification sample probabilities;

[0039] The obtaining of training samples and verification samples comprises:

[0040] Obtaining sample microorganisms of a plurality of samples and a sample probability corresponding to each of the sample microorganisms;

[0041] Obtaining a sample gene sequence of each of the sample microorganisms;

[0042] Obtaining initial HGT events from the sample gene sequences;

[0043] Normalizing and reliably verifying the initial HGT events to obtain sample HGT events;

[0044] Dividing the sample HGT events into training HGT events and verification HGT events according to a preset ratio;

[0045] Obtaining the training samples according to the training HGT events and corresponding sample probabilities;

[0046] The verification sample is obtained according to the verification HGT event and the corresponding sample probability.

[0047] Optionally, the HGT tumor marker probability of the subject to be screened is obtained according to the second HGT event and the standard HGT event in the following manner:

[0048] According to multiple decision trees, multiple reference probabilities are obtained;

[0049] Obtaining an average of a plurality of the reference probabilities as the HGT tumor marker probability of the subject to be screened;

[0050] The method of obtaining the HGT tumor marker probability of the subject to be screened is as follows:

[0051]

[0052]

[0053]

[0054] x is the HGT vector corresponding to the second HGT event, y is the species abundance vector, x and y are used to construct the decision tree, i, j, γ, δ, ζ, η, μ are hyperparameters,

[0055] M is the adjacency matrix between the second HGT event graph and the standard HGT event graph, I is the identity matrix, U is the pseudo-technical matrix, H is the adjacency matrix between the second HGT event graph and the standard HGT event graph, C is the adjacency matrix between the second HGT event abundance graph and the standard event abundance graph,

[0056] P t (CRC) is the t-th reference probability, T is the number of decision trees, and P(CRC) is the HGT tumor marker probability of the subject to be screened.

[0057] In a second aspect, a screening device for HGT tumor markers is provided, the device comprising:

[0058] An extraction unit, used to extract microorganisms of an object to be screened as target microorganisms;

[0059] The extraction unit is also used to obtain the gene sequence of the target microorganism as a target gene sequence;

[0060] An HGT event acquisition unit, used for acquiring a first HGT event from the target gene sequence;

[0061] a normalization unit, configured to normalize the first HGT event to obtain a normalized first HGT event;

[0062] A verification unit, configured to verify the reliability of the normalized first HGT event to obtain a second HGT event;

[0063] The probability acquisition unit is used to acquire the HGT tumor marker probability of the object to be screened according to the second HGT event and the standard HGT event.

[0064] According to a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above methods when executing the computer program.

[0065] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method as described in any one of the above items is implemented.

[0066] The present invention provides a screening method, device, computer equipment and storage medium for HGT tumor markers, the method comprising: extracting a microorganism of a subject to be screened as a target microorganism; obtaining a gene sequence of the target microorganism as a target gene sequence; obtaining a first HGT event from the target gene sequence; normalizing the first HGT event to obtain a normalized first HGT event; verifying the reliability of the normalized first HGT event to obtain a second HGT event; and obtaining the probability of the HGT tumor marker of the subject to be screened according to the second HGT event and the standard HGT event. The method of the embodiment of the present invention extracts a base sequence from a microorganism and obtains an HGT event from a gene sequence. Since there are a large number of intestinal microorganisms in the human intestine, horizontal gene transfer occurs between human intestinal cells and intestinal microorganisms. If there is a tumor in the colorectal intestine of a human body, the genetic material of the colorectal cancer tumor will be horizontally transferred to microorganisms such as bacteria in the colorectum. The method of the present invention obtains the probability of the HGT tumor marker of the subject to be screened by analyzing the HGT event of the microorganism. In the embodiment of the present invention, intestinal microorganisms are extracted from feces, which is non-invasive, so the human intestine will not be damaged, and there will be no adverse effects on human health. In addition, since there are many types and numbers of intestinal microorganisms, it is easy to extract undamaged samples from feces, and it is easy to collect a large number of samples. The extraction of microorganisms such as bacteria is relatively easy, and the process requirements are relatively low, which can reduce the cost of extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0069] Figure 1 This is an application environment diagram of the HGT tumor marker screening method according to an embodiment of the present invention;

[0070] Figure 2 Schematic diagram of the process of the screening method for HGT tumor markers according to an embodiment of the present invention;

[0071] Figure 3 This is a structural block diagram of a screening device for HGT tumor markers according to an embodiment of the present invention;

[0072] Figure 4 1 is a diagram showing the internal structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] Figure 1 FIG. 4 is an application environment diagram of a method for screening HGT tumor markers in an embodiment. Figure 1 , the screening method for HGT tumor markers is applied to the screening system for HGT tumor markers. The screening method for HGT tumor markers includes a terminal 110 and / or a server 120. The terminal 110 and the server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented as an independent server or a server cluster composed of multiple servers.

[0075] The HGT tumor marker screening method of the present invention is applied to the terminal 110 and / or the server 120 .

[0076] HGT (horizontal gene transfer), also known as lateral gene transfer, refers to the exchange of genetic material between different biological individuals or between organelles within a single cell, rather than vertical transmission from parents to offspring.

[0077] HGT plays a key role in the evolution of microorganisms such as bacteria, and common pathways include conjugation, transduction, and transformation. Through HGT, bacteria can quickly acquire multiple genes. HGT events can also be called HGT breakpoints, which refer to the specific locations where genes are inserted or transferred during HGT events. A horizontally transferred DNA fragment can have multiple different insertion locations in the recipient genome, and these locations are called HGT events.

[0078] like Figure 2 As shown, a screening method for HGT tumor markers includes:

[0079] Step 210, extracting microorganisms of the object to be screened as target microorganisms;

[0080] Step 220, obtaining the gene sequence of the target microorganism as a target gene sequence;

[0081] Step 230, obtaining a first HGT event from the target gene sequence;

[0082] Step 240, normalizing the first HGT event to obtain a normalized first HGT event;

[0083] Step 250, verifying the reliability of the normalized first HGT event to obtain a second HGT event;

[0084] Step 260: Obtain the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event.

[0085] The method of the embodiment of the present invention extracts base sequences from microorganisms and obtains HGT events from gene sequences. Since there are a large number of intestinal microorganisms in the human intestine, horizontal gene transfer will occur between human intestinal cells and intestinal microorganisms. If there is a tumor in the human colorectal intestine, the genetic material of the colorectal cancer tumor will be horizontally transferred to the bacteria and other microorganisms in the colorectal intestine. The method of the present invention obtains the probability of HGT tumor markers of the object to be screened by analyzing the HGT events of the microorganisms. In the embodiment of the present invention, the intestinal microorganisms are extracted from feces, which is non-invasive, so the human intestine will not be damaged, and there will be no adverse effects on human health. In addition, since there are many types of intestinal microorganisms and a large number of them, it is also easy to extract undamaged samples from feces, and it is easy to collect a large number of samples, and the extraction of microorganisms such as bacteria is relatively easy, and the process requirements are relatively low, which can reduce the cost of extraction.

[0086] In the embodiment of the present invention, in step 240, normalizing the first HGT event to obtain a normalized first HGT event includes:

[0087] According to the target gene sequence, obtaining a likelihood function of a first HGT event;

[0088] According to the standard gene sequence, obtaining a priori function of the standard HGT event;

[0089] According to the likelihood function of the first HGT event and the prior function of the standard HGT event, the posterior probability of the first HGT event is obtained, and the posterior probability of the first HGT event is used as the normalized first HGT event.

[0090] In the embodiment of the present invention, the posterior probability of the first HGT event is obtained according to the likelihood function of the first HGT event and the prior function of the standard HGT event, and is performed in the following manner:

[0091]

[0092]

[0093]

[0094]

[0095] Among them, P(data|θ) is the likelihood function of the first HGT event, g is the total number of the target gene sequences, m is the total number of the first HGT event, θ is the probability of the first HGT event, f(θ|a, b) is the prior function of the standard HGT event, B(a, b) is the probability function of a and b, a and b are fixed parameters, and P(θ|data) is the posterior probability of the first HGT event.

[0096] In the embodiment of the present invention, in step 250, the reliability verification of the normalized first HGT event is performed to obtain the second HGT event, which is obtained according to the following method;

[0097]

[0098] α=a+m

[0099] β=b+gm

[0100] Wherein, P(σ) is the second HGT event, α and β are intermediate parameters, g is the total number of target gene sequences, m is the total number of first HGT events, and B(α, β) is the probability function of α and β.

[0101] In the embodiment of the present invention, in step 260, obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event includes:

[0102] Inputting the second HGT event into the HGT model to obtain the HGT tumor marker probability of the subject to be screened;

[0103] Before obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event, the method further includes:

[0104] Construct an initial probability model;

[0105] Acquire a training sample and a validation sample, wherein the training sample includes a training HGT event and a training sample probability, and the validation sample includes a validation HGT event and a validation sample probability;

[0106] According to the standard HGT event, obtaining differential HGT from the training samples;

[0107] Obtaining a difference sample corresponding to the difference HGT;

[0108] Training the initial probability model according to the difference samples to obtain a model to be verified;

[0109] Verifying the model to be verified according to the verification sample;

[0110] The model to be verified that has passed the verification is used as the HGT model.

[0111] In the embodiment of the present invention, the training samples include training HGT events and training sample probabilities, and the verification samples include verification HGT events and verification sample probabilities;

[0112] The obtaining of training samples and verification samples comprises:

[0113] Obtaining sample microorganisms of a plurality of samples and a sample probability corresponding to each of the sample microorganisms;

[0114] Obtaining a sample gene sequence of each of the sample microorganisms;

[0115] Obtaining initial HGT events from the sample gene sequences;

[0116] Normalizing and reliably verifying the initial HGT events to obtain sample HGT events;

[0117] Dividing the sample HGT events into training HGT events and verification HGT events according to a preset ratio;

[0118] Obtaining the training samples according to the training HGT events and corresponding sample probabilities;

[0119] The verification sample is obtained according to the verification HGT event and the corresponding sample probability.

[0120] In the embodiment of the present invention, in step 260, the HGT tumor marker probability of the subject to be screened is obtained according to the second HGT event and the standard HGT event in the following manner:

[0121] According to multiple decision trees, multiple reference probabilities are obtained;

[0122] Obtaining an average of a plurality of the reference probabilities as the HGT tumor marker probability of the subject to be screened;

[0123] The method of obtaining the HGT tumor marker probability of the subject to be screened is as follows:

[0124]

[0125]

[0126]

[0127] x is the HGT vector corresponding to the second HGT event, y is the species abundance vector, x and y are used to construct the decision tree, i, j, γ, δ, ζ, η, μ are hyperparameters,

[0128] M is the adjacency matrix between the second HGT event graph and the standard HGT event graph, I is the identity matrix, U is the pseudo-technical matrix, H is the adjacency matrix between the second HGT event graph and the standard HGT event graph, C is the adjacency matrix between the second HGT event abundance graph and the standard event abundance graph,

[0129] P t (CRC) is the t-th reference probability, T is the number of decision trees, and P(CRC) is the HGT tumor marker probability of the subject to be screened.

[0130] In the embodiment of the present invention, HGT events, or HGT breakpoints, may include Acetatifactor & CAG-882, Agathobacter & UBA 11774, etc. Species abundance may include Pepto streptococcus_stomatis, Fusobacterium_nucleatum, etc.

[0131] In an embodiment of the present invention, when the probability of HGT tumor markers of the screening object is obtained through a decision tree, two graphs can be constructed to represent different microbial characteristics. The first graph is constructed based on HGT events, that is, the above-mentioned HGT event graph. In this graph, each vertex represents a species or genus, and each edge indicates that a gene exchange event has occurred between the two species or genera in the sample. This means that if there is gene transfer between two species, they will be connected by an edge in the graph.

[0132] The second graph is constructed based on abundance correlation, which is the HGT event abundance graph mentioned above. In this graph, each vertex also represents a species or genus, but each edge indicates that there is a significant correlation between the abundance of these two species or genera. Specifically, if the Pearson correlation coefficient of the abundance of two species is greater than 0.3, they will be connected by an edge in the graph. For each pair of taxa, we use the Python module Scipy to calculate the Pearson correlation coefficient of the abundance values ​​between the samples. The adjacency matrix, identity matrix and pseudo count matrix of the two graphs are used to correct the abundance values.

[0133] The screening method for HGT tumor markers of the embodiment of the present invention actually obtains a probability. The standard HGT event can be an HGT event of the gene sequence of a completely healthy sample microorganism, and can also include an HGT event of the gene sequence of a sample microorganism that has been diagnosed with a tumor. The probability of the tumor marker can be obtained by the similarity or difference / distinction between the HGT of the object to be screened and the HGT of the standard sample. The embodiment of the present invention obtains a probability, not a conclusion, but through probability, early and very early screening can be achieved.

[0134] like Figure 3 As shown, the present invention also provides a screening device for HGT tumor markers, the device comprising:

[0135] An extraction unit 310 is used to extract microorganisms of the object to be screened as target microorganisms;

[0136] The extraction unit 310 is also used to obtain the gene sequence of the target microorganism as a target gene sequence;

[0137] An HGT event acquisition unit 320 is used to acquire a first HGT event from the target gene sequence;

[0138] A normalization unit 330, configured to normalize the first HGT event to obtain a normalized first HGT event;

[0139] A verification unit 340, configured to verify the reliability of the normalized first HGT event to obtain a second HGT event;

[0140] The probability acquisition unit 350 is used to acquire the HGT tumor marker probability of the object to be screened according to the second HGT event and the standard HGT event.

[0141] In the embodiment of the present invention, the normalization unit 330 is further used for:

[0142] According to the target gene sequence, obtaining a likelihood function of a first HGT event;

[0143] According to the standard gene sequence, obtaining a priori function of the standard HGT event;

[0144] According to the likelihood function of the first HGT event and the prior function of the standard HGT event, the posterior probability of the first HGT event is obtained, and the posterior probability of the first HGT event is used as the normalized first HGT event.

[0145] In the embodiment of the present invention, the normalization unit 330 is further used for:

[0146] The posterior probability of the first HGT event is obtained according to the likelihood function of the first HGT event and the prior function of the standard HGT event, in the following manner:

[0147]

[0148]

[0149]

[0150]

[0151] Among them, P(data|θ) is the likelihood function of the first HGT event, g is the total number of the target gene sequences, m is the total number of the first HGT event, θ is the probability of the first HGT event, f(θ|a, b) is the prior function of the standard HGT event, B(a, b) is the probability function of a and b, a and b are fixed parameters, and P(θ|data) is the posterior probability of the first HGT event.

[0152] In the embodiment of the present invention, the verification unit is further used to: perform reliability verification on the normalized first HGT event to obtain a second HGT event, which is obtained according to the following method;

[0153]

[0154] α=a+m

[0155] β=b+gm

[0156] Wherein, P(σ) is the second HGT event, α and β are intermediate parameters, g is the total number of target gene sequences, m is the total number of first HGT events, and B(α, β) is the probability function of α and β.

[0157] In the embodiment of the present invention, the probability acquisition unit 350 is further used for:

[0158] Inputting the second HGT event into the HGT model to obtain the HGT tumor marker probability of the subject to be screened;

[0159] Before obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event, the method further includes:

[0160] Construct an initial probability model;

[0161] Acquire a training sample and a validation sample, wherein the training sample includes a training HGT event and a training sample probability, and the validation sample includes a validation HGT event and a validation sample probability;

[0162] According to the standard HGT event, obtaining differential HGT from the training samples;

[0163] Obtaining a difference sample corresponding to the difference HGT;

[0164] Training the initial probability model according to the difference samples to obtain a model to be verified;

[0165] Verifying the model to be verified according to the verification sample;

[0166] The model to be verified that has passed the verification is used as the HGT model.

[0167] In the embodiment of the present invention, the training samples include training HGT events and training sample probabilities, and the verification samples include verification HGT events and verification sample probabilities;

[0168] The probability acquisition unit 350 is further used for:

[0169] Obtaining sample microorganisms of a plurality of samples and a sample probability corresponding to each of the sample microorganisms;

[0170] Obtaining a sample gene sequence of each of the sample microorganisms;

[0171] Obtaining initial HGT events from the sample gene sequences;

[0172] Normalizing and reliably verifying the initial HGT events to obtain sample HGT events;

[0173] Dividing the sample HGT events into training HGT events and verification HGT events according to a preset ratio;

[0174] Obtaining the training samples according to the training HGT events and corresponding sample probabilities;

[0175] The verification sample is obtained according to the verification HGT event and the corresponding sample probability.

[0176] In the embodiment of the present invention, the probability acquisition unit 350 is further used for:

[0177] According to multiple decision trees, multiple reference probabilities are obtained;

[0178] Obtaining an average of a plurality of the reference probabilities as the HGT tumor marker probability of the subject to be screened;

[0179] The method of obtaining the HGT tumor marker probability of the subject to be screened is as follows:

[0180]

[0181]

[0182]

[0183] x is the HGT vector corresponding to the second HGT event, y is the species abundance vector, x and y are used to construct the decision tree, i, j, γ, δ, ζ, η, μ are hyperparameters,

[0184] M is the adjacency matrix between the second HGT event graph and the standard HGT event graph, I is the identity matrix, U is the pseudo-technical matrix, H is the adjacency matrix between the second HGT event graph and the standard HGT event graph, C is the adjacency matrix between the second HGT event abundance graph and the standard event abundance graph,

[0185] P t (CRC) is the t-th reference probability, T is the number of decision trees, and P(CRC) is the HGT tumor marker probability of the subject to be screened.

[0186] The device of the embodiment of the present invention extracts base sequences from microorganisms and obtains HGT events from gene sequences. Since there are a large number of intestinal microorganisms in the human intestine, horizontal gene transfer will occur between human intestinal cells and intestinal microorganisms. If there is a tumor in the human colorectal intestine, the genetic material of the colorectal cancer tumor will be horizontally transferred to the bacteria and other microorganisms in the colorectum. In the embodiment of the present invention, the intestinal microorganisms are extracted from feces, which is non-invasive, so it will not damage the human intestine and will not have an adverse effect on human health. In addition, since there are many types of intestinal microorganisms and a large number of them, it is also easy to extract undamaged samples from feces, and it is easy to collect a large number of samples, and the extraction of microorganisms such as bacteria is relatively easy, and the process requirements are relatively low, which can reduce the cost of extraction.

[0187] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following method when executing the computer program: extracting a microorganism of an object to be screened as a target microorganism; obtaining a gene sequence of the target microorganism as a target gene sequence; obtaining a first HGT event from the target gene sequence; normalizing the first HGT event to obtain a normalized first HGT event; performing reliability verification on the normalized first HGT event to obtain a second HGT event; and obtaining the HGT tumor marker probability of the object to be screened based on the second HGT event and the standard HGT event.

[0188] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the following method: extracting a microorganism of an object to be screened as a target microorganism; obtaining a gene sequence of the target microorganism as a target gene sequence; obtaining a first HGT event from the target gene sequence; normalizing the first HGT event to obtain a normalized first HGT event; performing reliability verification on the normalized first HGT event to obtain a second HGT event; and obtaining the HGT tumor marker probability of the object to be screened based on the second HGT event and the standard HGT event.

[0189] The above-mentioned screening method for HGT tumor markers achieves the beneficial effect of being able to solve the technical problems raised in the background technology.

[0190] Figure 2 FIG. 1 is a flow chart of a method for screening HGT tumor markers in one embodiment. Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0191] Figure 4 The internal structure diagram of a computer device in one embodiment is shown. The computer device may specifically be Figure 1 The server 120 in FIG. Figure 4As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the screening method for HGT tumor markers. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the screening method for HGT tumor markers. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0192] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0194] It should be noted that, in this article, 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 such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0195] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for screening HGT tumor markers, characterized in that: The method comprises: extracting microorganisms of the object to be screened as target microorganisms; obtaining a gene sequence of the target microorganism as a target gene sequence; Obtaining a first HGT event from the target gene sequence; Normalizing the first HGT event to obtain a normalized first HGT event; Performing reliability verification on the normalized first HGT event to obtain a second HGT event; According to the second HGT event and the standard HGT event, the HGT tumor marker probability of the object to be screened is obtained.

2. The method according to claim 1, characterized in that The step of normalizing the first HGT event to obtain a normalized first HGT event comprises: According to the target gene sequence, obtaining a likelihood function of a first HGT event; According to the standard gene sequence, obtaining a priori function of the standard HGT event; According to the likelihood function of the first HGT event and the prior function of the standard HGT event, the posterior probability of the first HGT event is obtained, and the posterior probability of the first HGT event is used as the normalized first HGT event.

3. The method according to claim 2, characterized in that The obtaining of the posterior probability of the first HGT event according to the likelihood function of the first HGT event and the prior function of the standard HGT event is performed in the following manner: Among them, P(data|θ) is the likelihood function of the first HGT event, g is the total number of the target gene sequences, m is the total number of the first HGT event, θ is the probability of the first HGT event, f(θ|a,b) is the prior function of the standard HGT event, B(a,b) is the probability function of a and b, a and b are fixed parameters, and P(θ|data) is the posterior probability of the first HGT event.

4. The method according to claim 1, characterized in that: The reliability verification of the normalized first HGT event is performed to obtain the second HGT event, and the second HGT event is obtained according to the following method; α=a+m β=b+gm Wherein, P(σ) is the second HGT event, α and β are intermediate parameters, g is the total number of target gene sequences, m is the total number of first HGT events, and B(α, β) is the probability function of α and β.

5. The method according to claim 1, characterized in that The step of obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event includes: Inputting the second HGT event into the HGT model to obtain the HGT tumor marker probability of the subject to be screened; Before obtaining the HGT tumor marker probability of the subject to be screened according to the second HGT event and the standard HGT event, the method further includes: Construct an initial probability model; Acquire a training sample and a validation sample, wherein the training sample includes a training HGT event and a training sample probability, and the validation sample includes a validation HGT event and a validation sample probability; According to the standard HGT event, obtaining differential HGT from the training samples; Obtaining a difference sample corresponding to the difference HGT; Training the initial probability model according to the difference samples to obtain a model to be verified; Verifying the model to be verified according to the verification sample; The model to be verified that has passed the verification is used as the HGT model.

6. The method according to claim 5, characterized in that The training samples include training HGT events and training sample probabilities, and the validation samples include validation HGT events and validation sample probabilities; The obtaining of training samples and verification samples comprises: Obtaining sample microorganisms of a plurality of samples and a sample probability corresponding to each of the sample microorganisms; Obtaining a sample gene sequence of each of the sample microorganisms; Obtaining initial HGT events from the sample gene sequences; Normalizing and reliably verifying the initial HGT events to obtain sample HGT events; Dividing the sample HGT events into training HGT events and verification HGT events according to a preset ratio; Obtaining the training samples according to the training HGT events and corresponding sample probabilities; The verification sample is obtained according to the verification HGT event and the corresponding sample probability.

7. The method according to claim 1, characterized in that The HGT tumor marker probability of the subject to be screened is obtained according to the second HGT event and the standard HGT event in the following manner: According to multiple decision trees, multiple reference probabilities are obtained; Obtaining an average of a plurality of the reference probabilities as the HGT tumor marker probability of the subject to be screened; The method of obtaining the HGT tumor marker probability of the subject to be screened is as follows: x is the HGT vector corresponding to the second HGT event, y is the species abundance vector, x and y are used to construct the decision tree, i, j, γ, δ, ζ, η, μ are hyperparameters, M is the adjacency matrix between the second HGT event graph and the standard HGT event graph, I is the identity matrix, U is the pseudo-technical matrix, H is the adjacency matrix between the second HGT event graph and the standard HGT event graph, C is the adjacency matrix between the second HGT event abundance graph and the standard event abundance graph, P t (CRC) is the t-th reference probability, T is the number of decision trees, and P(CRC) is the HGT tumor marker probability of the subject to be screened.

8. A screening device for HGT tumor markers, characterized in that: The device comprises: An extraction unit, used to extract microorganisms of an object to be screened as target microorganisms; The extraction unit is also used to obtain the gene sequence of the target microorganism as a target gene sequence; An HGT event acquisition unit, used for acquiring a first HGT event from the target gene sequence; a normalization unit, configured to normalize the first HGT event to obtain a normalized first HGT event; A verification unit, configured to verify the reliability of the normalized first HGT event to obtain a second HGT event; The probability acquisition unit is used to acquire the HGT tumor marker probability of the object to be screened according to the second HGT event and the standard HGT event.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images