Biclustering in gene expression data by tendency

Jinze Liu, Jiong Yang, Wei Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

62 Scopus citations


The advent of DNA microarray technologies has revolutionized the experimental study of gene expression. Clustering is the most popular approach of analyzing gene expression data and has indeed proven to be successful in many applications. Our work focuses on discovering a subset of genes which exhibit similar expression patterns along a subset of conditions in the gene expression matrix. Specifically, we are looking for the Order Preserving clusters (OP-Cluster), in each of which a subset of genes induce a similar linear ordering along a subset of conditions. The pioneering work of the OPSM model[3], which enforces the strict order shared by the genes in a cluster, is included in our model as a special case. Our model is more robust than OPSM because similarly expressed conditions are allowed to form order equivalent groups and no restriction is placed on the order within a group. Guided by our model, we design and implement a deterministic algorithm, namely OPC-Tree, to discover OP-Clusters. Experimental study on two real datasets demonstrates the effectiveness of the algorithm in the application of tissue classification and cell cycle identification. In addition, a large percentage of OP-Clusters exhibit significant enrichment of one or more function categories, which implies that OP-Clusters indeed carry significant biological relevance.

Original languageEnglish
Title of host publicationProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004
Number of pages12
StatePublished - 2004
EventProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004 - Stanford, CA, United States
Duration: Aug 16 2004Aug 19 2004

Publication series

NameProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004


ConferenceProceedings - 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004
Country/TerritoryUnited States
CityStanford, CA


  • Biclustering
  • Gene expression data
  • Microarray data
  • Order preserving

ASJC Scopus subject areas

  • Engineering (all)


Dive into the research topics of 'Biclustering in gene expression data by tendency'. Together they form a unique fingerprint.

Cite this