Lung adenocarcinoma molecular subtype prediction method and device, medium and program product

Abstract

The invention belongs to the field of intelligent medical treatment, and particularly relates to a lung adenocarcinoma molecular subtype prediction method and device, a medium and a program product. The method comprises the following steps: acquiring gene data of a to-be-detected sample; processing the gene data of the to-be-detected sample to obtain key feature genes; the key characteristic genes comprise NDNF (Neonatal Derived Neonatal Function), CCNA2 or RNASE1; the key feature genes are input into a classifier, and a classification result of the LUAD-C2 subtype or the non-LUAD-C2 subtype is obtained; the cell apoptosis of the LUAD-C2 subtype is high; the cell apoptosis of the non-LUAD-C2 subtype is low. According to the application, two different molecular subtypes are obtained by researching lung adenocarcinoma, and the subtype prediction is realized through the gene expression quantity; the two different subtypes correspond to different cell apoptosis rates.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical treatment, and more specifically, to a method, device, medium and program product for predicting molecular subtypes of lung adenocarcinoma. Background Art

[0002] Lung adenocarcinoma (LUAD) is a common form of non-small cell lung cancer (NSCLC) and accounts for a large proportion of all lung cancer cases. LUAD originates from glandular cells in the lungs that are responsible for secreting mucus and other fluids, and has a complex molecular structure and diverse clinical manifestations. This complexity poses challenges to its diagnosis and treatment. Despite advances in radiotherapy, chemotherapy, and surgical intervention, the complexity of LUAD requires a deep understanding to develop effective treatment strategies, and therefore requires comprehensive research and analysis in this field. The molecular landscape of LUAD is very complex, characterized by a wide range of genetic mutations, gene expression variations, and multiple epigenetic alterations. This heterogeneity not only complicates the understanding of the pathogenesis of the disease, but also poses a major challenge to the development of effective targeted therapeutic strategies. Due to the unique molecular characteristics of each patient's tumor, traditional "one-size-fits-all" treatments are often ineffective. Therefore, there is an urgent need for a comprehensive analysis of the molecular landscape of LUAD. Such an analysis would include the integration of multi-omics data—genomics, transcriptomics, proteomics, and epigenomics—to obtain a holistic view of the disease. This integrative approach is essential to identify specific molecular subtypes of LUAD, understand the underlying mechanisms driving each subtype, and discover potential therapeutic targets.

[0003] Recent advances in multi-omics technologies have ushered in a new era in our understanding of diseases such as LUAD. Multi-omics refers to the collective analysis and integration of datasets from various biological layers, including genomics, transcriptomics, proteomics, and epigenomics. Each of these “omics” layers provides unique insights into the cellular and molecular mechanisms of cancer. Genomics reveals DNA sequence and structural variations, providing a blueprint of gene mutations and changes. Transcriptomics examines RNA and gene expression patterns, providing a dynamic view of gene activity and regulation in response to various conditions. Proteomics delves into the proteome, the entire set of proteins produced, revealing their functions, modifications, and interactions. Finally, epigenomics focuses on epigenetic changes, such as DNA methylation and histone modifications, which affect gene expression without changing the DNA sequence. The integration of these different datasets through multi-omics analysis has enabled a comprehensive understanding of LUAD, which allows researchers to link genomic alterations to changes in gene expression, protein function, and epigenetic modifications, providing a holistic view of cancer biology. This integrated approach has been critical in dissecting the heterogeneity of LUAD as it has revealed the multifaceted interactions and regulatory mechanisms that drive the disease. By integrating multi-omics data, researchers can identify different molecular subtypes of LUAD, explore the underlying mechanisms of the disease, and discover new therapeutic targets. Summary of the invention

[0004] In view of the above problems, the present invention provides a method for predicting molecular subtypes of lung adenocarcinoma, which analyzes the complex molecular landscape of LUAD by integrating various multi-group data sets and promotes the identification of different molecular subtypes. This comprehensive approach uses the complementary insights provided by genomics, transcriptomics, proteomics and epigenomics to provide a more detailed understanding of the heterogeneity of LUAD, understand the case mechanism of the disease, and promote the impact on the prognosis and treatment of the disease.

[0005] The present application (first aspect) discloses a method for predicting molecular subtypes of lung adenocarcinoma, comprising:

[0006] Obtaining genetic data of the sample to be tested;

[0007] Processing the gene data of the sample to be tested to obtain key characteristic genes; the key characteristic genes include: NDNF, CCNA2 or RNASE1;

[0008] The key feature genes are input into a classifier to obtain a classification result of LUAD-C2 subtype or non-LUAD-C2 subtype; the LUAD-C2 subtype tumor cells have high apoptosis; the non-LUAD-C2 subtype tumor cells have low apoptosis.

[0009] Furthermore, the method of obtaining the classifier includes:

[0010] Get the genetic dataset for the training set;

[0011] Clustering the gene dataset to obtain LUAD-C2 subtype and non-LUAD-C2 subtype;

[0012] Differential expression analysis of genes between LUAD-C2 subtype and non-LUAD-C2 subtype was performed to obtain differentially expressed genes;

[0013] Performing feature selection on the differentially expressed genes to obtain key feature genes;

[0014] The key feature genes are input into a machine learning model to obtain a predicted classification result, which is compared with the classification label, and the model is optimized according to the comparison result to obtain the classifier.

[0015] Further, based on the classification result of the LUAD-C2 subtype, the result of the high immune activity TME of the sample cells to be tested is output; based on the classification result of the non-LUAD-C2 subtype, the result of the low immune activity TME of the sample cells to be tested is output.

[0016] Furthermore, the method further comprises: the expression level of NDNF in the LUAD-C2 subtype is high, and the expression level of CCNA2 is low.

[0017] Furthermore, the key characteristic genes also include: CIP2A; the expression level of CIP2A in the LUAD-C2 subtype is low;

[0018] Optionally, the key characteristic gene further includes: MYBL2; the expression level of MYBL2 in the LUAD-C2 subtype is low;

[0019] Optionally, the key characteristic gene also includes: MELK; the expression level of MELK in the LUAD-C2 subtype is low.

[0020] Furthermore, the key characteristic genes also include: CASP-3; the expression level of CASP-3 in the LUAD-C2 subtype is low;

[0021] Furthermore, the key characteristic genes also include: the key characteristic genes also include RNASE1, and the expression level of RNASE1 in the LUAD-C2 subtype is high.

[0022] The second aspect of the present application discloses a prediction system for molecular subtypes of lung adenocarcinoma, comprising:

[0023] Acquisition module: obtains the genetic data of the sample to be tested;

[0024] Feature extraction module: Processing the sequencing data of the sample to be tested to obtain key feature genes; the key feature genes include: NDNF, CCNA2 or RNASE1;

[0025] Prediction module: used to input the key feature genes into a classifier to obtain a classification result of LUAD-C2 subtype or non-LUAD-C2 subtype; the LUAD-C2 subtype has high apoptosis; the non-LUAD-C2 subtype has low apoptosis.

[0026] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the above method.

[0027] A fourth aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0028] A fifth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0029] This application has the following beneficial effects:

[0030] (1) This application obtained two different molecular subtypes through the study of lung adenocarcinoma and achieved subtype prediction through gene expression;

[0031] (2) This application confirmed that LUAD-C2 subtype tumor cells have low viability and high apoptosis through molecular experiments to induce overexpression of key characteristic genes of the subtype;

[0032] (3) Targeted therapy for the subtypes identified in this application is a potential treatment subtype for lung adenocarcinoma. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention;

[0035] Figure 2 is a schematic diagram of a program product provided by the second aspect of an embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0037] Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention;

[0038] Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention;

[0039] Figure 6 The present invention provides a multi-omics integrated consensus subtype of LUAD: (A) Cluster prediction index (CPI, blue dashed line) and gap statistics (red solid line) are plotted to identify the optimal number of clusters from multi-omics data. The elbow method indicates the optimal number of clusters based on the trends observed in these indicators; (B) A comprehensive heat map of the consensus set subtypes, including mRNA, lncRNA, miRNA, DNA CpG methylation sites, and mutant genes; (C) The silhouette plot shows two clusters (C1 and C2) and their silhouette widths, reflecting the clustering confidence; the average silhouette width of 0.6 indicates a reasonable structure in the data set; (D) MUC patients are clustered by 10 cutting-edge multi-omics clustering methods; (E) Consensus clustering matrices of three new prognostic subtypes based on 10 algorithms; (F) The survival outcomes of the two subtypes are different;

[0040] Figure 7 1. A comprehensive molecular characterization and validation of consensus subtypes (CSs) of LUAD provided by an embodiment of the present invention: (A) Heat map showing the enrichment differences of key pathways between two identified subtypes (CS1 and CS2); (B) Heat map showing immune and stromal enrichment scores, as well as immune checkpoint gene expression of the two subtypes; (C) Nearest template prediction (NTP) analysis confirmed that patients in the META-LUAD cohort were divided into CS1 and CS2; (D) Consistency evaluation of CMOIC and NTP classification; (E) Kaplan-Meier survival curves, indicating that there was a significant difference in the overall survival rate between CS1 and CS2; (FG) CMOIC, NTP and PAM classification methods were highly consistent; (H) Bar chart of biological process enrichment analysis associated with each subtype;

[0041] Figure 8It is a comprehensive immune landscape analysis of a cancer patient cohort provided by an embodiment of the present invention: a comprehensive bioinformatics analysis and prediction model of gene importance under multiple conditions; 22 (A) PCA diagram illustrates the distribution of individuals in the datasets GSE31210, GSE50081, GSE68465 and TCGA along the first two principal components; (B) PCA scatter plot visualizes gene expression data, and the ellipse represents the confidence interval that reveals sample grouping and expression profile overlap; (C) Scatter plot of Cox coefficient relative to the negative logarithm of p-value for various factors; the dotted line indicates the threshold of statistical significance; (D) Feature selection frequency waterfall plot according to the selection frequency Genes are ranked, and a color gradient is used to highlight genes that are consistently important across the analysis; (E) Classifier stability plot shows feature importance scores across multiple runs; (F) Model accuracy scatter plot combines beeswax plots and boxplots to compare the predictive accuracy (C-index) of prognostic models; (G) Forest plot shows the hazard ratio and 95% confidence interval of each gene in the survival analysis in the TCGA-LUAD dataset; (H) Boxplot illustrates the distribution of C-index for various models, including CoxBoost and XGBoost; (I) Boxplot illustrates the IBS for various models, including CoxBoost and XGBoost;

[0042] Fig. 9 The present invention provides a comprehensive immune landscape analysis of a cancer patient cohort: (A) a box plot illustrating the relative abundance of infiltrating immune cell types in patients belonging to high-risk and low-risk groups; (B-C) a box plot of the relative expression levels of 27 immune checkpoint profiles between high-risk and low-risk patients; (D) a color-coded scatter plot and box plot showing the distribution of risk scores for treatment response (PR, PD, CR, SD); (E) a bar chart of immune checkpoint inhibitor response; (F) a box plot comparing TIDE scores, IFNG scores, dysfunction scores, exclusion scores, TAM / M2 scores, and MDSC scores between high-risk and low-risk groups;

[0043] Fig.101. A comprehensive analysis of the comparison between high-risk and low-risk LUAD patient groups provided in an embodiment of the present invention: (A) Volcano plot and scatter plot of the correlation coefficient between 3S-MMR score and drug-available mRNA expression in the TCGA-LUAD cohort obtained by Spearman rank correlation analysis; red dots indicate significant positive correlation (p<0.05, Spearman's r>0.2); (B) Volcano plot and scatter plot of the correlation and significance between 3S-MMR score and drug target CERES score; green dots indicate significant negative correlation (p<0.05, Spearman's r<-0.2); (C) Comparison of IC50 values ​​between high and low 3S-MMR score groups of paclitaxel, gemcitabine and cisplatin; (D) Spearman correlation analysis results of CTRP-derived compounds and PRISM-derived compounds; The results of differential drug response analysis between CTP-derived compounds and PRISM-derived compounds showed that the lower the y-axis value of the box plot, the higher the drug sensitivity; Abbreviations: *p<0.05; **p<0.01; ***p<0.001;

[0044] Fig.11 is a comprehensive analysis of LUAD molecular subtypes and immune landscapes provided by an embodiment of the present invention: (A) a radar chart comparing the molecular features of high-risk (HR) and low-risk (LR) LUAD patients; (B) a heat map showing the expression patterns of numerous genes in multiple patient samples, using hierarchical clustering to group similar profiles; (C) a heat map of immune-related gene expression, showing that HR patients had higher levels of inhibitory checkpoints and lower HLA gene expression;

[0045] Fig.12 The present invention provides a multifaceted analysis of gene networks, immune cell interactions, and expression variability in LUAD: (A) GeneMANIA network visualization depicting the functional network of selected genes; (B) correlation matrix describing the relationship between various immune cells and their functional states; (C) correlation matrix of key LUAD-related genes; (D) correlation plot of gene expression levels and immune infiltration scores; (E) mutation frequency plot of LUAD samples with key gene mutations;

[0046] Fig.13An insight into single-cell data and gt activity provided by an embodiment of the present invention: (A) Cell populations were divided into 32 clusters; (B) Samples were annotated into 12 unique cell types in the TME using UMAP; (C) Expression profiles of cell typing marker genes; (D) Expression levels of various genes (AURKB, CDK1, CDKN3, CDT1, CHEK1, DLGAP5, EXO1, FOSL1, KRT6A) in different cell types, including T cells, NK cells, epithelial cells, macrophages, monocytes, fibroblasts, mast cells, endothelial cells, plasma cells, and plasmacytoid dendritic cells (PDCs);

[0047] Fig.14 The present invention provides an embodiment of the role of NDNF in the progression of LUAD and its potential as a therapeutic target: (A) quantitative PCR analysis of CDT1, PLK1, RNASE1 and NDNF expression levels in normal and LUAD samples; (B) Western blot analysis of NDNF protein levels in normal and LUAD tissue samples; (C) quantitative determination of NDNF protein levels in normal and LUAD tissue samples; (D) Western blot analysis confirmed that NDNF expression was reduced in LUAD cells compared with normal lung cells; (E) quantitative determination of NDNF protein levels in normal and LUAD tissue samples; (F) CCK-8 method to evaluate the effect of nndnf overexpression on LUAD cell viability; (G) comparison of apoptosis rates between control (NC) and LUAD cells overexpressing nndnf (OE); (H) Western blot analysis of cleaved Caspase-3, Caspase-3 and NDNF protein levels in control (CT) and LUAD cells overexpressing NDNF (OE); (1) The expression of cleaved Caspase-3 in LUAD cells overexpressing nndnf was significantly higher than that in LUAD cells overexpressing nndnf (OE). Quantitative analysis of Caspase-3 protein levels showed a significant increase in apoptotic markers;

[0048] Fig.15 The difference in gene expression between a LUAD-C2 subtype and a non-LUAD-C2 subtype provided in an embodiment of the present invention; AF respectively show the expression differences of NDNF, MYBL2, MELK, CIP2A, CCNA2, and CASP3;

[0049] Fig.16The ROC curves of several LUAD-C2 subtype prediction models provided in the embodiments of the present invention are as follows: Figure A is the ROC curve of the training set predicted by NDNF and CCNA2, and the AUC values ​​from top to bottom respectively represent the accuracy of NDNF and CCNA2 prediction alone and in combination; Figure B is the joint prediction curve and AUC value of the training set NDNF+CCNA2+MYBL2; Figure C is the joint prediction curve and AUC value of the training set NDNF+MYBL2+CCNA2+MELK; Figure D is the ROC curve of the validation set predicted by NDNF and CCNA2, and the AUC values ​​from top to bottom respectively represent the accuracy of NDNF and CCNA2 prediction alone and in combination; Figure E is the joint prediction curve and AUC value of the validation set NDNF+CCNA2+MYBL2; Figure F is the joint prediction curve and AUC value of the validation set NDNF+MYBL2+CCNA2+MELK. DETAILED DESCRIPTION

[0050] 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.

[0051] 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 executed in parallel. The sequence numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the sequence 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., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0053] Figure 1 1 is a flow chart of a prediction method based on evaluating the molecular subtypes of lung adenocarcinoma provided by an embodiment of the present invention. Specifically, the method comprises the following steps:

[0054] S101: Obtaining genetic data of a sample to be tested;

[0055] S102: Processing the sequencing data of the sample to be tested to obtain key characteristic genes; the key characteristic genes include: NDNF, CCNA2 or RNASE1:

[0056] S103: Inputting the key feature genes into a classifier to obtain a classification result of LUAD-C2 subtype or non-LUAD-C2 subtype; the LUAD-C2 subtype has high apoptosis; the non-LUAD-C2 subtype has low apoptosis.

[0057] In some embodiments, we combined mRNA, long noncoding RNA (lncRNA) and microRNA (miRNA) expression profiles, genomic mutations and epigenomic DNA methylation data to develop an integrated consensus subtype of LUAD using 10 multi-omics integration strategies.

[0058] In this study, we used the Multi-Omics Integration and Visualization in Cancer Subtype Analysis (MOVICS) package to filter gene signatures through the "getElites" function. For continuous variables (mRNA, lncRNA, miRNA, and methylation), we set the "method" parameter of the "getElites" function to "mad" to filter the top 1500 genes with the highest degree of variation.

[0059] Then, 7 machine learning algorithms including CoxBoost, Elastic Net (Enet), Lasso, Cox Partial Least Squares Regression (plsRcox), Ridge, Supervised Principal Component (SuperPC), and eXtreme Gradient Boosting Survival (XGBoost) were benchmarked. The hyperparameters of each algorithm were tuned using internal 5-fold CV, and the performance of the best tuned model was evaluated using external 10-fold CV. Finally, the best model algorithm was determined by comparing the average values ​​of Harrell's Concordance Index (C-index) and Integrated Brier Score (IBS) of 10 test folds.

[0060] Immune cell infiltration analysis and immunotherapy response prediction: We used 7 algorithms (“CIBERSORT”, “MCPcounter”, “EPIC”, “ESTIMATE”, “TIMER”, “quanTIseq”, “IPS”) to estimate the infiltration level of immune cells in the tumor microenvironment and visualized it through “complex heatmap”. Specifically, we used the R package CIBERSORT and the single-sample gene set enrichment analysis (ssGSEA) algorithm to determine the distribution of immune cell types and the enrichment score of each immune cell between the high-risk and low-risk groups. In addition, the expression levels of several important immune checkpoint genes between the two different score groups were compared. The Tumor Immune Dysfunction and Exclusion (TIDE) algorithm was originally used to evaluate potential differences in treatment response between high-risk and low-risk groups. Higher TIDE scores indicate reduced efficacy, emphasizing the negative correlation between TIDE scores and treatment efficacy.

[0061] Functional enrichment analysis To identify specific biological pathways enriched in different clusters, we performed a comprehensive analysis. We used the R package CIBERSORT and the single-sample gene set enrichment analysis (ssGSEA) algorithm to determine the distribution of immune cell types and the enrichment score of each immune cell between the high-CMLS and low-CMLS groups. In addition, the expression levels of some important immune checkpoint genes between the two different risk groups were compared. Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis was also performed to elucidate the functions of the selected core genes.

[0062] Cluster Analysis: The clustering process is guided by two main metrics: the Cluster Prediction Index (CPI) and the Gap Statistics. The CPI is used to assess the internal consistency and separation between potential clusters, providing a quantifiable measure of cluster quality based on the within-cluster variance relative to the between-cluster variance. On the other hand, the Gap Statistics compares the log-transformed within-cluster sum of squares for different values ​​of k to the expected value under the null reference distribution of the data.

[0063] Determine the number of clusters: Use the silhouette plot and the Gap Statistics to determine the optimal number of clusters. Silhouette analysis involves calculating a score for each sample in a cluster that measures how similar that sample is to samples in its own cluster compared to samples in other clusters. This measure ranges from -1 to 1, with high values ​​indicating that the sample matches its own cluster well and matches neighboring clusters poorly. The silhouette plot provides a visual representation of how each cluster is distinguished from the others, which helps determine the most coherent and unique cluster solution. These findings are further corroborated by the Gap Statistics, which provide a statistical basis for choosing the number of clusters that best captures the inherent groupings in the data.

[0064] Clustering Algorithms: To robustly cluster multiple sets of data, ten advanced clustering methods were used, each of which can effectively handle the complexity and dimensionality of the data. These methods include K-means, Hierarchical Clustering, Gaussian Mixture Model (GMM), DBSCAN, Spectral Clustering, Affinity Propagation, Agglomerative Clustering, BIRCH, Mean Shift, and CURE. Each algorithm uses a unique approach to group the data: K-means partitions the data into K clusters based on centroids; Hierarchical builds nested clusters by stepwise merging or splitting; GMM models clusters as a mixture of Gaussian distributions; DBSCAN groups densely packed points and marks outliers in low-density areas. The selection was based on each method's ability to discover nonlinear patterns and handle different cluster sizes, shapes, and densities. These methods were evaluated based on their performance metrics, such as silhouette score and Davies-Bouldin index, to ensure that the final clustering results are statistically valid and meaningful for subsequent biological interpretation.

[0065] Subtype identification and validation: Consensus clustering was used to integrate the results of multiple clustering algorithms and enhance the robustness and reproducibility of identifying subtypes. This method uses a consensus clustering matrix to aggregate clustering results from different methods, where each entry in the matrix represents the proportion of algorithms that assign the same pair of samples to the same cluster. Therefore, the consensus matrix provides an intuitive and quantitative measure of consistency between various methods, highlighting consistent groupings. The final subtypes were determined based on the stability of clustering across algorithms, as demonstrated by high consensus values ​​and low variability, ensuring that the selected clusters represent true underlying biological patterns rather than the artifacts of any single clustering technique.

[0066] Validation Methods: The identified LUAD subtypes were validated using external cohorts (META-LUAD and IMvigor-LUAD) to confirm their generalizability and robustness. Two main approaches were used: nearest template prediction (NTP) and prediction analysis by microarray (PAM). NTP involves comparing the molecular features of new samples with predefined template features representing each subtype to assign the most similar template to each sample. PAM, on the other hand, uses a class prediction strategy based on gene expression data to classify new samples into one of the established subtypes. These approaches were critical to demonstrate that the subtypes not only hold true in the original TCGA cohorts, but also retain their prognostic relevance and unique molecular features in different and independent patient populations. Statistical metrics such as classification accuracy, sensitivity, and specificity were calculated to evaluate the performance of subtype assignment in these validation cohorts.

[0067] Immune microenvironment analysis: To assess immune cell infiltration in the tumor microenvironment, several computational tools were used, each providing unique insights into the composition and function of immune cells in the context of LUAD. CIBERSORT was used to deconvolute the cellular composition of complex tissues based on gene expression data to estimate the relative proportions of immune cell types within the tumor. MCPcounter uses a set of marker genes unique to each cell type to estimate the abundance of various immune and stromal cell populations, providing quantification of these cells in tumor samples. TIMER uses a similar approach but emphasizes the impact of tumor purity, thereby adjusting the infiltration score to more accurately reflect the true immune landscape. Finally, quantISEQ was applied to specifically quantify tumor-infiltrating lymphocytes using a machine learning model trained with digital cytometry data.

[0068] Analysis of differential expression of immune checkpoint genes: The researchers analyzed the expression of immune checkpoint genes to understand their differential regulation between the identified molecular subtypes. Immune checkpoint genes play a key role in regulating immune responses. Using RNA-Seq data, the expression levels of key checkpoint genes such as PD-1, CTLA-4, and LAG-3 were quantified. Statistical tests, including analysis of variance and post hoc Tukey tests, detected significant differences in expression between subtypes. This analysis was complemented by related studies that linked expression patterns to clinical data such as treatment response and survival outcomes. In addition, visualization of the data using box plots and heat maps helped to intuitively understand the expression changes of checkpoint genes in different subtypes. This analysis not only highlights the potential mechanisms of immune evasion, but also proposes targeted treatment strategies based on the specific immune profiles of different LUAD subtypes to improve the efficacy of immunotherapy.

[0069] Single-cell RNA sequencing and data analysis: LUAD and adjacent normal tissue samples were collected from surgical patients. Fresh tissue samples were immediately dissociated into single cells using enzymatic digestion according to established protocols. Single-cell suspensions were filtered to remove cell debris, and then cell viability was assessed using trypan blue staining. Cells with a viability of >85% were used for subsequent analysis.

[0070] Single-cell RNA sequencing libraries were prepared using the 10x Genomics Chromium platform according to the manufacturer's instructions. Single cells were captured in droplets, and barcoded mRNA was reverse transcribed to generate cDNA libraries. Sequencing was performed on the Illumina platform, generating paired-end reads with an average depth of 50,000 reads per cell.

[0071] The raw sequencing data were processed using the Cell Ranger pipeline (v.3.1, 10x Genomics), reads were aligned to the human reference genome (GRCh38), and a gene expression matrix was generated. Low-quality cells with fewer than 200 detected genes or cells with >10% mitochondrial gene content were excluded from the analysis. Genes expressed in fewer than three cells were also removed.

[0072] After normalization and logarithmic transformation of expression data, highly variable genes were selected for downstream analysis. Principal component analysis (PCA) was used for dimensionality reduction, and the optimal principal components were selected for clustering. Cells were clustered using the Seurat R software package (v.3.1) based on the Louvain algorithm. Uniform manifold approximation and projection (UMAP) was used to visualize the clustering results.

[0073] Clusters were annotated by comparing the differentially expressed genes (DEGs) in each cluster with known cell type markers from published literature. The identified cell types included T cells, B cells, NK cells, epithelial cells (Epi), macrophages (Mac), monocytes (Mon), fibroblasts (Fib), dendritic cells (MDC), mast cells (mast), plasma cells (plasma), endothelial cells (Endo), and plasmacytoid dendritic cells (PDC).

[0074] Cell culture: Normal lung cells and LUAD cell line A549 cells were cultured in Dulbecco's Modified Eagle Medium (DMEM) supplemented with 10% fetal bovine serum and 1% penicillin-streptomycin. Cells were maintained at 37°C in a humidified atmosphere containing 5% CO2. The medium was changed every 2-3 days, and cells were passaged at about 80-90% confluence using trypsin-EDTA solution for detachment.

[0075] qPCR analysis: Total RNA was extracted from cell samples using an RNA extraction kit. RNA was then reverse transcribed into cDNA using a reverse transcription kit. Quantitative PCR (qPCR) was performed using specific primers for nndnf and SYBR Green master mix. GAPDH was used as an internal control and the relative expression of NDNF was calculated using the 2^-ΔΔCt method.

[0076] Western Blot Analysis: Proteins were extracted from cell samples using lysis buffer. The extracted proteins were separated by SDS-PAGE and transferred to a PVDF membrane. The membrane was then probed with an anti-ndnf primary antibody and then incubated with an enzyme-labeled secondary antibody. Protein bands were visualized using an enhanced chemiluminescence (ECL) detection system, and relative protein levels were quantified using image analysis software.

[0077] Adenoviral Vector Construction: Adenoviral vectors containing the full-length cDNA of NDNF were constructed using standard cloning techniques. The NDNF cDNA was inserted into the adenoviral vector under the control of a strong promoter. A549 cells were then transduced with the adenoviral vector using appropriate transduction reagents. The efficiency of transduction was monitored by the expression of a reporter gene contained in the vector.

[0078] CCK8 Assay: nndnf-overexpressing and control A549 cells were seeded into 96-well plates at a density of 5,000 cells per well. After allowing the cells to adhere and grow for 24 hours, the Cell Counting Kit-8 (CCK8) reagent was added to each well according to the manufacturer's instructions. Incubate at 37°C for 2 hours. The absorbance of each well was measured at 450 nm using a microplate reader. Cell viability was assessed by comparing the absorbance values ​​of nndnf-overexpressing cells with those of control cells.

[0079] Cell cultureNormal lung cell samples and LUAD cell line A549 cells were cultured in Dulbecco's modified Eagle's medium (DMEM) supplemented with 10% fetal bovine serum (FBS) and 1% penicillin-streptomycin. The cells were maintained at 37°C in a humidified atmosphere containing 5% CO2. The culture medium was replaced every 2-3 days, and the cells were detached using trypsin-EDTA solution and passaged at approximately 80-90% confluence.

[0080] qPCR analysis: Total RNA was extracted from the cell samples using an RNA extraction kit. The RNA was then reverse transcribed into cDNA using a reverse transcription kit. Quantitative PCR (qPCR) was performed using specific primers for NDNF and SYBR Green master mix. The relative expression level of NDNF was calculated using the 2^-ΔΔCt method, with GAPDH as an internal reference.

[0081] Western Blot Analysis: Proteins were extracted from the cell samples using lysis buffer. The extracted proteins were separated by SDS-PAGE and transferred to a PVDF membrane. The membrane was then probed with an anti-NDNF primary antibody followed by incubation with an HRP-conjugated secondary antibody. Protein bands were visualized using an enhanced chemiluminescence (ECL) detection system and relative protein levels were quantified using image analysis software. 13. Adenoviral Vector Construction An adenoviral vector containing the full-length cDNA of NDNF was constructed using standard cloning techniques. The NDNF cDNA was inserted into the adenoviral vector under the control of a strong promoter. A549 cells were then transduced with the adenoviral vector using an appropriate transduction reagent. The transduction efficiency was monitored by the expression of a reporter gene contained in the vector.

[0082] CCK8 assay: NDNF-overexpressing and control A549 cells were seeded into 96-well plates at a density of 5,000 cells per well. After allowing the cells to adhere and grow for 24 h, the Cell Counting Kit 8 (CCK8) reagent was added to each well according to the manufacturer's instructions. The plates were incubated at 37 °C for 2 h. The absorbance of each well was measured at 450 nm using a microplate reader. Cell viability was assessed by comparing the absorbance values ​​of NDNF-overexpressing cells with those of control cells. Data were analyzed using GraphPad Prism or similar statistical software. For comparisons between two groups, an unpaired Student's t-test was performed. For multiple group comparisons, a one-way ANOVA was used, followed by a post hoc test, such as Tukey's or Bonferroni's multiple comparison test. A p value of less than 0.05 was considered statistically significant. All experiments were repeated at least three times to ensure reproducibility, and data are presented as mean ± standard error (SEM).

[0083] The analyses described in this study were supported by a comprehensive set of software tools and packages, primarily in the R and Python ecosystems. Various statistical tests were applied to ensure the validity of the results of different types of data analysis: Kaplan-Meier analysis and Cox proportional hazards model: These methods were used to assess survival differences, and the log-rank test was used to compare Kaplan-Meier curves to determine statistical significance. ANOVA and t-test: These were used to compare gene expression between multiple groups, and when significant ANOVA results were found, post hoc Tukey tests were used to adjust for multiple comparisons. Mann-Whitney U and Wilcoxon sign-rank tests: These nonparametric tests were used when the data were not normally distributed and are suitable for comparing two independent or paired groups, respectively. Benjamin-Hochberg procedure: This false discovery rate (FDR) control procedure was used to adjust p-values ​​in the context of multiple hypothesis testing, especially in gene expression and biomarker analysis, ensuring that the possibility of type I errors was minimized.

[0084] Results (1): Multi-omics consensus prognostic-associated molecular subtypes of LUAD were discovered: In our comprehensive analysis of LUAD, multiple omics data types were integrated to identify different molecular subtypes. We independently identified two subtypes from the Molecular Understanding of Cancer (MUC) TCGA LUAD cohort using 10 multi-omics ensemble clustering algorithms. The optimal number of clusters ( Figure 6 A), the contour plot shows that the clusters are well structured and well separated ( Figure 6C). The clustering results were then further combined with different molecular patterns including transcriptome expression (mRNA, lncRNA and miRNA), epigenetic methylation and somatic mutations ( Figure 6 B. Figure 6 D-6E).

[0085] Survival analysis showed a significant difference in overall survival between the two subtypes, with the C1 (CS1) subtype associated with a significantly worse prognosis (p = 0.001). This finding emphasizes the prognostic significance of molecular subtypes, suggesting that patients with the CS1 subtype may require more aggressive or targeted therapeutic interventions compared with patients with the CS2 subtype ( Figure 6 F).

[0086] Delineation of LUAD integrative consensus molecular subtypes: Currently, molecular subtypes are mainly classified based on molecular expression levels, which may be associated with specific biological functions. We used the single sample gene set enrichment analysis (ssGSEA) algorithm to explore the different molecular characteristics of these two CS. The results showed that CS1 was significantly enriched in the cell cycle and DNA replication pathways, while CS2 was significantly enriched in the FGFR3 co-expressed genes, PPARG, and WNTβ-catenin pathways ( Figure 7 A). Tumor immunity plays a vital role in the occurrence and development of tumors. Therefore, we quantified the infiltration level of immune cells in the microenvironment and found that the infiltration of immune cells in CS2 was relatively high ( Figure 7 B).

[0087] Based on differential expression analysis between subtypes, genes upregulated in C1 and downregulated in C2 included: MYBL2, UBE2C, TPX2, SLC2A1, CDC20, BIRC5, TOP2A, ANLN, KIF2C, TNNT1, MELK, CCNA2, CDCA5, FOXM1, TRIP13, HJURP, CEP55, RRM2, TK1, KIF4A, DLGAP5, KIFC1, CCNB1, and MMP12. , AURKB, CENPA, CDCA8, MAGEA3, LYPD3, NEK2, CCNB2, KRT6A, CDKN3, CDC6, CDK1, UCHL1, MKI67, COL11A1, AUR KA, CENPW, GJB2, DSP, HMGA1, PRR11, NDC80, CDC45, NUF2, KIF18B, NCAPG, GCLC, FAM83D, KPNA2, PLOD2, RPL3 9L, PLK1, TROAP, BUB1, UBE2S, TTK, FOSL1, SPAG5, EIF4EBP1, UBE2T, TXNRD1, ZWINT, CENPF, CDT1, PBK, CTHR C1, FAM83A, KIF11, PFN2, MAD2L1, CTSV, KIF23, BUB1B, CXCL10, PIMREG, MAGEA6, ASF1B, RAD51AP1, NCAPH, A RNTL2, MCM2, SERPINB5, KIF20A, CDA, GZMB, CCNE1, RACGAP1, EXO1, SLC16A1, MCM4, SKA1, SKA3, CHEK1, UHRF 1. GJB3, C15orf48, MCM10, GREM1, FSCN1, ORC1, GTSE1, ECT2, STEAP1, IQGAP3, PRAME, HILPDA, HMMR, CIP2A;

[0088] The C2 promoter genes include C16orf89, CACNA2D2, TMPRSS2, CYP4B1, NAPSA, and CFAP221. SELENBP1, ADGRF5, SCNN1B, DLC1, TMEM163, CTSH, SCTR, TMEM125, NFIX, IN MT, SFTPB, SUSD2, SLC22A3, PRDM16, HLF, PLA2G1B, ADH1B, VSIG2, GGTLC1. FCER1A, RNASE1, SCGB3A2, RHOBTB2, PLA2G4F, ABCA3, PIGR, C4BPA, SLC26A 9. SFTPD, B3GNT8, SLC22A31, SFTA2, ST3GAL5, GPRC5C, KCNQ1, C1orf116, V.S EGFD, PGC, PEBP4, ALPL, MFSD2A, FOLR1, RAP1GAP, NPC2, VWA2, PARM1, CAPN 8. LRRK2, C7, FOXA2, CD207, ATP13A4, CDKL2, C9orf152, SLC34A2, BTG2, CX CL17, ROS1, MGP, NKX2.1, SHE, KCNJ15, CPAMD8, GGT6, HSD17B6, MALL, DUOX 1, IRX3, IRX5, IRX2, DRAM1, CRYM, SFTPA1, LMO3, HABP2, CHRDL1, ELN, SFTP A2, C5orf38, LPL, WFDC2, FMO5, WIF1, MFAP4, AQP3, MAOA, CLU, HOPX, DMBT1 AQP4, ZNF750, SCGB3A1, PLA2G10, SLC44A4, GKN2, ACKR1, LAMP3, AHCYL2 MUC1, NDNF, PTPN13, AQP1, SCNN1G, CLDN2, HAS3, CD1A, PPP1R1B, SFTPC, AL OX15B, CYP4X1, ZNF385B, AGER, MLPH, ACSL5, FCGBP, PRR15L, CRTAC1, GJB1 、AGR3、CLIC6、NRGN、CLDN18、SPINK5、FOS、SERPIND1、TPPP3、APOD、AQP5、S T6GALNAC1, ELAPOR1, PCP4L1, GDF15, CREB3L1, CTSE, HLA.DQB2, HPGD, GFR A3, C3, MS4A15, SCGB1A1, CXCL14, SLPI, SPINK1, CEACAM6, HP, CRLF1, MSLN.

[0089] Classifiers were constructed based on the above genes and validated in multiple external cohorts to further verify the stability of the subtypes. The nearest template prediction (NTP) classified each sample in the external cohort into one of the identified CS. Consistent with this, CS2 in the META LUAD cohort had a better prognosis than CS1 (p < 0.005), and the results of other external cohorts were similar ( Figure 7 E). The agreement of CS with NTP, partitioned periventricular medium (PAM), and COMIC algorithms was also evaluated (p < 0.005; Figure 2 D. Figure 2 F-2G). In addition, we performed disease ontology (DO) enrichment analysis on 200 classified genes and found that they were mainly enriched in lung diseases and non-small cell lung cancer, which indirectly verified the validity of the classification ( Figure 7 H).

[0090] In order to continue to select key characteristic genes from the differentially expressed genes between subtypes, continue with the following operations:

[0091] Based on the differentially expressed genes between the subtypes screened, a model was constructed to distinguish two different molecular subtypes.

[0092] Due to the serious batch effects in different cohorts ( Figure 8 A), we first remove the batch effect ( Figure 8 Next, we performed univariate Cox regression analysis in the training cohort and identified 129 genes that were significantly associated with lung adenocarcinoma prognosis (p < 0.05, Figure 8 C). To ensure the robustness of the selection, we first used the bootstrap method to All patients were sampled 1000 times, and 88 genes with p < 0.05 that were sampled more than 500 times were retrieved ( Figure 8 D) Then, I Based on the Boruta algorithm, we compared the importance of selected features and random features and previous literature research and retained 18 Genes considered to be more relevant to prognosis ( Figure 8 E-8G, as shown in Table 1) to construct a predictive model for molecular typing. To build accurate and stable models, seven machine learning algorithms were benchmarked in the TCGA-LUAD cohort by nested cross-validation (CV). Specifically, we tuned the hyperparameters of each algorithm using an internal five-fold CV and evaluated the performance of the best tuned model using an external ten-fold CV. We determined the model performance by comparing the average of the Harrell Chord Index (C-index) and the Integrated Brier Score (IBS) across the 10 test folds. Ridge Algorithm The best performance is ( Figure 8 H-8I).

[0093] After analysis, the model Ridge Algorithm The reason for the best performance is that there is a synergistic effect in gene expression, which leads to multicollinearity in gene expression characteristics. In order to accurately screen the key characteristic genes for distinguishing molecular subtypes, based on Fig. 9 Results in D, we test the multicollinearity of these 18 features (Table 1):

[0094] Table 1 Multicollinearity between genes and typing

[0095] Gene KRT6A FOSL1 NDNF LYPD3 RNASE1 SLC34A2 UBE2S PBK CDT1 VIF 1.602 1.692 1.767 1.848 1.991 2.004 3.052 3.997 4.373 Gene AURKB CHEK1 CDK1 RRM2 PLK1 EXO1 NEK2 CDKN3 DLGAP5 VIF 5.43 5.614 6.212 6.669 6.717 7.15 8.452 9.156 11.739

[0096] Finally, based on the results in Table 1 , we selected KRT6A, FOSL1, NDNF, LYPD3, RNASE1, SLC34A2, UBE2S, PBK, and CDT1 for constructing a prediction model for molecular typing based on the strict VIF < 5 requirement.

[0097] Ultimately, a strong consensus machine learning driven signature / score (CMLS) was built.

[0098] The ability of CMLS score to predict the efficacy of immunotherapy: Using the Immuno-Oncology Biology Research (IOBR) R software package, we conducted a comprehensive analysis of the tumor microenvironment (TME) of LUAD and observed that the levels of immune cell infiltration, including CD4 T cells, DC cells, NK cells, and CAF cells in patients with low CMLS were significantly higher than those in patients with high CMLS, indicating an immune activation state. Patients with high CMLS mainly accumulated myeloid-driven suppressor cells (MDSCs), showing an immunosuppressive state ( Fig. 9 A). We further calculated the tracking tumor immune phenotype (TIP) to explore the potential biological mechanisms associated with LUAD, and the results showed that the low CMLS group showed significant differences mainly in step 4 (CD4 T cell recruitment) and step 5 (immune cell infiltration), which was consistent with the above analysis results ( Fig. 9 B). Comparison of the relative expression of immune checkpoints between the high and low groups revealed that CD274, CD276, CD70, and IDO1 were significantly upregulated in the high group, while CD27, CD40LG, CD28, and HHLA2 were significantly upregulated in the low group ( Fig. 9 C). These findings suggest that LUAD characterized by low levels of CMLS are more likely to be classified as "hot tumors", while LUAD with high levels of CMLS are more likely to be classified as "cold tumors". The distribution of CMLS in patients with different degrees of response also showed that the CMLS score of the response group (complete response [CR] / partial response [PR]) was significantly lower than that of the non-response group (progressive disease [PD] / stable disease [SD]) (p < 0.05; Figure 8 D). In addition, using the Tumor Immune Dysfunction and Exclusion (TIDE) algorithm to evaluate patients' response to immunotherapy, the low CMLS group showed better responsiveness (P [Fisher's exact test] < -0.2, p < 0.05).

[0099] Characteristic gene mutation status and immune-related analysis: We further analyzed the proteins and immune cells associated with the 18 characteristic genes involved in model construction ( Figure 8AC). These 18 genes are associated with a variety of immune cells and may play an important role in immune response. Among them, NDNF, RNASE1, and SLC34A2 are positively correlated with immune cells, while other genes are negatively correlated with most immune cells. The immune score also showed the same result ( Fig. 9 D), indicating that NDNF, RNASE1, and SLC34A2 may be key genes in promoting immune response. Tumor mutation burden (TMB) is a powerful molecular marker that can be used to quantitatively assess the mutations carried by tumor cells. The waterfall plot shows that the top four genes with the highest mutation frequency are EXO1, KRT6A, SLC34A2, and NDNF ( Figure 8 E).

[0100] By comparing LUAD with normal tissues, we found that 14 of the 18 significantly differentially expressed signature genes (AURKB, CDK1, CDKN3, CDT1, CHEK1, DLGAP5, EXO1, KRT6A, LYPD3, NEK2, PBK, PLK1, PRM2, and UBE2S) were significantly upregulated in lung adenocarcinoma tissues, indicating their potential roles in promoting lung adenocarcinoma progression. The expression levels of FOSL1, NDNF, RNASE1, and SLC34A2 were higher in normal tissues ( Fig. 9 A). Fig.10 B shows paired box plots comparing gene expression between matched normal and LUAD tissues from the same patients. The upward trend in gene expression from normal to LUAD tissues was consistent in all genes analyzed, including AURKB, CDK1, CDKN3, and CDT1, further confirming their significant upregulation in cancer tissues. Paired data visualization highlights the robustness of these genes as potential biomarkers for distinguishing LUAD from normal lung tissues.

[0101] We further analyzed the single-cell data of LUAD. We first performed quality control on the single-cell sequencing data and then used t-SNE to divide the cells into 32 different subsets by dimensionality reduction ( Fig.10 A). Fig.10 C shows the expression of cell type marker genes, Fig.11 B shows the t-SNE distribution of each cell ratio. A total of 12 cell types were identified, including plasma cells, mast cells, fibroblasts, macrophages, and tumor cells. We showed the expression of 18 characteristic genes in these 12 cell types and found that most genes were mainly expressed in epithelial cells and macrophages ( Fig.11 D).

[0102] The role of NDNF in LUAD progression and its potential as a therapeutic target:

[0103] Based on the previous studies, after removing the colinear gene expression, we selected KRT6A, FOSL1, NDNF, LYPD3, RNASE1, SLC34A2, UBE2S, PBK, and CDT1 for constructing the prediction model of molecular typing;

[0104] In the analysis of characteristic gene mutation status and immune correlation, we found that NDNF, RNASE1, and SLC34A2 were positively correlated with immune cells, while other genes were negatively correlated with most immune cells; this prompted us to further study the reasons why NDNF, RNASE1, and SLC34A2 are the key characteristic genes for molecular typing.

[0105] Fig.14 A, 13C also showed that NDNF expression was significantly reduced in LUAD samples compared with normal lung tissues. To confirm this result, we analyzed NDNF expression in normal lung cells and LUAD cells at the gene and protein levels, revealing a significant downregulation of NDNF in LUAD cells.

[0106] Therefore, we wanted to further explore the functional role of NDNF in LUAD, and we constructed a LUAD cell model (A549) that overexpressed NDNF. qPCR results confirmed that NDNF was successfully overexpressed ( Fig.12 D-11E). Using CCK-8 assay, we observed a significant decrease in cell viability in NDNF-overexpressing cells, indicating that NDNF inhibits cell proliferation ( Fig.13 F). In addition, flow cytometry and western blot analysis showed that apoptosis was significantly increased in NDNF-overexpressing A549 cells ( Fig.14 G-13I). Western blot results also showed that the level of cleaved caspase-3, a key apoptosis marker, was increased in cells overexpressing NDNF ( Fig.14 HI).

[0107] Therefore, we revised the conclusion that subtypes are related to prognosis and believed that subtypes are related to apoptosis, and the difference in apoptosis affects the difference in prognosis;

[0108] We established an A549 LUAD cell line model that overexpresses NDNF. This model showed that NDNF overexpression inhibited LUAD cell viability and promoted cell apoptosis.

[0109] In the study described above, we retained the genes related to prognosis to construct the molecular subtype classifier and obtained the following prediction accuracy.

[0110] Table 2 Feature selection and corresponding AUC for predicting LUAD-C2

[0111]

[0112]

[0113] Molecular experiments confirmed the relationship between NDNF and tumor cell apoptosis. We eliminated the inherent thinking related to prognosis and directly screened the differentially expressed genes based on C1 and C2. During the screening process, we used the feature selection algorithm of machine learning to screen and abandoned the test of prognostic relevance of genes. We screened out 6 genes that were more relevant to the classification of molecular subtypes, such as Fig.15 As shown in Table 3:

[0114] It can be seen that the prediction in Table 3 can use fewer genes to obtain more accurate prediction results, and the C1 and C2 subtypes can predict different levels of cell apoptosis (see some ROC diagrams in Fig.16 ).

[0115] Table 3 Feature selection and corresponding AUC for predicting LUAD-C2

[0116]

[0117]

[0118] - indicates missing information in the test set.

[0119] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0120] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, operations and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0121] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0122] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as ROM 3030 or hard disk 3070, may store various data or files used for processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0123] The embodiment of the present invention also provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium provided by an embodiment of the present invention, and a computer readable instruction 4010 is stored on the computer storage medium 4020. When the computer readable instruction 4010 is executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0124] The present disclosure also provides a computer program product or a computer program, which implements the steps of the above method when executed by a processor, such as Figure 2 As shown, the computer program product or computer program comprises:

[0125] Acquisition module 201: Acquisition of gene data of a sample to be tested;

[0126] Feature extraction module 202: Processing the sequencing data of the sample to be tested to obtain key feature genes; the key feature genes include: NDNF, CCNA2 or RNASE1;

[0127] Prediction module 203: inputting the key feature genes into a classifier to obtain a classification result of LUAD-C2 subtype or non-LUAD-C2 subtype; the LUAD-C2 subtype has high apoptosis; the non-LUAD-C2 subtype has low apoptosis.

[0128] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for predicting molecular subtypes of lung adenocarcinoma, characterized in that: The method comprises: Obtaining genetic data of the sample to be tested; Processing the gene data of the sample to be tested to obtain key characteristic genes; the key characteristic genes include: NDNF, CCNA2 or RNASE1; The key feature genes are input into a classifier to obtain a classification result of LUAD-C2 subtype or non-LUAD-C2 subtype; the LUAD-C2 subtype tumor cells have high apoptosis; and the non-LUAD-C2 subtype tumor cells have low apoptosis.

2. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 1, characterized in that: The method for obtaining the classifier includes: Get the genetic dataset for the training set; Clustering the gene dataset to obtain LUAD-C2 subtype and non-LUAD-C2 subtype; Differential expression analysis of genes between LUAD-C2 subtype and non-LUAD-C2 subtype was performed to obtain differentially expressed genes; Performing feature selection on the differentially expressed genes to obtain key feature genes; The key feature genes are input into a machine learning model to obtain a predicted classification result, which is compared with the classification label, and the model is optimized according to the comparison result to obtain the classifier.

3. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 1, characterized in that: Based on the classification result of the LUAD-C2 subtype, a result indicating that the immune activity of the cells of the sample to be tested is high is output; based on the classification result of the non-LUAD-C2 subtype, a result indicating that the immune activity of the cells of the sample to be tested is low is output.

4. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 1, characterized in that: The method further includes: the expression levels of NDNF and RNASE1 in the LUAD-C2 subtype are high, and the expression level of CCNA2 is low.

5. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 1, characterized in that: The key characteristic genes also include: CIP2A; the expression level of CIP2A in the LUAD-C2 subtype is low; Optionally, the key characteristic gene further includes: MYBL2; the expression level of MYBL2 in the LUAD-C2 subtype is low; Optionally, the key characteristic gene further includes: MELK; the expression level of MELK in the LUAD-C2 subtype is low; Optionally, the key characteristic gene also includes: CASP-3; the expression level of CASP-3 in the LUAD-C2 subtype is low.

6. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 1, characterized in that: The key characteristic genes also include: SLC34A2; the expression level of SLC34A2 in the LUAD-C2 subtype is high.

7. The method for predicting molecular subtypes of lung adenocarcinoma according to claim 6, characterized in that: The key characteristic genes also include any one or more of the following: KRT6A, FOSL1, LYPD3, UBE2S, PBK, CDT1; the expression levels of KRT6A, FOSL1, LYPD3, UBE2S, PBK, and CDT1 in the LUAD-C2 subtype are low.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images