한국생물정보학회:학술대회논문집 (Proceedings of the Korean Society for Bioinformatics Conference)
- 한국생물정보시스템생물학회 2001년도 제2회 생물정보학 국제심포지엄
- /
- Pages.103-127
- /
- 2001
Statistical bioinformatics for gene expression data
초록
Gene expression studies require statistical experimental designs and validation before laboratory confirmation. Various clustering approaches, such as hierarchical, Kmeans, SOM are commonly used for unsupervised learning in gene expression data. Several classification methods, such as gene voting, SVM, or discriminant analysis are used for supervised lerning, where well-defined response classification is possible. Estimating gene-condition interaction effects require advanced, computationally-intensive statistical approaches.
키워드