Microplastic-mediated drug resistance gene risk assessment method, device, equipment and medium
Through a multidimensional risk assessment method based on metagenomic sequencing data, combined with deep learning and comparative learning algorithms, the problem of low accuracy in risk assessment of microplastic-mediated drug-resistant genes in existing technologies has been solved, and a more accurate risk assessment has been achieved.
Patent Information
- Application Number
- CN202410271426.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-07
- Publication Date
- 2025-09-09
AI Technical Summary
Existing microplastic-mediated drug-resistance gene risk assessment methods have low accuracy and fail to fully consider multiple risk factors, resulting in inaccurate assessment results.
Based on metagenomic sequencing data, combined with deep learning and comparative learning algorithms, factors such as drug-resistant genes, mobile gene elements and pathogens are predicted. The CompRanking framework is used for risk assessment, and a multi-dimensional risk score calculation formula is adopted to improve assessment accuracy.
A multi-dimensional assessment of the risk of microplastic-mediated drug-resistant genes has been achieved, improving the accuracy and precision of risk assessment.
Smart Images
Figure CN120613010A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of ecological risk assessment and control, and in particular to a method, device, computer equipment and storage medium for microplastic-mediated drug-resistant gene risk assessment. Background Art
[0002] Antibiotic resistance is a major emerging global health issue, with resistance genes playing a key role. Carrying resistance genes can cause microorganisms to develop tolerance to specific antibiotics or drugs, thereby affecting treatment effectiveness. When plastic waste enters the natural world, it continues to shrink, forming microplastics (particle size less than 5mm). The surface of microplastics is considered a "hotspot" for the accumulation of resistance genes, meaning that microplastic surfaces are prone to carrying large numbers of resistance genes. However, there is currently no dedicated risk assessment method for evaluating microplastic-mediated resistance genes. Existing methods primarily use qPCR (real-time fluorescence quantitative analysis) or meta-omics-based methods to quantify the relative abundance of resistance genes, using this as a proxy for risk, and thus comparing resistance risks in different microplastic samples. However, there are many factors that contribute to resistance risk, and existing methods for assessing risk are relatively single-factor, resulting in low accuracy in risk assessment results. Therefore, how to implement risk assessment of microplastic-mediated resistance genes and improve the accuracy of ecological risk assessment of microplastic-mediated resistance genes has become an urgent issue that needs to be addressed. Summary of the Invention
[0003] The present application provides a microplastic-mediated drug-resistance gene risk assessment method, device, computer equipment and storage medium to achieve microplastic-mediated drug-resistance gene risk assessment and improve the accuracy of microplastic-mediated drug-resistance gene ecological risk assessment.
[0004] In a first aspect, the present application provides a method for risk assessment of drug-resistant genes mediated by microplastics, the method comprising:
[0005] Based on the microplastic sample to be evaluated, obtaining metagenomic sequencing data of the microplastic sample to be evaluated;
[0006] Based on a preset prediction algorithm, predicting the drug resistance risk factors in the metagenomic sequencing data to obtain a prediction result;
[0007] Based on the prediction results, a risk score calculation is performed to obtain an assessment score for drug resistance risk.
[0008] Furthermore, the risk score calculation is performed based on the prediction result to obtain an assessment score of drug resistance risk, including:
[0009] Determining the risk level of the contig corresponding to the metagenomic sequencing data based on the prediction result;
[0010] Obtain a risk sub-score calculation formula corresponding to the risk level;
[0011] Based on the risk sub-score calculation formula, processing the antibiotic resistance gene ARG-like sequence in the contig to obtain the risk sub-score of the contig;
[0012] The assessment score is obtained based on a preset total risk calculation formula and the risk score.
[0013] Furthermore, the total risk calculation formula is:
[0014]
[0015] Wherein, SCORE(s) is the evaluation score, s is the normalized value of the ARG-like sequence, and h is the empirical parameter;
[0016] in, dist(s, h) is the Euclidean distance between s and h in the risk space, and Ndim is the number of dimensions of the drug resistance risk factor.
[0017] Furthermore, the drug resistance risk factors in the metagenomic sequencing data are predicted based on a preset prediction algorithm to obtain prediction results, including:
[0018] Based on the open reading frame corresponding to the metagenomic sequencing data, predicting drug-resistant genes on the metagenomic sequencing data to obtain a first prediction result;
[0019] Based on the contigs corresponding to the metagenomic sequencing data and the open reading frame, performing mobile gene element prediction on the metagenomic sequencing data to obtain a second prediction result;
[0020] Based on the contigs, predicting pathogens on the metagenomic sequencing data to obtain a third prediction result;
[0021] The prediction result is generated based on the first prediction result, the second prediction result and the third prediction result.
[0022] Furthermore, the method further comprises: performing mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame, before obtaining the second prediction result;
[0023] Based on the metagenomic sequencing data, obtaining a short read sequence to be assembled;
[0024] Based on a preset assembly tool, the short read sequences to be assembled are assembled to obtain the contigs.
[0025] Furthermore, the mobile gene element prediction is performed on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result, including:
[0026] Predicting mobile gene elements of the metagenomic sequencing data based on a deep learning algorithm and the contigs to obtain an initial prediction result;
[0027] Obtaining annotation information of mobile gene elements in the metagenomic sequencing data based on a comparative learning algorithm and the open reading frame;
[0028] The initial prediction result is corrected based on the annotation result to obtain the second prediction result.
[0029] Furthermore, the drug resistance risk factors include drug resistance genes, mobile gene elements and pathogens.
[0030] In a second aspect, the present application also provides a microplastic-mediated drug-resistance gene risk assessment device, comprising:
[0031] A data acquisition module is used to obtain metagenomic sequencing data of the microplastic sample to be evaluated based on the microplastic sample to be evaluated;
[0032] A prediction result acquisition module is used to predict the drug resistance risk factors in the metagenomic sequencing data based on a preset prediction algorithm to obtain a prediction result;
[0033] The evaluation score acquisition module is used to calculate the risk score based on the prediction result to obtain the evaluation score of drug resistance risk.
[0034] In a third aspect, the present application also provides a computer device comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the microplastic-mediated drug-resistance gene risk assessment method as described above when executing the computer program.
[0035] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the microplastic-mediated drug-resistance gene risk assessment method as described above.
[0036] The present application discloses a microplastic-mediated drug-resistance gene risk assessment method, apparatus, computer equipment and storage medium. Based on the microplastic sample to be assessed, the metagenomic sequencing data of the microplastic sample to be assessed is obtained; based on a preset prediction algorithm, the drug-resistance risk factors in the metagenomic sequencing data are predicted to obtain a prediction result; based on the prediction result, a risk score is calculated to obtain an assessment score for the drug-resistance risk. The present method predicts the drug-resistance risk factors in the metagenomic prediction data according to a preset prediction algorithm to determine the risk factors existing in the current metagenomic prediction data, and then calculates the risk score based on the actual prediction result. In the above manner, the risk assessment method of the present application is not limited to risk factors of a single dimension, but is combined with the actual risk factor situation of the metagenomic prediction data. Microplastic-mediated drug-resistance gene risk assessment is achieved, and the accuracy of the results of drug-resistance gene risk assessment is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0038] Figure 1 This is a schematic flow chart of a first embodiment of a microplastic-mediated drug-resistance gene risk assessment method provided in an embodiment of the present application;
[0039] Figure 2 This is a schematic flow chart of a second embodiment of a microplastic-mediated drug-resistance gene risk assessment method provided in an embodiment of the present application;
[0040] Figure 3 This is a schematic flow chart of a third embodiment of a microplastic-mediated drug-resistance gene risk assessment method provided in the embodiments of the present application;
[0041] Figure 4 A schematic block diagram of a microplastic-mediated drug resistance gene risk assessment device provided in an embodiment of the present application;
[0042] Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0044] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.
[0045] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.
[0046] It should be further understood that the term “and / or” used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0047] The embodiments of the present application provide a method, device, computer equipment and storage medium for assessing the risk of microplastic-mediated drug-resistant genes. Among them, the microplastic-mediated drug-resistant gene risk assessment method can be applied to a server, and the risk factors existing in the current metagenome prediction data are predicted by predicting the drug-resistant risk factors in the metagenome prediction data, and then the risk score is calculated based on the actual prediction results. It is not limited to risk factors of a single dimension, but combines the actual risk factors of the metagenome prediction data. It realizes the risk assessment of microplastic-mediated drug-resistant genes and improves the accuracy of the ecological risk assessment of microplastic-mediated drug-resistant genes. Among them, the server can be an independent server or a server cluster.
[0048] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.
[0049] See also Figure 1 , Figure 1 This is a schematic flow chart of a microplastic-mediated drug-resistance gene risk assessment method provided in an embodiment of the present application.
[0050] like Figure 1As shown, the microplastic-mediated drug-resistance gene risk assessment method specifically includes steps S101 to S104.
[0051] S101. Based on the microplastic sample to be evaluated, obtaining metagenomic sequencing data of the microplastic sample to be evaluated;
[0052] In one embodiment, the microplastic samples to be evaluated are environmental samples that require drug resistance risk assessment, such as hospital wastewater, sewage treatment plant effluent, and urban river water.
[0053] In one embodiment, the total DNA (deoxyribonucleic acid) of all microorganisms in the microplastic sample to be evaluated is subjected to high-throughput sequencing using Illumina second-generation sequencing technology to obtain metagenomic sequencing data.
[0054] S102, predicting drug resistance risk factors in the metagenomic sequencing data based on a preset prediction algorithm to obtain a prediction result;
[0055] Furthermore, the drug resistance risk factors include drug resistance genes, mobile gene elements and pathogens.
[0056] In one embodiment, the present application provides a CompRanking (risk ranking) framework for implementing microplastic-mediated drug-resistance gene risk assessment. The CompRanking framework includes four modules: a drug-resistance gene prediction module, a mobile gene element prediction module, a pathogen prediction module, and a data integration and calculation module.
[0057] The drug-resistance gene prediction module, mobile gene element prediction module, and pathogen prediction module are used to predict drug-resistance genes, mobile gene elements, and pathogens in metagenomic sequencing data, respectively, and obtain prediction results for drug-resistance genes, mobile gene elements, and pathogens. The data integration and calculation module is used to integrate the prediction results of the drug-resistance gene prediction module, mobile gene element prediction module, and pathogen prediction module to output the final prediction results.
[0058] In one embodiment, the prediction results are output in the form of metadata, which includes the index of the contigs corresponding to the metagenomic sequencing data and the drug resistance related information in each contig (such as the type of drug resistance gene, the type of mobile gene element, and whether it is a pathogen, etc.).
[0059] In one embodiment, prediction algorithms are used to predict drug resistance risk factors in metagenomic sequencing data. These can include deep learning algorithms (such as Seeker and DeepVirFinder) and local alignment algorithms (such as blastx (Basic Local Alignment Search Tool, a short sequence alignment tool for aligning nucleotide sequences to amino acid databases)).
[0060] S103. Based on the prediction result, a risk score is calculated to obtain an assessment score for drug resistance risk.
[0061] In one embodiment, risk levels are classified based on the prediction results. Then, a risk subscore calculation formula corresponding to each risk level is obtained, and the risk subscores of overlapping groups at different risk levels are calculated. Finally, the overall risk calculation formula and the risk subscores of each overlapping group are combined to obtain a drug resistance risk assessment score for the microplastic sample to be evaluated.
[0062] The above embodiment provides a microplastic-mediated drug-resistant gene risk assessment method, which can predict the drug resistance risk factors in the metagenomic prediction data according to a preset prediction algorithm to determine the risk factors existing in the current metagenomic prediction data, and then calculate the risk score based on the actual prediction results. In this way, the risk assessment method of the present application is not limited to the risk factors of a single dimension, but combines the actual risk factors of the metagenomic prediction data. This improves the accuracy of the results of the drug-resistant gene risk assessment.
[0063] See also Figure 2 , Figure 2 This is a schematic flow chart of a microplastic-mediated drug-resistance gene risk assessment method provided in an embodiment of the present application. This microplastic-mediated drug-resistance gene risk assessment method can be applied to a server to comprehensively assess the risk of drug-resistance gene transmission based on multiple dimensional factors, thereby improving the accuracy of the assessment results.
[0064] like Figure 2 As shown, the microplastic-mediated drug-resistance gene risk assessment method specifically includes steps S201 to S204.
[0065] S201, determining the risk level of the contig corresponding to the metagenomic sequencing data based on the prediction result;
[0066] S202: Obtain a risk sub-score calculation formula corresponding to the risk level;
[0067] S203, processing the antibiotic resistance gene ARG-like sequence in the contig based on the risk sub-score calculation formula to obtain a risk sub-score for the contig;
[0068] S204: Obtain the assessment score based on a preset total risk calculation formula and the risk score.
[0069] Furthermore, the total risk calculation formula is:
[0070]
[0071] Wherein, SCORE(s) is the evaluation score, s is the normalized value of the ARG-like sequence, and h is the empirical parameter;
[0072] in, dist(s, h) is the Euclidean distance between s and h in the risk space, and Ndim is the number of dimensions of the drug resistance risk factor.
[0073] In one embodiment, different rules are set according to the level of Contig (contig), which is divided into different levels: (1) unclassified contigs are annotated as Risk IV (risk level 4), (2) contigs containing only ARGs are annotated as Risk III (risk level 3), (3) contigs containing both ARGs and MGEs (mobile gene elements) are annotated as Risk II (risk level 2), and (4) contigs containing both ARGs, MGEs and PATHs (pathogens) are annotated as Risk I (risk level 1).
[0074] In a specific embodiment, when the prediction result is that only drug-resistant genes are found in the overlapping group, the risk level of the overlapping group is defined as risk level 3; when the prediction result is that drug-resistant genes and mobile gene elements are found in the overlapping group at the same time, the risk level of the overlapping group is defined as risk level 2; when the prediction result is that drug-resistant genes, mobile gene elements and pathogens are found in the overlapping group at the same time, the risk level of the overlapping group is defined as risk level 1.
[0075] In one embodiment, the risk level is determined by annotation, ie, the contigs are annotated according to corresponding levels.
[0076] In one embodiment, to perform quantitative ranking, the number of contigs for each risk level is divided by the total number of contigs to obtain a subscore for each risk.
[0077] In one embodiment, for a given Contig c and the entire Contig C set, define
[0078]
[0079] Among them, ARG represents antibiotic resistance gene, that is, drug-resistant gene.
[0080] In one embodiment, ARG in the above formula can be replaced by ARG∩MGE or ARG∩MGE∩PATH according to actual prediction results.
[0081] In one embodiment, the formula for calculating the risk sub-score corresponding to risk level 3 is:
[0082]
[0083] Where Q(ARG) represents the risk sub-score of risk level 3, N comtigs represents the total number of contigs.
[0084] In one embodiment, the formula for calculating the risk sub-score corresponding to risk level 2 is:
[0085]
[0086] Where Q(ARG,MGE) represents the risk subscore of risk level 2; MGE represents mobile genetic element.
[0087] In one embodiment, the formula for calculating the risk sub-score corresponding to risk level 1 is:
[0088]
[0089] Where PATH represents the pathogen (or virulence factor); Q(ARG, MGE, PATH) represents the risk subscore of risk level 1.
[0090] In a specific embodiment, a calculation formula for the risk sub-score corresponding to each risk level is obtained according to the risk level, and a calculation result is obtained.
[0091] In one embodiment, according to the Euclidean distance calculation formula in the danger space Calculate the Euclidean distance between s and h to obtain dist(s, h). Wherein, f in the formula is (ARG), (ARG, MGE) or (ARG, MGE, PATH). Ndim represents the number of dimensions considered when describing the resistance group of a sample. In the embodiment of the present application, it is three, and the number of dimensions can also be set according to actual needs. h represents the maximum empirical parameter set to 0.01. s represents the numerical value of Q(ARG), Q(ARG, MGE) and Q(ARG, MGE, PATH).
[0092] In one embodiment, the evaluation score can be used to evaluate the drug resistance risk of the microplastic sample to be evaluated.
[0093] Exemplarily, the method provided in the above examples was used to perform risk grading on in situ plastogenomic data generated from the Dasha River. Degradable microplastics (Risks I-III: 9.95e-05, 5.58e-05, 8.38e-04) showed a higher AMR transmission risk than non-degradable microplastics (Risks I-III: 3.86e-05, 3.97e-05, 5.64e-04), wood pellets (Risks I-III: 6.75e-05, 6.91e-05, 8.06e-04), and the aquatic microbiome (Risks I-III: 4.72e-05, 4.75e-05, 8.27e-04) in terms of the average risk scores of the three categories. In terms of overall risk scores, biodegradable plastics (PCL: 21.25, PHA: 21.52) had higher mean risk scores than refractory plastics (PP = 20.09, PS = 19.80). Microplastics (refractory: 21.39; biodegradable: 19.97; overall: 20.68) showed no significant differences in risk scores compared to environmental samples (aquatic samples = 20.77, wood pellets = 21.30) (one-way ANOVA, p>0.05). While biodegradable plastics showed no significant differences in risk scores compared to aquatic samples and wood pellets (one-way ANOVA, p>0.05), refractory plastics had significantly lower risk scores than biodegradable plastics (one-way ANOVA, p<0.05) and aquatic samples (unpaired t-test, p<0.01), indicating that refractory plastics pose a lower risk of AMR transmission.
[0094] See also Figure 3 , Figure 3 This is a schematic flow chart of a microplastic-mediated drug-resistance gene risk assessment method provided in an embodiment of the present application. This microplastic-mediated drug-resistance gene risk assessment method can be applied to a server to predict drug resistance risk factors using multiple methods, improving prediction efficiency and accuracy.
[0095] like Figure 3 As shown, the microplastic-mediated drug-resistance gene risk assessment method specifically includes steps S301 to S304.
[0096] S301, predicting drug-resistant genes on the metagenomic sequencing data based on the open reading frames corresponding to the metagenomic sequencing data to obtain a first prediction result;
[0097] In one embodiment, drug-resistance gene predictions were performed entirely on the ORFs (open reading frames) corresponding to metagenomic sequencing data. This was achieved by combining DeepARG (a deep learning-based drug-resistance gene prediction method), RGI (a drug-resistance gene identifier), and Blast (a basic local alignment search tool). This improved the accuracy of the initial prediction results.
[0098] An ORF is a theoretically continuous amino acid coding region that begins at the start codon and ends at the stop codon. This can be determined by analyzing a gene sequence. The gene's mRNA (messenger RNA) is fed into an analysis program, which searches for the start codon within the nucleic acid sequence.
[0099] In one embodiment, the first prediction result includes two results: the current contig contains the drug-resistant gene and the current contig does not contain the drug-resistant gene.
[0100] S302, performing mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result;
[0101] Furthermore, the step S302 includes: predicting the mobile gene elements of the metagenomic sequencing data based on the deep learning algorithm and the overlapping group to obtain an initial prediction result; obtaining annotation information of the mobile gene elements of the metagenomic sequencing data based on the comparative learning algorithm and the open reading frame; and correcting the initial prediction result based on the annotation result to obtain the second prediction result.
[0102] In one embodiment, the prediction of mobile gene elements uses a deep learning algorithm and a contrastive learning algorithm.
[0103] In one embodiment, deep learning-based mobile gene element prediction is performed on contigs, using Seeker and DeepVirFinder. Alignment-based mobile gene element prediction is performed on ORFs, which are then aligned to the MobileOG-db database to obtain annotation information. The MobileOG-db database is a mobile gene element database.
[0104] In one example, a strategy was adopted to combine predictions from a deep learning framework (primarily targeting plasmids and phages) with reference annotations (for all types of MGEs) to produce final predictions. The final predictions were refined using annotations from the Mobile-OG database to correct for false positives generated by the deep learning framework, thereby improving prediction accuracy.
[0105] In one embodiment, the second prediction result includes two results: the current contig contains the mobile genetic element; and the current contig does not contain the mobile genetic element.
[0106] Furthermore, before step S302, the method further includes: obtaining short read sequences to be assembled based on the metagenomic sequencing data; and assembling the short read sequences to be assembled based on a preset assembly tool to obtain the contigs.
[0107] In one embodiment, first, the metagenomic sequencing data is quality controlled to obtain high-quality cleanreads (clean sequences, i.e., short read length sequences to be assembled). Specifically, the DNA in the metagenomic sequencing data is randomly interrupted by the illumina second-generation sequencing technology, and the two ends are filled with enzymes. Then connectors and indexes are added to both ends of these fragments, and after PCR (Polymerase Chain Reaction) amplification, they are put on the machine for testing. The current length of the second-generation sequencing is about 150-250bp. During the sequencing process, the sequences at both ends of the reads (read length) are extremely prone to errors. Therefore, the rawdata (raw data) obtained by sequencing contains some low-quality reads (sequences) with connectors. In order to ensure the quality of information analysis, the raw reads (original sequences) are filtered to obtain clean reads. Among them, reads (read length) refers to the base sequence obtained by word sequencing of the sequencer.
[0108] In one embodiment, the metagenomic assembly is then performed using a preset assembly tool to obtain contigs corresponding to the metagenomic sequencing data, forming a fasta (a text format for recording nucleic acid sequences or peptide sequences) file. The metagenomic sequencing data can be assembled to obtain multiple contigs.
[0109] In one embodiment, the preset assembly tool may be the Megahit tool, which is a metagenomic de novo assembly tool.
[0110] S303, performing pathogen prediction on the metagenomic sequencing data based on the contigs to obtain a third prediction result;
[0111] In one embodiment, for pathogen prediction, only an alignment-based approach was used, using blastx to align contig-level sequences to the built-in pathogen database of MetaCompare, a publicly available tool for ranking “resistance risk.”
[0112] In one embodiment, the third prediction result includes two results: the current contig contains pathogens and the current contig does not contain pathogens.
[0113] S304: Generate the prediction result based on the first prediction result, the second prediction result, and the third prediction result.
[0114] In one embodiment, when the first prediction result is that the current contig contains drug-resistant genes, the second prediction result is that the current contig does not contain mobile gene elements, and the third prediction result is that the current contig does not contain pathogens, the prediction result is that only drug-resistant genes are found in the current contig.
[0115] In one embodiment, when the first prediction result is that the current contig contains drug-resistant genes, the second prediction result is that the current contig contains mobile gene elements, and the third prediction result is that the current contig does not contain pathogens, the prediction result is that both drug-resistant genes and mobile gene elements are found in the current contig.
[0116] In one embodiment, when the first prediction result is that the current overlapping group contains drug-resistant genes, the second prediction result is that the current overlapping group contains mobile gene elements, and the third prediction result is that the current overlapping group contains pathogens, the prediction result obtained is that drug-resistant genes, mobile gene elements and pathogens are found in the current overlapping group at the same time.
[0117] In one embodiment, the prediction results may also include the type of drug-resistant gene predicted, the type of mobile gene element, and whether it is a pathogen.
[0118] See also Figure 4 , Figure 4 This embodiment of the present application provides a schematic block diagram of a microplastic-mediated drug-resistance gene risk assessment device, which is used to perform the aforementioned microplastic-mediated drug-resistance gene risk assessment method. The microplastic-mediated drug-resistance gene risk assessment device can be configured on a server.
[0119] like Figure 4 As shown, the microplastic-mediated drug-resistance gene risk assessment device 400 includes:
[0120] A data acquisition module 401 is used to obtain metagenomic sequencing data of the microplastic sample to be evaluated based on the microplastic sample to be evaluated;
[0121] A prediction result obtaining module 402 is used to predict the drug resistance risk factors in the metagenomic sequencing data based on a preset prediction algorithm to obtain a prediction result;
[0122] The evaluation score obtaining module 403 is used to calculate the risk score based on the prediction result to obtain an evaluation score for drug resistance risk.
[0123] Furthermore, the evaluation score obtaining module 403 includes:
[0124] a risk level determination unit, configured to determine a risk level of the contig corresponding to the metagenomic sequencing data based on the prediction result;
[0125] a risk sub-score calculation formula acquisition unit, configured to acquire a risk sub-score calculation formula corresponding to the risk level;
[0126] a risk score obtaining unit, configured to process the antibiotic resistance gene ARG-like sequence in the contig based on the risk sub-score calculation formula to obtain a risk sub-score for the contig;
[0127] An assessment score obtaining unit is configured to obtain the assessment score based on a preset total risk calculation formula and the risk score.
[0128] Furthermore, the total risk calculation formula is:
[0129]
[0130] Wherein, SCORE(s) is the evaluation score, s is the normalized value of the ARG-like sequence, and h is the empirical parameter;
[0131] in, dist(s, h) is the Euclidean distance between s and h in the risk space, and Ndim is the number of dimensions of the drug resistance risk factor.
[0132] Furthermore, the prediction result obtaining module 402 includes:
[0133] A first prediction result obtaining unit is configured to perform drug-resistant gene prediction on the metagenomic sequencing data based on the open reading frame corresponding to the metagenomic sequencing data to obtain a first prediction result;
[0134] A second prediction result obtaining unit is configured to perform mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result;
[0135] A third prediction result obtaining unit is configured to perform pathogen prediction on the metagenomic sequencing data based on the contigs to obtain a third prediction result;
[0136] A prediction result generating unit is used to generate the prediction result based on the first prediction result, the second prediction result and the third prediction result.
[0137] Furthermore, the prediction result obtaining module 402 further includes:
[0138] A short-read sequence obtaining unit to be assembled, used to obtain a short-read sequence to be assembled based on the metagenomic sequencing data;
[0139] The contig obtaining unit is used to assemble the short read sequence to be assembled based on a preset assembly tool to obtain the contig.
[0140] Furthermore, the second prediction result obtaining unit includes:
[0141] An initial prediction result obtaining subunit is used to predict the mobile gene elements of the metagenomic sequencing data based on a deep learning algorithm and the contigs to obtain an initial prediction result;
[0142] An annotation acquisition subunit, configured to obtain annotation information of mobile gene elements in the metagenomic sequencing data based on a comparative learning algorithm and the open reading frame;
[0143] The result correction subunit is configured to correct the initial prediction result based on the annotation result to obtain the second prediction result.
[0144] Furthermore, the drug resistance risk factors include drug resistance genes, mobile gene elements and pathogens.
[0145] It should be noted that those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0146] The above-mentioned device can be realized in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer equipment shown.
[0147] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.
[0148] See Figure 5The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
[0149] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to execute any one of the microplastic-mediated drug resistance gene risk assessment methods.
[0150] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0151] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any microplastic-mediated drug-resistance gene risk assessment method.
[0152] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
[0153] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.
[0154] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:
[0155] Based on the microplastic sample to be evaluated, obtaining metagenomic sequencing data of the microplastic sample to be evaluated;
[0156] Based on a preset prediction algorithm, predicting the drug resistance risk factors in the metagenomic sequencing data to obtain a prediction result;
[0157] Based on the prediction results, a risk score calculation is performed to obtain an assessment score for drug resistance risk.
[0158] In one embodiment, when the processor calculates the risk score based on the prediction result to obtain the assessment score of drug resistance risk, it is configured to implement:
[0159] Determining the risk level of the contig corresponding to the metagenomic sequencing data based on the prediction result;
[0160] Obtain a risk sub-score calculation formula corresponding to the risk level;
[0161] Based on the risk sub-score calculation formula, processing the antibiotic resistance gene ARG-like sequence in the contig to obtain the risk sub-score of the contig;
[0162] The assessment score is obtained based on a preset total risk calculation formula and the risk score.
[0163] In one embodiment, the total risk calculation formula is:
[0164]
[0165] Wherein, SCORE(s) is the evaluation score, s is the normalized value of the ARG-like sequence, and h is the empirical parameter;
[0166] in, dist(s, h) is the Euclidean distance between s and h in the risk space, and Ndim is the number of dimensions of the drug resistance risk factor.
[0167] In one embodiment, the processor, when implementing a preset prediction algorithm to predict the drug resistance risk factors in the metagenomic sequencing data and obtaining a prediction result, is used to implement:
[0168] Based on the open reading frame corresponding to the metagenomic sequencing data, predicting drug-resistant genes on the metagenomic sequencing data to obtain a first prediction result;
[0169] Based on the contigs corresponding to the metagenomic sequencing data and the open reading frame, performing mobile gene element prediction on the metagenomic sequencing data to obtain a second prediction result;
[0170] Based on the contigs, predicting pathogens on the metagenomic sequencing data to obtain a third prediction result;
[0171] The prediction result is generated based on the first prediction result, the second prediction result and the third prediction result.
[0172] In one embodiment, before performing mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result, the processor is further configured to implement:
[0173] Based on the metagenomic sequencing data, obtaining a short read sequence to be assembled;
[0174] Based on a preset assembly tool, the short read sequences to be assembled are assembled to obtain the contigs.
[0175] In one embodiment, when the processor performs mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result, it is configured to implement:
[0176] Predicting mobile gene elements of the metagenomic sequencing data based on a deep learning algorithm and the contigs to obtain an initial prediction result;
[0177] Obtaining annotation information of mobile gene elements in the metagenomic sequencing data based on a comparative learning algorithm and the open reading frame;
[0178] The initial prediction result is corrected based on the annotation result to obtain the second prediction result.
[0179] In one embodiment, the drug resistance risk factors include drug resistance genes, mobile gene elements and pathogens.
[0180] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the microplastic-mediated drug-resistance gene risk assessment methods provided in the embodiments of the present application.
[0181] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.
[0182] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.
Claims
1. A method for assessing the risk of microplastic-mediated drug-resistant genes, characterized in that: include: Based on the microplastic sample to be evaluated, obtaining metagenomic sequencing data of the microplastic sample to be evaluated; Based on a preset prediction algorithm, predicting the drug resistance risk factors in the metagenomic sequencing data to obtain a prediction result; Based on the prediction results, a risk score calculation is performed to obtain an assessment score for drug resistance risk.
2. The microplastic-mediated drug-resistance gene risk assessment method according to claim 1, characterized in that: The step of calculating a risk score based on the prediction result to obtain an assessment score for drug resistance risk includes: Determining the risk level of the contig corresponding to the metagenomic sequencing data based on the prediction result; Obtain a risk sub-score calculation formula corresponding to the risk level; Based on the risk sub-score calculation formula, processing the antibiotic resistance gene ARG-like sequence in the contig to obtain the risk sub-score of the contig; The assessment score is obtained based on a preset total risk calculation formula and the risk score.
3. The microplastic-mediated drug-resistance gene risk assessment method according to claim 2, characterized in that: The total risk calculation formula is: Wherein, SCORE(s) is the evaluation score, s is the normalized value of the ARG-like sequence, and h is the empirical parameter; in, dist(s, h) is the Euclidean distance between s and h in the risk space, and Ndim is the number of dimensions of the drug resistance risk factor.
4. The microplastic-mediated drug-resistance gene risk assessment method according to claim 1, characterized in that: The method of predicting drug resistance risk factors in the metagenomic sequencing data based on a preset prediction algorithm to obtain prediction results includes: Based on the open reading frame corresponding to the metagenomic sequencing data, predicting drug-resistant genes on the metagenomic sequencing data to obtain a first prediction result; Based on the contigs corresponding to the metagenomic sequencing data and the open reading frame, performing mobile gene element prediction on the metagenomic sequencing data to obtain a second prediction result; Based on the contigs, predicting pathogens on the metagenomic sequencing data to obtain a third prediction result; The prediction result is generated based on the first prediction result, the second prediction result and the third prediction result.
5. The microplastic-mediated drug-resistance gene risk assessment method according to claim 4, characterized in that: Before performing mobile gene element prediction on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain the second prediction result, the method further comprises: Based on the metagenomic sequencing data, obtaining a short read sequence to be assembled; Based on a preset assembly tool, the short read sequences to be assembled are assembled to obtain the contigs.
6. The microplastic-mediated drug-resistance gene risk assessment method according to claim 4, characterized in that: The step of predicting mobile gene elements on the metagenomic sequencing data based on the contigs corresponding to the metagenomic sequencing data and the open reading frame to obtain a second prediction result includes: Predicting mobile gene elements of the metagenomic sequencing data based on a deep learning algorithm and the contigs to obtain an initial prediction result; Obtaining annotation information of mobile gene elements in the metagenomic sequencing data based on a comparative learning algorithm and the open reading frame; The initial prediction result is corrected based on the annotation result to obtain the second prediction result.
7. The microplastic-mediated drug-resistance gene risk assessment method according to any one of claims 1 to 6, characterized in that: The drug resistance risk factors include drug resistance genes, mobile gene elements and pathogens.
8. A microplastic-mediated drug-resistance gene risk assessment device, characterized in that: include: A data acquisition module is used to obtain metagenomic sequencing data of the microplastic sample to be evaluated based on the microplastic sample to be evaluated; A prediction result acquisition module is used to predict the drug resistance risk factors in the metagenomic sequencing data based on a preset prediction algorithm to obtain a prediction result; The evaluation score acquisition module is used to calculate the risk score based on the prediction result to obtain the evaluation score of drug resistance risk.
9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the microplastic-mediated drug-resistance gene risk assessment method as described in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to implement the microplastic-mediated drug-resistance gene risk assessment method as described in any one of claims 1 to 7.