A method of classifying cho cells

Abstract

The invention relates to a method for constructing a biomarker of a first target phenotype of CHO (Chinese hamster ovary) cells. The method comprises the following steps: (a) determining methylation values of all CpG sites in genomic DNAs (Deoxyribose Nucleic Acid) of different CHO cell populations; the CHO cell population represents the first target phenotype and is part of a training sample; (b) defining a set of specific CpG loci from the training sample of step (a), the loci CpG having stable and reproducible methylation values; and (c) processing the methylation value in the step (b) and the target phenotype of the training sample by using a model based on machine learning, thereby obtaining a specific CpG site with a corresponding weight coefficient, which defines a biomarker of the first target phenotype.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202480073845.5 (22) Application Date 2024.11.13 (30) Priority Data 23211921.4 2023.11.24 EP (85) PCT International Application Entering National Phase Date 2026.05.21 (86) PCT International Application Application Data PCT / EP2024 / 082144 2024.11.13 (87) PCT International Application Publication Data WO2025 / 108795 EN 2025.05.30 (71) Applicant: Evonik Operations Ltd. Address: Essen, Germany (72) Inventors: F. Boel, E.I. Igui, S. Roy, K.Y. Huang, S. Nagarajjan, L. Huang (74) Patent Agency: Yongxin Patent & Trademark Agency Ltd. 72002 Patent Attorney: Tan Banghui (51) Int.Cl. G16B 20 / 00 (2006.01) G16B 40 / 20 (2006.01) (54) Invention Title: Method for Classifying CHO Cells (57) Abstract: This invention relates to a method for constructing a biomarker for a first target phenotype of CHO cells, the method comprising the steps of: (a) determining the methylation value of all CpG sites in the genomic DNA of different CHO cell populations; the CHO cell populations representing the first target phenotype and being part of a training sample; (b) defining a set of specific CpG sites from the training sample of step (a), the CpG sites having stable and reproducible methylation values; and (c) The methylation values ​​of step (b) and the target phenotype of the training samples are processed using a machine learning-based model to obtain specific CpG sites with corresponding weight coefficients, which define biomarkers of the first target phenotype.Claims 2 pages, Description 14 pages, Drawings 2 pages, CN 122249858 A 2026.06.19 CN 1 22 24 98 58 A 1. A method for constructing a biomarker for a first target phenotype of CHO cells, the method comprising the steps of: (a) determining the methylation values ​​of all CpG sites in the genomic DNA of a CHO cell population; the CHO cell population representing the first target phenotype and being part of a training sample; (b) identifying a set of specific CpG sites from the training sample of step (a), the CpG sites having consistent and reproducible methylation values; and (c) processing the methylation values ​​of step (b) and the target phenotype of the training sample using a machine learning-based model; thereby obtaining specific CpG sites with corresponding weighting coefficients that define the biomarker of the first target phenotype. 2. The method of claim 1, wherein the machine learning-based model is a classifier algorithm selected from the group consisting of: random forest, decision tree, support vector machine (SVM), K-nearest neighbor (KNN), neural network, multilayer perceptron, and Gaussian mixture model. 3. The method of claim 1 or 2, wherein steps (b) and (c) are performed on a computer. 4. The method of any preceding claim, wherein steps (a)-(c) are repeated for a second target phenotype and subsequent target phenotypes, such that each target phenotype corresponds to at least one biomarker, to generate a set of biomarkers for different target phenotypes. 5. The method of any preceding claim, wherein the DNA methylation value is determined using a bead-based DNA methylation array. 6. The method of any one of claims 1-4, wherein in step (a) methylation rate and read coverage of CpG sites are determined using hydrothionite sequencing; and in step (b) specific CpG site sets are determined using hydrothionite sequencing and truncation values. 7. The method of claim 6, wherein the minimum coverage cutoff value determined in step (b) is 3.8. An in vitro method for predicting the classification of CHO test cells, the method comprising the steps of: a) determining the DNA methylation level of a specific CpG site in genomic DNA extracted from CHO test cells; b) analyzing the methylation level obtained in step (a) using a machine learning-based model to predict the expression level of a target phenotype in the CHO test cells, wherein the specific CpG site is a parameter of a target phenotype biomarker, and the classification of the CHO test cells is determined by the target phenotype expressed by the CHO test cells, wherein the biomarker is determined using the method of any one of claims 1 to 7. 9. The method according to any one of the preceding claims, wherein the target phenotype is selected from the group consisting of: phenotypic homogeneity, protein mass, optimal carbohydrate metabolism, optimal amino acid metabolism, optimal lipid metabolism, optimal heterologous protein production, optimal cell viability, and combinations thereof. 10. The method according to any one of the preceding claims, wherein the specific CpG site is distributed in low-methylated regions (LMR), CpG islands, variable methylation sites, and / or differentially methylated regions in the CHO cell genome. 11. The method according to any one of claims 8 to 10, wherein the DNA methylation level in step (a) is determined using a bead-based DNA methylation array. 12. A computer-implemented method for constructing a biomarker for a first target phenotype of a CHO cell population, the method comprising the steps of: (a) inputting methylation values ​​of all CpG sites taken from the genomic DNA of a CHO cell population; the CHO cell population expressing a specific target phenotype related to cell fitness and being part of a training sample; (b) identifying and determining specific CpG sites exhibiting consistent and reproducible methylation values ​​from all CpG sites in step (a); and (c) using a machine learning-based model to correlate the CpG methylation levels of the CpG sites obtained in step (a) with the target phenotype; thereby obtaining specific CpG sites with corresponding weighting coefficients, which are used as parameters for defining the biomarker of the first target phenotype. 13. The method of claim 12, wherein the machine learning-based model is a classifier algorithm selected from the group consisting of: random forest, decision tree, support vector machine (SVM), K nearest neighbors (KNN), neural network, multilayer perceptron, and Gaussian mixture model.Claims 2 / 2 Page 3 CN 122249858 A Method for Classifying CHO Cells Technical Field

[0001] This invention relates to a method based on epigenetics for quantitatively and qualitatively classifying Chinese hamster ovary (CHO) cells for bioprocessing according to a target phenotype. Specifically, the method determines the methylation level of specific CpG sites and uses a specific statistical algorithm to determine the target phenotype expressed by CHO cells, and classifies CHO cells based on the target phenotype expressed by the cells. Background Art

[0002] Since 1987, Chinese hamster ovary (CHO) cells have been the core tool cells for the industrial production of recombinant therapeutic proteins, and are therefore widely used in biopharmaceutical production. Currently, approximately 70% of all recombinant biopharmaceutical proteins worldwide, as well as all monoclonal antibodies approved since 2016, are produced using CHO cells. Several advantages of using CHO cells to produce biopharmaceuticals include: tolerance to gene manipulation, ease of adaptation to scale-up production, rapid growth rate, and the ability to perform human-compatible post-translational modifications. However, the bioproduct manufacturing system based on CHO cells currently faces a bottleneck: protein productivity decreases with prolonged culture time.

[0003] The initial protein expression / production level of the cell line is usually high, but the yield decreases during long-term culture. This leads to a decrease in process yield, affects project cycle and increases costs. Changes in the cell culture environment can cause changes in cell behavior and protein yield of the production cell line.

[0004] Current methods for determining whether a CHO clone is suitable for target protein production are not only time-consuming, but also not specific enough as to read out the interaction between the cell and its microenvironment, which is crucial for screening the optimal protein production cell clone or cell. For example, US2017 / 0081732 discloses a method for screening cells capable of long-term expression or secretion of peptides based on histone acylation assay (measured by PCR), but this method is complex and lacks accuracy. In addition, PCR is a non-high-throughput method and cannot achieve whole-genome CpG detection, making the detection process incomplete.

[0005] Furthermore, CHO clones with the same genetic background may also exhibit heterogeneous phenotypes, leading to instability and reduced efficiency in established production processes, and causing economic losses in industrial-scale heterologous protein production. Methods relying solely on phenotypic analysis to compare and screen CHO clones cannot guarantee long-term stability. Moreover, genotypic comparisons of CHO clones cannot explain how genes differentially express themselves to adapt to environmental conditions.As shown by Wippermann A et al. in Appl Microbiol Biotechnol. 2014 Jan;98(2):579-89, butyrate supplementation, which is known to increase specific production in CHO cells, can also lead to changes in epigenetic silencing events.

[0006] Therefore, there is a need in the art for an efficient and economical tool for the global assessment and regulation of CHO cell metabolism and protein production. There is also a need for methods for screening and maintaining a homogeneous CHO cell population to improve production speed, quality, efficiency and stability. Specifically, there is an urgent need for new descriptive and predictive markers to identify CHO cells with positive and valuable phenotypes in order to identify and classify CHO cells suitable for genetic modification and / or heterologous protein production as early as possible. Summary of the Invention

[0007] The present invention solves the above problems by providing an accurate, simple and reproducible means to classify CHO cells suitable for growth and protein production in the early stages of bioprocessing. Specifically, the present invention provides a means to ensure the stability, high efficiency, and reduced economic losses of heterologous protein production (especially industrial-scale production) as described on page 1 / 14 of the specification, CN 122249858 A.

[0008] The inventors have identified a method for classifying CHO cells using epigenetics, wherein DNA methylation of the CHO cell genome is measured, and a machine learning-based model is used to correlate the DNA methylation level with the target phenotype expressed by the cell. That is, measuring DNA methylation at a specific location (CpG site) can accurately predict the expression of the target phenotype in any CHO cell being tested, thereby enabling the classification of the cell. Since genotypic comparisons of CHO clones cannot determine how genes differentially express themselves to adapt to environmental conditions, and phenotypic analysis alone cannot guarantee long-term stability, epigenetic methods (especially DNA methylation) offer a cutting-edge technology that can determine whether CHO test cells exhibit a target phenotype and, if so, what that phenotype, at any stage of CHO cell bioprocessing (especially in the early stages of CHO cell bioproduct production), thereby determining their suitability for gene modification and other scientific research. The method described in any aspect of this invention allows the use of DNA methylation as a tool for the quantitative and qualitative classification of CHO cells based on protein production.

[0009] According to one aspect of the present invention, a method for constructing a biomarker for a first target phenotype of CHO cells is provided, the method comprising the following steps: (a) determining the methylation values ​​of all CpG sites in the genomic DNA of a CHO cell population; the cell population representing the first target phenotype and being a portion of a training sample; (b) identifying a set of specific CpG sites from the training sample of step (a), the CpG sites having consistent and reproducible methylation values; and (c) processing the methylation values ​​of step (b) and the target phenotype of the training sample using a machine learning-based model; thereby obtaining specific CpG sites with corresponding weight coefficients, defining a biomarker for the first target phenotype.

[0010] Specifically, the machine learning-based model is a classifier algorithm (Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd edition). Stanford, California: Stanford University.), which may be selected from the following groups: Random Forest, Decision Tree (A. Floares and A. Birlutiu, The 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, Queensland, Australia, 2012, pp. 1-7), Support Vector Machine (SVM) (Wang, C., et al. Scientific Reports, (2020) 10:5880 and Yousef, M. et al, BMC Bioinformatics 2009, 10:337), K Nearest Neighbor (KNN) (Wang, C., 2020), Neural Network (Daoud, M. et al., 2019, 97: 204-214), Multilayer Perceptron (Wang, C., 2020 and Daoud, M. et al., 2019) and Gaussian Mixture Model (Prabakaran, I. et al. Cancer Res; 79(13), 2019: 3492-3502).

[0011] In one instance, the specific CpG site set in step (b) can ultimately be selected using machine learning techniques such as random forests (Breiman L (2001). "Random Forests". Machine Learning. 45 (1): 5-32. doi:10.1023 / A:1010933404324). Random forest predictors are powerful machine learning algorithms that can handle large datasets with high-dimensional features, such as DNA methylation data. They work by constructing multiple decision trees based on random subsets of data and features, and then combining their predictions to obtain more accurate and robust results. In the context of screening for specific CpG sites for CHO cell line engineering, random forest predictors can be trained on a set of labeled samples with known phenotypes (e.g., high or low yield, growth rate or viability). The input feature is the methylation level of CpG sites throughout the genome, and the output is the predicted phenotype for each sample. By analyzing the importance scores of various CpG sites in the random forest model (page 2 / 14 of the manual, CN 122249858 A), the sites with the most informative and discriminative power for phenotype prediction can be identified.

[0012] The biomarkers described in any aspect of the present invention can also be called "CHO ​​methylation clocks," which can establish the correlation between the target phenotype expressed by CHO cells and the DNA methylation pattern. Using the method described in any aspect of the present invention, CHO cells can be classified based on their methylation patterns and the target phenotypes they express or are expected to express.

[0013] The term "biomarker" as used herein refers to a natural feature that can be used to identify a specific pathological or physiological process in CHO cells. Specifically, the biomarker refers to a feature that can be used to identify a target phenotype in CHO cells, especially a DNA methylation pattern. Therefore, a biomarker used to identify a target phenotype in CHO cells refers to a specific CpG site with a corresponding weight coefficient as a parameter. The biomarker for the first target phenotype refers to the first group of specific CpG sites with corresponding weight coefficients. The biomarkers for the second target phenotype refer to the second group of specific CpG sites, each with a corresponding weighting coefficient. The biomarkers for the third, fourth, and subsequent target phenotypes refer to the specific CpG sites of the third, fourth, and subsequent groups, respectively, each with a corresponding weighting coefficient. Multiple biomarkers can be integrated to obtain a biomarker set to determine a series of target phenotypes in CHO test cells. Specifically, the specific CpG site set is determined from all CpG sites in CHO cells based on the methylation values ​​measured in step (a), using any DNA methylation detection method known in the art.More specifically, the specific CpG sites are obtained based on screening for reliable methylation values ​​(i.e., the methylation values ​​of the specific CpG sites are consistent and reproducible using any methylation detection method known in the art). When DNA methylation is measured multiple times using the same method, the specific CpG site group yields the same or highly similar methylation values. Therefore, the CpG sites produce consistent and reproducible methylation value readings.

[0014] Steps (b) and (c) of any aspect of the invention can be performed by a person skilled in the art via a computer.

[0015] As used herein, the term “CHO cell genome” refers to the genomic DNA of a CHO cell, excluding the DNA of viruses (especially CMV and SV40) used to introduce exogenous DNA into the cell. Specifically, a CHO cell genome may refer to a cell with a genome structure that is naturally visible in the wild. The term may also include genes added to the CHO genome through genetic modification (e.g., for purposes such as improving protein production), but may not include, and may not exclude, viral genes and promoters used to introduce genes into the CHO genome. Therefore, the term "CHO ​​cell genome" may exclude viral genes and promoters, and / or may include endogenous or homologous genes of CHO cells and / or genetically modified endogenous or homologous genes of CHO cells, and / or intergenic genes (i.e., DNA located between CHO cell genes).

[0016] The CHO cell line refers to an immortalized Chinese hamster ovary cell line (CHO) derived from the Chinese hamster (Cricetulus griseus). Specifically, the CHO cell line may be selected from the following group: CHO-K1 (ATCC), CHO-DG44 (Thermo Fisher Scientific), CHO-DXB11 (ATCC), ExpiCHO-S™ cells (Thermo Fisher Scientific), FreeStyle™ CHO-S™ cells (Thermo Fisher Scientific), CHO 1-15500 (ATCC), and Agarabi CHO (ATCC).

[0017] As used herein, the term “CHO cell population” refers to a plurality of CHO cells used as reference CHO cells, which exhibit at least one target phenotype. Different CHO cells expressing the target phenotype are then used to determine different CpG sites that are typically methylated, thereby determining a methylation pattern or reference methylation map of the first target phenotype. In one example, different CpG sites are collected from multiple CHO cells, each exhibiting the first target phenotype, to obtain a reference methylation map of the first target phenotype or a biomarker of the first target phenotype.Therefore, the reference methylation map described in any aspect of this invention is not a natural methylation map derived from a single CHO cell, but rather an artificial map obtained by combining relevant CpG sites from different reference CHO cell lines (each exhibiting at least one target phenotype). A population of CHO cells is considered representative of the first target phenotype, and the methylation pattern of each CHO cell constituting the first target phenotype population forms part of a training sample used to generate a biomarker for the first target phenotype. In one example, different CpG sites are collected from a single reference CHO cell exhibiting at least one target phenotype. In another example, different CpG sites are collected from multiple CHO cells, each exhibiting at least one target phenotype. The reference map can be determined from multiple training samples using multivariate statistical methods (e.g., principal component analysis or multidimensional scaling).

[0018] As used herein, the term "target phenotype" in relation to CHO cells refers to cells exhibiting at least one characteristic selected from the group consisting of: optimal heterologous protein production, phenotypic homogeneity, protein quality, optimal carbohydrate metabolism, optimal amino acid metabolism, optimal lipid metabolism, optimal cell viability, and combinations thereof. Specifically, a target phenotype refers to the characteristics exhibited by CHO cells according to any aspect of the invention that are conducive to cell viability, suitable for protein production, and enhance overall cellular protein production levels. All these phenotypes can be used collectively to classify CHO cells and determine their suitability for protein production. The more target phenotypes a CHO cell is predicted to express or is classified as, the more suitable it is for heterologous protein production and for larger-scale protein production.

[0019] As used herein, the term "fitness" refers to a CHO cell line suitable for achieving optimal heterologous protein production. In one example, the suitability of CHO cells for optimal heterologous protein production can be determined before the transgene is introduced into the cells. In this case, the CHO cells may possess at least one target phenotype or characteristic that enables them to grow well, readily take up the target transgene, and achieve optimal heterologous protein production after taking up the transgene, wherein the protein is a product of the target transgene. These characteristics or target phenotypes include at least: optimal glucose consumption, growth rate, lactate production, ammonia accumulation, etc. When it is confirmed that the CHO cells exhibit at least one of the above-mentioned target phenotypes, it can be determined that the cells are suitable for optimal heterologous protein production when the target transgene is introduced.

[0020] In another example, it can be determined whether the CHO cells are suitable for optimal heterologous protein production after the transgene is introduced into the cells.In this case, CHO cells are genetically modified using methods known in the art to introduce transgenes, the genetically modified cells being able to achieve optimal heterologous protein production, wherein the protein is the translation product of the transgene. The CHO cells in this example may have at least one target phenotype, enabling the genetically modified cell line to have good viability and optimal target protein productivity. These target phenotypes may include: cell viability (survival rate), protein productivity (in terms of protein yield and quality), phenotypic uniformity, cell exhaustion, etc. Therefore, the methods described in any aspect of the present invention can be used with genetically modified (i.e., transgenes have been introduced into the cells) CHO cells, or with unmodified CHO cells. In both cases, the CHO cells can be used for heterologous protein production.

[0021] As used herein, the term "transgene" refers to a gene that is taken from the genome of one organism and inserted into the genome of another organism through artificial gene-modification techniques. For example, a human gene is artificially introduced into the genome of a CHO cell for the production of at least one target protein, particularly a therapeutic protein.

[0022] As used herein, the term "therapeutic protein" refers to a genetically engineered version of a natural human protein. Examples of therapeutic proteins include: antibody-based drugs, anticoagulants, coagulation factors, bone morphogenetic proteins, engineered protein scaffolds, enzymes, growth factors, hormones, interferons, interleukins, etc.

[0023] The term “cell viability” as used herein refers to the ability of a cell to remain viable and proliferate. Cell viability is a measure of the proportion of live cells in a cell population. Cell proliferation refers to the increase in the number of cells due to cell division. Commonly used methods for detecting cell viability include: BrdU cell proliferation assay, MTT cell proliferation assay, trypanosome cyanocyte count, and ATP cell viability assay.

[0024] The term “cell exhaustion” as used herein refers to a state in which cells lose the ability to perform metabolic activities (including the production of heterologous proteins). Cell exhaustion can be determined by metabolite detection methods.

[0025] The term “phenotypic homogeneity” as used herein refers to a state in which all cells in a cell population exhibit the same phenotype under specific conditions. Instruction manual, page 4 / 14, CN 122249858 A

[0026] As used herein, the term "heterologous protein production" refers to the production of non-cellular endogenous proteins, i.e., the expression of genes not naturally expressed in host CHO cells, especially transgenic proteins. Commonly used quantitative assays for heterologous protein production include: enzyme-linked immunosorbent assay (ELISA), chromatography, and bioprocess analyzers.

[0027] As used herein, the term "host cell" refers to the cellular system used for heterologous protein expression. For example, CHO cells are the primary host for the production of various therapeutic proteins.

[0028] As used herein, the term "optimal heterologous protein production" refers to the ability of CHO cells to produce proteins at high levels, especially during the industrial or large-scale production of recombinant proteins, where the proteins are typically functional proteins not naturally present in wild-type CHO cells. Specifically, to achieve optimal heterologous protein production, CHO cells exhibit minimized metabolic burden and cytotoxicity. More specifically, "optimal heterologous protein production" refers to high-level protein production, wherein CHO cells not only produce high levels of the target protein but also maintain protein production throughout the entire production period (i.e., the extended culture period), thereby ensuring consistent and stable quality of the produced protein. Specifically, for CHO cells to achieve "optimal heterologous protein production," they must exhibit at least one or more of the following target phenotypes: phenotypic homogeneity, protein productivity, and protein quality. More specifically, to achieve "optimal heterologous protein production," CHO cells may possess phenotypic homogeneity and protein productivity, or phenotypic homogeneity and protein quality, or protein productivity and protein quality, or phenotypic homogeneity, protein productivity, and protein quality.

[0029] As used herein, the term “protein productivity” refers to the amount of protein produced per living cell at a single titer point. It is calculated by dividing the titer (mg) by the living cell density (VCD, or cells / mL), with the final measurement expressed as the amount of protein per cell (mg / cell).

[0030] The term “protein mass” refers to post-translational modifications that determine protein efficacy and function. These modifications typically include phosphorylation, glycosylation, ubiquitination, methylation, acetylation, protein folding, etc. For example, protein glycosylation is a key quality attribute regulating the efficacy, stability, and half-life of therapeutic proteins. Protein mass can be determined using immunoprecipitation-based techniques, biochemical assays, mass spectrometry (MS), etc.

[0031] As used herein, the term “carbohydrate metabolism” refers to almost all or all of the biochemical processes within cells responsible for the generation, breakdown, and interconversion of carbohydrates. This involves multiple pathways, such as glycolysis, gluconeogenesis, glycogenolysis, and glycogen synthesis. For example, glycolysis is one of the key metabolic pathways in CHO cells. CHO cells consume glucose as their primary carbon source to generate energy through glycolysis, producing lactic acid as the most common metabolic byproduct. Specifically, "optimal carbohydrate metabolism" refers to the ideal or optimal carbohydrate metabolism that CHO cells can achieve.

[0032] Similarly, the term "amino acid metabolism" as used herein refers to all the biochemical processes within CHO cells responsible for the generation, breakdown, and interconversion of amino acids. Amino acids are the basic building blocks of proteins, constituting all proteinaceous substances in cells, including the cytoskeleton, the protein components of enzymes, receptors, and signaling molecules. Furthermore, amino acids are used for cell growth and maintenance.For example, glutamine breakdown is a key metabolic pathway in CHO cells. Glutamine breakdown is the main pathway by which CHO cells absorb organic nitrogen for biomass synthesis while releasing ammonium as a major byproduct. Specifically, the term "optimal amino acid metabolism" refers to the ideal or optimal amino acid metabolic state that CHO cells can achieve.

[0033] The term "lipid metabolism" as used herein refers to the synthesis and degradation of lipids in CHO cells, including lipolysis for energy or storage, and the synthesis of structural and functional lipids. Lipids are the main components of cell membranes and act as second messengers in cell communication, participating in signal transduction, transport, and secretion. Lipids can also serve as an important energy source through β-oxidation and the tricarboxylic acid (TCA) cycle. Lipid metabolism can significantly affect cell growth. For example, the synthesis and degradation of triglycerides in CHO cells can greatly affect overall cell metabolism and survival. Specifically, the term "optimal lipid metabolism" refers to the ideal or optimal lipid metabolic state that CHO cells can achieve. Specification 5 / 14 pages 8 CN 122249858 A

[0034] Carbohydrate, amino acid and lipid metabolism can be determined by metabolite detection, HPLC and bioprocess analyzer. These methods are disclosed at least in Coulet, M. et al. (Cells, 2022, 11, 1929), Fan Y et al. (Biotechnol Bioeng, 2015, 112 (3):521-535) and Ali AS et al. (Biotechnol J, 2018, 13 (10):e1700745).

[0035] Specifically, the target phenotype described in any aspect of the present invention is selected from the group consisting of: phenotypic homogeneity, protein mass, optimal carbohydrate metabolism, optimal amino acid metabolism, optimal lipid metabolism, optimal heterologous protein production, optimal cell viability and combinations thereof.

[0036] In the context of this invention, the term "methylation value" refers to the average methylation value of at least one cytosine (C) residue within a CHO cell genomic DNA sequence. Both β and M values ​​can be used as indicators of (average) methylation levels. The M value has higher statistical validity in analyses of differences in methylation levels. The β value is more biologically interpretable, and it needs to be reported simultaneously when using the M value method for differential methylation analysis. The methylation value of CpG sites or DNA regions with multiple CpG sites can be determined using any method known in the art. In one example, DNA methylation values ​​were determined using a bead-based DNA methylation array.

[0037] The term "methylation rate" refers to the number of methylated cytosine residues at a specific site divided by the total number of cytosine residues covered.The methylation rate of CpG sites in step (b) can advantageously be determined using hydrothionite sequencing.

[0038] The term “CpG site read coverage” should be understood as the number of sequencing reads aligned to known CpG sites in a reference sequence. The methylation rate and read coverage of genomic CpG sites in step (a) can be determined using hydrothionite sequencing. In one example, hydrothionite sequencing is used in step (a) to determine the methylation rate and read coverage of CpG sites; hydrothionite sequencing is used in step (b) and the specific CpG site set is determined by truncation values.

[0039] Step (b) of the first aspect of the invention may include a hydrothionite conversion process.

[0040] Hydrothionite treatment of genomic DNA (which is used interchangeably with the term “hydrothionite modification”) refers to the treatment of genomic DNA with a deamination agent (e.g., hydrothionite), which can be used to treat all DNA, regardless of whether it is methylated. Specifically, the term "hydrothionite" as used herein includes any suitable type of hydrothionite (e.g., sodium bisulfite), or other chemical reagents capable of chemically converting cytosine (C) to uracil (U) without chemically modifying methylated cytosine, thus enabling differential modification of DNA sequences based on their methylation state, as described in US 2010 / 0112595. Reagents used herein capable of "differentiating" methylated or unmethylated DNA include any reagent capable of modifying methylated and / or unmethylated DNA through processes that produce distinguishable products, thereby enabling the identification of DNA methylation status. Such processes may include, but are not limited to, chemical reactions (e.g., hydrothionite-mediated C to U conversion) and enzymatic treatments (e.g., cleavage by methylation-dependent endonucleases). Therefore, enzymes that preferentially cleave or digest methylated DNA are more efficient at cleaving or digesting DNA molecules when DNA is methylated; while enzymes that preferentially cleave or digest unmethylated DNA exhibit higher efficiency when DNA is unmethylated.

[0041] Therefore, before performing step (a) of any aspect of the invention, the genomic DNA contained in or obtained from / extracted from the cell is first subjected to hydrothionite treatment.

[0042] Alternative methods known in the art can be used instead of hydrothionite treatment. Those skilled in the art will know which other methods can be used. In one example, TET-assisted pyridinium borohydride sequencing (TAPS) can be used to detect 5mC and 5hmC (Yibin Liu et al., Nature Biotechnology, 37:424-429, 2019).

[0043] Whole-genome bisulfite sequencing is a whole-genome DNA methylation analysis method based on the conversion of genomic DNA with sodium bisulfite, followed by sequencing on a next-generation sequencing platform. The sequences are then re-aligned to a reference genome, and the methylation status of CpG dinucleotides is determined based on mismatches resulting from the conversion of unmethylated cytosine to uracil. Specifically, in step (a) of CN 122249858 A (page 6 / 14 of the specification), bisulfite sequencing is used to determine the methylation rate and read coverage of CpG sites; in step (b), bisulfite sequencing is used and the specific CpG site set is determined by the cutoff value.

[0044] The term "test" used herein in conjunction with the term "cell" refers to cells tested using the methods described in any aspect of the present invention, forming the basis of the analytical applications of the present invention. Therefore, "test cell" refers to CHO cells or a group of CHO cells tested using the methods described in any aspect of the present invention, or a map obtained or generated in this context. Conversely, the term “reference” or “control” refers primarily to a pre-determined object used for comparison with the test subject. Specifically, “test cell” refers to a cell whose methylation status needs to be measured to determine whether it is suitable for optimal heterologous protein production; “control” or “reference” refers to a cell known to exhibit optimal heterologous protein production or its methylation profile.

[0045] As used herein, “CpG site” or “methylation site” refers to a nucleotide in a nucleic acid (DNA or RNA) that is susceptible to methylation, whether by natural in vivo events or by artificial chemical methylation of nucleotides in vitro. Some of these sites in a cell may be hypermethylated, and some may be hypomethylated. In some cases, CpG sites may not be completely hypermethylated or hypomethylated, but rather have a quantifiable level of methylation. Therefore, methylation can be quantified rather than being an absolute hypermethylated or hypomethylated state.

[0046] As used herein, “methylated nucleic acid molecule” refers to a nucleic acid molecule containing one or more methylated nucleotides.

[0047] The training samples associated with the target phenotype of CHO cells in step (a) can be collected, for example, at any stage of CHO cell growth. The samples are always CHO genomic DNA.

[0048] Any machine learning-based model can be used to screen for the most predictive CpG sites, differentially methylated regions (DMRs), low-methylated regions (LMRs), and CpG sites within subsets of these regions for each target phenotype. These specific CpG sites screened by any aspect of the present invention can then be used to develop means of classifying CHO cells into different categories based on the target phenotype and DNA methylation characteristics.

[0049] Specifically, the specific CpG sites described in any aspect of the present invention are distributed within low-methylation regions (LMRs), CpG islands, variable methylation sites, and / or differentially methylated regions (DMRs) in the CHO cell genome.

[0050] A low-methylation region (LMR) refers to a genomic region in which less than 60% of CpG sites are methylated. More specifically, less than 50%, 40%, 30%, 20%, or 10% of CpG sites in an LMR are methylated. LMRs in genomic DNA can be identified or detected using any method known in the art. Known methods include using procedures such as MethylSeekR. Specifically, an LMR in genomic DNA has at least three consecutive CpG sites, and no single nucleotide polymorphism (SNP) is present at any CpG site. More specifically, LMRs in genomic DNA are identified at least according to the methods published by Burger L (Nucleic Acids Research, 2013, 41(16):e155) and / or Stadler M (Nature, 2011, 480, 490-495). Known LMRs have an average methylation level between 10% and 50%; are regions with low CG density that do not overlap with CpG islands; are often rich in H3K4me1, DHS, and p300 / CBP; and / or are primarily located in intergenic regions or at the promoter distal to intron regions. Specifically, LMRs are: - Average methylation levels between 10% and 50%; - Regions with low CG density; - Rich in lysine 4-monomethylated histone H3 (H3K4me1), DNase I hypersensitive sites (DHS), and transcriptional coactivators CREB-binding protein (CPB) and p300; - Primarily located at the promoter distal end of intergenic or intronic regions; and / or - Lacking single nucleotide polymorphisms (SNPs) at any CpG location.

[0051] Low-methylated regions (LMRs) represent key features of the dynamic methylome. LMRs are locally reduced regions in the DNA methylation map, representing CpG-poor distal regulatory regions that typically reflect the binding of transcription factors and other DNA-binding proteins. LMR was first described in mice (Stadler et al., 2011, Nature, 480, 490-95). The evolutionary conservation of LMR outside of mammals has not been studied.

[0052] As used in this paper, “CpG island” refers to a DNA sequence that has a functionally or structurally deviated CpG density.For example, Yamada et al. described a set of criteria for CpG islands: a length of at least 400 nucleotides, a GC content greater than 50%, and an OCF / ECF ratio greater than 0.6 (Yamada et al., 2004, Genome Research, 14, 247-266). Other researchers use a more lenient definition: a length of at least 200 nucleotides, a GC content greater than 50%, and an OCF / ECF ratio greater than 0.6 (Takai et al., 2002, Proc. Natl. Acad. Sci. USA, 99, 3740-3745). In the context of this invention, the terms "methylation map," "methylation pattern," and "methylation state" are used to describe the methylation status, condition, or state of a genomic sequence, referring to the methylation characteristics of a DNA fragment at a specific genomic locus. Such features include, but are not limited to: the presence of methylated cytosine (C) residues within the DNA sequence, the location of methylated C residues, the proportion of methylated C residues within a specific residue fragment, and allele methylation differences due to, for example, different allele origins.

[0053] Differentially methylated regions (DMRs) refer to genomic regions with different methylation states among multiple biological samples (such as tissues, cells, individuals, etc.). These are genomic regions with phenotypic differences. Statistical power may be higher when adjacent differentially methylated sites (DMPs) are combined as a whole for analysis (Gu H et al., 2010, Nat Methods, 7:133-6). The length of DMRs can range from hundreds to thousands of bases (Rakyan et al., 2011, Nat Rev Genet, 12:529-41; Bock C, 2012, Nat Rev Genet, 13:705-19).

[0054] DMRs can be distributed throughout the genome, but are particularly identified near gene promoter regions, intragenetic regions, and intergenetic regulatory regions. There are two types of regions: predefined and user-defined. Regions with special biological significance (e.g., CpG islands, CpG shores, UTRs, etc.) belong to predefined regions. Many traditional statistical tests (including t-tests and Wilcoxon rank-sum tests) can be performed at the region level. For user-defined regions, they can be determined based on criteria such as fixed region length, a fixed number of significantly adjacent CpG sites, and significant and smooth evaluation effect size.

[0055] Partially methylated domains (PMDs) are extended regions in the genome that exhibit a reduced average DNA methylation level. They cover gene-poor and transcriptionally inactive regions and tend to form heterochromatin.

[0056] Differentially methylated sites (DMPs) refer to CpG sites with different DNA methylation states among different biological samples, and are considered as potential functional regions involved in gene transcription regulation.

[0057] Specifically, steps (a)-(c) of any aspect of the present invention are repeated for the second target phenotype and subsequent target phenotypes, so that each target phenotype corresponds to at least one biomarker, thereby generating a set of biomarkers for different target phenotypes.

[0058] Specifically, the biomarkers of any aspect of the present invention are a set of specific CpG sites, corresponding weight coefficients, and intercepts of linear model equations associated with the first target phenotype. Therefore, the set of biomarkers refers to multiple biomarkers, wherein each biomarker is associated with at least one target phenotype exhibited by CHO cells.

[0059] The minimum coverage cutoff value determined in step (b) can be 10, 9, 8, 7, 6, 5, 4, or 3. Specifically, the minimum coverage cutoff value determined in step (b) can be 3.

[0060] According to another aspect of the present invention, a method for classifying CHO test cells is provided, the method comprising the steps of: (a) determining the DNA methylation level of specific CpG sites in genomic DNA extracted from CHO test cells; and (b) comparing the methylation level of these specific CpG sites in step (a) with the methylation level of the same specific CpG sites in reference CHO cells known to exhibit at least one target phenotype; and (c) deriving the target phenotype expressed by the CHO test cells accordingly; wherein the specific CpG sites and their respective weighting coefficients are parameters of a target phenotype biomarker, and the classification of the CHO test cells is determined by the target phenotype expressed by the CHO test cells.

[0061] Specifically, the biomarkers according to any aspect of the present invention are determined using the method of the first aspect of the present invention.

[0062] The DNA methylation level of any aspect of the present invention can be determined using any method known in the art. In one instance, the commercial Illumina™ platform can be used to determine methylation levels. In another instance, an array of DNA methylation-based microbeads can be used to determine methylation levels.

[0063] The arrays allow for high-throughput and robust methods to determine semi-quantitative / quantitative DNA methylation information from small amounts of extracted target DNA samples. These custom-designed arrays can employ Illumina iScan and Infinium platform technologies or equivalent technologies, for example, each chip can accommodate 100,000 different types of microbeads that can covalently bind DNA methylation probes.Each probe represents a CpG methylation site at the end of the probe sequence. Before hybridization on the array chip, the DNA sample undergoes bisulfite conversion, amplification, fragmentation, precipitation, and resuspension. The DNA hybridizes with microbeads at each CpG site on the chip, allowing for specific detection of methylation changes at each site via single nucleotide extension. This method is particularly advantageous because array-based methods are simple to operate, and array results are accurate and reproducible.

[0064] Furthermore, array technology has a shorter turnaround time compared to conventional sequencing (which can take weeks to generate data). The amount and complexity of the generated data are lower than sequencing, reducing its computational burden. This allows for faster computation to obtain interpretable results from experimental groups. Overall, microarray technology is approximately 10 times faster and 10 times cheaper than conventional sequencing, while still allowing for quantitative detection of methylation levels at specific CpG sites.

[0065] As used herein, the term "array" refers to an intentionally constructed collection of probe molecules prepared by synthetic or biosynthetic methods. Probe molecules in an array may be identical or different from each other. The array can take various forms, such as a soluble molecular library; or a compound library attached to resin beads, a silica chip, or other solid support.

[0066] In particular, the array provides a convenient platform for the simultaneous analysis of a large number of CpG sites, such as at least 2, 3, 4, 5, 6, 7, 8, 9, 10, 50, 100, 500, 1000, 5000, 10,000, 100,000, or more sites or loci. In particular, the array contains multiple different probe molecules that may be attached to a substrate or otherwise spatially distinguished within the array. Examples of arrays that can be used in any aspect of the invention include slide arrays, silicon wafer arrays, liquid phase arrays, bead-based arrays, etc. In one example, the array technology used according to any aspect of the invention combines a miniaturized array platform, high-level multiplexing, and scalable automation for sample handling and data processing.

[0067] In particular, an array according to any aspect of the invention can be an array of arrays (also referred to as a composite array) having multiple individual arrays configured to allow simultaneous processing of multiple samples. Examples of composite arrays and the underlying technology are disclosed in at least US 6,429,027 and US 2002 / 0102578. The substrate of the composite array may include multiple individual array sites, each array site having multiple probes, and physically separated from other measurement sites on the same substrate, such that fluid contacting one array site is prevented from contacting another array site. Each array site may have multiple different probe molecules that are directly attached to the substrate or attached to the substrate via rigid particles within pores (also referred to herein as beads within pores).

[0068] In one example, the array substrate may be a bundle of optical fibers or an array of optical fibers as described in US 6,023,540, US 6,200,737 and / or US 6,327,410. The bundle of optical fibers or the array of optical fibers may have probes attached directly to the fibers or attached by beads. Those skilled in the art will be able to readily determine which substrate is most suitable for the array in any aspect of the present invention. WO2004110246 further discloses other substrates that can be used in the arrays of any aspect of the present invention and methods for attaching beads to the substrate.

[0069] In one example, the substrate surface may have physical modifications to enable probe attachment or create array positions. For example, the substrate surface may be modified to include chemically modified sites that can be used for covalently or non-covalently attaching probe molecules or particles with attached probe molecules. Probes can be attached using any of a variety of methods known in the art, including inkjet printing methods, spotting techniques, photolithography synthesis methods, or printing methods using masks. These techniques are disclosed in more detail in WO2004110246.

[0070] In one example, an array according to any aspect of the invention can be a bead-based array, wherein the beads are associated with a solid support, such as those commercially available from Illumina Corporation (San Diego, California). Bead arrays that can be used in any aspect of the invention can also be in fluid form, such as a fluid flow from a flow cytometer or similar device. Commercially available fluid forms used to distinguish beads include, for example, those used in Luminex Corporation's XMAP™ technology or Lynx Therapeutics Corporation's MPSS™ method.

[0071] The terms “solid support,” “support,” and “substrate” as used herein are used interchangeably and refer to a material or group of materials having a rigid or semi-rigid surface. In many instances, at least one surface of the solid support is substantially flat, although in some instances, it may be necessary to physically separate the synthesis regions of different compounds by means of, for example, pores, raised regions, needles, etched trenches, etc.

[0072] Arrays or microarrays according to any aspect of the invention can be ultra-high density arrays, such as those having about 10,000,000 probes / cm² to about 2,000,000,000 probes / cm² or about 100,000,000 probes / cm² to about 1,000,000,000 probes / cm². High-density arrays according to any aspect of the invention are particularly useful for containing a large number of CpG sites on the array.

[0073] Arrays according to any aspect of the invention can be used to simultaneously or sequentially analyze or evaluate multiple loci as needed.In one instance, multiple different probe molecules may be attached to a substrate or otherwise spatially distinguished in an array. Each probe is typically specific to a particular locus and can be used to distinguish the methylation state of that locus.

[0074] The terms “probe molecule” or “probe” as used interchangeably herein refer to a surface-immobilized molecule that can be recognized by a specific target. Probes used in an array may be specific to methylated alleles at CpG sites, unmethylated alleles at CpG sites, or both, or to methylated alleles at non-CpG sites, unmethylated alleles at non-CpG sites, or both.

[0075] The term “target” as used herein refers to a molecule that has an affinity for a given probe molecule. Targets may be naturally occurring or artificial molecules. Furthermore, they may be used in an unchanged state or as aggregates. Targets may be covalently or non-covalently attached to binding members, directly or through a specific binding substance. Examples of targets that may be used according to any aspect of the invention are methylated and unmethylated CpG sites. The target is sometimes referred to in the art as a reverse probe. The term target as used herein is not intended to create a difference in meaning.

[0076] The term “complementary” as used herein refers to hybridization or base pairing between nucleotides or nucleic acids, such as between the two strands of a double-stranded DNA molecule, or between an oligonucleotide primer and a primer binding site on a single-stranded nucleic acid to be sequenced or amplified. Complementary nucleotides are typically A and T (or A and U), or C and G. Two single-stranded RNA or DNA molecules are considered complementary when the nucleotides of one strand, after optimal alignment and comparison and appropriate insertion or deletion of nucleotides, pair with at least about 80%, typically at least about 90% to 95%, more preferably about 98% to 100% of the nucleotides of the other strand. Perfect complementarity means 100% complementarity in sequence length. For example, a 25-base probe is perfectly complementary to a target when all 25 bases of the probe are complementary to a consecutive 25-base sequence of the target, and there is no mismatch between the probe and the target in probe length. Specification 10 / 14 pages 13 CN 122249858 A

[0077] According to one aspect of the present invention, an in vitro method for predicting the classification of CHO test cells is provided, the method comprising the steps of: a) determining the DNA methylation level of a specific CpG site in genomic DNA extracted from CHO test cells, and b) analyzing the methylation level obtained in step (a) using a machine learning-based model to predict the expression level of a target phenotype in the CHO test cells, wherein the specific CpG site is a parameter of a target phenotype biomarker, and the classification of the CHO test cells is determined by using the method of any aspect of the present invention (i.e., the first aspect).

[0078] According to another aspect of the present invention, an in vitro method for predicting the classification of CHO test cells is provided, the method comprising the steps of: a) determining the DNA methylation level of specific CpG sites in genomic DNA extracted from CHO test cells and multiplying it by their respective weighting coefficients to obtain the weighted methylation rate of those CpG sites; b) analyzing the weighted methylation rate obtained in step (a) using a machine learning-based model to predict the expression level of a target phenotype in the CHO test cells, wherein the specific CpG sites and their respective weighting coefficients are parameters of the target phenotype biomarker, and the classification of the CHO test cells is determined by using the method of any aspect of the present invention (i.e., the first aspect).

[0079] According to another aspect of the present invention, a computer-implemented method for establishing a biomarker for a first target phenotype of a CHO cell population is provided, the method comprising the steps of: (a) inputting the methylation values ​​of all CpG sites in the genomic DNA of a CHO cell population; the CHO cell population expressing a specific target phenotype related to cell fitness and being part of a training sample; (b) identifying and determining specific CpG sites exhibiting consistent and reproducible methylation values ​​from all CpG sites in step (a); and (c) using a machine learning-based model to correlate the CpG methylation levels of the CpG sites obtained in step (a) with the target phenotype; thereby obtaining specific CpG sites with corresponding weight coefficients as parameters, which are used as parameters for defining the first target phenotype biomarker.

[0080] Specifically, the machine learning-based model is a classifier algorithm, selectable from the following group: random forest, decision tree, support vector machine (SVM), K nearest neighbors (KNN), neural network, multilayer perceptron, and Gaussian mixture model.

[0081] According to another aspect of the invention, a computer program loaded into a computer memory is provided, which implements the method according to any aspect of the invention.

[0082] According to yet another aspect of the invention, a tangible computer-readable medium is provided, which contains computer-readable code that, when executed by a computer, causes the computer to perform the method according to any aspect of the invention.

[0083] According to yet another aspect of the invention, the medium according to any aspect of the invention is provided for use in predicting the classification of CHO test cells, wherein the classification of said cells is based on the expression of at least one target phenotype of said cells.

[0084] Unless otherwise stated, all percentages (%) given are mass percentages.

[0085] The embodiments described below are examples of the invention, but are not intended to limit the scope of the invention (which is obvious from the entire specification and claims, pages 11 / 14, CN 122249858 A) to the embodiments specified in the examples.

[0086] Brief Description of the Drawings Figure 1 is a graph showing IgG productivity classified into three groups based on productivity level, with an equal number of samples in each group: low, medium, and high productivity groups.

[0087] Figure 2 is a receiver operating characteristic (ROC) curve plotted using a support vector machine (SVM) for the three productivity groups.

[0088] Examples Example 1: Predicting Specific Productivity Rate (pg / cell / day) from CHO Cells Wet Experiment Method In this experiment, 60 transgenic CHO clones were cultured in basal medium at 37°C, 8% CO2, and a shaking speed of 225 rpm. Sixty transgenic CHO cell lines were selected, including low-yield (specific production rate <10 pg / cell / day), medium-yield (specific production rate 10-20 pg / cell / day), and high-yield (specific production rate >20 pg / cell / day). Culture flasks were seeded at 3E5 viable cells / mL on day 0, with appropriate feed added on days 3, 5, 7, 9, and 11. When glucose dropped below 2 g / L, it was replenished to 6 g / L using 45% glucose. The 60 clones were fed batch cultured for 14 days. Cell counts, cell viability, and specific production rate were measured on day 14, and cell pellet was collected on day 14.

[0089] DNA extraction was performed using the PureLink Genomic DNA Isolation Mini Kit (Invitrogen), including RNase treatment according to the manufacturer's instructions. DNA quantity was measured using the PicoGreen assay, and DNA quality was assessed using NanoDrop (Thermo Scientific) to ensure an A260 / 280 ratio ≤1.8. A small number of samples were then analyzed using automated electrophoresis on TapeStation (Agilent) to ensure that each sample contained high molecular weight DNA.

[0090] Genomic DNA (500 ng) from the samples was sequenced to prepare whole-genome bisulfite sequencing (WGBS) libraries. Sequencing of the libraries was performed by a third party on the NovaSeq platform, generating 125 GB of data per sample with 20X coverage.

[0091] Preprocessing of Whole Genome Bisulfite Sequencing (WGBS) Data using Bioinformatics Methods: Raw WGBS data underwent quality control and then adapter trimming was performed using trim galore (https: / / www.bioinformatics.babraham.ac.uk / projects / trim_galore / ). Paired reads were then mapped to the reference genome [CriGri-PICRH-1.0](https: / / www.ncbi.nlm.nih.gov / assembly / GCF_003668045.3 / ) using Bismark (https: / / www.bioinformatics.babraham.ac.uk / projects / bismark / ). Bismark was also used to perform deduplication and extract the number of reads with methylated CpG and the total number of reads at that position. The methylation ratio was determined by dividing the number of methylated reads by the total number of reads.

[0092] Preprocessing of methylation array data: Custom chip array data processing was performed using R version 4.1.2 and sesame version 1.14.2. The DNA methylation level at each site was calculated as a methylation β value. The β value was defined as methylation signal / (methylation signal + unmethylation signal). It could be calculated using the getBetas function. The SeSAMe procedure (Zhou et al., 2018) was used to generate normalized β values ​​and perform quality control. Low-intensity detection calls and generation (based on p-values) were performed using pOOBAH. Background subtraction based on the out-of-band probe noob (Triche et al., 2013) with normal exponential deconvolution was also implemented, with optional additional crosstalk subtraction. Specification 12 / 14 pages 15 CN 122249858 A

[0093] Model building: A classifier was built to predict phenotypes based on the methylation ratio of each CpG. The classifier was based on a random forest. Hyperparameters of the random forest model, such as the number of trees and maximum depth, were tuned by cross-validation. The model performance was evaluated using predictive scoring metrics, such as accuracy or area under the receiver operating characteristic curve (ROC AUC), to determine the optimal hyperparameters. The classifier was fitted to the full dataset using the fine-tuned hyperparameters. The coefficients or importance of features were analyzed to understand their impact on the phenotype.

[0094] Example 2: Predicting growth status from CHO cells in terms of viable cell density (cells / mL) Wet laboratory method In this experiment, 60 transgenic CHO clones were cultured in fed basal medium at 37°C, 8% CO2, and 225 rpm shaking speed.Sixty transgenic CHO cell lines were included: slow-growing (viable cell density <1E7 cells / mL), medium-growing (viable cell density 1E7–3E7 cells / mL), and fast-growing (viable cell density >3E7 cells / mL). Culture flasks were seeded at 3E5 viable cells / mL on day 0, with appropriate feed added on days 3, 5, 7, 9, and 11. When glucose dropped below 2 g / L, it was replenished to 6 g / L using 45% glucose. The 60 clones were fed batch cultured for 14 days. Cell counts and viability were measured on day 7, and cell pellet was collected on day 7.

[0095] The growth status of the tested CHO cells (in viable cell density (cells / mL)) was predicted using the same DNA extraction, sequencing analysis, and bioinformatics methods as in Example 1.

[0096] Example 3: CHO Cell Culture The cells used in this study belonged to the Humira431 CHO cell line (A*Star BTI), which was derived from CHO DG44 cells modified to express a therapeutic antibody (adalimumab biosimilar). Cells were seeded at 3 x 10⁵ cells / mL in 30 mL of culture medium and placed in 125 mL shake flasks. The culture conditions were maintained at 37°C, 8% CO₂, and shaken at 150 rpm. For fed-batch culture, 10% v / v of glucose-free EX-CELL Advanced CHO Feed 1 (24368C, Merck) was added every other day from day 3 to day 14, and D-(+)-glucose solution (G8769, Merck) was added when the glucose concentration dropped to 2 g / L. From day 3 until the end of the culture, samples were taken from each culture flask daily for cell counting and metabolite analysis. Viable cell density (VCD) was determined using a Vi-CELL BLU analyzer (Beckman Coulter), and metabolite concentrations were measured using a Cedex Bio analyzer (Roche).

[0097] Whole-genome bisulfite sequencing (WGBS): Humira CHO samples were cultured using fed-batch or batch culture, IgG titers were measured, and then whole-genome bisulfite sequencing (WGBS) was performed.

[0098] Bisulfite conversion was performed using the EZ DNA Methylation-Gold™ kit, and library preparation was performed using the VAHTS Universal Pro DNA Library Preparation Kit. Whole-genome bisulfite sequencing (WGBS) was performed using an Illumina NovaSeq 6000.

[0099] Data processing: Raw WGBS data were quality controlled using FastQC, and adapter trimming was performed using TrimGalore.The aligned reads were mapped to the CriGri-PICRH-1.0 reference genome using Bismark, which was also used for deduplication and extraction of the β value for each CpG site. Only samples with more than 10 million CpG sites and a coverage greater than 10 were retained for subsequent analysis.

[0100] To ensure the reliability of the methylation data and its suitability for model building, all samples needed to share the same CpG sites and have sufficient coverage. Therefore, various coverage thresholds were explored to determine the optimal level. A threshold of 10 was chosen based on the balance between its rigor and the retention of a large number of CpG sites as described on pages 13 / 14 of the specification, CN 122249858 A. CpGs associated with culture type were removed to avoid confounding effects, refining the dataset to 543,613 CpG sites in 114 samples suitable for modeling.

[0101] IgG productivity was classified into three groups based on productivity level, with an equal number of samples in each group: low, medium, and high productivity groups (as shown in Figure 1).

[0102] Machine Learning Model Development: Three machine learning classifiers—Random Forest (RF), Logistic Regression, and Support Vector Machine (SVM)—were evaluated to predict results based on the dataset. The implementation and hyperparameter tuning of these models were performed using the SciKit-Learn library, with systematic hyperparameter optimization utilizing GridSearchCV.

[0103] Results: The performance of the three models was evaluated using 5-fold cross-validation, and key metrics such as mean accuracy and mean error rate were calculated. The results are summarized in Table 1.

[0104] The Support Vector Machine (SVM) showed the highest mean accuracy (0.792) and the lowest mean error rate (0.208) among the tested models. To further evaluate the discriminative ability of the SVM model, receiver operating characteristic (ROC) curves were plotted for each class, and the corresponding AUC values ​​were calculated (Figure 2). Figure 2 shows that the SVM model provides robust classification performance, with an AUC of 0.98 for low-class, 0.86 for mid-class, and 0.94 for high-class. These results highlight the model's strong ability to distinguish between different classes.

[0105] Table 1: Model Evaluation Instruction Manual 14 / 14 Page 17 CN 122249858 A Figure 1 Instruction Manual Appendix 1 / 2 Page 18 CN 122249858 A Figure 2 Instruction Manual Appendix 2 / 2 Page 19 CN 122249858 A.

Claims

1. A method for constructing a biomarker for a first target phenotype of CHO cells, the method comprising the following steps: (a) Determine the methylation value of all CpG sites in the genomic DNA of a CHO cell population; the CHO cell population represents the first target phenotype and is part of the training sample; (b) Identify a set of specific CpG sites from the training samples of step (a), wherein the CpG sites have consistent and reproducible methylation values; as well as (c) Use a machine learning-based model to process the methylation values ​​of step (b) and the target phenotype of the training samples; This allows for the acquisition of specific CpG sites with corresponding weighting coefficients, which define biomarkers for the first target phenotype.

2. The method according to claim 1, wherein the machine learning-based model is a classifier algorithm selected from the group consisting of: random forest, decision tree, support vector machine (SVM), K nearest neighbors (KNN), neural network, multilayer perceptron, and Gaussian mixture model.

3. The method according to claim 1 or 2, wherein steps (b) and (c) are performed on a computer.

4. The method according to any one of the preceding claims, wherein steps (a)-(c) are repeated for a second target phenotype and subsequent target phenotypes, such that each target phenotype corresponds to at least one biomarker, to generate a set of biomarkers for different target phenotypes.

5. The method according to any one of the preceding claims, wherein the DNA methylation value is determined using a bead-based DNA methylation array.

6. The method according to any one of claims 1-4, wherein in step (a) thionite sequencing is used to determine the methylation rate and read coverage of CpG sites; and in step (b) thionite sequencing is used to determine the specific CpG site set by cutoff value.

7. The method of claim 6, wherein the minimum coverage cutoff value determined in step (b) is 3.

8. An in vitro method for predicting CHO test cell classification, the method comprising the following steps: a) Determine the DNA methylation level at specific CpG sites in genomic DNA extracted from CHO test cells. b) Analyze the methylation levels obtained in step (a) using a machine learning-based model to predict the expression levels of the target phenotype in CHO test cells. Wherein, the specific CpG site is a parameter of the target phenotypic biomarker, and The classification of the CHO test cells is determined by the target phenotype expressed by the CHO test cells, wherein the biomarker is determined using the method of any one of claims 1 to 7.

9. The method according to any one of the preceding claims, wherein the target phenotype is selected from the group consisting of: phenotypic homogeneity, protein mass, optimal carbohydrate metabolism, optimal amino acid metabolism, optimal lipid metabolism, optimal heterologous protein production, optimal cell viability, and combinations thereof.

10. The method according to any one of the preceding claims, wherein the specific CpG sites are distributed in low methylation regions (LMR), CpG islands, variable methylation sites and / or differential methylation regions in the CHO cell genome.

11. The method according to any one of claims 8 to 10, wherein the DNA methylation level in step (a) is determined using a bead-based DNA methylation array.

12. A computer-implemented method for constructing a biomarker for a first target phenotype of a CHO cell population, the method comprising the following steps: (a) Input the methylation values ​​of all CpG sites in the genomic DNA of a CHO cell population; the CHO cell population expresses a specific target phenotype related to cell fitness and is part of the training sample; (b) Identify and determine specific CpG sites that exhibit consistent and reproducible methylation values ​​from all CpG sites in step (a); as well as (c) Use a machine learning-based model to correlate the CpG methylation level of the CpG sites obtained in step (a) with the target phenotype; This allows for the acquisition of specific CpG sites with corresponding weighting coefficients, which are then used as parameters for defining biomarkers of the first target phenotype.

13. The method of claim 12, wherein the machine learning-based model is a classifier algorithm selected from the group consisting of: random forest, decision tree, support vector machine (SVM), K nearest neighbors (KNN), neural network, multilayer perceptron, and Gaussian mixture model.

Images