摘要
背景:结直肠癌(CRC)是全球第三大常见癌症。癌症鉴别是使用微阵列技术进行基因表达分析的典型应用。然而,微阵列数据遭受维数的诅咒和多数(肿瘤样本)和少数(正常样本)类别之间通常不平衡的类别分布。特征基因的选择对于癌症的鉴别是必要且重要的。 目的:选择特征基因来鉴别CRC。 方法:我们改进了基于差分进化,DEFSw的特征选择算法,方法是使用RUSBoost分类器和权重精度,而不是通用分类器和评估措施,从不平衡数据中选择特征基因。我们首先从TCGA的CRC数据集中提取不同表达的基因(DEG),然后使用改进的DEFSw算法从DEG中选择特征基因。最后,我们使用独立的数据集验证选定的特征基因集,并根据通过Coremine Medical在线数据库进行的文本挖掘,检索这些基因的癌症相关信息。 结果:我们选择了16个单基因特征集用于大肠癌的鉴别和19个单基因特征集,仅用于结肠癌的鉴别。结论:总而言之,我们发现了一系列潜在的候选生物标志物或标记,可以高度敏感和特异性地区分结肠癌和直肠癌中的一个或两个。
关键词: 大肠癌,特征基因选择,癌症鉴别,数据不平衡
[http://dx.doi.org/10.1002/ijc.29210] [PMID: 25220842]
[http://dx.doi.org/10.1053/j.seminoncol.2011.05.008] [PMID: 21810513]
[http://dx.doi.org/10.1109/TCBB.2010.36]
[http://dx.doi.org/10.1371/journal.pone.0102541] [PMID: 25048512]
[http://dx.doi.org/10.1016/j.gdata.2016.02.012] [PMID: 27081632]
[http://dx.doi.org/10.1155/2015/604910] [PMID: 25961028]
[http://dx.doi.org/10.1371/journal.pone.0056499] [PMID: 23437146]
[http://dx.doi.org/10.1023/A:1012487302797]
[http://dx.doi.org/10.1016/j.compbiomed.2014.01.014] [PMID: 24561345]
[http://dx.doi.org/10.1109/TCBB.2007.1006]
[http://dx.doi.org/10.1016/j.swevo.2012.09.003]
[http://dx.doi.org/10.1109/TPAMI.2004.105] [PMID: 15521491]
[http://dx.doi.org/10.1016/j.compbiolchem.2007.09.005] [PMID: 18023261]
[http://dx.doi.org/10.1186/s40709-016-0045-8] [PMID: 27437198]
[http://dx.doi.org/10.1109/TSMCA.2009.2029559]
[http://dx.doi.org/10.1007/978-3-540-39804-2_12]
[http://dx.doi.org/10.1093/bioinformatics/btm486] [PMID: 18048398]
[http://dx.doi.org/10.1371/journal.pmed.1001453] [PMID: 23700391]
[http://dx.doi.org/10.1002/ijc.27419] [PMID: 22213152]
[http://dx.doi.org/10.1172/JCI73531] [PMID: 24642471]
[http://dx.doi.org/10.1517/14728222.11.5.613] [PMID: 17465721]
[http://dx.doi.org/10.1016/j.canep.2013.12.005] [PMID: 24445140]
[PMID: 21229891]
[PMID: 2253221]
[PMID: 25006740]
[http://dx.doi.org/10.1158/1055-9965.EPI-07-0518] [PMID: 18086775]
[http://dx.doi.org/10.3748/wjg.v16.i11.1409] [PMID: 20238409]
[http://dx.doi.org/10.1038/sj.bjc.6602790] [PMID: 16175182]
[http://dx.doi.org/10.1038/bjc.1992.427] [PMID: 1280991]
[http://dx.doi.org/10.1007/s00795-011-0565-0] [PMID: 23224602]
[http://dx.doi.org/10.1038/onc.2009.144] [PMID: 19483721]
[PMID: 10690527]
[http://dx.doi.org/10.1021/pr100236r] [PMID: 20455597]
[http://dx.doi.org/10.1002/pmic.200401355] [PMID: 16586428]
[PMID: 17493385]
[http://dx.doi.org/10.18632/oncotarget.2305] [PMID: 25226615]
[http://dx.doi.org/10.1007/s12253-014-9751-4] [PMID: 24599561]
[http://dx.doi.org/10.1002/jcp.24930] [PMID: 25612232]
[http://dx.doi.org/10.1016/j.bbrc.2003.09.147] [PMID: 14559244]
[PMID: 25337260]
[http://dx.doi.org/10.1186/1471-2407-14-734] [PMID: 25269858]
[http://dx.doi.org/10.1371/journal.pone.0055749] [PMID: 23405208]
[http://dx.doi.org/10.1016/j.ajpath.2011.03.046] [PMID: 21703417]
[http://dx.doi.org/10.1038/modpathol.2010.189] [PMID: 20852590]
[http://dx.doi.org/10.1002/ijc.25427] [PMID: 20473917]
[PMID: 19528487]
[PMID: 19846933]
[http://dx.doi.org/10.1158/1078-0432.CCR-08-1086] [PMID: 18927288]
[http://dx.doi.org/10.1111/j.1349-7006.2008.00921.x] [PMID: 18811693]
[PMID: 9815605]
[http://dx.doi.org/10.1111/cen.12878] [PMID: 26285159]
[http://dx.doi.org/10.3892/or.2014.3545] [PMID: 25322858]
[http://dx.doi.org/10.1016/j.prp.2014.01.014] [PMID: 24636838]
[http://dx.doi.org/10.1016/j.humpath.2011.08.020] [PMID: 22209340]
[http://dx.doi.org/10.18632/oncotarget.5921] [PMID: 26437221]
[http://dx.doi.org/10.18632/oncotarget.3978] [PMID: 26009875]
[PMID: 26045799]
[http://dx.doi.org/10.18632/oncotarget.2220] [PMID: 25051373]
[http://dx.doi.org/10.3892/or.2014.3038] [PMID: 24573670]
[http://dx.doi.org/10.1186/1471-2407-14-194] [PMID: 24628760]
[PMID: 21443102]
[http://dx.doi.org/10.1002/jbt.21594] [PMID: 25130429]
[http://dx.doi.org/10.1007/s13402-014-0209-1] [PMID: 25450519]
[http://dx.doi.org/10.1242/jcs.130013] [PMID: 23986482]
[http://dx.doi.org/10.1002/ijc.30381] [PMID: 27529686]
[http://dx.doi.org/10.1016/j.mcn.2007.12.002] [PMID: 18249135]
[http://dx.doi.org/10.1038/srep04852] [PMID: 24781822]
[http://dx.doi.org/10.1111/php.12290] [PMID: 24842606]
[http://dx.doi.org/10.12659/MSM.891340] [PMID: 25287716]
[http://dx.doi.org/10.1007/s10549-015-3446-8] [PMID: 26026468]
[http://dx.doi.org/10.1016/j.ejso.2011.04.001] [PMID: 21546206]
[PMID: 22267128]
[http://dx.doi.org/10.1002/cncr.22983] [PMID: 17849461]
[http://dx.doi.org/10.1016/j.critrevonc.2009.09.001] [PMID: 19836969]
[http://dx.doi.org/10.1371/journal.pone.0105306] [PMID: 25144746]
[http://dx.doi.org/10.1097/MD.0000000000002729] [PMID: 26871813]
[http://dx.doi.org/10.3727/096504015X14478843952861] [PMID: 26802652]
[http://dx.doi.org/10.1186/s12885-016-2109-4] [PMID: 26867589]
[http://dx.doi.org/10.1371/journal.pone.0097094] [PMID: 24865582]
[http://dx.doi.org/10.1371/journal.pone.0134366] [PMID: 26252635]
[http://dx.doi.org/10.7314/APJCP.2014.15.2.825] [PMID: 24568503]
[http://dx.doi.org/10.1016/j.biopha.2015.01.016] [PMID: 25776494]
[http://dx.doi.org/10.3390/molecules21111575] [PMID: 27869781]
[http://dx.doi.org/10.1038/sj.onc.1208794] [PMID: 16007190]
[http://dx.doi.org/10.3109/02656736.2015.1016557] [PMID: 25811737]
[http://dx.doi.org/10.1002/jat.3268] [PMID: 26663444]
[http://dx.doi.org/10.1371/journal.pone.0070183] [PMID: 23922954]
[http://dx.doi.org/10.1074/jbc.M112.370064] [PMID: 22859303]
[http://dx.doi.org/10.1371/journal.pone.0016281] [PMID: 21283832]
[http://dx.doi.org/10.1002/cncr.23335] [PMID: 18327804]
[http://dx.doi.org/10.1186/1471-2407-9-79] [PMID: 19267921]
[http://dx.doi.org/10.1038/srep16007] [PMID: 26537865]
[http://dx.doi.org/10.3892/or.2013.2761] [PMID: 24085226]
[http://dx.doi.org/10.1093/carcin/bgq146] [PMID: 20610541]
[http://dx.doi.org/10.1016/j.mce.2004.02.016] [PMID: 15451571]
[http://dx.doi.org/10.18632/oncotarget.5349] [PMID: 26447543]
[PMID: 20043075]
[http://dx.doi.org/10.1053/j.gastro.2004.03.011] [PMID: 15188178]
[http://dx.doi.org/10.1371/journal.pone.0090575] [PMID: 24599287]
[http://dx.doi.org/10.1016/j.canlet.2014.10.037] [PMID: 25449777]
[http://dx.doi.org/10.1359/jbmr.090219] [PMID: 19257827]
[PMID: 18936525]
[http://dx.doi.org/10.1080/02841860801898616] [PMID: 18607840]
[http://dx.doi.org/10.1159/000292104] [PMID: 20332657]
[http://dx.doi.org/10.1371/journal.pone.0043147] [PMID: 22912812]
[PMID: 23348390]
[http://dx.doi.org/10.1038/sj.bjc.6605299] [PMID: 19755982]
[http://dx.doi.org/10.1042/BJ20061597] [PMID: 17381424]
[http://dx.doi.org/10.1080/15592294.2016.1190894] [PMID: 27245242]
[http://dx.doi.org/10.1107/S1744309105030836] [PMID: 16511206]
[http://dx.doi.org/10.1016/j.cellsig.2016.10.005] [PMID: 27751915]
[PMID: 19260473]
[http://dx.doi.org/10.21873/anticanres.11150] [PMID: 27793888]
[http://dx.doi.org/10.18632/oncotarget.5689] [PMID: 26497556]
[http://dx.doi.org/10.1074/mcp.M700590-MCP200] [PMID: 18353764]
[http://dx.doi.org/10.1158/1078-0432.CCR-08-1908] [PMID: 19188145]
[http://dx.doi.org/10.1002/gcc.22378] [PMID: 27218826]
[PMID: 26753642]
[http://dx.doi.org/10.1159/000070297] [PMID: 12759536]
[http://dx.doi.org/10.1007/s00428-015-1755-2] [PMID: 25800244]
[http://dx.doi.org/10.1093/hmg/ddt638] [PMID: 24334765]
[http://dx.doi.org/10.1007/s10689-015-9818-8] [PMID: 26071763]