Development and validation of a novel gene signatures based on a random forest algorithm and artificial neural network for predictive diagnosis of cervical squamous cell carcinoma

Background: Effective treatment of cervical carcinoma can be challenging due to the lack of specific symptoms in the initial phase, as well as patients often only seeking medical attention in the middle and late stages of the disease when symptoms become more apparent. This study aims to address these limitations by developing and validating a gene signature for predicting cervical squamous cell carcinoma (CESC) using both the random forest algorithm and artificial neural network. Methods: Potential predictive genes for CESC were identified by analyzing three matrix datasets containing tissues from individuals with normal cervical epithelium and patients with CESC. Then, the random forest algorithm and artificial neural network were used to construct predictive models for CESC diagnosis, which were validated using both an independent validation dataset and in vitro experiments. To confirm the validity of the identified genes, protein and mRNA expression of eight disease signature genes were detected in the two groups using Western blotting and real-time quantitative polymerase chain reaction. Additionally, immunoinfiltration analysis was performed. Results: A total of 241 differentially expressed genes (DEGs) were identified, based on which eight genes with the highest predictive ability were selected and used to construct a molecular prognostic scoring system, which demonstrated exceptional predictive accuracy (Area Under Curve (AUC) = 0.995). Validation using an independent dataset confirmed the model’s remarkable predictive ability (AUC = 1.000). In vitro experiments demonstrated significant differences in the expression of the eight disease signature genes between the two groups. Immunoinfiltration analysis also revealed significant differences in immune cell infiltration, with squamous cell carcinoma of the cervix showing a higher degree of macrophage infiltration than normal cervical epithelium. Conclusions: Random forest algorithm and artificial neural network were used to obtain new gene signatures, based on which a molecular prognostic scoring system was developed to predict CESC and aid clinical decision-making.

Cervical squamous cell carcinoma; Diagnosis and treatment; Artificial neural network; Prediction model; Random forest algorithm; Immunity

[1] Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2021; 71: 209–249.

[2] Zhen J, Liu YD, Song CH, Wu S, Bi XJ. The relationship between the expression of RNA-binding protein Musashi2 and cervical squamous-cell carcinoma. Tianjin Medical Journal. 2021; 49: 842–846.

[3] Hang S, Zhang H, Li W, Song YJ, Wang Q, Qi J. Expression of EMMPRIN in cervical cquamous cell carcinoma and its influence on the migration and invasion of cancer cells. Chinese Journal of Diagnostic Pathology. 2021; 28: 210–213. (In Chinese)

[4] Wei M, Chen S, Huang H. Research progress of comprehensive treatment mode for locally advanced cervical cancer. China Cancer. 2019; 28: 456–460. (In Chinese)

[5] Zhang J, Dong D, Wei Q, Ren L. CXCL10 serves as a potential serum biomarker complementing SCC-Ag for diagnosing cervical squamous cell carcinoma. BMC Cancer. 2022; 22: 1052.

[6] Worachartcheewan A, Shoombuatong W, Pidetcha P, Nopnithipat W, Prachayasittikul V, Nantasenamat C. Predicting metabolic syndrome using the random forest method. The Scientific World Journal. 2015; 2015: 581501.

[7] Zafeiris D, Rutella S, Ball GR. An artificial neural network integrated pipeline for biomarker discovery using Alzheimer’s disease as a case study. Computational and Structural Biotechnology Journal. 2018; 16: 77–87.

[8] Bar-Yoseph H, Levhar N, Selinger L, Manor U, Yavzori M, Picard O, et al. Early drug and anti‐infliximab antibody levels for prediction of primary nonresponse to infliximab therapy. Alimentary Pharmacology & Therapeutics. 2018; 47: 212–218.

[9] Scotto L, Narayan G, Nandula SV, Arias-Pulido H, Subramaniyam S, Schneider A, et al. Identification of copy number gain and overexpressed genes on chromosome arm 20q by an integrative genomic approach in cervical cancer: potential role in progression. Genes Chromosomes Cancer. 2008; 47: 755–765.

[10] den Boon JA, Pyeon D, Wang SS, Horswill M, Schiffman M, Sherman M, et al. Molecular transitions from papillomavirus infection to cervical precancer and cancer: role of stromal estrogen receptor signaling. Proceedings of the National Academy of Sciences. 2015; 112: E3255–E3264.

[11] Roychowdhury A, Samadder S, Das P, Mazumder DI, Chatterjee A, Addya S, et al. Deregulation of H19 is associated with cervical carcinoma. Genomics. 2020; 112: 961–970.

[12] Zhai Y, Kuick R, Nan B, Ota I, Weiss SJ, Trimble CL, et al. Gene expression analysis of preinvasive and invasive cervical squamous cell carcinomas identifies HOXC10 as a key mediator of invasion. Cancer Research. 2007; 67: 10163–10172.

[13] Ritchie ME, Phipson B, Wu D, Hu Y, Law CW, Shi W, et al. Limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Research. 2015; 43: e47.

[14] Zhang MY, Huo C, Liu JY, Shi ZE, Zhang WD, Qu JJ, et al. Identification of a five autophagy subtype-related gene expression pattern for improving the prognosis of lung adenocarcinoma. Frontiers in Cell and Developmental Biology. 2021; 9: 756911.

[15] Zhou Y, Zhou B, Pache L, Chang M, Khodabakhshi AH, Tanaseichuk O, et al. Metascape provides a biologist-oriented resource for the analysis of systems-level datasets. Nature Communications. 2019; 10: 1523.

[16] Wu T, Hu E, Xu S, Chen M, Guo P, Dai Z, et al. clusterProfiler 4.0: a universal enrichment tool for interpreting omics data. The Innovation. 2021; 2: 100141.

[17] Ma X, Zhang X, Leng T, Ma J, Yuan Z, Gu Y, et al. Identification of oxidative stress-related biomarkers in diabetic kidney disease. Evidence-Based Complementary and Alternative Medicine. 2022; 2022: 1067504.

[18] Zhao Y, Huang T, Huang P. Integrated analysis of tumor mutation burden and immune infiltrates in hepatocellular carcinoma. Diagnostics. 2022; 12: 1918.

[19] Walter W, Sánchez-Cabo F, Ricote M. GOplot: an R package for visually combining expression data with functional analysis. Bioinformatics. 2015; 31: 2912–2914.

[20] Xin W, Zhang L, Zhang W, Gao J, Yi J, Zhen X, et al. An integrated analysis of the rice transcriptome and metabolome reveals root growth regulation mechanisms in response to nitrogen availability. International Journal of Molecular Sciences. 2019; 20: 5893.

[21] Li H, Lai L, Shen J. Development of a susceptibility gene based novel predictive model for the diagnosis of ulcerative colitis using random forest and artificial neural network. Aging. 2020; 12: 20471–20482.

[22] Beck MW. NeuralNetTools: visualization and analysis tools for neural networks. Journal of Statistical Software. 2018; 85: 1–20.

[23] Shimizu H, Nakayama KI. A 23 gene-based molecular prognostic score precisely predicts overall survival of breast cancer patients. EBioMedicine. 2019; 46: 150–159.

[24] Rice ME, Harris GT. Comparing effect sizes in follow-up studies: ROC area, Cohen’s d, and r. Law and Human Behavior. 2005; 29: 615–620.

[25] Livak KJ, Schmittgen TD. Analysis of relative gene expression data using real-time quantitative PCR and the 2(−Delta Delta C(T)) Method. Methods. 2001; 25: 402–408.

[26] Liu Z, Wang L, Xing Q, Liu X, Hu Y, Li W, et al. Identification of GLS as a cuproptosis-related diagnosis gene in acute myocardial infarction. Frontiers in Cardiovascular Medicine. 2022; 9: 1016081.

[27] Cohen PA, Jhingran A, Oaknin A, Denny L. Cervical cancer. The Lancet. 2019; 393: 169–182.

[28] Li X, Abdel-Maksoud MA, Iqbal I, Mubarak A, Farrag MA, Haris M, et al. Deciphering cervical cancer-associated biomarkers by integrated multi-omics approach. American Journal of Translational Research. 2022; 14: 8843–8861.

[29] Campos SK. Subcellular trafficking of the papillomavirus genome during initial infection: the remarkable abilities of minor capsid protein L2. Viruses. 2017; 9: 370.

[30] Prabhakar AT, James CD, Das D, Otoa R, Day M, Burgner J, et al. CK2 phosphorylation of human papillomavirus 16 E2 on serine 23 promotes interaction with TopBP1 and is critical for E2 interaction with mitotic chromatin and the viral life cycle. mBio. 2021; 12: e0116321.

[31] Li X, Qin G, Tang J. Correlation analysis of serum 25-hydroxyvitamin D[25(OH)D] and estradiol levels with the incidence of cervical cancer. Jilin Medical Journal. 2021; 42: 1976–1977. (In Chinese)

[32] Liu J. Correlation between serum Hcy, Gal-9 and 1,25-(OH)2D; levels and grade of cervical lesions. China Medical Engineering. 2022; 30: 103–105. (In Chinese)

[33] Yin J, Ye Y. Research advances of vitamin D and its receptor in gynecologic cancer. Journal of Modern Oncology. 2022; 30: 1129–1133. (In Chinese)

[34] van de Weerdt BC, Medema RH. Polo-like kinases: a team in control of the division. Cell Cycle. 2006; 5: 853–864.

[35] Rizki A, Mott JD, Bissell MJ. Polo-like kinase 1 is involved in invasion through extracellular matrix. Cancer Research. 2007; 67: 11106–11110.

[36] Zhao C, Gong L, Li W, Chen L. Overexpression of Plk1 promotes malignant progress in human esophageal squamous cell carcinoma. Journal of Cancer Research and Clinical Oncology. 2010; 136: 9–16.

[37] Shapouri‐Moghaddam A, Mohammadian S, Vazini H, Taghadosi M, Esmaeili S, Mardani F, et al. Macrophage plasticity, polarization, and function in health and disease. Journal of Cellular Physiology. 2018; 233: 6425–6440.

[38] Wu K, Lin K, Li X, Yuan X, Xu P, Ni P, et al. Redefining tumor-associated macrophage subpopulations and functions in the tumor microenvironment. Frontiers in Immunology. 2020; 11: 1731.

[39] Anderson NR, Minutolo NG, Gill S, Klichinsky M. Macrophage-based approaches for cancer immunotherapy. Cancer Research. 2021; 81: 1201–1208.

[40] Yunna C, Mengru H, Lei W, Weidong C. Macrophage M1/M2 polarization. European Journal of Pharmacology. 2020; 877: 173090.