Online phenotype discovery based on minimum classification error model

PATTERN RECOGNITION

卷:42

Article; Proceedings Paper

Yin, Zheng^1,2,3  Zhou, Xiaobo^2,3  Sun, Youxian¹  Wong, Stephen T. C.^2,3 

[1] Zhejiang Univ, State Key Lab Ind Control Technol, Hangzhou 310027, Zhejiang, Peoples R China

[2] Methodist Hosp, Res Inst, Ctr Biotechnol & Informat, Houston, TX 77030 USA

[3] Weill Cornell Coll Med, Houston, TX 77030 USA

关键词: Online phenotype discovery;    Minimum classification error;    RNA interference;    High content screen;    Gap statistics;   

DOI  :  10.1016/j.patcog.2008.09.032

来源: Elsevier

【 摘 要 】

Identifying and validating novel phenotypes from images inputting online is a major challenge against high-content RNA interference (RNAi) screening. Newly discovered phenotypes should be visually distinct from existing ones and make biological sense. An online phenotype discovery method featuring adaptive phenotype modeling and iterative cluster merging using improved gap statistics is proposed. Clustering results based on compactness criteria and Gaussian Mixture models (GMM) for existing phenotypes iteratively modify each other by multiple hypothesis test and model optimization based on minimum classification error (MCE). The method works well on discovering new phenotypes adaptively when applied to both of synthetic datasets and RNAi high content screen (HCS) images with ground truth labels. (C) 2008 Elsevier Ltd. All rights reserved.

【 授权许可】

Free