Mining meaningful and comprehensive molecular characterization of cancers from The Cancer Genome Atlas (TCGA) data has become a bioinformatics bottleneck. Meanwhile, recent progress in cancer analysis shows that multi-omics data can effectively and systematically detect the cancer-related genes at all levels. In this study, we propose an improved particle swarm optimization with dynamic scale-free network, named DSFPSO, to extract features on multi-omics data. The highlights of DSFPSO are taking the dynamic scale-free network as its population structure and diverse velocity updating strategies for fully considering the heterogeneity of particles and their neighbors. Experiments of DSFPSO and its comparison with several state-of-the-art feature extraction approaches are performed on two public data sets from TCGA. Results show that DSFPSO can extract genes associated with cancers effectively.
Get full access to this article
View all access options for this article.
References
1.
BersanelliM., MoscaE., RemondiniD., et al.2016. Methods for the integration of multi-omics data: Mathematical aspects. BMC Bioinformatics, 17, S15.
2.
ChenH.H., TsengY.J., WangS.Y., et al.2015. The metabolome profiling and pathway analysis in metabolic healthy and abnormal obesity. Int. J. Obes. 39, 1241.
3.
ChengQ., ChenA., DuQ., et al.2018. Novel insights into ion channels in cancer stem cells. Int. J. Oncol. 53, 1435–1441.
4.
ChuangL.Y., ChangH.W., TuC.J., et al.2008. Improved binary PSO for feature selection using gene expression data. Comput. Biol. Chem. 32, 29–38.
5.
DaiM., ChenX., MoS., et al.2017. Meta-signature LncRNAs serve as novel biomarkers for colorectal cancer: Integrated bioinformatics analysis, experimental validation and diagnostic evaluation. Sci. Rep. 7, 46572.
6.
DeloriaA.J., HöflmayerD., KienzlP., et al.2016. Epithelial splicing regulatory protein 1 and 2 paralogues correlate with splice signatures and favorable outcome in human colorectal cancer. Oncotarget, 7, 73800–73816.
7.
EberhartR.C. and ShiY.2001. Particle swarm optimization: Developments, applications and resources. In Proceedings of the 2001 Congress on Evolutionary Computation, Seoul, Korea, 81–86.
8.
EberhartR., and KennedyJ.1995. A new optimizer using particle swarm theory. In MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 39–43.
9.
FagooneeS., PiccoG., OrsoF., et al.2017. The RNA-binding protein ESRP1 promotes human colorectal cancer progression. Oncotarget, 8, 10007.
10.
FuquaC., ParsekM.R., and GreenbergE.P.2001. Regulation of gene expression by cell-to-cell communication: Acyl-homoserine lactone quorum sensing. Annu. Rev. Genet. 35, 439–468.
HuangD.W., ShermanB.T., and LempickiR.A.2009. Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nat. Protoc. 4, 44.
13.
JosseC., BouznadN., GeurtsP., et al.2014. Identification of a microRNA landscape targeting the PI3K/Akt signaling pathway in inflammation-induced colorectal carcinogenesis. Am. J. Physiol. Gastrointest. Liver Physiol. 306, 229–243.
14.
KanehisaM., ArakiM., and GotoS., et al.2008. KEGG for linking genomes to life and the environment. Nucl. Acids Res. 36, D480–D484.
15.
KarS., SharmaK.D., and MaitraM.2015. Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K -nearest neighborhood technique. Expert Syst. Appl. 42, 612–627.
16.
KennedyJ., and MendesR.2002. Population structure and particle swarm performance. In CEC ’02. Proceedings of the 2002 Congress on Evolutionary Computation, Hawaii, USA, 1671–1676.
17.
LeeH.J., FlahertyP., and JiH.P.2013. Systematic genomic identification of colorectal cancer genes delineating advanced from early clinical stage and metastasis. BMC Med. Genomics, 6, 54.
18.
LeontievaO.V., and IonovY.2009. RNA-binding motif protein 35A is a novel tumor suppressor for colorectal cancer. Cell Cycle, 8, 490–497.
19.
LeskinenT., RinnankoskituikkaR., RintalaM., et al.2010. Differences in muscle and adipose tissue gene expression and cardio-metabolic risk factors in the members of physical activity discordant twin pairs. PLoS One, 5, e12609.
20.
LiL., DuanT., WangX., et al.2016. KCTD12 regulates colorectal cancer cell stemness through the ERK pathway. Sci. Rep. 6, 20460.
21.
LiN., BuX., TianX., et al.2012. Fatty acid synthase regulates proliferation and migration of colorectal cancer cells via HER2-PI3K/Akt signaling pathway. Nutr. Cancer, 64, 864–870.
22.
LiZ., ZhangX., YangY., et al.2015. Periostin expression and its prognostic value for colorectal cancer. Int. J. Mol. Sci. 16, 12108–12118.
23.
LiuC., DuW.B., and WangW.X.2014a. Particle swarm optimization with scale-free interactions. PLoS One, 9, e97822.
24.
LiuJ.X., GaoY.L., XuY., et al.2014b. Differential expression analysis on RNA-Seq count data based on penalized matrix decomposition. IEEE Trans. Nanobiosci. 13, 12–18.
25.
LiuJ.X., GaoY.L., ZhengC.H., et al.2016. Block-constraint robust principal component analysis and its application to integrated analysis of TCGA data. IEEE Trans. Nanobiosci. 15, 510–516.
26.
LiuJ.X., ZhengC.H., and XuY.2012. Extracting plants core genes responding to abiotic stresses by penalized matrix decomposition. Comput. Biol. Med. 42, 582–589.
27.
LuoL., CuiJ., FengZ., et al.2017. Lentiviral-mediated overexpression of KCTD12 inhibits the proliferation of human uveal melanoma OCM-1 cells. Oncol. Rep. 37, 871–878.
28.
LussR., and D'AspremontA.2010. Clustering and feature selection using sparse principal component analysis. Optim. Eng. 11, 145–157.
29.
PanT., XuJ., and ZhuY.2017. Self-renewal molecular mechanisms of colorectal cancer stem cells. Int. J. Mol. Med. 39, 9–20.
30.
RothV.2004. The generalized LASSO. IEEE Trans. Neural Netw. 15, 16–28.
31.
ShangJ., SunY., LiS., et al.2015. An improved opposition-based learning particle swarm optimization for the detection of SNP-SNP interactions. Biomed. Res. Int. 2015, 524821.
32.
VaD.J.P., YuanK., LyuksyutovaM.A., et al.2014. Whole-exome sequencing reveals TopBP1 as a novel gene in idiopathic pulmonary arterial hypertension. Am. J. Respir. Crit. Care Med. 189, 1260–1272.
33.
WenZ., PanT., YangS., et al.2017. Up-regulated NRIP2 in colorectal cancer initiating cells modulates the Wnt pathway by targeting RORβ. Mol. Cancer. 16, 20.
34.
WenZ., XuS., FengS., et al.2015. Su2003 Nrip2, a novel regulator of the non-canonical wnt pathway, promotes the self-renewal of colorectal cancer initiating cells. Gastroenterology, 148, S-572.
35.
XuX., SunQ., LiuZ., et al.2010. The correlation between the malignant proliferation on cholangiocarcinoma cell lines and in bile from Helicobacter pylori infected patients with biliary tract stones. J. Toxicol. Environ. Health Sci. 2, 17–23.
36.
ZambettiG.P., BargonettiJ., WalkerK., et al.1992. Wild-type p53 mediates positive regulation of gene expression through a specific DNA sequence element. Genes Dev. 6, 1143–1152.
37.
ZhangW., ShangJ., LiH., et al.2016. SIPSO: Selectively informed particle swarm optimization based on mutual information to determine SNP-SNP interactions, 112–121. In International Conference on Intelligent Computing, Lanzhou, China, 112–121.
38.
ZhaoS.Z., LiangJ.J., SuganthanP.N., et al.2008. Dynamic multi-swarm particle swarm optimizer with local search for large scale global optimization. In IEEE World Congress on Computational Intelligence, Hong Kong, China, 3845–3852.
