Skip to main content
SpringerLink
Log in

Construction of a combined random forest and artificial neural network diagnosis model to screening potential biomarker for hepatoblastoma

  • Original Article
  • Published:
Pediatric Surgery International Aims and scope Submit manuscript

Abstract

Purpose

The purpose of our study is to identify potential biomarkers of hepatoblastoma (HB) and further explore the pathogenesis of it.

Methods

Differentially expressed genes (DEGs) were incorporated into the combined random forest and artificial neural network diagnosis model to screen candidate genes for HB. Gene set enrichment analysis (GSEA) was used to analyze the ARHGEF2. Student’s t test was performed to evaluate the difference of tumor-infiltrating immune cells (TIICs) between normal and HB samples. Spearson correlation analysis was used to calculate the correlation between ARHGEF2 and TIICs.

Results

ARHGEF2, TCF3, TMED3, STMN1 and RAVER2 were screened by the new model. The GSEA of ARHGEF2 included cell cycle pathway and antigen processing presenting pathway. There were significant differences in the composition of partial TIICs between HB and normal samples (p < 0.05). ARHGEF2 was significantly correlated with memory B cells (Cor = 0.509, p < 0.05).

Conclusion

These 5 candidate genes contribute to the molecular diagnosis and targeted therapy of HB. And we found “ARHGEF2–RhoA–Cyclin D1/CDK4/CDK6–EF2” is a key mechanism regulating cell cycle pathway in HB. This will be helpful in the treatment of HB. The occurrence of HB is related to abnormal TIICs. We speculated that memory B cells play an important role in HB.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Liu L, Wang J, Sun G et al (2019) m6A mRNA methylation regulates CTNNB1 to promote the proliferation of hepatoblastoma. Mol Cancer 18:188. https://doi.org/10.1186/s12943-019-1119-7

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Hager J, Sergi CM (2021) Hepatoblastoma. In: Sergi CM (ed) Liver cancer [Internet]. Exon publications, Brisbane. Chapter 8. https://doi.org/10.36255/exonpublications.livercancer.2021.ch8

  3. Hafberg E, Borinstein SC, Alexopoulos SP (2019) Contemporary management of hepatoblastoma. Curr Opin Organ Transplant 24(2):113–117. https://doi.org/10.1097/MOT.0000000000000618

    Article  PubMed  Google Scholar 

  4. Edgar R, Lash A (2002). The Gene Expression Omnibus (GEO): a gene expression and hybridization repository. http://www.icgeb.res.in/whotdr/cd1/PreCourseReading/NCBI_Handbook2/ch6d1.pdf

  5. Valanejad L, Cast A, Wright M et al (2018) PARP1 activation increases expression of modified tumor suppressors and pathways underlying development of aggressive hepatoblastoma. Commun Biol 1:67. https://doi.org/10.1038/s42003-018-0077-8

  6. Hiyama E, Ueda Y, Kurihara S et al (2021) Gene expression profiling in hepatoblastoma cases of the Japanese Study Group for Pediatric Liver Tumors-2 (JPLT-2) trial. European J Mol Cancer. https://doi.org/10.31487/j.EJMC.2018.01.003

  7. Carrillo-Reixach J, Torrens L, Simon-Coma M et al (2020) Epigenetic footprint enables molecular risk stratification of hepatoblastoma with clinical implications. J Hepatol 73(2):328–341. https://doi.org/10.1016/j.jhep.2020.03.025

  8. Ritchie ME, Phipson B, Wu D et al (2015) limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res 43(7):e47. https://doi.org/10.1093/nar/gkv007

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Lê S, Josse J, Husson F (2008) FactoMineR : an R package for multivariate analysis. J Stat Soft. https://doi.org/10.18637/jss.v025.i01

    Article  Google Scholar 

  10. Wickham H. (2016) ggplot2: Elegant graphics for data analysis. Springer-verlag New York. https://ggplot2.tidyverse.orghttps://ggplot2.tidyverse.org

  11. Kolde R. (2019) pheatmap: Pretty Heatmaps. https://CRAN.R-project.org/package=pheatmap. Accessed 6 May 2022

  12. Wu T, Hu E, Xu S et al (2021) clusterProfiler 4.0: a universal enrichment tool for interpreting omics data. Innovation 2(3):100141. https://doi.org/10.1016/j.xinn.2021.100141

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Doms A, Schroeder M (2005) GoPubMed: exploring PubMed with the gene ontology. Nucleic Acids Res 33:W783–W786. https://doi.org/10.1093/nar/gki470

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Kanehisa M, Goto S, Kawashima S, Nakaya A (2002) The KEGG databases at genomenet. Nucleic Acids Res 30(1):42–46. https://doi.org/10.1093/nar/30.1.42

  15. Liaw A, Wiener M (2002). Classification and Regression by randomForest. R News 2(3), 18-22. https://CRAN.R-project.org/doc/Rnews/

  16. Robin X, Turck N, Hainard A et al (2011) pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 12:77. https://doi.org/10.1186/1471-2105-12-77

    Article  PubMed  PubMed Central  Google Scholar 

  17. Günther F, Fritsch S (2010) Neuralnet: training of neural networks. The R Journal 2(1):30. https://doi.org/10.32614/RJ-2010-006

    Article  Google Scholar 

  18. Kassambara A. (2020) ggpubr: “ggplot2” Based Publication Ready Plots. Published online June 27, 2020. https://CRAN.R-project.org/package=ggpubr. Accessed 14 May 2022

  19. Luo W, Brouwer C (2013) Pathview: an R/Bioconductor package for pathway-based data integration and visualization. Bioinformatics 29(14):1830–1831. https://doi.org/10.1093/bioinformatics/btt285

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Hänzelmann S, Castelo R, Guinney J (2013) GSVA: gene set variation analysis for microarray and RNA-Seq data. BMC Bioinformatics 14(1):7. https://doi.org/10.1186/1471-2105-14-7

    Article  PubMed  PubMed Central  Google Scholar 

  21. Czauderna P, Garnier H (2018) Hepatoblastoma: current understanding, recent advances, and controversies. F1000Res 7:53. https://doi.org/10.12688/f1000research.12239.1

    Article  PubMed  PubMed Central  Google Scholar 

  22. Sha YL, Liu S, Yan WW, Dong B (2019) Wnt/β-catenin signaling as a useful therapeutic target in hepatoblastoma. Biosci Rep 39(9):BSR20192466. https://doi.org/10.1042/BSR20192466

    Article  PubMed  PubMed Central  Google Scholar 

  23. Bao P, Yokobori T, Altan B et al (2017) High STMN1 expression is associated with cancer progression and chemo-resistance in lung squamous cell carcinoma. Ann Surg Oncol 24(13):4017–4024. https://doi.org/10.1245/s10434-017-6083-0

    Article  PubMed  Google Scholar 

  24. Yan L, Dong X, Gao J et al (2018) A novel rapid quantitative method reveals stathmin-1 as a promising marker for esophageal squamous cell carcinoma. Cancer Med 7(5):1802–1813. https://doi.org/10.1002/cam4.1449

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. Zhou Q, Ching AKK, Leung WKC et al (2011) Novel therapeutic potential in targeting microtubules by nanoparticle albumin-bound paclitaxel in hepatocellular carcinoma. Int J Oncol 38(3):721–731. https://doi.org/10.3892/ijo.2011.902

    Article  CAS  PubMed  Google Scholar 

  26. Nagata T, Takahashi Y, Ishii Y et al (2003) Transcriptional profiling in hepatoblastomas using high-density oligonucleotide DNA array. Cancer Genet Cytogenet 145(2):152–160. https://doi.org/10.1016/s0165-4608(03)00065-7

    Article  CAS  PubMed  Google Scholar 

  27. Pu XY, Zheng DF, Lv T, Zhou YJ, Yang JY, Jiang L (2022) Overexpression of transcription factor 3 drives hepatocarcinoma development by enhancing cell proliferation via activating Wnt signaling pathway. Hepatobiliary Pancreat Dis Int. https://doi.org/10.1016/j.hbpd.2022.01.003

    Article  PubMed  Google Scholar 

  28. Zheng H, Yang Y, Han J et al (2016) TMED3 promotes hepatocellular carcinoma progression via IL-11/STAT3 signaling. Sci Rep 6:37070. https://doi.org/10.1038/srep37070

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Bartoletti-Stella A, Gasparini L, Giacomini C et al (2015) Messenger RNA processing is altered in autosomal dominant leukodystrophy. Hum Mol Genet 24(10):2746–2756. https://doi.org/10.1093/hmg/ddv034

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Bouzid D, Fourati H, Amouri A et al (2012) Association of the RAVER2 gene with increased susceptibility for ulcerative colitis. Hum Immunol 73(7):732–735. https://doi.org/10.1016/j.humimm.2012.04.018

    Article  CAS  PubMed  Google Scholar 

  31. Birukova AA, Adyshev D, Gorshkov B, Bokoch GM, Birukov KG, Verin AD (2006) GEF-H1 is involved in agonist-induced human pulmonary endothelial barrier dysfunction. Am J Physiol Lung Cell Mol Physiol 290(3):L540-548. https://doi.org/10.1152/ajplung.00259.2005

    Article  CAS  PubMed  Google Scholar 

  32. Cullis J, Meiri D, Sandi MJ et al (2014) The RhoGEF GEF-H1 is required for oncogenic RAS signaling via KSR-1. Cancer Cell 25(2):181–195. https://doi.org/10.1016/j.ccr.2014.01.025

    Article  CAS  PubMed  Google Scholar 

  33. Nalbant P, Chang YC, Birkenfeld J, Chang ZF, Bokoch GM (2009) Guanine nucleotide exchange factor-H1 regulates cell migration via localized activation of RhoA at the leading edge. Mol Biol Cell 20(18):4070–4082. https://doi.org/10.1091/mbc.E09-01-0041

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Cao J, Yang T, Tang D, Zhou F, Qian Y, Zou X (2019) Increased expression of GEF-H1 promotes colon cancer progression by RhoA signaling. Pathol Res Pract 215(5):1012–1019. https://doi.org/10.1016/j.prp.2019.02.008

    Article  CAS  PubMed  Google Scholar 

  35. Wang S, Gao S, Zeng Y et al (2022) N6-methyladenosine reader YTHDF1 promotes ARHGEF2 translation and RhoA signaling in colorectal cancer. Gastroenterology 162(4):1183–1196. https://doi.org/10.1053/j.gastro.2021.12.269

    Article  CAS  PubMed  Google Scholar 

  36. Joo E, Olson MF (2021) Regulation and functions of the RhoA regulatory guanine nucleotide exchange factor GEF-H1. Small GTPases 12(5–6):358–371. https://doi.org/10.1080/21541248.2020.1840889

  37. Cheng IK, Tsang BC, Lai KP et al (2012) GEF-H1 over-expression in hepatocellular carcinoma promotes cell motility via activation of RhoA signalling. J Pathol 228(4):575–585. https://doi.org/10.1002/path.4084

    Article  CAS  PubMed  Google Scholar 

  38. Chen H, Gao F, He M et al (2019) Long-read RNA sequencing identifies alternative splice variants in hepatocellular carcinoma and tumor-specific isoforms. Hepatology 70(3):1011–1025. https://doi.org/10.1002/hep.30500

    Article  CAS  PubMed  Google Scholar 

  39. Nakao Y, Nakagawa S, Yamashita ichi Y et al (2021) High ARHGEF2 (GEF-H1) expression is associated with poor prognosis via cell cycle regulation in patients with pancreatic cancer. Ann Surg Oncol 28(8):4733–4743. https://doi.org/10.1245/s10434-020-09383-9

    Article  PubMed  Google Scholar 

  40. Nie M, Aijaz S, Leefa Chong San IV, Balda MS, Matter K (2009) The Y-box factor ZONAB/DbpA associates with GEF-H1/Lfc and mediates Rho-stimulated transcription. EMBO Rep 10(10):1125–1131. https://doi.org/10.1038/embor.2009.182

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Montalto FI, De Amicis F (2020) Cyclin D1 in cancer: a molecular connection for cell cycle control, adhesion and invasion in tumor and stroma. Cells 9(12):2648. https://doi.org/10.3390/cells9122648

    Article  CAS  PubMed Central  Google Scholar 

  42. Zhang Y, Zhang T, Yin Q, Luo H (2021) Development and validation of genomic and epigenomic signatures associated with tumor immune microenvironment in hepatoblastoma. BMC Cancer 21:1156. https://doi.org/10.1186/s12885-021-08893-3

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Calvisi DF, Solinas A (2020) Hepatoblastoma: current knowledge and promises from preclinical studies. Transl Gastroenterol Hepatol 5:42. https://doi.org/10.21037/tgh.2019.12.03

    Article  PubMed  PubMed Central  Google Scholar 

  44. Jin J, Jin J, Woodfield SE et al (2019) Targeting LRH-1 in hepatoblastoma cell lines causes decreased proliferation. Oncol Rep 41(1):143–153. https://doi.org/10.3892/or.2018.6793

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

We acknowledge the Tianjin Science and Technology Program and the Natural Science Foundation of Xinjiang Uygur Autonomous Region for research support.

Author information

Authors and Affiliations

  1. Clinical School of Paediatrics, Tianjin Medical University, 238 Longyan Road, Beichen District, Tianjin, 300400, China

    Shaowen Liu, Qipeng Zheng, Ruifeng Zhang, Tengfei Li & Jianghua Zhan

  2. Tianjin Children’s Hospital, 238 Longyan Road, Beichen District, Tianjin, 300400, China

    Jianghua Zhan

Authors
  1. Shaowen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qipeng Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ruifeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tengfei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jianghua Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

SWL and TFL: conceived and designed the study. SWL and RFZ: collecting and analyzing data, drafting the manuscript. QPZ and JHZ: read and approved the final manuscript. All authors reviewed the manuscript.

Corresponding author

Correspondence to Jianghua Zhan.

Ethics declarations

Conflict of interests

The authors declare that they have no competing interests.

Ethical approval

Not applicable.

Informed consent

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

383_2022_5255_MOESM1_ESM.tif

Supplementary file1 Standardization for the datasets. A The boxplot before standardization of the new dataset. B The boxplot after standardization of the new data set. C The boxplot before standardization of the GSE133039 dataset. D The boxplot after standardization of the GSE133039 dataset. The X-axis represents the sample. The Y-axis represents the value of gene expression. The black horizontal line in each box represents the median of the data, and the median represents the standardized gene expression value (TIF 51212 KB)

383_2022_5255_MOESM2_ESM.tif

Supplementary file 2 PCA for the datasets. A PCA for the classifications of normal samples and hepatoblastoma samples in the new dataset. B PCA for the classifications of normal samples and hepatoblastoma samples in the GSE133039 dataset (TIF 128615 KB)

Supplementary file 3 The 554 DEGs in the new dataset (XLSX 64 KB)

Supplementary file 4 The 6623 DEGs in the GSE133039 dataset (XLSX 661 KB)

Supplementary file 5 The 321 DEGs shared by the new dataset and the GSE133039 dataset (XLSX 12 KB)

383_2022_5255_MOESM6_ESM.tif

Supplementary file 6 Total of 321 DEGs identified from 2 datasets (6623 in the GSE133039 dataset and 554 in the new dataset) (TIF 14242 KB)

383_2022_5255_MOESM7_ESM.tif

Supplementary file 7 Volcano maps and heat maps of DEGs in two datasets. Up-regulated DEGs is red, reduced DEGs are shown in blue, non-DEGs are indicated in gray. A Volcano maps for the new dataset. B Volcano maps for GSE133039 dataset. C Heat maps for the new dataset. D Heat maps for GSE133039 dataset (TIF 59161 KB)

Supplementary file 8 GO enrichment analysis results (XLSX 89 KB)

Supplementary file 9 KEGG enrichment analysis results (XLSX 13 KB)

383_2022_5255_MOESM10_ESM.tif

Supplementary file 10 Functional enrichment analysis for DEGs. A GO enrichment bubble diagram of DEGs (Top 5). B KEGG pathway enrichment bubble map of DEGs (Top 15). C Circular graph of KEGG pathway of DEGs (Top 15). D Interaction network of 15 KEGG pathways (TIF 49787 KB)

Supplementary file 11 The miRNAs associated with HB (XLSX 9 KB)

Supplementary file 12 The mRNAs controlled by miRNAs (XLSX 188 KB)

Supplementary file 13 Association of mRNAs with miRNAs after hybridization with DEGs (XLSX 10 KB)

383_2022_5255_MOESM14_ESM.tif

Supplementary file 14 Construction of ceRNA network. mRNAs, miRNAs and lncRNAs were represented by purple circle node, yellow V-shaped node and green diamond node, respectively (TIF 44049 KB)

Supplementary file 15 MeanDecreaseAccuracy and MeanDecreaseGini values for 321 DEGs (XLSX 21 KB)

383_2022_5255_MOESM16_ESM.tif

Supplementary file 16 Unsupervised clustering of 5 candidate genes. A Clustering of the 5 candidate genes in new dataset. B Clustering of the 5 candidate genes in GSE133039 dataset (TIF 57900 KB)

383_2022_5255_MOESM17_ESM.tif

Supplementary file 17 The expression differences of the 5 candidate genes between tumor and normal samples. The expression of A ARHGEF2, B TCF3, C TMED3, D STMN1, E RAVER2 was significantly up-regulated in the tumor samples. *** P<0.001, ** P<0.01, * P<0.05 (TIF 35085 KB)

Supplementary file 18 The GSEA of the candidate gene ARHGEF2 (XLSX 18 KB)

Supplementary file 19 The KEGG diagram of the cell cycle (TIF 50776 KB)

Supplementary file 20 GSVA enrichment scores of 28 TIICs from normal samples and HB samples (XLSX 34 KB)

383_2022_5255_MOESM21_ESM.tif

Supplementary file 21 Correlation between ARHGEF2 and immune cells. A-O Correlation between ARHGEF2 and activated CD4 T cell, activated CD8 T cell, activated dendritic cell, CD56bright natural killer cel, CD56dim natural killer cell, central memory CD4 T cell, eosinophil, gamma delta T cell, memory B cell, monocyte, neutrophil, plasmacytoid dendritic cell, regulatory T cell , T follicular helper cell and type 2 T helper cell (TIF 217306 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, S., Zheng, Q., Zhang, R. et al. Construction of a combined random forest and artificial neural network diagnosis model to screening potential biomarker for hepatoblastoma. Pediatr Surg Int 38, 2023–2034 (2022). https://doi.org/10.1007/s00383-022-05255-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00383-022-05255-3

Keywords

Search

Navigation