Ensemble learning for detecting gene-gene interactions in colorectal cancer.
Ensemble learning for detecting gene-gene interactions in colorectal cancer.
复制标题
作者：
Dorani F;Hu T;Woods MO;Zhai G
结直肠癌 (CRC) 在男性和女性中的发病率都很高，每年影响数百万人。 CRC 的全基因组关联研究 (GWAS) 成功揭示了与 CRC 风险相关的常见单核苷酸多态性 (SNP)。然而，它们只能解释疾病遗传性的非常有限的一部分。原因之一可能是 GWAS 中常见的单变量分析，一次检查一个遗传变异。考虑到癌症的复杂性，多种遗传变异之间的非加性相互作用效应有可能解释缺失的遗传性。在这项研究中，我们采用了两种强大的集成学习算法：随机森林和梯度增强机 (GBM)，来搜索通过非加性基因-基因相互作用导致疾病风险的 SNP。我们能够找到 44 个可能的易感性 SNP，这些 SNP 被两种算法排名为最重要。在这 44 个 SNP 中，29 个位于编码区。这 29 个基因包括先前发现与 CRC 相关的 ARRDC5、DCC、ALK 和 ITGA1，以及可能与 CRC 相关的 E2F3 和 NID2，因为它们已知与其他类型的癌症存在关联。我们利用信息论技术对44个SNP进行了配对和三向相互作用分析，发现其中有17个配对（p < 0.02）和16个三向（p ≤ 0.001）相互作用。此外，功能富集分析提出了 16 个功能术语或生物学途径，可以帮助我们更好地了解该疾病的病因。
Colorectal cancer (CRC) has a high incident rate in both men and women and is affecting millions of people every year. Genome-wide association studies (GWAS) on CRC have successfully revealed common single-nucleotide polymorphisms (SNPs) associated with CRC risk. However, they can only explain a very limited fraction of the disease heritability. One reason may be the common uni-variable analyses in GWAS where genetic variants are examined one at a time. Given the complexity of cancers, the non-additive interaction effects among multiple genetic variants have a potential of explaining the missing heritability. In this study, we employed two powerful ensemble learning algorithms, random forests and gradient boosting machine (GBM), to search for SNPs that contribute to the disease risk through non-additive gene-gene interactions. We were able to find 44 possible susceptibility SNPs that were ranked most significant by both algorithms. Out of those 44 SNPs, 29 are in coding regions. The 29 genes include ARRDC5, DCC, ALK, and ITGA1, which have been found previously associated with CRC, and E2F3 and NID2, which are potentially related to CRC since they have known associations with other types of cancer. We performed pairwise and three-way interaction analysis on the 44 SNPs using information theoretical techniques and found 17 pairwise (p < 0.02) and 16 three-way (p ≤ 0.001) interactions among them. Moreover, functional enrichment analysis suggested 16 functional terms or biological pathways that may help us better understand the etiology of the disease.
登录
查看更多内容
使用统计上居性网络在人类疾病关联研究中表征遗传相互作用。
影响因子：
3
作者：
Hu T;Sinnott-Armstrong NA;Kiralis JW;Andrew AS;Karagas MR;Moore JH
通讯作者：
Moore JH
影响因子：
4.4
作者：
Chen, Xi;Ishwaran, Hemant
通讯作者：
Ishwaran, Hemant
DOI：
10.1158/1541-7786.mcr-13-0479-t
发表时间：
2014-01
期刊：
Molecular cancer research : MCR
影响因子：
--
作者：
Aisner DL;Nguyen TT;Paskulin DD;Le AT;Haney J;Schulte N;Chionh F;Hardingham J;Mariadason J;Tebbutt N;Doebele RC;Weickhardt AJ;Varella-Garcia M
通讯作者：
Varella-Garcia M
影响因子：
1.9
作者：
Garcia-Magarinos, Manuel;Lopez-de-Ullibarri, Inaki;Salas, Antonio
通讯作者：
Salas, Antonio
影响因子：
3.5
作者：
Easton, Douglas F.;Eeles, Rosalind A.
通讯作者：
Eeles, Rosalind A.