Clustering Microarray-Derived Gene Lists through Implicit Literature Relationships.

@article{citeulike:1562635, abstract = {MOTIVATION: Microarrays rapidly generate large quantities of gene expression information, but interpreting such data within a biological context is still relatively complex and laborious. New methods that can identify functionally related genes via shared literature concepts will be useful in addressing these needs. RESULTS: We have developed a novel method that uses implicit literature relationships (concepts related via shared, intermediate concepts) to cluster related genes. Genes are evaluated for implicit connections within a network of biomedical objects (other genes, ontological concepts, and diseases) that are connected via their co-occurrences in Medline titles and/or abstracts. On the basis of these implicit relationships, individual gene pairs are scored using a probability-based algorithm. Scores are generated for all pairwise combinations of genes, which are then clustered based on the scores. We applied this method to a test set composed of nine functional groups with known relationships. The method scored highly for all nine groups and significantly better than a benchmark co-occurrence-based method for six groups. We then applied this method to gene sets specific to two previously defined breast tumor subtypes. Analysis of the results recapitulated known biological relationships and identified novel pathway relationships unique to each tumor subtype. We demonstrate that this method provides a valuable new means of identifying and visualizing significantly related genes within gene lists via their implicit relationships in the literature. SUPPLEMENTARY INFORMATION: Supplemental Figures 1 - 5. Supplemental Tables 1 and 2.}, address = {Departments of Internal Medicine and Biochemistry, The McDermott Center for Human Growth and Development, Division of Translational Research, The University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd., Dallas, Texas 75390, USA, Arthritis \& Immunology Program, Oklahoma Medical Research Foundation, 825 N.E. 13th Street, Oklahoma City, Oklahoma 73104,USA, Lineberger Comprehensive Cancer Center, Department of Genetics, Department of Pathology \& Laboratory Medicine, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.}, author = {Burkart, Mark F F. and Wren, Jonathan D D. and Herschkowitz, Jason I I. and Perou, Charles M M. and Garner, Harold R R. }, citeulike-article-id = {1562635}, doi = {doi:10.1093/bioinformatics/btm261 }, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {literature-based-discovery, microarray}, month = {May}, posted-at = {2007-08-15 15:23:38}, priority = {2}, title = {Clustering Microarray-Derived Gene Lists through Implicit Literature Relationships.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17537751}, year = {2007} }

TY - JOUR ID - citeulike:1562635 L3 - citeulike-article-id:1562635 TI - Clustering Microarray-Derived Gene Lists through Implicit Literature Relationships. JF - Bioinformatics AD - Departments of Internal Medicine and Biochemistry, The McDermott Center for Human Growth and Development, Division of Translational Research, The University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd., Dallas, Texas 75390, USA, Arthritis & Immunology Program, Oklahoma Medical Research Foundation, 825 N.E. 13th Street, Oklahoma City, Oklahoma 73104,USA, Lineberger Comprehensive Cancer Center, Department of Genetics, Department of Pathology & Laboratory Medicine, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. SN - 1460-2059 N2 - MOTIVATION: Microarrays rapidly generate large quantities of gene expression information, but interpreting such data within a biological context is still relatively complex and laborious. New methods that can identify functionally related genes via shared literature concepts will be useful in addressing these needs. RESULTS: We have developed a novel method that uses implicit literature relationships (concepts related via shared, intermediate concepts) to cluster related genes. Genes are evaluated for implicit connections within a network of biomedical objects (other genes, ontological concepts, and diseases) that are connected via their co-occurrences in Medline titles and/or abstracts. On the basis of these implicit relationships, individual gene pairs are scored using a probability-based algorithm. Scores are generated for all pairwise combinations of genes, which are then clustered based on the scores. We applied this method to a test set composed of nine functional groups with known relationships. The method scored highly for all nine groups and significantly better than a benchmark co-occurrence-based method for six groups. We then applied this method to gene sets specific to two previously defined breast tumor subtypes. Analysis of the results recapitulated known biological relationships and identified novel pathway relationships unique to each tumor subtype. We demonstrate that this method provides a valuable new means of identifying and visualizing significantly related genes within gene lists via their implicit relationships in the literature. SUPPLEMENTARY INFORMATION: Supplemental Figures 1 - 5. Supplemental Tables 1 and 2. KW - literature-based-discovery KW - microarray AU - Burkart, Mark F AU - Wren, Jonathan D AU - Herschkowitz, Jason I AU - Perou, Charles M AU - Garner, Harold R PY - 2007/05/30/ UR - http://view.ncbi.nlm.nih.gov/pubmed/17537751 ER -