A support vector machine classifier for the prediction of osteosarcoma metastasis with high accuracy

He,Yunfei; Ma,Jun; Ye,Xiaojian

doi:10.3892/ijmm.2017.3126

A support vector machine classifier for the prediction of osteosarcoma metastasis with high accuracy

Authors:
- Yunfei He
- Jun Ma
- Xiaojian Ye
View Affiliations

Affiliations: Department of Orthopaedics, Changzheng Hospital Αffiliated to Second Military Medical University, Shanghai 200003, P.R. China
Published online on: September 7, 2017 https://doi.org/10.3892/ijmm.2017.3126
Pages: 1357-1364
Copyright: © He et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

In this study, gene expression profiles of osteosarcoma (OS) were analyzed to identify critical genes associated with metastasis. Five gene expression datasets were screened and downloaded from Gene Expression Omnibus (GEO). Following assessment by MetaQC, the dataset GSE9508 was excluded for poor quality. Subsequently, differentially expressed genes (DEGs) between metastatic and non-metastatic OS were identified using meta‑analysis. A protein-protein interaction (PPI) network was constructed with information from Human Protein Reference Database (HPRD) for the DEGs. Betweenness centrality (BC) was calculated for each node in the network and top featured genes ranked by BC were selected out to construct support vector machine (SVM) classifier using the training set GSE21257, which was then validated using the other three independent datasets. Pathway enrichment analysis was performed for the featured genes using Fisher's exact test. A total of 353 DEGs were identified and a PPI network including 164 nodes and 272 edges was then constructed. The top 64 featured genes ranked by BC were included in the SVM classifier. The SVM classifier exhibited high prediction accuracies in all of the 4 datasets, with accuracies of 100, 100, 92.6 and 100%, respectively. Further analysis of the featured genes revealed that 11 Gene Ontology (GO) biological pathways and 5 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways were significantly over-represented, including the regulation of cell proliferation, regulation of apoptosis, pathways in cancer, regulation of actin cytoskeleton and the TGF-β signaling pathway. On the whole, an SVM classifier with high prediction accuracy was constructed and validated, in which key genes associated with metastasis in OS were also revealed. These findings may promote the development of genetic diagnostic methods and may enhance our understanding of the molecular mechanisms underlying the metastasis of OS.

View Figures

View References

1	Jaffe N, Bruland OS and Bielack S: Pediatric and Adolescent Osteosarcoma. Springer; pp. 152Berlin: 2010
2	Hou CH, Lin FL, Tong KB, Hou SM and Liu JF: Transforming growth factor alpha promotes osteosarcoma metastasis by ICAM-1 and PI3K/Akt signaling pathway. Biochem Pharmacol. 89:453–463. 2014. View Article : Google Scholar : PubMed/NCBI
3	Dong Y, Liang G, Yuan B, Yang C, Gao R and Zhou X: MALAT1 promotes the proliferation and metastasis of osteosarcoma cells by activating the PI3K/Akt pathway. Tumour Biol. 36:1477–1486. 2015. View Article : Google Scholar
4	Guo YS, Zhao R, Ma J, Cui W, Sun Z, Gao B, He S, Han YH, Fan J, Yang L, et al: βig-h3 promotes human osteosarcoma cells metastasis by interacting with integrin α2β1 and activating PI3K signaling pathway. PLoS One. 9:e902202014. View Article : Google Scholar
5	Liao D, Zhong L, Duan T, Zhang RH, Wang X, Wang G, Hu K, Lv X and Kang T: Aspirin suppresses the growth and metastasis of osteosarcoma through the NF-κB pathway. Clin Cancer Res. 21:5349–5359. 2015. View Article : Google Scholar : PubMed/NCBI
6	Zhang P, Yang Y, Zweidler-McKay P and Hughes DPM: Retraction: Critical role of notch signaling in osteosarcoma invasion and metastasis. Clin Cancer Res. 19:5256–5257. 2013. View Article : Google Scholar : PubMed/NCBI
7	Guan G, Zhang Y, Lu Y, Liu L, Shi D, Wen Y, Yang L, Ma Q, Liu T, Zhu X, et al: The HIF-1α/CXCR4 pathway supports hypoxia-induced metastasis of human osteosarcoma cells. Cancer Lett. 357:254–264. 2015. View Article : Google Scholar
8	Khanna C, Wan X, Bose S, Cassaday R, Olomu O, Mendoza A, Yeung C, Gorlick R, Hewitt SM and Helman LJ: The membrane-cytoskeleton linker ezrin is necessary for osteosarcoma metastasis. Nat Med. 10:182–186. 2004. View Article : Google Scholar : PubMed/NCBI
9	Ren L, Hong SH, Cassavaugh J, Osborne T, Chou AJ, Kim SY, Gorlick R, Hewitt SM and Khanna C: The actin-cytoskeleton linker protein ezrin is regulated during osteosarcoma metastasis by PKC. Oncogene. 28:792–802. 2009. View Article : Google Scholar
10	Wan X, Kim SY, Guenther LM, Mendoza A, Briggs J, Yeung C, Currier D, Zhang H, Mackall C, Li WJ, et al: Beta4 integrin promotes osteosarcoma metastasis and interacts with ezrin. Oncogene. 28:3401–3411. 2009. View Article : Google Scholar : PubMed/NCBI
11	Long F, Cai X, Luo W, Chen L and Li K: Role of aldolase A in osteosarcoma progression and metastasis: In vitro and in vivo evidence. Oncol Rep. 32:2031–2037. 2014. View Article : Google Scholar : PubMed/NCBI
12	Qu L and Liu B: Cyclooxygeanse-2 promotes metastasis in osteosarcoma. Cancer Cell Int. 15:692015. View Article : Google Scholar : PubMed/NCBI
13	Su Y, Wagner ER, Luo Q, Huang J, Chen L, He BC, Zuo GW, Shi Q, Zhang BQ, Zhu G, et al: Insulin-like growth factor binding protein 5 suppresses tumor growth and metastasis of human osteosarcoma. Oncogene. 30:3907–3917. 2011. View Article : Google Scholar : PubMed/NCBI
14	Namløs HM, Kresse SH, Müller CR, Henriksen J, Holdhus R, Sæter G, Bruland OS, Bjerkehagen B, Steen VM and Myklebost O: Global gene expression profiling of human osteosarcomas reveals metastasis-associated chemokine pattern. Sarcoma. 2012:6390382012. View Article : Google Scholar : PubMed/NCBI
15	Odagiri H, Kadomatsu T, Endo M, Masuda T, Morioka MS, Fukuhara S, Miyamoto T, Kobayashi E, Miyata K, Aoi J, et al: The secreted protein ANGPTL2 promotes metastasis of osteosarcoma cells through integrin α5β1, p38 MAPK, and matrix metalloproteinases. Sci Signal. 7:ra72014. View Article : Google Scholar
16	Endo-Munoz L, Cumming A, Rickwood D, Wilson D, Cueva C, Ng C, Strutton G, Cassady AI, Evdokiou A, Sommerville S, et al: Loss of osteoclasts contributes to development of osteosarcoma pulmonary metastases. Cancer Res. 70:7063–7072. 2010. View Article : Google Scholar : PubMed/NCBI
17	Buddingh EP, Kuijjer ML, Duim RA, Bürger H, Agelopoulos K, Myklebost O, Serra M, Mertens F, Hogendoorn PC, Lankester AC, et al: Tumor-infiltrating macrophages are associated with metastasis suppression in high-grade osteosarcoma: A rationale for treatment with macrophage activating agents. Clin Cancer Res. 17:2110–2119. 2011. View Article : Google Scholar : PubMed/NCBI
18	Smyth GK: Limma: Linear Models for Microarray Data. Bioinformatics and Computational Biology Solutions Using R and Bioconductor. Gentleman R, Carey VJ, Huber W, Irizarry RA and Dudoit S: Springer; New York, NY: pp. 397–420. 2005, View Article : Google Scholar
19	Wang X, Kang DD, Shen K, Song C, Lu S, Chang LC, Liao SG, Huo Z, Tang S, Ding Y, et al: An R package suite for microarray meta-analysis in quality control, differentially expressed gene analysis and pathway enrichment detection. Bioinformatics. 28:2534–2536. 2012. View Article : Google Scholar : PubMed/NCBI
20	Chatr-Aryamontri A, Breitkreutz BJ, Oughtred R, Boucher L, Heinicke S, Chen D, Stark C, Breitkreutz A, Kolas N, O'Donnell L, et al: The BioGRID interaction database: 2015 update. Nucleic Acids Res. 43:D470–D478. 2015. View Article : Google Scholar :
21	Keshava Prasad TS, Goel R, Kandasamy K, Keerthikumar S, Kumar S, Mathivanan S, Telikicherla D, Raju R, Shafreen B, Venugopal A, et al: Human Protein Reference Database – 2009 update. Nucleic Acids Res. 37:D767–D772. 2009. View Article : Google Scholar
22	Xenarios I, Rice DW, Salwinski L, Baron MK, Marcotte EM and Eisenberg D: DIP: The database of interacting proteins. Nucleic Acids Res. 28:289–291. 2000. View Article : Google Scholar
23	Smoot ME, Ono K, Ruscheinski J, Wang PL and Ideker T: Cytoscape 2.8: New features for data integration and network visualization. Bioinformatics. 27:431–432. 2011. View Article : Google Scholar :
24	Kim HS, Park YB, Oh JH, Jeong J, Kim CJ and Lee SH: Expression of CD44 isoforms correlates with the metastatic potential of osteosarcoma. Clin Orthop Relat Res. 396:184–190. 2002. View Article : Google Scholar
25	Zhao H, Ma B, Wang Y, Han T, Zheng L, Sun C, Liu T, Zhang Y, Qiu X and Fan Q: miR-34a inhibits the metastasis of osteosarcoma cells by repressing the expression of CD44. Oncol Rep. 29:1027–1036. 2013. View Article : Google Scholar : PubMed/NCBI
26	Fritsche-Guenther R, Noske A, Ungethüm U, Kuban RJ, Schlag PM, Tunn PU, Karle J, Krenn V, Dietel M and Sers C: De novo expression of EphA2 in osteosarcoma modulates activation of the mitogenic signalling pathway. Histopathology. 57:836–850. 2010. View Article : Google Scholar : PubMed/NCBI
27	Posthumadeboer J, Piersma SR, Pham TV, van Egmond PW, Knol JC, Cleton-Jansen AM, van Geer MA, van Beusechem VW, Kaspers GJ, van Royen BJ, et al: Surface proteomic analysis of osteosarcoma identifies EPHA2 as receptor for targeted drug delivery. Br J Cancer. 109:2142–2154. 2013. View Article : Google Scholar : PubMed/NCBI
28	Liang G, Xu E, Yang C, Zhang C, Sheng X and Zhou X: Nucleosome-binding protein HMGN2 exhibits antitumor activity in human SaO2 and U2-OS osteosarcoma cell lines. Oncol Rep. 33:1300–1306. 2015. View Article : Google Scholar
29	Yang J, Annala M, Ji P, Wang G, Zheng H, Codgell D, Du X, Fang Z, Sun B, Nykter M, et al: Recurrent LRP1-SNRNP25 and KCNMB4-CCND3 fusion genes promote tumor cell motility in human osteosarcoma. J Hematol Oncol. 7:762014. View Article : Google Scholar : PubMed/NCBI
30	Wang J, Xu G, Shen F and Kang Y: miR-132 targeting cyclin E1 suppresses cell proliferation in osteosarcoma cells. Tumour Biol. 35:4859–4865. 2014. View Article : Google Scholar : PubMed/NCBI
31	Liu J, Gu J, Feng Z, Yang Y, Zhu N, Lu W and Qi F: Both HDAC5 and HDAC6 are required for the proliferation and metastasis of melanoma cells. J Transl Med. 14:72016. View Article : Google Scholar : PubMed/NCBI
32	Wang XC, Ma Y, Meng PS, Han JL, Yu HY and Bi LJ: miR-433 inhibits oral squamous cell carcinoma (OSCC) cell growth and metastasis by targeting HDAC6. Oral Oncol. 51:674–682. 2015. View Article : Google Scholar : PubMed/NCBI
33	Guo DL, Zhang J, Yuen ST, Tsui WY, Chan AS, Ho C, Ji J, Leung SY and Chen X: Reduced expression of EphB2 that parallels invasion and metastasis in colorectal tumours. Carcinogenesis. 27:454–464. 2006. View Article : Google Scholar
34	Oshima T, Akaike M, Yoshihara K, Shiozawa M, Yamamoto N, Sato T, Akihito N, Nagano Y, Fujii S, Kunisaki C, et al: Overexpression of EphA4 gene and reduced expression of EphB2 gene correlates with liver metastasis in colorectal cancer. Int J Oncol. 33:573–577. 2008.PubMed/NCBI
35	Feng X, Wu Z, Wu Y, Hankey W, Prior TW, Li L, Ganju RK, Shen R and Zou X: Cdc25A regulates matrix metalloprotease 1 through Foxo1 and mediates metastasis of breast cancer cells. Mol Cell Biol. 31:3457–3471. 2011. View Article : Google Scholar : PubMed/NCBI
36	Zurita M, Lara PC, del Moral R, Torres B, Linares-Fernández JL, Arrabal SR, Martínez-Galán J, Oliver FJ and Ruiz de Almodóvar JM: Hypermethylated 14-3-3-σ and ESR1 gene promoters in serum as candidate biomarkers for the diagnosis and treatment efficacy of breast cancer metastasis. BMC Cancer. 10:2172010. View Article : Google Scholar
37	Sonaglio V, de Carvalho AC, Toledo SR, Salinas-Souza C, Carvalho AL, Petrilli AS, de Camargo B and Vettore AL: Aberrant DNA methylation of ESR1 and 14ARF genes could be useful as prognostic indicators in osteosarcoma. Onco Targets Ther. 6:713–723. 2013.