Identifying projected clusters from gene expression profiles

摘要: In microarray gene expression data, clusters may hide in subspaces. Traditional clustering algorithms that make use of similarity measurements the full input space fail to detect clusters. recent years a number have been proposed identify this kind projected clusters, but many them rely on some critical parameters whose proper values are hard for users determine. paper new algorithm dynamically adjusts its internal thresholds is proposed. It has low dependency user while allowing domain knowledge should they be available. Experimental results show capable identifying interesting from real data.