Application of bone marrow gene marker in predicting marrow cleaning sensitivity of sulfonic acid alkylating agent

Abstract

The invention provides an application of a bone marrow gene marker in predicting the marrow cleaning sensitivity of a sulfonic acid alkylating agent, comprises a method for predicting the marrow cleaning sensitivity of a subject to the sulfonic acid alkylating agent, a computer system, computer equipment and a computer readable storage medium, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring data: acquiring expression data of a gene marker of a sample to be detected; the gene marker is prepared from one or more of the following components: Lrg1, Lilr4b, H2-Eb1, Ak4, Glg2, Glg2, Glg2, Glg2, Glg2, Glg2, processing the data, inputting the expression data of the gene marker into a constructed prediction model, and predicting the sensitivity of the subject to the marrow removal of the sulfonic acid alkylating agent by the prediction model based on the expression data of the gene marker; and outputting a prediction result.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent medicine and relates to the application of bone marrow gene markers in computer prediction of myeloablative sensitivity to sulfonic acid alkylating agents. Background Art

[0002] Sulfonic acid alkylating agents are a class of chemotherapy drugs that directly damage cellular DNA to prevent tumor cell proliferation. They act at all stages of the cell cycle and are subsequently used in myeloablative conditioning prior to hematopoietic stem cell transplantation due to their damaging effects on bone marrow hematopoietic stem cells. Busulfan (BU) is a commonly used sulfonic acid bifunctional alkylating agent in clinical practice, often used as part of a multidrug myeloablative conditioning regimen. It primarily induces premature hematopoietic stem cell senescence by inducing elevated oxidative free radicals and promoting DNA damage, thereby eliminating hematopoietic stem cells from the recipient's body and providing the necessary engraftment space for the transplant.

[0003] The steady-state plasma concentration of busulfan is closely associated with the prognosis of hematopoietic stem cell transplantation (HSCT). Inadequate dosing can lead to poor transplantation outcomes, such as disease relapse or graft rejection; overdose can increase the incidence of treatment-related toxicities, such as sinusoidal obstructive syndrome (SOS) and treatment-related mortality. Steady-state plasma concentrations of busulfan vary widely among individuals, and sensitivity to busulfan varies significantly between patients / subjects. This makes it difficult for physicians to accurately assess a patient's sensitivity based solely on clinical characteristics and clinical experience, hindering the development of effective dosing regimens. Current research on predictors of busulfan sensitivity has primarily used metabolomics approaches to identify indicators that can predict busulfan concentrations and clearance. However, recent studies have found that busulfan clearance cannot predict the risk of hepatic veno-occlusive disease in hematopoietic stem cell transplant patients, suggesting that other factors, such as genetic background, may need to be considered in determining the efficacy and toxicity of busulfan.

[0004] With the rapid advancement of molecular and cell biology, researchers and clinicians have begun to focus on using biomarkers to predict patient / subject sensitivity to busulfan myeloablation. The development of novel biomarkers, predictive models, and systems that can efficiently and accurately predict busulfan-induced bone marrow hematopoietic stem cell damage can provide patients / subjects with more effective and accurate drug sensitivity assessment indicators, thereby helping clinicians develop personalized treatment plans, reduce adverse reactions caused by blind medication use, and monitor drug efficacy. Summary of the Invention

[0005] In order to overcome the deficiencies of the prior art, the present invention aims to provide a method for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, a computer system for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, a computer device for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, and a computer-readable storage medium.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A first aspect of the present invention provides a method for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, the method being performed by a computer and comprising the following steps:

[0008] Acquiring data, acquiring expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4;

[0009] Processing the data, inputting the expression data of the gene markers into a constructed prediction model, wherein the prediction model predicts the sensitivity of the subject to myeloablation with a sulfonic acid alkylating agent based on the expression data of the gene markers;

[0010] Output the prediction results.

[0011] Furthermore, the expression data of the gene marker includes mRNA expression level data or protein expression level data.

[0012] Furthermore, the mRNA expression level data include, but are not limited to, data obtained by RT-PCR, qRT-PCR, in situ hybridization, and RNA sequencing.

[0013] Furthermore, the protein expression level data include but are not limited to data obtained by immunoblotting, immunohistochemistry, enzyme-linked immunosorbent assay, and mass spectrometry.

[0014] Furthermore, the steps of constructing the prediction model are as follows:

[0015] Obtaining gene marker expression data, wherein the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; the gene marker expression data are from a population sensitive to myeloablation with sulfonic acid alkylating agents and a population insensitive to myeloablation with sulfonic acid alkylating agents;

[0016] The expression data of gene markers are divided into training set and test set. The expression data of gene markers in the training set are extracted and input into the machine learning algorithm to build a prediction model, which is then verified through the test set to evaluate the model effectiveness.

[0017] Furthermore, the prediction model obtains prediction results according to the following criteria: when the expression levels of any one or several of the gene markers Lrg1, Lilr4b, and H2-Eb1 are higher than a threshold, and / or the expression level of Ak4 is lower than a threshold, a classification result is obtained that the sample to be tested is sensitive to myeloablation by sulfonic acid alkylating agents; when the expression levels of any one or several of the gene markers Lrg1, Lilr4b, and H2-Eb1 are lower than a threshold, and / or the expression level of Ak4 is higher than a threshold, a classification result is obtained that the sample to be tested is insensitive to myeloablation by sulfonic acid alkylating agents.

[0018] Furthermore, the machine learning algorithm includes algorithm models developed using various development tools.

[0019] Furthermore, the development tools include but are not limited to TensorFlow, Scikit Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, VertexAI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell.

[0020] Furthermore, the algorithm model includes but is not limited to a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model or a random forest model.

[0021] Furthermore, the sulfonic acid alkylating agents include but are not limited to busulfan and melphalan.

[0022] Furthermore, the sulfonic acid alkylating agent is busulfan.

[0023] Furthermore, the myeloablation includes inducing bone marrow damage.

[0024] Furthermore, the bone marrow damage includes bone marrow hematopoietic stem cell damage.

[0025] A second aspect of the present invention provides a computer system for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, the system comprising:

[0026] A data acquisition module is used to obtain gene marker expression data of the sample to be tested, wherein the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4;

[0027] a data classification module, configured to classify and predict the data obtained in the data acquisition module using the prediction model described in the first aspect of the present invention, and obtain a classification result of whether the sample to be tested is sensitive to myeloablation with sulfonic acid alkylating agents;

[0028] Output module, used to output classification results.

[0029] A third aspect of the present invention provides a computer device for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent, the computer device comprising:

[0030] a processor adapted to implement the instructions; and

[0031] A memory adapted to store a plurality of instructions adapted to be loaded by a processor and executed by the processor:

[0032] Acquiring data, acquiring expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4;

[0033] Processing data, inputting the expression data of the gene markers into the prediction model according to the first aspect of the present invention, wherein the prediction model predicts the sensitivity of the subject to myeloablation with a sulfonic acid alkylating agent based on the expression data of the gene markers;

[0034] Output the prediction results.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the following steps:

[0036] Acquiring data, acquiring expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4;

[0037] Processing data, inputting the expression data of the gene markers into the prediction model according to the first aspect of the present invention, wherein the prediction model predicts the sensitivity of the subject to myeloablation with a sulfonic acid alkylating agent based on the expression data of the gene markers;

[0038] Output the prediction results.

[0039] Advantages and beneficial effects of the present invention:

[0040] Based on the gene marker combination of the present invention, corresponding computer systems, computer devices, computer-readable storage media, and developed prediction models and methods are developed, which can predict the drug sensitivity of subjects to myeloablation with sulfonic acid alkylating agents without the need for blood draws to test the drug AUC after administration, thereby guiding clinicians to specify individualized treatment plans for patients or subjects, reducing blindness in medication use, and detecting drug efficacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a method for predicting a subject's sensitivity to myeloablation with sulfonic acid alkylating agents;

[0042] Figure 2 A schematic diagram of the structure of a computer system for predicting the sensitivity of a subject to myeloablation with sulfonic acid alkylating agents;

[0043] Figure 3 Schematic diagram of the structure of a computer device for predicting the sensitivity of a subject to myeloablation with sulfonic acid alkylating agents;

[0044] Figure 4 The graph shows the correlation results of biological replicates of mice with different sensitivities, where A1-A3 are C57 control groups, B1-B3 are C57 drug-treated groups, C1-C3 are NUK control groups, D1-D3 are NUK drug-treated groups, E1-E3 are LAM control groups, and F1-F3 are LAM drug-treated groups;

[0045] Figure 5 This is the GO enrichment analysis result of differentially expressed genes before and after BU administration. Figure 5 A in the figure is the GO enrichment analysis diagram of differential proteins before and after drug administration in LAM mice. Figure 5 Figure B is the GO enrichment analysis of differential proteins before and after drug administration in C57 mice. Figure 5 Figure C is the GO enrichment analysis diagram of differential proteins before and after administration of NUK mice;

[0046] Figure 6 This is a statistical chart of gene expression detected by fluorescence quantitative PCR, where Figure 6 A in the figure is a statistical graph of Lrg1 expression in bone marrow cells. Figure 6 B in the figure is a statistical graph of Lilr4b expression in bone marrow cells. Figure 6 C in the figure is a statistical graph of H2-Eb1 expression in bone marrow cells. Figure 6 D in the figure is a statistical graph of Ak4 expression in bone marrow cells;

[0047] Figure 7 is the ROC curve, where Figure 7 A in the figure is the ROC curve of Lrg1 in bone marrow cells for diagnosing LAM and NUK groups. Figure 7 B is the ROC curve of Lilr4b in bone marrow cells for diagnosing LAM and NUK groups. Figure 7 C in the figure is the ROC curve of H2-Eb1 in bone marrow cells for diagnosing LAM and NUK groups. Figure 7 D in the figure is the ROC curve diagram of Ak4 in bone marrow cells for diagnosing LAM group and NUK group. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0049] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0051] Figure 1 : is a flow chart of a method for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent provided by the present invention. Specifically, the method comprises the following steps:

[0052] 101: Acquire data, acquire expression data of gene markers of the sample to be tested; the gene markers include the following One or more: Lrg1, Lilr4b, H2-Eb1, Ak4 ;

[0053] In some embodiments, the present invention conducts extensive and in-depth research, selects three different strains of GD mice with different sensitivities to busulfan myeloablation, namely, highly sensitive NUK, moderately sensitive C57, and low-sensitive LAM, studies the relationship between bone marrow genes and busulfan drug sensitivity, and screens for genetic markers indicating differences in busulfan myeloablation sensitivity. It is found that Lrg1, Lilr4b, H2-Eb1, and / or Ak4 show significant differences among the three strains of GD mice, suggesting that Lrg1, Lilr4b, H2-Eb1, and / or Ak4 can be used as better markers to predict or promote busulfan myeloablation sensitivity.

[0054] In the present invention, the term "gene marker" refers to a gene or gene product that is a target for regulating one or more target phenotypes.

[0055] In some embodiments, the term also encompasses a measurable entity that has been identified as a target that is indicative of an output of interest, such as one or more diagnostic, prognostic, predictive drug sensitivity, and / or therapeutic outputs.

[0056] In some embodiments, the term also encompasses compositions that regulate genes or gene products, including anti-gene product antibodies and antigen-binding fragments thereof. Thus, gene markers include, but are not limited to, nucleic acids (e.g., genomic nucleic acids and / or transcribed nucleic acids), proteins, and antibodies (and antigen-binding fragments thereof).

[0057] In the present invention, the term "expression data" refers to the amount, accumulation, or rate of a gene marker molecule. Expression levels can be represented by the amount or synthesis rate of messenger RNA (mRNA) encoded by a gene, the amount or synthesis rate of a polypeptide or protein encoded by a gene, or the amount or synthesis rate of a biomolecule accumulated in a cell or biological fluid.

[0058] In a specific embodiment of the present invention, the expression data of gene markers were obtained by the following method: bone marrow cells of three strains of mice were lysed and then LSK cells were sorted, total RNA was extracted, reverse transcribed into cDNA and then qRT-PCR was performed. -ΔΔCt The expression data of gene markers were obtained by calculating the expression level.

[0059] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes LSK cell sorting:

[0060] a. Bone marrow cells from three strains of GD mice were lysed and then mixed with biotin-labeled primary antibodies CD4, CD8, B220, Ter119, Gr1, and CD11b in appropriate proportions and incubated at 4°C for 30 minutes.

[0061] b. Add 3 mL PBS to wash once, centrifuge at 1500 r / min, 4°C, 5 min, discard the supernatant,

[0062] c. Resuspend in 1 mL of PBS and add a mixture of antibodies: Streptavidin (labeled with PerCP), Sca-1 (labeled with PE), and c-kit (labeled with APC) according to the ratio in Table 2. Incubate at 4°C in the dark for 1 hour.

[0063] d. Wash once with 3 mL of PBS and centrifuge as above.

[0064] e. LSK cells (Lin-c-kit+Sca-1+) were sorted by flow cytometry. The sorted LSK cells (about 1×10 5cells, three samples per group) were evenly dispersed in 0.1 mL Trizol solution for RNA-sequence detection.

[0065] In a specific embodiment of the present invention, the step of obtaining gene marker expression data includes RNA extraction: extracting total RNA, measuring the concentration and OD260 / OD280 using a NanoDrop 2000 spectrophotometer (Thermo Scientific, USA), and detecting RNA integrity by agarose gel electrophoresis.

[0066] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes reverse transcription: the test RNA is reverse transcribed into cDNA using the TransScript All-in-One First-Strand cDNA Synthesis SuperMIX for qPCR Kit. The reverse transcription system is as follows: 0.5 μg total RNA; 2 μl of 5× TransScript All-in-one SuperMix for qPCR; 0.5 μl of gDNA Remover; and Nuclease-free H2O added to 10 μl. The reaction procedure is: 42°C for 15 minutes, 85°C for 5 seconds. After reverse transcription, 90 μl of Nuclease-free H2O is added and the mixture is stored at -20°C until needed.

[0067] In a specific embodiment of the present invention, the step of obtaining the expression data of the gene marker includes fluorescence quantitative PCR: using the PerfectStart™ Green qPCR SuperMix kit in Reactions were performed on a 480 II fluorescent quantitative PCR instrument (Roche, Switzerland). The system consisted of 2× PerfectStart™ Green qPCR SuperMix (5 μl); 10 μM forward primer (0.2 μl); 10 μM reverse primer (0.2 μl); cDNA (1 μl); and nuclease-free H₂O (3.6 μl). The PCR program was as follows: 94°C for 30 s; 94°C for 5 s; 60°C for 30 s, for 45 cycles. After cycling, product specificity was assessed using a melting curve analysis: the temperature was slowly increased from 60°C to 97°C, with fluorescence signals collected five times at each temperature increment.

[0068] In a specific embodiment of the present invention, the step of obtaining the expression data of the gene marker includes calculating the expression level: using 2 -ΔΔCt The expression data of gene markers were calculated by the method. The results are as follows Figure 6 shown.

[0069] Lrg1 includes wild-type, mutant forms, or fragments thereof. The term encompasses full-length, unprocessed Lrg1, as well as any form of Lrg1 derived from processing in cells. The term encompasses naturally occurring variants of Lrg1 (e.g., splice variants or allelic variants). The term encompasses, for example, Lrg1 genes, human Lrg1, and Lrg1 from any other vertebrate source, including mammals, such as primates and rodents (e.g., mice and rats). As a preferred embodiment, in the present invention, Lrg1 is a human gene with gene ID 116844.

[0070] Lilr4b includes wild-type, mutant forms, or fragments thereof. The term encompasses full-length, unprocessed Lilr4b, as well as any form of Lilr4b derived from processing in cells. The term encompasses naturally occurring variants of Lilr4b (e.g., splice variants or allelic variants). The term encompasses, for example, the Lilr4b gene, human Lilr4b, and Lilr4b from any other vertebrate source, including mammals, such as primates and rodents (e.g., mice and rats). As a preferred embodiment, in the present invention, Lilr4b is a human gene with gene ID 14727.

[0071] H2-Eb1 includes wild-type, mutant forms, or fragments thereof. The term encompasses full-length, unprocessed H2-Eb1, as well as any form of H2-Eb1 derived from processing in cells. The term encompasses naturally occurring variants of H2-Eb1 (e.g., splice variants or allelic variants). The term encompasses, for example, the H2-Eb1 gene, human H2-Eb1, as well as H2-Eb1 from any other vertebrate source, including mammals, such as primates and rodents (e.g., mice and rats). As a preferred embodiment, in the present invention, H2-Eb1 is a human gene with gene ID 14969.

[0072] Ak4 includes wild type, mutant or fragments thereof. The term encompasses full-length, unprocessed Ak4, as well as any form of Ak4 derived from processing in cells. The term encompasses naturally occurring variants of Ak4 (e.g., splice variants or allelic variants). The term encompasses, for example, Ak4 genes, human Ak4, and Ak4 from any other vertebrate source, including mammals, such as primates and rodents (e.g., mice and rats). As a preferred embodiment, in the present invention, Ak4 is a human gene with a gene ID of 205.

[0073] As used in the context of the present invention, the term "sample" refers to a composition obtained from or derived from a patient / subject that contains cells and / or other molecular entities to be characterized and / or identified based on, for example, physical, biochemical, chemical and / or physiological characteristics. For example, a sample refers to any sample derived from a patient / subject that is expected or known to contain cells and / or molecular entities to be characterized. Samples include, but are not limited to, tissue samples, primary or cultured cells or cell lines, cell cultures, cell supernatants, cell lysates, platelets, serum, plasma, vitreous humor, lymph fluid, synovial fluid, follicular fluid, semen, amniotic fluid, milk, whole blood, blood-derived cells, urine, cerebrospinal fluid, saliva, sputum, tears, sweat, mucus, tissue culture fluid, tissue extracts, homogenized tissue, cell extracts, and combinations thereof.

[0074] In a specific embodiment of the present invention, the sample is a bone marrow cell lysozyme extract.

[0075] The term "RT-PCR," also known as "reverse transcription polymerase chain reaction," combines reverse transcription (RT) of RNA with polymerase chain amplification (PCR) of cDNA. First, cDNA is synthesized from RNA using reverse transcriptase. DNA polymerase then amplifies the target fragment using the cDNA as a template. RT-PCR is a sensitive and versatile technique that can be used to monitor gene expression levels in cells, detect RNA viral load in cells, and directly clone cDNA sequences of specific genes.

[0076] The term "qRT-PCR," also known as "quantitative real-time polymerase chain reaction," refers to the use of changes in fluorescence signals to detect changes in the amount of amplified product in each cycle of the PCR amplification reaction in real time, ultimately performing accurate quantitative analysis of the starting template.

[0077] The term "RNA sequencing", also known as "transcriptome sequencing" or "RNA-Seq", can comprehensively and quickly obtain the sequence information and expression information of almost all transcripts in a certain state of a specific cell or tissue, including protein-coding mRNA and various non-coding RNAs, and the expression abundance of different transcripts produced by selective gene splicing. While analyzing the structure and expression level of transcripts, unknown transcripts and rare transcripts are also discovered, thereby accurately analyzing important issues in life sciences such as gene expression differences, gene structural variations, and screening molecular markers. The RNA sequencing method can detect the overall transcriptional activity of any species without the need to design probes for known sequences in advance. The transcriptome refers broadly to the collection of all transcription products in a cell under a certain physiological condition, including messenger RNA, ribosomal RNA, transfer RNA, and non-coding RNA; in a narrow sense, it refers to the collection of all mRNAs.

[0078] In a specific embodiment of the present invention, the expression data of gene markers were obtained by extracting bone marrow cells from three strains of mice before and after administration for LSK cell sorting, followed by RNA extraction and library construction, and RNA sequencing, differentially expressed gene analysis, and gene enrichment analysis of the transcriptome library.

[0079] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes LSK cell sorting:

[0080] a. Each mouse can isolate approximately 3×10 8 Bone marrow cells were added with biotin-labeled mixed primary antibodies CD4, CD8, B220, Ter119, Gr1, and CD11b according to the ratio in Table 1 and incubated at 4°C for 30 min.

[0081] b. Add 3 mL PBS to wash once, centrifuge at 1500 r / min, 4°C, 5 min, discard the supernatant,

[0082] c. Resuspend in 1 mL of PBS and add a mixture of antibodies: Streptavidin (labeled with PerCP), Sca-1 (labeled with PE), and c-kit (labeled with APC) according to the ratio in Table 2. Incubate at 4°C in the dark for 1 hour.

[0083] d. Wash once with 3 mL of PBS and centrifuge as above;

[0084] e. LSK cells (Lin-, c-kit+, Sca-1+) were sorted by flow cytometry. The sorted LSK cells (about 1×10 5 cells, three samples per group) were evenly dispersed in 0.1 mL Trizol solution for RNA-sequence detection.

[0085] Table 1. Biotin-labeled mixed primary antibody formula

[0086]

[0087] Table 2. Secondary antibody formulation

[0088]

[0089]

[0090] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes RNA extraction and library construction: total RNA was extracted using TRIzol reagent according to the manufacturer's instructions. RNA purity and quantification were determined using a NanoDrop 2000 spectrophotometer (ThermoScientific, USA), and RNA integrity was assessed using an Agilent 2100 Bioanalyzer (Agilent Technologies, Santa Clara, CA, USA). Transcriptome libraries were constructed using the VAHTS Universal V5 RNA-seq Library Prep Kit according to the manufacturer's instructions. Transcriptome sequencing and analysis were performed by Shanghai Ouyi Biotechnology Co., Ltd. (Shanghai, China).

[0091] In a specific embodiment of the present invention, the step of acquiring the expression data of the gene marker includes RNA sequencing of the transcriptome library: the library is sequenced using the llumina Novaseq 6000 sequencing platform, and 150bp double-end reads are generated. The raw reads in the fastq format are processed using fastp software, and cleanreads are obtained after removing low-quality reads for subsequent data analysis. HISAT2 software is used for reference genome alignment and gene expression level (FPKM) calculation, and the read counts (counts) of each gene are obtained by HTSeq-count. PCA analysis and plotting of genes (counts) are performed using R (v 3.2.0) to evaluate the biological repetition of samples, and the results are shown in FIG. Figure 4 shown.

[0092] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes differentially expressed gene analysis: differentially expressed gene analysis is performed using DESeq2 software, where genes that meet a q-value < 0.05 and a foldchange > 2 or a foldchange < 0.5 threshold are defined as differentially expressed genes (DEGs). Hierarchical cluster analysis of DEGs is performed using R (v 3.2.0) to display gene expression patterns across different groups and samples. Radar plots of the top 30 genes are created using the R package ggradar to display expression changes of upregulated or downregulated genes.

[0093] In a specific embodiment of the present invention, the step of acquiring gene marker expression data includes gene enrichment analysis: GO, KEGG Pathway, Reactome, and WikiPathways enrichment analysis is performed on differentially expressed genes using the hypergeometric distribution algorithm to screen for significantly enriched functional terms. R (v 3.2.0) is used to plot bar charts, chord diagrams, or enrichment analysis circle plots for the significantly enriched functional terms.

[0094] In a specific embodiment of the present invention, GSEA software is used to perform gene set enrichment analysis. Using a predefined gene set, genes are ranked according to their differential expression between the two types of samples, and then the predefined gene set is tested to see whether it is enriched at the top or bottom of the ranking table.

[0095] like Figure 4 As shown in the figure, the biological replicate samples within the control group and the drug-treated group of mice with different sensitivities were well correlated. Among them, the samples of the C57 strain control group (group A) and the drug-treated group (group B), as well as the samples of the LAM mouse control group (group E) and the drug-treated group (group F) were highly correlated, indicating that the composition of the samples of the C57 and LAM strains before and after drug treatment was similar; the samples of the NUK mouse control group (group C) and the drug-treated group (group D) were weakly correlated, suggesting that BU had a greater effect on NUK than on the other two strains; all samples had good biological replicate correlation, ensuring the credibility of the DEGs screened by management.

[0096] GO analysis results are as follows Figure 5 As shown in Figure A, the differentially expressed genes in the LAM, C57, and NUK strains were enriched in biological processes related to blood cell development and regulation, primarily processes related to erythrocytes and platelets. The differentially expressed genes in LAM and NUK were also enriched in immune response-related processes. The differences were that the differentially expressed genes in LAM were also associated with apoptotic cell clearance, positive regulation of peptidyl-tyrosine phosphorylation, and positive regulation of the ERK1 and ERK2 cascades; the differentially expressed genes in C57 were also associated with mitochondrial translation and RNA polymerase regulation of transcription; and the differentially expressed genes in NUK were also associated with inflammatory responses, neutrophil chemotaxis, tumor necrosis factor regulation, and phagocytosis.

[0097] Cell composition, such as Figure 5 As shown in Figure B, differentially expressed genes in LAM, C57, and NUK strains are all enriched in various membrane and cytoplasmic structures. The difference is that differentially expressed genes in LAM and NUK are also enriched in extracellular structures and the cytoplasm, while those in C57 are enriched in structures related to the nucleus and mitochondria.

[0098] Molecular function, such as Figure 5As shown in Figure C, the differentially expressed genes in the LAM, C57, and NUK lines are all enriched for functions related to binding to various proteins, chemokines, and enzymes. However, the differentially expressed genes in LAM and NUK are also related to various metal ion binding processes.

[0099] As used herein, the term "myeloablative" refers to the preconditioning step prior to hematopoietic stem cell transplantation, which typically aims to eliminate the patient's hematopoietic stem cells from the bone marrow niche, thereby providing ample space for the transplanted donor's hematopoietic stem cells to proliferate and differentiate. Myeloablative conditioning regimens are typically categorized as either total body irradiation-based or high-dose chemotherapy-based.

[0100] In some embodiments, the chemotherapy drug is an alkylating agent; further, the alkylating agent is a sulfonic acid alkylating agent; further, the sulfonic acid alkylating agent includes but is not limited to busulfan and melphalan; further, the sulfonic acid alkylating agent is busulfan.

[0101] In a specific embodiment of the present invention, busulfan was used to induce hematopoietic stem cell damage in different mouse strains. The following information was used for the different mouse strains: 10 SPF male LAM-DA (hereinafter referred to as LAM) and NUK genetically diverse (GD) mice, aged 8-10 weeks, were provided by the Institute of Laboratory Animal Science, Chinese Academy of Medical Sciences [SCXK (Beijing) 2014-0011]. Ten SPF male C57BL / 6J mice (hereinafter referred to as C57), aged 8-10 weeks, were provided by Beijing Huafukang Biotechnology Co., Ltd. [SCXK (Beijing) 2014-0004]. The mice were housed in a barrier environment animal facility at the Institute of Laboratory Animal Science, Chinese Academy of Medical Sciences [SYXK (Beijing) 2015-0035]. The mice were housed in a standard environment (half-day and half-night, constant humidity, and a temperature of 20°C-25°C) for 3 days prior to the start of the experiment. All animal experiments were conducted in accordance with animal welfare standards and the Guidelines for the Care and Use of Laboratory Animals established by the Institute of Medical Laboratory Animals, China. The experimental protocols were approved by the Institute's Laboratory Animal Care and Use Committee (IACUC No. MAM21001). All experimental procedures were reviewed and approved by the Ethics Committee of the Institute of Medical Laboratory Animals, Chinese Academy of Medical Sciences.

[0102] In a specific embodiment of the present invention, the experimental grouping and modeling procedures for inducing hematopoietic stem cell damage in different mouse strains using busulfan are as follows: 10 mice each from the LAM, C57, and NUK strains were randomly divided into a control group and a BU-treated group, with 5 mice in each group. The differences in sensitivity of different GD mouse strains to busulfan-induced bone marrow hematopoietic stem cell damage were observed. Busulfan powder was prepared in DMSO at 80 mg / mL as a stock solution for storage and diluted with PBS to the desired concentration upon use. The treated group received an intraperitoneal injection of 40 mg / kg busulfan, administered 20 mg / kg daily over two days. The control group received an equal volume of PBS containing 5% DMSO as a control.

[0103] In a specific embodiment of the present invention, the effect of busulfan-induced hematopoietic stem cell damage in different mouse strains was evaluated by measuring the bone marrow cell colony-forming ability: 14 days after busulfan administration, mouse bone marrow cells were obtained under sterile conditions, and the concentration of mouse bone marrow was adjusted to 4×10 5 Cells were collected at a concentration of 0.2 mL / mL for each sample and added to 1 mL of pre-packaged M3434 culture medium. The cells were thoroughly mixed on a shaker and allowed to stand for 2-5 minutes. After the bubbles disappeared, the cells were added to a 24-well plate with a volume of 0.5 mL per well. The culture plate was gently shaken to evenly distribute the culture medium. The 24-well plate was cultured in a 37°C, 5% CO2 incubator. On day 7, the granulocyte-macrophage colony-forming unit (CFU-GM) count was measured to assess the hematopoietic stem cell function of the mice. After busulfan administration, the number of bone marrow cell colonies formed in vitro decreased in all three mouse strains, and the differences were significant (P < 0.05). This indicates that busulfan inhibits the proliferation of hematopoietic stem and progenitor cells. Compared with C57, NUK is more sensitive to busulfan treatment, while LAM is relatively less sensitive to busulfan.

[0104] 102: Process the data, input the expression data of the gene marker into the constructed prediction model, The prediction model predicts the subject's sensitivity to myeloablation with sulfonic acid alkylating agents based on the expression data of the gene markers;

[0105] In some embodiments of the present invention, methods for constructing a predictive model are known to those skilled in the art, and the step of correlating gene marker expression levels with a probability or risk can be implemented and achieved in various ways. Preferably, the measured concentrations of the marker and one or more other markers are mathematically combined, and the combined value is correlated with the underlying drug sensitivity question. The measured marker values ​​can be combined using any suitable prior art mathematical method, and the predictive model constructed using a machine learning algorithm.

[0106] In the context of the present invention, the term "machine learning" refers to the use of computers to simulate or implement human learning activities. Technicians typically use different development tools to build machine learning algorithm models. The development tools include but are not limited to TensorFlow, Scikit Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, Spell. The algorithm models include but are not limited to linear regression models, logistic regression models, Lasso regression models, Ridge regression models, linear discriminant analysis models, nearest neighbor models, decision tree models, perceptron models, neural network models, support vector machine models, naive Bayes models, AdaBoost models, GBDT models, XGBoost models, LightGBM models, CatBoost models, or random forest models.

[0107] After the prediction model was constructed, the ROC curve analysis was used to evaluate the diagnostic efficacy of the prediction model.

[0108] The ROC curve is a graph of the true positive rate (sensitivity) of a test against the false positive rate (100%-specificity) of the test. It is useful to describe the performance of a specific feature (e.g., any biomarker described herein and / or any entry of other biomedical information) when distinguishing between two populations (e.g., individuals responding to a therapeutic agent and those responding non-responsive). Typically, feature data is selected across the entire population in ascending order based on the value of a single feature. Then, for each value of the feature, the true positive and false positive rates of the data are calculated. The true positive rate is determined by counting the number of cases that are higher than the value of the feature and divided by the total number of cases. The false positive rate is determined by counting the number of controls that are higher than the value of the feature and divided by the total number of controls. Although this definition refers to a situation where a feature is increased compared to a control, this definition is also applied to situations where a feature is lower compared to a control (in this case, samples with a value lower than the feature are counted). ROC curves can be generated for individual features, and can be generated for other individual outputs. For example, a combination of two or more features can be mathematically combined (e.g., added, subtracted, multiplied, etc.) to provide a single sum value, and this single sum value can be plotted in an ROC curve. In addition, any combination of multiple features where the combination is derived from individual output values ​​can be plotted in an ROC curve.

[0109] In some embodiments of the present invention, the ROC curve is generated for a single feature, specifically a ROC curve for predicting a patient / subject's sensitivity to busulfan myeloablation.

[0110] In a specific embodiment of the present invention, the ROC working curve of the subjects was drawn using GraphPad, and the diagnostic efficacy of the AUC value, sensitivity and specificity judgment indicators were analyzed. The results showed that the diagnostic efficacy of Lrg1, Lilr4b, H2-Eb1, and Ak4 was as follows: Figure 7 The results showed that the Lrg1 expression level in LSK cells had an AUC value of 1 for diagnosing mice in the LAM and NUK groups, with a sensitivity of 100% and a specificity of 0%. The Lilr4b expression level in LSK cells had an AUC value of 0.8667 for diagnosing mice in the LAM and NUK groups, with a sensitivity of 100% and a specificity of 40%. The H2-Eb1 expression level in LSK cells had an AUC value of 1 for diagnosing mice in the LAM and NUK groups, with a sensitivity of 100% and a specificity of 0%. The Ak4 expression level in LSK cells had an AUC value of 1 for diagnosing mice in the LAM and NUK groups, with a sensitivity of 100% and a specificity of 0%. These results indicate that Lrg1, Lilr4b, H2-Eb1, and Ak4 can predict the sensitivity to busulfan-induced bone marrow damage.

[0111] In the context of the present invention, "AUC" refers to the area under the curve, which is a measure of the ability of a classifier to distinguish between classes and is used as a summary of the ROC curve. It can usually be obtained using the integral method or the trapezoidal method. The AUC measurement is useful for comparing the accuracy of classifiers across the entire data range. A higher AUC means that the classifier has better performance and can more accurately classify between two target groups.

[0112] In a specific embodiment of the present invention, the two target groups are the group that is sensitive to busulfan myeloablation and the group that is insensitive to busulfan myeloablation.

[0113] 103: Output the prediction result.

[0114] Figure 2 A schematic diagram showing the structure of a computer system for predicting a subject's sensitivity to myeloablation with sulfonic acid alkylating agents provided by the present invention.

[0115] The system is programmed or otherwise configured to include a data acquisition module 201 , a data classification module 202 , and an output module 203 ;

[0116] The data acquisition module 201 is used to obtain gene marker expression data of the sample to be tested, wherein the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4;

[0117] A data classification module 202 is configured to classify and predict the data obtained in the data acquisition module using the prediction model obtained by the construction method described in the first aspect of the present invention, and obtain a classification result of whether the sample to be tested is sensitive to myeloablation with sulfonic acid alkylating agents;

[0118] The output module 203 is used to output the classification results.

[0119] The system may be the user's electronic device or a computer system located remotely from the electronic device.

[0120] Figure 3 A schematic diagram showing the structure of a computer device for predicting a subject's sensitivity to myeloablation with a sulfonic acid alkylating agent provided by the present invention.

[0121] The computer device 300 includes a processor 301 and a memory 302 coupled to the processor 301. The memory 302 stores program instructions. When the program instructions are executed by the processor 301, the processor 301 performs the steps of predicting the myeloablative sensitivity of a subject to a sulfonic acid alkylating agent as described in any of the above embodiments.

[0122] The processor 301 may also be referred to as a CPU (Central Processing Unit). The processor 301 may be an integrated circuit chip having signal processing capabilities. The processor 301 may 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 device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor may be a microprocessor or any conventional processor.

[0123] The computer device 300 may be a mobile electronic device.

[0124] The storage medium of an embodiment of the present invention stores program instructions capable of implementing the aforementioned method for predicting a subject's myeloablative sensitivity to a sulfonic acid alkylating agent. The program instructions may be stored in the aforementioned storage medium in the form of a software product, including instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a computer device such as a computer, server, mobile phone, or tablet.

[0125] It should be understood that the systems, devices, and methods described herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementations may employ other division methods, such as combining or integrating multiple modules or components into another system, or omitting or disabling certain features. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or modules via some interface, which may be electrical, mechanical, or other forms.

[0126] The modules described as separate components may or may not be physically separate, and 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 elements. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0128] The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for predicting the sensitivity of a subject to myeloablation by a sulfonic acid alkylating agent, the method being performed by a computer and comprising the following steps: Acquiring data, acquiring expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; Processing data, inputting the expression data of the gene markers into a constructed prediction model, wherein the prediction model predicts the sensitivity of the subject to myeloablation with sulfonic acid alkylating agents based on the expression data of the gene markers; Output the prediction results.

2. The method according to claim 1, characterized in that The expression data of the gene markers include mRNA expression level data or protein expression level data; The mRNA expression level data include but are not limited to data obtained by RT-PCR, qRT-PCR, in situ hybridization and RNA sequencing; The protein expression level data include, but are not limited to, data obtained by immunoblotting, immunohistochemistry, enzyme-linked immunosorbent assay, and mass spectrometry.

3. The method according to claim 1, characterized in that The steps for constructing the prediction model are as follows: Acquiring expression data of gene markers, wherein the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; the expression data of the gene markers are from a population that is sensitive to myeloablation with sulfonic acid alkylating agents and a population that is insensitive to myeloablation with sulfonic acid alkylating agents; The expression data of gene markers are divided into training set and test set. The expression data of gene markers in the training set are extracted and input into the machine learning algorithm to build a prediction model, which is then verified through the test set to evaluate the model effectiveness.

4. The method according to claim 1, characterized in that: The prediction model obtains prediction results through the following criteria: When the expression levels of any one or several of the gene markers Lrg1, Lilr4b, and H2-Eb1 are higher than the threshold, and / or the expression level of Ak4 is lower than the threshold, a classification result is obtained that the sample to be tested is sensitive to myeloablation by sulfonic acid alkylating agents; when the expression levels of any one or several of the gene markers Lrg1, Lilr4b, and H2-Eb1 are lower than the threshold, and / or the expression level of Ak4 is higher than the threshold, a classification result is obtained that the sample to be tested is insensitive to myeloablation by sulfonic acid alkylating agents.

5. The method according to claim 1, characterized in that The machine learning algorithm includes algorithm models developed using various development tools.

6. The method according to claim 5, characterized in that The development tools include but are not limited to TensorFlow, Scikit Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell.

7. The method according to claim 5, characterized in that The algorithm model includes but is not limited to a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model or a random forest model.

8. A computer system for predicting a subject's sensitivity to myeloablation by a sulfonic acid alkylating agent, the system comprising: A data acquisition module is used to acquire gene marker expression data of the sample to be tested, wherein the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; A data classification module, used to classify and predict the data obtained in the data acquisition module through the prediction model obtained by the construction method according to claim 3, and obtain a classification result of whether the sample to be tested is sensitive to myeloablation by sulfonic acid alkylating agents; Output module, used to output classification results.

9. A computer device for predicting a subject's sensitivity to myeloablation by a sulfonic acid alkylating agent, 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 expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; Processing data, inputting the expression data of the gene markers into a constructed prediction model, wherein the prediction model predicts the sensitivity of the subject to myeloablation with sulfonic acid alkylating agents based on the expression data of the gene markers; Output the prediction results.

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 expression data of gene markers of the sample to be tested; the gene markers include one or more of the following: Lrg1, Lilr4b, H2-Eb1, Ak4; Processing data, inputting the expression data of the gene markers into a constructed prediction model, wherein the prediction model predicts the sensitivity of the subject to myeloablation with sulfonic acid alkylating agents based on the expression data of the gene markers; Output the prediction results.

Images