Identification of Schizophrenia-Associated Gene Polymorphisms Using Hybrid Filtering Feature Selection with Structural Information
文献类型：会议论文
| 作者 | Yingying Wang; Zichun Zeng; Yunpeng Cai |
| 出版日期 | 2015 |
| 会议名称 | The 4th International Conference on Health Information Science (HIS 2015) |
| 会议地点 | Melbourne,Australia |
| 英文摘要 | Schizophrenia is a complex and severe neurological disorder that affects lots of people worldwide. Despite its strong evidence of heritability revealed by lots of genetic studies, research for locating of schizophrenia associated genes remains frustrating as numerous efforts had failed to identify biomarkers that could strongly impact the diagnosis and prognosis of schizophrenia. The major challenge lies in the weak discrimination of single gene marker and the enormous number of gene variants that exist in human genome. In this paper we propose a hybrid feature selection method that utilizes the biological structural information of the gene variants to tackle this problem. A set of statistical techniques are developed to encourage the clustering of multiple informative SNP variants on the same gene, which boost the probability of finding biologically meaningful features and suppresses false discoveries. As a result, the proposed method achieves significantly better performance on a published schizophrenia human genome data set compared with previous studies, with an area-under-ROC-curve of 65% and an odd ratio of 2.82 (95%CI: 1.80 – 4.40). 36 gene markers are discovered to be associated with the onset of schizophrenia with many of which verified directly or indirectly by previous literature. The method proposed in this paper can be also adopted for efficient control of false discoveries in finding biomarkers from genomic data. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/7278]  |
| 专题 | 深圳先进技术研究院_医工所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | Yingying Wang,Zichun Zeng,Yunpeng Cai. Identification of Schizophrenia-Associated Gene Polymorphisms Using Hybrid Filtering Feature Selection with Structural Information[C]. 见:The 4th International Conference on Health Information Science (HIS 2015) . Melbourne,Australia. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。