Computer-implemented method for evaluating nitrogen absorption capacity of plant through rhizosphere soil environment characteristics

Abstract

The invention provides a computer implementation method for evaluating the nitrogen absorption capacity of a plant through rhizosphere soil environment characteristics, a computer system for evaluating the nitrogen absorption capacity of the plant, computer equipment and a computer readable storage medium. Based on the method, the computer system, the computer equipment and the computer readable storage medium provided by the invention, the nitrogen absorption capability of the plant root system can be better evaluated, so that the subsequent targeted ecological restoration and treatment of the stony desertification region are facilitated.

Description

Technical Field

[0001] This invention relates to the field of computer-based intelligent plant monitoring, and specifically to a computer-implemented method for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics. Background Technology

[0002] The world's karst area is approximately 22 million km². 2 Karst ecosystems are most widely distributed in southern China, centered on Guizhou Province. Due to their unique background of well-developed carbonate rocks and fragmented surface, karst ecosystems are characterized by habitat fragility and diversity. Furthermore, human agricultural activities have led to ecosystem degradation, resulting in severe desertification. In these desertified areas, long-term human activity has resulted in widespread bedrock exposure, shallow and discontinuous soil layers, severe soil erosion, poor water and nutrient retention capacity, and severe nutrient deficiency. The soil is also nitrogen-poor, hindering the absorption and utilization of nutrients such as nitrogen by plants. Over time, this makes plant survival difficult in desertified areas, negatively impacting the ecosystem and creating a vicious cycle. This has become a critical ecological and economic problem hindering the sustainable development of the southwestern karst region.

[0003] Against this backdrop, to better promote plant nutrient absorption and utilization, explore solutions to the problem of rocky desertification, and provide insights into addressing severe soil erosion, ecological imbalance, and low vegetation cover in rocky desertification areas, further research is needed into the mechanism of the relationship chain between plant root nitrogen absorption, soil nitrogen, soil metabolites, and microorganisms. Therefore, there is an urgent need to develop a method for accurately evaluating the nitrogen absorption capacity of plant roots, thereby facilitating targeted ecological restoration and management. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, the present invention aims to provide a computer-based method, computer system, computer equipment, and computer-readable storage medium for evaluating the nitrogen uptake capacity of plants in rocky desertification areas based on rhizosphere soil environmental characteristics.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The first aspect of the present invention provides a computer-based method for evaluating the nitrogen uptake capacity of plants through rhizosphere soil environmental characteristics. The method comprises the following steps: acquiring data on metabolite levels and / or microbial abundance in the sample to be tested, and comparing them with reference values.

[0007] The comparison refers to the following: if one or more levels in metabolite group 1) are higher than the reference value, one or more levels in metabolite group 2) are lower than the reference value, one or more abundances in microbiome 3) are higher than the reference value, and / or one or more abundances in microorganism 4) are lower than the reference value, then the evaluation result of the nitrogen uptake capacity of the plant represented by the test sample is good; otherwise, the evaluation result of the nitrogen uptake capacity of the plant represented by the test sample is poor.

[0008] The metabolite group 1) includes Decanoic acid, 3-Iodopropanoic acid, Pentadecanoic acid, Methylcobalamin, Dipentyl phthalate, Geranylgeranylcysteine, Cycloheptasiloxane, tetradecamethyl-, Hexadecane, 2,6,11,15-tetramethyl-.

[0009] The metabolite group 2) includes meso-Pristane, L-Histidinol, Dimethicone, Dodecanal, and 1-(5-Acetyl-2hydroxyphenyl)-3-methyl-1-butanone.

[0010] The microbiome 3) includes Bacteroidetes, Actinobacteria, Acidobacteria, Chryseolinea, Ohtaekwangia, Planctomycetes, Rhizophagus, Euryarchaeota, and Nitrosocosmicus.

[0011] The microbiome 4) includes Chloroflexi, Gemmatimonadetes, Ramlibacter, Penicillium, Zopfia, Aspergillus, Crenarchaeota, and Thaumarchaoota.

[0012] The second aspect of the present invention provides a method for evaluating the nitrogen uptake capacity of plants using a computer based on the characteristics of the rhizosphere soil environment. The method comprises the following steps: acquiring data on the metabolite levels and / or microbial abundance in the sample to be tested, and evaluating the nitrogen uptake capacity of plants based on a pre-constructed evaluation model.

[0013] Furthermore, the constructed evaluation model obtains results indicating good or poor plant nitrogen uptake capacity based on data on metabolite levels and / or microbial abundance in the sample to be tested.

[0014] The metabolites include L-serine, 2,4,6-Trihydroxybenzoic acid, 4-Ethylbenzoic acid, Serylserine, Monoisobutyl phthalic acid, Stearyl citrate, Monoethylhexylphthalic acid, Diisobutyl phthalate, Tetradecanedioic acid, Decanoic acid, Acetic acid, Amyl salicylate, 3-Iodopropanoic acid, A-Ketoglutaric acid oxime, Iodotyrosine, Hydroxypyruvic acid, Methylcobalamin, 3,5-Diiodothyronine, Dipentylphthalate, Dimethylmalonic acid, Methyl 3-methylbutanoate, Ferulic acid, alpha-Hydroxyisobutyric acid, Isopropyl hexadecanoate, (E)-6-Methyl-6-(5-methyl-2-furanyl)-3-hepten-2-one, 1,1-Dimethylethyl heptanoic acid, 1-Decanol, 1-Hexadecanol, 1-Octadecanol, 2-Hydroxyhexadecanoic acid, Diethyl succinate, Ganolucidic acid D, Geranylgeranylcysteine, Ethene, Heptaethylene glycol, L-Histidinol, Octadecyl octyl ether, Pentadecane, 2,6,10,14-tetramethyl-, Pentadecanoic acid, Squalene, 1H-Tetrazol-5-amine, 3,5-Dimethyl-1,2,4-trithiolane, Quercitrin, 2,6-Di-tert-butyl-4-hydroxymethylphenol, Benzaldehyde, 2,4-dimethyl-, Cinnamyl benzoate, cis-3-Hexenyl pentanoate, Dimethicone, 2,4-Dihydroxybenzaldehyde、N-Acetylglucosamine 6-sulfate、Dihydroxyacetonephosphate、2-(3,4-dimethoxyphenyl)-3-hydroxychromen-4-one、3,5,5-Trimethyl-2-cyclohexen-1-one、Dodecanal、Ethanolamine、4-Ethyl-2-octylthiazole、N,N-Dimethylphenethylamine、Kaempferol、Morphine、Dibutyl phthalate、Isopropylmyristate、Methyl stearate、Benzocyclodecene,tetradecahydro-、Benzeneethanamine,N-(2-phenylethyl)-、Phthalic acid,di(2-propylpentyl)ester、Hexadecanoic acid,methyl ester、Benzenepropanoic acid,3,5-bis(1,1-dimethylethyl)-4-hydroxy-,methyl ester、2,4-Di-tert-butylphenol、Phenol,2,2'-methylenebis[6-(1,1-dimethylethyl)-4-methyl-、1,4-Benzenedicarboxylic acid,bis(2-ethylhexyl)ester、Pentadecane、Tetradecane、1-Decanol,2-hexyl-、Heneicosane、Heptadecane、Hexadecane、5,5-Dibutylnonane、Undecane,5-methyl-、2,4-Dimethyldodecane、2,6,10-Trimethyltridecane、Undecane,4-ethyl-、Tetradecane,4-methyl-、Silane,cyclohexyldimethoxymethyl-、Cyclohexasiloxane,dodecamethyl-、Cyclotetrasiloxane,octamethyl-、Decane,1-iodo-、Sulfurous acid,2-pentyltetradecyl ester.

[0015] Furthermore, the method for detecting the metabolite level includes any one or more of the following: gas chromatography-mass spectrometry, mass spectrometry, nuclear magnetic resonance spectroscopy, liquid chromatography-mass spectrometry, capillary electrophoresis-mass spectrometry, surface-enhanced Raman spectroscopy, matrix-assisted laser desorption / ionization mass spectrometry, quantitative mass spectrometry imaging, and surface-assisted laser desorption / ionization mass spectrometry.

[0016] Furthermore, the method for detecting the metabolite level is gas chromatography-mass spectrometry.

[0017] The microorganisms include bacteria, fungi, and archaea.

[0018] Furthermore, the bacteria include Acidobacteria, Actinobacteria, Agrobacterium, Alphaproteobacteria, Arthrobacter, Bacillus, Bacteroidetes, Betaproteobacteria, Blastocatellia, Bradyrhizobium, Brevibaelerium, Burkholderiales, Chloroflexi, Chryseolinea, Comamonadaceae, Corallococcus, Cyanobacteria, Cyrophaga, Cytophagia, Deltaproteobacteria, Desulfovibro, Eubaererium, Firmicutes, Fulvivirirgaceae, Gemmatimonas, Gemmationadetes, Geothrix, Halomonas, Helicobacter spp, Kallotenuaceae, Luteitalea, Lysobacter, Mesobacillus, Neisseria, Nitrososphaera, Nocardioides, Ohtaaekwangia, Paracoccus, Planctomycetes, Polyangium, Pseudomonas, Ramlibacter, Rhodopseudomonas, Roseiflexus, Salmonella, Serratia, Sorangium, Spirillum, Streptococcus, Thermoanaerobaculia, Thiobacillus, Thiophaera, Verrucomicrobia, Vibrio, Vulcaniibacterium, Xanthomomadales.

[0019] Further, the fungi include Spizellomyces, Fusarium, Pseudogymnoascus, Cadophora, Mucor, Sclerotinia sclerotiorum, Gigaspora, Zopfia, Penicillium, Sphaerobolus, Colletotrichum, Talaromyces, Ascomycota, Mucoromycota, Chytridiomycota, Basidiomycota, Zoopagomycota, Microsporidia, Cryptomycota, Blastocladiomycota.

[0020] Furthermore, the archaea include Thaumarchaeota, Euryarchaeota, Woesearchaeota, Crenarchaeota, and Nanoarchaeota.

[0021] Furthermore, the methods for detecting microbial abundance include any one or more of metagenomic sequencing, 16S-rRNA sequencing, ITS sequencing, qRT-PCR, DNA blotting, and in situ hybridization.

[0022] Furthermore, the method for detecting the abundance of microorganisms is metagenomic sequencing.

[0023] The construction of the evaluation model refers to the use of machine learning to construct an evaluation model based on the metabolite levels and / or the microbial abundance.

[0024] Furthermore, the construction of the evaluation model refers to using machine learning to construct an evaluation model based on the abundance of the following microorganisms: Acidibacter, Funneliformis, Rhizophagus, Setophoma, Chloroflexi, Actinobacteriota, Firmicutes, and Proteobacteria.

[0025] Furthermore, the machine learning includes convolutional neural networks, autoencoders, deep belief networks, linear regression, logistic regression, Lasso regression, Ridge regression, linear discriminant analysis, K-nearest neighbors algorithm, decision trees, perceptrons, support vector machines, ensemble learning, correlation analysis, Naive Bayes, AdaBoost, GBDT, XGBoost, LightGBM, CatBoost, or random forests.

[0026] Furthermore, the machine learning method is random forest.

[0027] The samples to be tested include soil samples.

[0028] Furthermore, the samples to be tested include surface soil samples, profile generation layer samples, and water-stable large aggregate samples.

[0029] Furthermore, the sample to be tested is a surface soil sample.

[0030] Furthermore, the sample to be tested is a surface soil sample from the plant rhizosphere.

[0031] Furthermore, the sample to be tested is a root zone surface soil sample from a rocky desertification area.

[0032] A third aspect of the present invention provides a method for screening candidate substances that enhance the nitrogen uptake capacity of plant rhizospheres, the steps of which are as follows:

[0033] Plant roots were treated with the substance to be screened, and the above-mentioned test samples were obtained.

[0034] The levels of metabolites described in the first aspect of the present invention and / or the abundance of microorganisms described in the first aspect of the present invention are detected in the sample to be tested.

[0035] When the substance to be screened alters the metabolite levels and microbial abundance in the sample to be tested, and one or more levels of metabolite group 1) described in the first aspect of the present invention are higher than the reference value, one or more levels of metabolite group 2) described in the first aspect of the present invention are lower than the reference value, one or more abundances of microbiome 3) described in the first aspect of the present invention are higher than the reference value, and / or one or more abundances of microorganism 4) described in the first aspect of the present invention are lower than the reference value, then the substance to be screened is a candidate substance for enhancing the nitrogen uptake capacity of plant rhizosphere.

[0036] When the substance to be screened does not change the metabolite level and microbial abundance in the sample or changes in the opposite direction, the substance to be screened is not a candidate substance for enhancing the rhizosphere nitrogen uptake capacity of plants.

[0037] A fourth aspect of the present invention provides a computer system for evaluating the nitrogen uptake capacity of plants, the system comprising:

[0038] The data acquisition module acquires data on the metabolite levels and / or microbial abundance described in the second aspect of the present invention in the sample to be tested.

[0039] The data processing module inputs the data into an evaluation model constructed based on the method for constructing an evaluation model according to the second aspect of the present invention. The evaluation model evaluates the nitrogen absorption capacity of plants based on the acquired data.

[0040] Output module, output results.

[0041] The fifth aspect of the present invention provides a computer device for evaluating the nitrogen uptake capacity of plants, the computer device comprising:

[0042] A processor adapted to implement instructions; and a memory adapted to store multiple instructions, said instructions adapted to be loaded by the processor and executed in accordance with the following steps:

[0043] Acquire data, specifically the levels of metabolites and / or the abundance of microorganisms as described in the second aspect of this invention in the sample to be tested.

[0044] The data is processed and input into an evaluation model constructed based on the method for constructing an evaluation model according to the second aspect of the present invention. The evaluation model evaluates the nitrogen uptake capacity of plants based on the acquired data.

[0045] Output results.

[0046] A sixth aspect of the present invention provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor and performing the following steps:

[0047] Acquire data, specifically the levels of metabolites and / or the abundance of microorganisms as described in the second aspect of this invention in the sample to be tested.

[0048] The data is processed and input into an evaluation model constructed based on the method for constructing an evaluation model according to the second aspect of the present invention. The evaluation model evaluates the nitrogen uptake capacity of plants based on the acquired data.

[0049] Output results.

[0050] Advantages and beneficial effects of the present invention:

[0051] This invention provides a computer-based method for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics. This method effectively distinguishes the nitrogen uptake capacity of plant roots, facilitating targeted ecological restoration and management. It aims to better promote plant nutrient absorption and utilization, explore solutions to rocky desertification, and provide insights into addressing severe soil erosion, ecological imbalance, and low vegetation cover in rocky desertification areas. Attached Figure Description

[0052] Figure 1 This is a schematic flowchart of a computer-implemented method for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics, as provided in the first aspect of the present invention.

[0053] Figure 2 A schematic flowchart of a computer-implemented method for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics, provided by the second aspect of the present invention.

[0054] Figure 3 A schematic flowchart of a method for screening candidate substances that enhance the nitrogen uptake capacity of plant rhizospheres, provided by a third aspect of the present invention.

[0055] Figure 4 This is a schematic diagram of the structure of a computer system for evaluating the nitrogen uptake capacity of plants based on rhizosphere soil environmental characteristics;

[0056] Figure 5 This is a schematic diagram of the structure of a computer device for evaluating the nitrogen uptake capacity of plants based on rhizosphere soil environmental characteristics;

[0057] Figure 6 This is a graph comparing the metabolite content of the control group (CK) with that of the fungal inoculation groups (Fm and Ri). Figure 6 In the figure, A represents a comparison of metabolite content in soil at different depths after inoculation with CK and Fm and Ri (volcano plot). Figure 6 B in the diagram represents the expression of differentially metabolites (VIPs).

[0058] Figure 7 This is a graph showing the alpha diversity analysis between the control group (CK) and the groups inoculated with fungi (Fm and Ri). Figure 7 A in the graph represents the Chao index. Figure 7 B in the graph represents the Shannon index.

[0059] Figure 8 This is a diagram showing the differentially expressed microorganisms between the control group (CK) and the groups inoculated with fungi (Fm and Ri). Figure 8 In the diagram, A represents the Venn diagram of the bacterial and fungal communities in the mulberry root system. Figure 8 B in the figure represents the difference analysis of sample and species composition and Kruskal-Wallis test.

[0060] Figure 9 The ML phylogenetic tree is shown for the control group CK and the groups inoculated with fungi Fm and Ri.

[0061] Figure 10 This is a KEGG enrichment analysis diagram of differentially expressed metabolites between the control group (CK) and the groups inoculated with fungi (Fm and Ri).

[0062] Figure 11 A network diagram showing the correlation between differentially identified metabolites and environmental factors between the control group (CK) and the groups inoculated with fungi (Fm and Ri).

[0063] Figure 12 The left side shows the LDA SCORE, and the right side shows the LDA SCORE, with the control group (CK) and the groups inoculated with fungi (Fm) and Ri as the LDA SCORE.

[0064] Figure 13The diagram shows the interaction network analysis within the bacterial and fungal kingdoms. The bar chart represents the interaction types of the top 10 nodes with the highest connectivity. The scatter plot shows the connectivity of bacterial, fungal, and archaea groups in the CK and AMF networks. Figure 14 This is a random forest prediction plot showing the differences in bacterial and fungal species between the control group (CK) and the inoculated fungal groups (Fm and Ri). Detailed Implementation

[0065] The present invention will now be described in further detail with reference to specific embodiments. The given embodiments are merely illustrative of the invention and not intended to limit its scope. In some processes described in the specification, claims, and accompanying drawings of the present invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein or may be executed in parallel. Operation numbers such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the terms "first," "second," etc., used herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0066] Arbuscular mycorrhiza (AM) fungi can form mycorrhizal symbionts with over two-thirds of plants on Earth. Their abundant mycelium broadens the nutrient absorption range of plant roots, helping plants absorb more mineral nutrients such as nitrogen and phosphorus from the soil. These nutrients are then converted into efficiently transportable amino acids through a series of processes, while simultaneously inducing the efficient expression of nutrient transport proteins, thus improving nutrient transport efficiency. Mulberry is the most typical species among plants capable of forming symbionts with arbuscular mycorrhizae. It possesses a strong adaptability to harsh environments and has been widely used in the ecological restoration of rocky desertification in southwestern my country, achieving good results. This invention uses Funneliformis mosseae (Fm) and Rhizophagus intraradices (Ri), dominant fungal species previously identified in the rhizosphere of mulberry trees in rocky desertification areas, as inoculants. The biomass, root nitrogen content, and changes in rhizosphere soil microorganisms and metabolites of mulberry seedlings after inoculation in rocky desertification soils are analyzed. A model is constructed based on these characteristics to evaluate the nitrogen uptake capacity of plant roots, providing a theoretical basis for controlling rocky desertification.

[0067] Figure 1 The present invention provides a schematic flowchart of a method according to the first aspect of the invention. The method steps are as follows: acquiring data on metabolite levels and / or microbial abundance in the sample to be tested, and comparing them with reference values. Specifically, the method includes the following:

[0068] 101 Data Acquisition: Acquire data on metabolite levels and microbial abundance in the samples to be tested;

[0069] The metabolite group 1) includes Decanoic acid, 3-Iodopropanoic acid, Pentadecanoic acid, Methylcobalamin, Dipentyl phthalate, Geranylgeranylcysteine, Cycloheptasiloxane, tetradecamethyl-, Hexadecane, 2,6,11,15-tetramethyl-.

[0070] The metabolite group 2) includes meso-Pristane, L-Histidinol, Dimethicone, Dodecanal, and 1-(5-Acetyl-2hydroxyphenyl)-3-methyl-1-butanone.

[0071] The methods for detecting metabolite levels include any one or more of the following: gas chromatography-mass spectrometry, mass spectrometry, nuclear magnetic resonance spectroscopy, liquid chromatography-mass spectrometry, capillary electrophoresis-mass spectrometry, surface-enhanced Raman spectroscopy, matrix-assisted laser desorption / ionization mass spectrometry, quantitative mass spectrometry imaging, and surface-assisted laser desorption / ionization mass spectrometry.

[0072] In a specific embodiment of the present invention, the method for detecting the metabolite level is gas chromatography-mass spectrometry, and the specific steps are as follows:

[0073] Weigh 4g of fresh soil sample into a 50mL centrifuge tube, add 20mL of extraction solution (methanol:ethyl acetate = 1:1), vortex until homogeneous, centrifuge at 8000r / min for 10min, collect the supernatant, concentrate the supernatant to about 2mL using a water bath nitrogen blower and rotary evaporator, filter the concentrated liquid through a 0.45μm filter membrane into an Agilent bottle, and place the extracted sample in a -20℃ freezer for testing.

[0074] Analytical Testing: The sample was placed in a gas chromatograph-mass spectrometer (GC-MS) equipped with an RTX-5MS column. The injection temperature was maintained at 250°C, and the oven temperature program was set as follows: start at 80°C and hold for 5 minutes, increase to 200°C at a rate of 15°C / min and hold for 5 minutes, then increase to 250°C at a rate of 8°C / min and hold for 8 minutes. The detector voltage was set to 0.93 kV, and the EI ionization voltage of the metabolite was 70 eV.

[0075] The microbiome 3) includes Bacteroidetes, Actinobacteria, Acidobacteria, Chryseolinea, Ohtaekwangia, Planctomycetes, Rhizophagus, Euryarchaeota, and Nitrosocosmicus.

[0076] The microbiome 4) includes Chloroflexi, Gemmatimonadetes, Ramlibacter, Penicillium, Zopfia, Aspergillus, Crenarchaeota, and Thaumarchaoota.

[0077] In the context of this invention, the term "abundance" refers to the quantity or trend of a specific species of microorganism active and reproducing in a system within a specific environment. It is an important indicator for measuring the structure, diversity, and ecological function of a microbial community. Generally, microorganisms constitute a dynamic biological community within their sphere of influence, which can be used to record and analyze abundance data.

[0078] The methods for detecting microbial abundance include any one or more of metagenomic sequencing, 16S-rRNA sequencing, ITS sequencing, qRT-PCR, DNA blotting, and in situ hybridization.

[0079] Metagenomic sequencing involves high-throughput sequencing of all microbial DNA in a sample. After sequence processing and analysis, it can identify the species structure, evolutionary relationships, and even the functional activity of the microbial community, explore molecular mechanisms such as pathogenicity or drug resistance, and uncover molecular pathways of research value. The metagenomic sequencing and analysis workflow includes sample collection, DNA extraction, library construction and sequencing, sequence assembly, binning, abundance and differential analysis, and personalized advanced analysis.

[0080] The Illumina platform refers to the sequencing chemistry technology employed by Illumina Corporation using next-generation sequencing (NGS) with clonal amplification and sequencing-by-synthesis (SBS). This process identifies DNA bases as they are integrated into the nucleic acid strand. Each base emits a unique fluorescent signal as it is added to the extending strand, which can be used to determine the sequence order of the DNA. Illumina sequencing technology is a high-throughput sequencing technology widely used in genomics, transcriptomics, and epigenomics research. Its principle is based on DNA synthesis and fluorescence imaging techniques, enabling the rapid and accurate sequencing of large numbers of DNA fragments.

[0081] In a specific embodiment of the present invention, the method for detecting microbial abundance is metagenomic sequencing, and the specific steps are as follows:

[0082] use Total genomic DNA was extracted from soil using the Soil DNA Kit (Omega Bio-Tek, USA) according to the kit's instructions. DNA purity and concentration were assessed using a NanoDrop 2000, and DNA integrity was checked using 1% agarose gel electrophoresis (5V / cm, 20min). The DNA was then fragmented into approximately 400bp fragments using a Covaris M220 ultrasonic disruptor for subsequent analysis. Libraries were constructed using the NEXTFLEX Rapid DNA-Seq Kit, and finally, metagenomic sequencing of the samples was performed using the Illumina NovaSeq sequencing platform (Shanghai Meiji Biomedical Technology Co., Ltd.).

[0083] The PE reads obtained from Illumina sequencing were first assembled based on overlap relationships. Simultaneously, sequence quality was controlled and filtered. The original sequences were flattened using the minimum sample sequence count. The dilution curves show that the curves flatten towards the ends, indicating a reasonable amount of sequencing data. The optimized number of fungal sequences was 1,952,752, and the number of bacterial sequences was 1,795,948.

[0084] In the context of this invention, the term "sample" refers to a composition obtained from or derived from a target of interest, comprising molecular entities to be characterized and / or identified based on, for example, physical, biochemical, chemical, and / or physiological characteristics. Samples include, but are not limited to, surface soil samples from different regions, profile generation layer samples, and water-stable macroaggregate samples. Preferably, the sample is a surface soil sample from the plant rhizosphere.

[0085] In a specific embodiment of the present invention, the soil sample to be tested was taken from the top 0-20cm of the unplanted mulberry garden (N, 106°39'E, 26°30', altitude 1116m) of the Sericulture Research Institute of the Guizhou Academy of Agricultural Sciences, located in Huaxi District, Guiyang City, Guizhou Province. The soil type was limestone soil. Plant root debris and stones were removed, air-dried, mixed, and then passed through a 5mm nylon mesh sieve. The samples were then sterilized by 10kGy cobalt-60 radiation.

[0086] The tested arbuscular mycorrhizal (AM) fungi, *Funneliformis mosseae* (Fm, BGC HUN03B) and *Rhizophagus intraradices* (Ri, BGC HEB07D), were both purchased from the Bank of Glomales in China (BGC), Institute of Plant Nutrition and Resources, Beijing Academy of Agricultural and Forestry Sciences. The purchased strains were propagated on river sand and vermiculite substrates using *Zea mays* and *Trifolium repens*. The spore counts for *Fm* were 6.4 spores / g soil, and for *Ri*, 80.7 spores / g soil.

[0087] Test seeds: The mulberry seed variety used in the experiment was Sangtuo No. 2. Before the formal experiment, the seeds were disinfected to ensure no interference from external microorganisms during the experiment. Specifically, they were soaked in 0.5% NaClO for 20 minutes. After that, the seeds were rinsed with pure water and sown in sterilized substrate. They were cultivated in the greenhouse of the Sericulture Research Institute of Guizhou Academy of Agricultural Sciences. During the cultivation period, sterile water was sprayed regularly to keep the substrate moist. After 40 days, the sterile mulberry seedlings were transplanted into sterilized rocky desertification soil.

[0088] The experiment was conducted from May to August 2022 in the Plant Growth Laboratory of the Sericulture Research Institute, Guizhou Academy of Agricultural Sciences. Three treatments were set up: an uninoculated control (CK) and two single-inoculation treatments (Fm and Ri treatments), with each treatment replicated four times. Sterilized soil was placed into root boxes measuring 24 cm long, 9.5 cm wide, and 34.5 cm high, with each box containing 6.6 kg of soil (4 cm from the top). The inoculated treatments were inoculated with 0.7 kg of inoculum, while the uninoculated CK was inoculated with 0.7 kg of sterilized inoculum (a mixture of two AM fungi in equal volumes) and 100 mL of AM fungal inoculum filtrate to ensure a consistent soil microbiota. One sterile mulberry seedling was planted in each box. During the mulberry growth period, the room temperature was maintained at 24-26℃, and LED plant growth lights were used for supplemental lighting 12 h / d. To ensure that the water content of the mulberry trees remained at approximately 70% of their field capacity during the experiment, water was added periodically by weighing.

[0089] After the experiment, rhizosphere soil was collected at different depths of 0-10cm, 10-20cm, and 20-30cm and stored at -80℃ before extracting metabolites. The remaining soil samples were completely dried and then ground and sieved to prepare soil samples for determining the soil's physicochemical properties.

[0090] 102 Data Comparison: Compare the reference values ​​with the metabolite levels and microbial abundance data in the test samples;

[0091] The comparison refers to the following: if one or more levels of metabolite group 1) in 101 are higher than the reference value, one or more levels of metabolite group 2) are lower than the reference value, one or more abundances of microbiome 3) are higher than the reference value, and / or one or more abundances of microorganism 4) are lower than the reference value, then the evaluation result of the plant nitrogen absorption capacity represented by the test sample is good; if one or more levels of metabolite group 1) are lower than the reference value, one or more levels of metabolite group 2) are higher than the reference value, one or more abundances of microbiome 3) are lower than the reference value, and / or one or more abundances of microbiome 4) are higher than the reference value, then the evaluation result of the plant nitrogen absorption capacity represented by the test sample is poor.

[0092] In this invention, the term "reference value" refers to a value that is statistically relevant to a particular result when compared with the analytical result. In a preferred embodiment, the reference value is determined based on the statistical conclusions of studies comparing untreated samples with AM fungus-treated samples. Some such studies are shown in the Examples section of this document, but studies from the literature and the experience of users of the methods described herein can also be used to generate or adjust reference values. Reference values ​​can also be determined by taking into account local soil composition, weather conditions, plant varieties, and other relevant factors.

[0093] In this invention, metabolites and microorganisms can exist differentially at any level, but generally exist at levels of difference that are increased by at least 5%, at least 10%, at least 15%, at least 20%, at least 25%, at least 30%, at least 35%, at least 40%, at least 45%, at least 50%, at least 55%, at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, at least 100%, at least 110%, at least 120%, at least 130%, and at least 140%, at least 150%, or more; or generally present at levels reduced by at least 5%, at least 10%, at least 15%, at least 20%, at least 25%, at least 30%, at least 35%, at least 40%, at least 45%, at least 50%, at least 55%, at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, or 100% (i.e., absent), preferably, the metabolite levels and microbial abundance have statistically significant differences (P < 0.05).

[0094] This can be seen from the difference volcano map (e.g.) Figure 6 As shown in Figure A), significant differences were detected in the content of various metabolites in the soil (P<0.05, Vip>1, as shown in Figure A). Figure 6As shown in B in the figure, the upregulated metabolites were significantly more numerous than the downregulated metabolites. Based on the combined metabolite data from the three soil layers, 52 differentially regulated metabolites were finally identified. These included 18 organic acids and their secretions (significantly more upregulated than downregulated); 13 lipids and lipid molecules (significantly more upregulated than downregulated); 3 organic nitrogen compounds (upregulated); 1 alkaloid and its derivative (upregulated); 1 flavonoid compound (upregulated); 4 organic heterocyclic compounds (upregulated); 4 benzene compounds (significantly more downregulated than upregulated); 5 organic oxygen compounds (downregulated); and 3 alkanes.

[0095] Alpha diversity analysis is a method in community ecology used to measure microbial diversity and richness within a single sample. It is typically used to describe species richness and evenness within a specific area and is crucial for protecting biodiversity and ecosystem health. The Chao index and Shannon index are indicators used to assess community diversity: The Chao index estimates the number of species in a community using the Chao1 algorithm and is often used to estimate the total number of species. The Shannon index, based on information entropy, represents the uncertainty of the community; a higher index indicates higher diversity.

[0096] In a specific embodiment of the present invention, at the phylum taxonomic level, significant changes occurred in the alpha diversity of bacterial and fungal communities in different profiles after AMF inoculation, as shown in the following results. Figure 7 As shown in the diagram, according to the Chao index, inoculation with Fm and Ri increased the diversity of bacterial communities in plant roots at different profiles, increased the diversity of fungal communities at 0-10 cm, but decreased the diversity of fungal communities at 10-20 cm and 20-30 cm. According to the Shannon index diagram, inoculation with Fm and Ri increased the diversity of bacterial and archaea communities, but decreased the diversity of fungal communities.

[0097] Venn diagrams are used to illustrate mathematical or logical relationships between different groups (sets) of things. In bioinformatics analysis, they are one of the statistical graphs commonly used to show the quantity (or proportion) of common (or unique) elements among samples (or groups).

[0098] In a specific embodiment of the present invention, the species composition of root bacterial and fungal communities changed in three different cross-sections after AMF inoculation, such as... Figure 8As shown in Figure A, inoculation with Fm and Ri significantly increased the number of bacterial community-specific species in the 0-10 cm root system and decreased the number of bacterial community-specific species in the 20-30 cm root system. Inoculation with Fm decreased the number of specific bacterial species in the 10-20 cm root system but increased the number of specific bacterial species in the 10-20 cm root system inoculated with Ri. Inoculation with Fm and Ri decreased the number of fungal community-specific species in the 0-10 cm and 20-30 cm root systems. Inoculation with Fm decreased the number of specific fungal species in the 10-20 cm root system but increased the number of specific fungal species in the 10-20 cm root system inoculated with Ri.

[0099] Circos diagrams visualize abundance tables, using the width of the lines to represent the magnitude of abundance values. They can be used to elegantly display complex biological data and represent virtually any type of data, such as showing the proportion of each gene (top 10 most abundant) in each sample, and the proportion of each gene in each sample. They can visually display the gene / species abundance of different samples, and are particularly suitable for genomic maps. The Kruskal-Wallis test is a statistical test used to compare groups of two or more continuous or discrete variables. It is a non-parametric test that does not assume a specific distribution of data and is similar to one-way ANOVA.

[0100] In a specific embodiment of the present invention, Circos analysis was used to display the community composition at the bacterial, fungal, and archaea levels for each treatment (where bacterial communities showed phyla with relative abundance >1%, and fungal communities showed phyla with relative abundance >0.1%). The Kruskal-Wallis multivariate algorithm was used to statistically analyze the bacterial and fungal genera showing significant differences between treatment groups, and the differences in each genera were displayed using bar charts. The results are as follows: Figure 8As shown in B in the figure. Analysis of the phylum-level distribution differences of bacteria in mulberry root systems showed that the most abundant bacteria in the rhizosphere of CK, Fm, and Ri plants were all Proteobacteria, accounting for 43%-81%. Using the Kruskal-Walis test to differentiate the bacterial communities between CK and AMF plant roots, inoculation significantly reduced the abundance of *Cellvibrio* and *Flavobacterium* by 21%-84%, significantly increased the abundance of *Allorhhizobium*, and significantly increased the abundance of *Bacillus* by 27%. Analysis of the phylum-level distribution differences of fungi in mulberry rhizosphere soil showed that the most abundant fungi in Fm and Ri were Ascomycota, accounting for 17%-79%, while the most abundant fungi in CK were Mucoromycota, accounting for 39%-61%. The Kruskal Wallis test was used to examine the differences in fungal communities between CK and AMF plant roots. Inoculation significantly increased the abundance of fungi Rhizophagus and Ascobolus, and significantly decreased the abundance of Rhizoctonia and Mortierella.

[0101] Phylogenetic tree: Also known as a phylogenetic tree or evolutionary tree, it uses a tree-like branching diagram to represent the kinship between species or genes. The process of constructing an evolutionary tree is called phylogenetic analysis, a method used to study the evolution of species or sequences and systematic classification. Mathematical statistical algorithms are used to calculate the evolutionary relationships between organisms. Finally, the calculation results are visualized as a phylogenetic tree. Common methods for constructing evolutionary trees include Neighbor-Joining (NJ), ML (Maximum Likelihood), and MP (Maximum Parsimony). NJ (Neighbor-Joining) is also known as the adjacency method, ML (Maximum Likelihood) is also known as the maximum likelihood method, and MP (Maximum Parsimony) is also known as the maximum parsimony method.

[0102] In a specific embodiment of the present invention, phylogenetic trees were constructed using ML (Maximum Likelihood) for the top 50 species in terms of horizontal abundance of bacteria and fungi. The results are as follows: Figure 9 As shown, the top 50 most abundant species mainly belong to the phylum Proteobacteria, and most denitrifying bacteria belong to this phylum, playing a dominant role in denitrification. The top 50 most abundant fungi mainly belong to the phylum Ascomycota.

[0103] 103 Output Results: Output the evaluation results.

[0104] Figure 2 The flowchart illustrates a computer-implemented method for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics, as provided in the second aspect of this invention. The method includes the following steps: acquiring data on metabolite levels and / or microbial abundance in the sample to be tested; evaluating plant nitrogen uptake capacity based on a pre-constructed evaluation model. Specifically, the method includes the following:

[0105] 201 Data Acquisition: Acquire data on metabolite levels and microbial abundance in the samples to be tested;

[0106] The metabolites include one or more of the following: L-serine, 2,4,6-Trihydroxybenzoic acid, 4-Ethylbenzoic acid, Serylserine, Monoisobutyl phthalic acid, Stearyl citrate, Monoethylhexyl phthalic acid, Diisobutyl phthalate, Tetradecanedioic acid, Decanoic acid, Acetic acid, Amyl salicylate, 3-Iodopropanoic acid, A-Ketoglutaricacid oxime, Iodotyrosine, Hydroxypyruvic acid, Methylcobalamin, 3,5-Diiodothyronine, Dipentyl phthalate, Dimethylmalonic acid, Methyl 3-methylbutanoate, Ferulic acid, alpha-Hydroxyisobutyric acid, Isopropylhexadecanoate, (E)-6-Methyl-6-(5-methyl-2-furanyl)-3-hepten-2-one, 1,1-Dimethylethyl heptanoic acid, 1-Decanol, 1-Hexadecanol, 1-Octadecanol, 2-Hydroxyhexadecanoic acid, Diethyl succinate, Ganolucidic acid D, Geranylgeranylcysteine, Ethene, Heptaethylene glycol, L-Histidinol, Octadecyloctyl ether, Pentadecane,2,6,10,14-tetramethyl-, Pentadecanoic acid, Squalene, 1H-Tetrazol-5-amine, 3,5-Dimethyl-1,2,4-trithiolane, Quercitrin, 2,6-Di-tert-butyl-4-hydroxymethylphenol, Benzaldehyde,2,4-dimethyl-、Cinnamyl benzoate、cis-3-Hexenyl pentanoate、Dimethicone、2,4-Dihydroxybenzaldehyde、N-Acetylglucosamine 6-sulfate、Dihydroxyacetone phosphate、2-(3,4-dimethoxyphenyl)-3-hydroxychromen-4-one、3,5,5-Trimethyl-2-cyclohexen-1-one、Dodecanal、Ethanolamine、4-Ethyl-2-octylthiazole、N,N-Dimethylphenethylamine、Kaempferol、Morphine、Dibutyl phthalate、Isopropyl myristate、Methyl stearate、Benzocyclodecene,tetradecahydro-、Benzeneethanamine,N-(2-phenylethyl)-、Phthalic acid,di(2-propylpentyl)ester、Hexadecanoic acid,methyl ester、Benzenepropanoic acid,3,5-bis(1,1-dimethylethyl)-4-hydroxy-,methyl ester、2,4-Di-tert-butylphenol、Phenol,2,2'-methylenebis[6-(1,1-dimethylethyl)-4-methyl-、1,4-Benzenedicarboxylic acid,bis(2-ethylhexyl)ester、Pentadecane、Tetradecane、1-Decanol,2-hexyl-、Heneicosane、Heptadecane、Hexadecane、5,5-Dibutylnonane、Undecane,5-methyl-、2,4-Dimethyldodecane、2,6,10-Trimethyltridecane、Undecane,4-ethyl-、Tetradecane,4-methyl-、Silane,cyclohexyldimethoxymethyl-、Cyclohexasiloxane,dodecamethyl-、Cyclotetrasiloxane,octamethyl-、Decane,1-iodo-、Sulfurous acid,2-pentyl tetradecyl ester。,

[0107] The microorganisms include one or more of the following: Acidobacteria, Actinobacteria, Agrobacterium, Alphaproteobacteria, Arthrobacter, Bacillus, Bacteroidetes, Betaproteobacteria, Blastocatellia, Bradyrhizobium, Brevibaelerium, Burkholderiales, Chloroflexi, Chryseolinea, Comamonadaceae, Corallococcus, Cyanobacteria, Cyrophaga, Cytophagia, Deltaproteobacteria, Desulfovibro, Eubaererium, Firmicutes, Fulvivirirgaceae, Gemmatimonas, Gemmationadetes, Geothrix, Halomonas, Helicobacter spp, Kallotenuaceae, Luteitalea, Lysobacter, Mesobacillus, Neisseria, Nitrososphaera, Nocardioides, Ohtaaekwangia, Paracoccus, Planctomycetes, Polyangium, Pseudomonas, Ramlibacter, Rhodopseudomonas, Roseiflexus, Salmonella, Serratia, Sorangium, Spirillum, Streptococcus, Thermoanaerobaculia, Thiobacillus, Thiophaera, Verrucomicrobia, Vibrio, Vulcaniibacterium, Xanthomomadales, Spizellomyces, Fusarium, Pseudogymnoascus, Cadophora, Mucor, Sclerotiniasclerotiorum, Gigaspora, Zopfia, Penicillium, Sphaerobolus, Colletotrichum, Talaromyces, Ascomycota, Mucoromycota, Chytridiomycota, Basidiomycot a.Zoopagomycota, Microsporidia, Cryptomycota, Blastocladiomycota, Thaumarchaeota, Euryarchaeota, Woesearchaeota, Crenarchaeota, Nanoarchaeota.

[0108] 202 Data Processing: Process metabolite levels and microbial abundance data according to the evaluation model;

[0109] The method for constructing the evaluation model refers to using machine learning to construct the evaluation model based on the aforementioned metabolite levels and / or microbial abundance.

[0110] The machine learning methods include convolutional neural networks, autoencoders, deep belief networks, linear regression, logistic regression, Lasso regression, Ridge regression, linear discriminant analysis, K-nearest neighbors, decision trees, perceptrons, support vector machines, ensemble learning, correlation analysis, enrichment analysis, Naive Bayes, AdaBoost, GBDT, XGBoost, LightGBM, CatBoost, or random forests.

[0111] In a specific embodiment of the present invention, constructing the evaluation model includes the following steps:

[0112] univariate analysis was performed using SPSS, and a LSD multiple comparison test was conducted at the 5% level to determine the significant differences in various soil physicochemical properties under different treatments. Excel 2012 and Origin 2019 were used to create charts and graphs. Machine learning random forest was employed to predict the contribution of soil physicochemical properties to changes in soil nitrogen speciation.

[0113] Metabolite data for each sample were exported in CSV format. Using component area as the relative content, the data for each sample were organized. Venn, PCA, and OPLA-LS plots were used in Origin 2021 to test the significance of metabolite differences between different treatments and the reliability of the fitted data model. FoldChange and P-value were calculated to screen for differentially expressed metabolites. Generally, FoldChange > 2, P-value < 0.05, and Vip > 1 were considered differentially expressed metabolites. Cluster analysis and KEGG enrichment analysis were performed on the screened differentially expressed metabolites using MetaboAnalyst 5.0. Finally, correlation analysis between environmental factors and differentially expressed metabolites was performed using R's "ggplot" function, and a correlation network diagram was drawn using Cytoscape.

[0114] The original microbial sequences detected were quality-cut using the software fastp (https: / / github.com / OpenGene / fastp, version 0.20.0). The optimized sequences obtained after cutting were then assembled using the software MEGAHIT (https: / / github.com / voutcn / megahit, version 1.1.2). Genes with nucleic acid lengths ≥100 bp in the assembled results were translated into amino acid sequences using MetaGene (http: / / metagene.cb.ku-tokyo.ac.jp / ). The obtained amino acid sequences were aligned with the NR database using Diamond (http: / / www.diamondsearch.org / index.php, version 0.8.35), and species annotations were obtained from the corresponding taxonomic information databases in the NR database. Subsequently, the abundance of a species was calculated by combining the gene abundance with the abundance of the corresponding gene. Simultaneously, the obtained amino acid sequences were matched with the KEGG database to read the KEGG functions of each gene. The abundance of each function was then calculated by combining the abundance of genes corresponding to KO, Pathway, EC, and Module from different perspectives. The R language "ggplot" was used to create sample clustering heatmaps of soil carbon and nitrogen metabolism pathways, nitrogen cycle-related microorganisms, and functional genes. The R language "linkET" was used to perform Mantel-test analysis and plot the relationships between nitrogen cycle-related microorganisms and functional genes screened from the soil and environmental factors. Structural equation models were constructed using IBM SPSS Amos 28 for AM fungi-mulberry growth-soil metabolites and microorganisms-soil nitrogen form-mulberry root nitrogen content.

[0115] Enrichment analysis is a data analysis method primarily used to understand the degree of enrichment of gene sets or other biological entities in specific experimental conditions or biological contexts regarding their functions, pathways, or specific biological processes. Its basic principle is that if a gene set is significantly enriched in a certain functional category or pathway under specific conditions, then these genes may collectively participate in a specific biological process or possess some common functional characteristics. The KEGG enrichment analysis used in this invention refers to using the KEGG database (Kyoto Encyclopedia of Genes and Genomes) to annotate all identified metabolites along pathways and analyze the major metabolic and signal transduction pathways in which these metabolites participate.

[0116] In a specific embodiment of the present invention, the differentially expressed metabolites at three depths were aggregated and enriched using KEGG analysis, revealing multiple metabolic pathways, such as glycolysis / gluconeogenesis, glycophospholipid metabolism, glycine, serine, and threonine metabolism, inositol phosphate metabolism, fructose and mannose metabolism, steroid biosynthesis, tyrosine metabolism, photosynthetic carbon fixation, and fatty acid biosynthesis. Significant differences were observed in glycolysis / gluconeogenesis, glyoxylate and dicarboxylate metabolism, and glycophospholipid metabolism, as shown in the results. Figure 10 As shown.

[0117] Correlation analysis, specifically the Mantel test, examines the correlation between two matrices. In ecology, it's used to test the correlation (Spearman, Pearson) between community distance matrices (such as the Bray-Curtis distance matrix) and environmental variable distance matrices (such as difference matrices for pH, temperature, or geographical location). A higher correlation coefficient and a smaller p-value in the Mantel test indicate a greater influence of environmental factors on the microbial community. Furthermore, partial analysis of the Mantel test (such as the partial Mantel test) can eliminate interference from autocorrelation between environmental factors.

[0118] In metabolomics, the VIP value can provide ranking information on the importance of metabolites, helping to explain the contribution of metabolites to sample classification or prediction. A higher VIP value indicates that the metabolite plays a more important role in sample differences. Therefore, the VIP value can be used to identify metabolites that play a key role in sample identification or prediction, and to infer their possible biological functions and metabolic pathways.

[0119] In a specific embodiment of the present invention, a correlation network analysis was performed on the differentially identified soil metabolites and soil environmental factors after inoculation with AM fungi, and nodes with a significance level of P < 0.05 were selected to construct a network diagram. The results are as follows: Figure 11 As shown, after inoculation with AM fungi, organic acids and their derivatives react with soil TN, AK, and NO3. - -N showed a significant negative correlation. Alkaloids and their derivatives showed a significant positive correlation with TOC and with NO3. - -N and TP showed a significant negative correlation. Benzene compounds showed a significant negative correlation with DON, while lipids and lipid molecules showed a significant negative correlation with DON and NH4. + -N and T-GRSP showed a significant negative correlation, while they were significantly positively correlated with pH and TOC; organic oxides showed a significant negative correlation with AP and a significant positive correlation with pH. Morphine, as a unique alkaloid found after inoculation of Fm and Ri into topsoil, correlated with soil TN and NO3. - -N content showed a significant negative correlation with NH4+. + -N showed a positive correlation; Ethanolamine, N,N-Dimethylphenethylamine, as a unique organic nitrogen compound after deep soil inoculation with AMF, was associated with TN and NH4+. + -N and NO3 - -N showed a positive correlation; 2,6-Di-tert-butyl-4-hydroxymethylphenol, a benzene compound whose expression was significantly reduced after AMF inoculation, showed a significant negative correlation with DON. Decanoic acid, a soil-specific organic acid after AMF inoculation, showed a positive correlation with NH4+.+ -N content showed a significant positive correlation, with heptaethylene glycol, a lipid compound unique to uninoculated soil, exhibiting a similar correlation with NH4+. + -N showed a significant negative correlation, and 3-Iodopropanoic acid, an organic acid whose expression was significantly upregulated after AMF inoculation, showed a significant negative correlation with TN content and NH4+ content. + -N is positively correlated.

[0120] LEfSe (Linear Discriminant Analysis Effect Size) is an analytical tool for discovering and interpreting biomarkers (taxonomic units, pathways, genes) in high-dimensional data. It can compare two or more groups, as well as perform comparative analysis between subgroups within a group, thereby identifying species (i.e., biomarkers) that show significant differences in abundance between groups.

[0121] In a specific embodiment of the present invention, LEfSe analysis was used to search for biomarkers (LDA>3) at the phylum to genus level, and the results are as follows: Figure 12 The results are presented using cladograms. The radiating circles represent taxonomic levels from phylum to genus. Each small circle at each taxonomic level represents a taxonomic subgroup at that level, and the diameter of the small circle is proportional to its relative abundance. Species without significant differences are uniformly colored yellow. Compared to the control (CK), the AMF treatment group showed a greater number of significantly enriched bacterial species, while inoculation reduced the number of significantly enriched fungal species in the AMF treatment. Differentially enriched bacteria in AMF were found in Bacteroidetes, Proteobacteria, and Actinobacteria (Actinobacteriota); differentially enriched bacteria in CK were found in Chloroflexi and Verrucomicrobia. Differentially enriched fungi in AMF were found in Glomeromycota, while differentially enriched fungi in CK were found in Ascomycota.

[0122] Interaction network analysis is a type of enrichment analysis that primarily observes the interactions between microorganisms to identify more important microorganisms. By analyzing these interactions, results resembling microbial networks can be obtained. Tools include the STRING database and Cytoscape. Additionally, CoNet can also be used to explore interactions between microorganisms.

[0123] In a specific embodiment of the present invention, interaction network analysis was performed at the genus level on the top 50 bacteria and fungi of rhizosphere soil abundance in CK and AMF, and the results are as follows: Figure 13 As shown. Intra-domain interaction network analysis results indicate that the number of nodes in the bacterial network is higher than that in the fungal network. Furthermore, in both bacterial and fungal networks, the top 10 nodes with high connectivity in the CK and AMF treatments primarily exhibit positive correlations in their interactions with other nodes. The bacterial CK has 414 nodes with 7 negative correlations. The CK bacteria Alcaligenaceae and Bacillus have 19 connected nodes, all positively correlated. Among the top 10 nodes with high connectivity, only Pseudomonas has a negative correlation with Sphingomonadaceae. The bacterial AMF has 250 nodes with 8 negative correlations. Steroidobacter interacts with 14 nodes, all positively correlated. Polyangium interacts with 13 neighboring nodes, one of which is negatively correlated with Rhizorhapis. The fungal CK has 470 nodes with 8 negative correlations. The most important node is Chlamydocillium, which has 22 connected nodes with other fungi, all positively correlated. Its clustering coefficient was 0.56. *Phaeomycocentrospora* interacted with 21 fungi, including one negatively correlated fungus, *Apiotrichum*, with a clustering coefficient of 0.59. The fungal AMF had a total of 144 nodes, with 6 negatively correlated. *Waldomea* interacted with 8 nodes, all positively correlated. *Fusarium* had a clustering coefficient of 0.6 with its neighboring nodes, making it an important node in the AMF fungal network. It formed an interaction network with 5 neighboring fungi, all with negative correlations. Inoculation with AMF significantly reduced the number of nodes in the bacterial-fungal interaction network, and the proportion of negative correlations in the bacterial-fungal interaction network increased after AMF inoculation.

[0124] Random forest is an ensemble learning model based on the Bagging (Bootstrap Aggregating) strategy. It effectively handles non-linear problems and excels at processing large numbers of samples and features. It consists of numerous independent decision trees (ranging from dozens to hundreds), resembling a dense forest. It forms a final prediction by aggregating the predictions of all the decision trees. The final result is obtained by voting on or weighting the predictions of all the trees. Furthermore, random forests emphasize reducing variance. During training, individual learners are independent, enabling parallel training. By ensembled with multiple models, it effectively addresses overfitting, improving the model's predictive accuracy and generalization ability. This model can be applied to classification, regression, and anomaly detection tasks.

[0125] In a specific embodiment of the present invention, a random forest model is constructed based on Read Numbers abundance to predict characteristic species that can clearly distinguish CK from AMF, and the results are as follows. Figure 14 As shown in the figure, the horizontal axis represents the distribution of the relative importance (mean decreasing accuracy) of species predicted by the random forest model, and the color of the points represents the average prediction error rate through 10-fold cross-validation of the random forest model. The results show that the characteristic species playing an important role in the bacterial community differences between CK and AMF is *Acidibacter*, belonging to the phylum Acidobacteria. The characteristic species playing an important role in the fungal community differences between CK and AMF are *Funneliformis* and *Rhizophagus*, belonging to the genus *Arbuscular Mycorrhizal Fungi*, demonstrating the successful colonization of arbuscular mycorrhizal fungi in mulberry trees. Secondly, *Setophoma* (stem mold) also plays a significant role; it belongs to the family Acidobacteriaceae and is the main pathogen of garlic root rot. *Chloroflexi*, as a marker species for bacteria CK, is negatively correlated with glomerulicin, and *Actinobacteriota* is negatively correlated with *ph*, with a significant correlation (p = 0.038). *Firmicutes* is significantly positively correlated with nitrate nitrogen and AK (p < 0.05). Proteobacteria, being the most abundant bacterium, showed a significant positive correlation with nitrate nitrogen and alkaline nitrogen (p<0.05).

[0126] 203 Output: Output the evaluation results.

[0127] Figure 3 The flowchart illustrates a method for screening candidate substances that enhance rhizosphere nitrogen uptake capacity in plants, as provided in the third aspect of this invention. The method steps are as follows:

[0128] 301 Data Acquisition: Plant roots were treated with the substances to be screened to obtain test samples, and the levels of their metabolites and microorganisms were obtained. Biological abundance data;

[0129] The metabolites and microorganisms are the same as in 101.

[0130] 302 Data Classification: Classified according to whether metabolite levels and microbial abundance have changed;

[0131] When the substance to be screened alters the levels of metabolites and the abundance of microorganisms in the sample to be tested, and one or more levels of metabolite group 1) are higher than the reference value, one or more levels of metabolite group 2) are lower than the reference value, one or more abundances of microbiome group 3) are higher than the reference value, and / or one or more abundances of microorganisms 4) are lower than the reference value, then the substance to be screened is a candidate substance for enhancing the nitrogen uptake capacity of plant rhizosphere.

[0132] When the substance to be screened does not change the metabolite level and microbial abundance in the sample or changes in the opposite direction, the substance to be screened is not a candidate substance for enhancing the rhizosphere nitrogen uptake capacity of plants.

[0133] The metabolites 1) and 2) are the same as the microbiome 3) and 4).

[0134] 303 Output: Outputs the classification results of the substances to be screened.

[0135] Figure 4 This diagram shows the structure of a computer system provided by the present invention for evaluating the nitrogen uptake capacity of plants based on rhizosphere soil environmental characteristics.

[0136] The system 400 is programmed or otherwise configured to include a data acquisition module 401, a data processing module 402, and an output module 403;

[0137] Data acquisition module 401 is used to acquire data on metabolite levels and microbial abundance in the sample to be tested;

[0138] Data processing module 402 is used to input the data into a constructed evaluation model, which evaluates the plant's nitrogen uptake capacity based on the metabolite level and microbial abundance data.

[0139] Output module 403 is used to output results.

[0140] The system may be a user's electronic device or a computer system remotely located relative to that electronic device.

[0141] Figure 5 This invention presents a schematic diagram of the structure of a computer device for evaluating plant nitrogen uptake capacity based on rhizosphere soil environmental characteristics.

[0142] The computer device 500 includes a processor 501 and a memory 502 coupled to the processor 501. The memory 502 stores program instructions. When the program instructions are executed by the processor 501, the processor 501 performs any of the methods described above for evaluating the nitrogen uptake capacity of plants in rocky desertification areas using rhizosphere soil environmental characteristics. The computer device 500 may be a mobile electronic device.

[0143] The processor 501 can also be referred to as a Central Processing Unit (CPU). The processor 501 may be an integrated circuit chip with signal processing capabilities. The processor 501 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0144] The storage medium of this invention stores program instructions capable of implementing the method for evaluating plant nitrogen uptake capacity through rhizosphere soil environmental characteristics. These program instructions can be stored in the storage medium as a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or computer devices such as computers, servers, mobile phones, and tablets.

[0145] It should be understood that the systems, apparatuses, and methods described in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, apparatuses, or modules, and may be electrical, mechanical, or other forms.

[0146] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0148] The present invention has been described in detail above. Those skilled in the art will recognize that the invention can be practiced in a wide range of ways with equivalent parameters, concentrations, and conditions without departing from its spirit and scope, and without requiring unnecessary experiments. Although embodiments have been provided, it should be understood that further modifications can be made to the invention. In summary, according to the principles of the invention, this application is intended to include any changes, uses, or improvements to the invention, including changes made using conventional techniques known in the art that depart from the scope disclosed herein.

Claims

1. A computer-implemented method for evaluating plant nitrogen absorption capacity by rhizosphere soil environmental characteristics, characterized in that: The method comprises the following steps: obtaining data on metabolite levels and / or microbial abundance in a sample to be tested, and comparing the data with reference values.

2. The method according to claim 1, characterized in that: The comparison means that if one or more levels in the metabolite group 1) are higher than the reference value, one or more levels in the metabolite group 2) are lower than the reference value, one or more abundances in the microbial group 3) are higher than the reference value and / or one or more abundances in the microorganism 4) are lower than the reference value, then an evaluation result is obtained that the nitrogen absorption capacity of the plant represented by the sample to be tested is good; otherwise, an evaluation result is obtained that the nitrogen absorption capacity of the plant represented by the sample to be tested is poor; The metabolite group 1) includes Decanoic acid, 3-Iodopropanoic acid, Pentadecanoic acid, Methylcobalamin, Dipentyl phthalate, Geranylgeranylcysteine, Cycloheptasiloxane, tetradecamethyl-, Hexadecane, 2,6,11,15-tetramethyl-; The metabolite group 2) includes meso-Pristane, L-Histidinol, Dimethicone, Dodecanal, 1-(5-Acetyl-2hydroxyphenyl)-3-methyl-1-butanone; The microbial group 3) includes Bacteroidetes, Actinobacteria, Acidobacteria, Chryseolinea, Ohtaekwangia, Planctomycetes, Rhizophagus, Euryarchaeota, Nitrosocosmicus; The microbial group 4) includes Chloroflexi, Gemmatimonadetes, Ramlibacter, Penicillium, Zopfia, Aspergillus, Crenarchaeota, and Thaumarchaeota.

3. A computer-implemented method for evaluating plant nitrogen absorption capacity by rhizosphere soil environmental characteristics, characterized in that: The method comprises the following steps: obtaining data on metabolite levels and / or microbial abundance in a sample to be tested, and evaluating the nitrogen absorption capacity of a plant based on a constructed evaluation model; The constructed evaluation model obtains the result of good plant nitrogen absorption capacity or poor plant nitrogen absorption capacity according to the data of metabolite level and / or microbial abundance in the sample to be tested.

4. The method according to any one of claims 1 to 3, characterized in that: The metabolites include L-serine, 2,4,6-Trihydroxybenzoic acid, 4-Ethylbenzoic acid, Serylserine, Monoisobutylphthalic acid, Stearyl citrate, Monethylhexyl phthalic acid, Diisobutylphthalate, Tetradecanedioic acid, Decanoic acid, Acetic acid, Amyl salicylate, 3-Iodopropanoic acid, A-Ketoglutaric acid oxime, Iodotyrosine, Hydroxypyruvicacid, Methylcobalamin, 3,5-Diiodothyronine, Dipentyl phthalate, Dimethylmalonicacid, Methyl 3-methylbutanoate, Ferulic acid, alpha-Hydroxyisobutyric acid, Isopropyl hexadecanoate, (E)-6-Methyl-6-(5-methyl-2-furanyl)-3-hepten-2-one, 1,1-Dimethylethyl heptanoic acid, 1-Decanol, 1-Hexadecanol, 1-Octadecanol, 2-Hydroxyhexadecanoic acid, Diethyl succinate, Ganolucidic acid D, Geranylgeranylcysteine, Ethene, Heptaethylene glycol, L-Histidinol, Octadecyloctyl ether, Pentadecane,2,6,10,14-tetramethyl-, Pentadecanoic acid, Squalene, 1H-Tetrazol-5-amine, 3,5-Dimethyl-1,2,4-trithiolane, Quercitrin, 2,6-Di-tert-butyl-4-hydroxymethylphenol, Benzaldehyde,2,4-dimethyl-, Cinnamyl benzoate, cis-3-Hexenyl pentanoate, Dimethicone, 2,4-Dihydroxybenzaldehyde、N-Acetylglucosamine 6-sulfate、Dihydroxyacetone phosphate、2-(3,4-dimethoxyphenyl)-3-hydroxychromen-4-one、3,5,5-Trimethyl-2-cyclohexen-1-one、Dodecanal、Ethanolamine、4-Ethyl-2-octylthiazole、N,N-Dimethylphenethylamine、Kaempferol、Morphine、Dibutyl phthalate、Isopropyl myristate、Methyl stearate、Benzocyclodecene,tetradecahydro-、Benzeneethanamine,N-(2-phenylethyl)-、Phthalic acid,di(2-propylpentyl)ester、Hexadecanoic acid,methyl ester、Benzenepropanoic acid,3,5-bis(1,1-dimethylethyl)-4-hydroxy-,methyl ester、2,4-Di-tert-butylphenol、Phenol,2,2'-methylenebis[6-(1,1-dimethylethyl)-4-methyl-、1,4-Benzenedicarboxylic acid,bis(2-ethylhexyl)ester、Pentadecane、Tetradecane、1-Decanol,2-hexyl-、Heneicosane、Heptadecane、Hexadecane、5,5-Dibutylnonane、Undecane,5-methyl-、2,4-Dimethyldodecane、2,6,10-Trimethyltridecane、Undecane,4-ethyl-、Tetradecane,4-methyl-、Silane,cyclohexyldimethoxymethyl-、Cyclohexasiloxane,dodecamethyl-、Cyclotetrasiloxane,octamethyl-、Decane,1-iodo-、Sulfurous acid,2-pentyl tetradecyl ester;, The method for detecting the metabolite level includes any one or more of gas chromatography-mass spectrometry, mass spectrometry, nuclear magnetic resonance spectroscopy, liquid chromatography-mass spectrometry, capillary electrophoresis-mass spectrometry, surface enhanced Raman spectroscopy, matrix-assisted laser desorption / ionization mass spectrometry, quantitative mass spectrometry imaging, and surface-assisted laser desorption / ionization mass spectrometry; Preferably, the metabolite level is detected by gas chromatography-mass spectrometry; The microorganisms include bacteria, fungi, and archaea; Preferably, the bacteria include Acidobacteria, Actinobacteria, Agrobacterium, Alphaproteobacteria, Arthrobacter, Bacillus, Bacteroidetes, Betaproteobacteria, Blastocatellia, Bradyrhizobium, Brevibaelerium, Burkholderiales, Chloroflexi, Chryseolinea, Comamonadaceae, Corallococcus, Cyanobacteria, Cyrophaga, Cytophagia, Deltaproteobacteria, Desulfovibro, Eubaererium, Firmicutes, Fulvivirirgaceae, Gemmatimonas, Gemmationadetes, Geothrix, Halomonas, Helicobacter spp, Kallotenuaceae, Luteitalea, Lysobacter, Mesobacillus, Neisseria, Nitrososphaera, Nocardioides, Ohtaaekwangia, Paracoccus, Planctomycetes, Polyangium, Pseudomonas, Ramlibacter, Rhodopseudomonas, Roseiflexus, Salmonella, Serratia, Sorangium, Spirillum, Streptococcus, Thermoanaerobaculia, Thiobacillus, Thiophaera, Verrucomicrobia, Vibrio, Vulcaniibacterium, Xanthomomadales; Preferably, the fungi include Spizellomyces, Fusarium, Pseudogymnoascus, Cadophora, Mucor, Sclerotinia sclerotiorum, Gigaspora, Zopfia, Penicillium, Sphaerobolus, Colletotrichum, Talaromyces, Ascomycota, Mucoromycota, Chytridiomycota, Basidiomycota, Zoopagomycota, Microsporidia, Cryptomycota, Blastocladiomycota; Preferably, the archaea include Thaumarchaeota, Euryarchaeota, Woesearchaeota, Crenarchaeota, Nanoarchaeota; The detection method of the microbial abundance includes any one or more of metagenomic sequencing, 16S-rRNA sequencing, ITS sequencing, qRT-PCR, Southern blotting, and in situ hybridization; Preferably, the method for detecting the abundance of microorganisms is metagenomic sequencing.

5. The method according to claim 3, characterized in that: The constructing of the evaluation model refers to constructing an evaluation model based on the metabolite level of claim 4 and / or the microbial abundance of claim 4 using machine learning; Preferably, the constructing of the evaluation model refers to constructing an evaluation model based on the abundance of the following microorganisms using machine learning: Acidibacter, Funneliformis, Rhizophagus, Setophoma, Chloroflexi, Actinobacteriota, Firmicutes, Proteobacteria; Preferably, the machine learning includes convolutional neural network, autoencoder, deep belief network, linear regression, logistic regression, Lasso regression, Ridge regression, linear discriminant analysis, K nearest neighbor algorithm, decision tree, perceptron, support vector machine, ensemble learning, correlation analysis, naive Bayes, AdaBoost, GBDT, XGBoost, LightGBM, CatBoost or random forest; Preferably, the machine learning is random forest.

6. The method according to any one of claims 1 to 3, characterized in that: The sample to be tested includes a soil sample; Preferably, the samples to be tested include surface soil samples, profile occurrence layer samples and water-stable macroaggregate samples; Preferably, the sample to be tested is a surface soil sample; Preferably, the sample to be tested is a plant rhizosphere surface soil sample.

7. A method for computer screening of candidate substances for enhancing the nitrogen absorption capacity of plant rhizosphere, characterized in that: The steps of the method are as follows: Treating the plant root system with the substance to be screened, and obtaining the sample to be tested as claimed in claim 6; Detecting the metabolite level of claim 2 and / or the abundance of the microorganism of claim 2 in the sample to be tested; When the substance to be screened changes the metabolite level and microbial abundance in the sample to be tested and one or more levels of the metabolite group 1) described in claim 2 are higher than the reference value, one or more levels of the metabolite group 2) described in claim 2 are lower than the reference value, one or more abundances of the microbial group 3) described in claim 2 are higher than the reference value and / or one or more abundances of the microorganisms 4) described in claim 2 are lower than the reference value, then the substance to be screened is a candidate substance for enhancing the nitrogen absorption capacity of the plant rhizosphere; When the substance to be screened does not change the metabolite level and microbial abundance in the sample to be tested or the direction of change is opposite to the above direction, the substance to be screened is not a candidate substance for enhancing the nitrogen absorption capacity of the plant rhizosphere.

8. A computer system for evaluating the nitrogen absorption capacity of a plant, the system comprising: A data acquisition module, for acquiring data on the metabolite level of claim 4 and / or the abundance of the microorganism of claim 4 in the sample to be tested; A data processing module, inputting the data into an evaluation model constructed based on the method for constructing an evaluation model according to claim 5, wherein the evaluation model evaluates the nitrogen absorption capacity of the plant based on the acquired data; Output module, output results.

9. A computer device for evaluating the nitrogen absorption capacity of a plant, the computer device comprising: a processor adapted to implement the instructions; as well as A memory adapted to store a plurality of instructions adapted to be loaded by a processor and to execute the following steps: Acquiring data, acquiring data on the metabolite level of claim 4 and / or the abundance of the microorganism of claim 4 in the sample to be tested; Processing data, inputting the data into an evaluation model constructed based on the method for constructing an evaluation model according to claim 5, wherein the evaluation model evaluates the nitrogen absorption capacity of the plant based on the acquired data; Output the result.

10. A computer-readable storage medium having a plurality of instructions stored therein, wherein the instructions are suitable for being loaded by a processor and executing the following steps: Acquiring data, acquiring data on the metabolite level of claim 4 and / or the abundance of the microorganism of claim 4 in the sample to be tested; Processing data, inputting the data into an evaluation model constructed based on the method for constructing an evaluation model according to claim 5, wherein the evaluation model evaluates the nitrogen absorption capacity of the plant based on the acquired data; Output the result.

Images