Text-mining assisted regulatory annotation

@article{citeulike:2369777, abstract = {BACKGROUND:Decoding transcriptional regulatory networks and the genomic cis-regulatory logic implemented in their control nodes are fundamental challenges in genome biology. High-throughput computational and experimental analyses of regulatory networks and sequences rely heavily on positive control data from prior small-scale experiments, but the vast majority of previously discovered regulatory data remains locked in the biomedical literature. RESULTS:We develop text-mining strategies to identify relevant publications and extract sequence information to assist the regulatory annotation process. Using a vector space model to identify Medline abstracts from papers likely to have high cis-regulatory content, we demonstrate that document relevance ranking can assist the curation of transcriptional regulatory networks and estimate that over 30,000 papers harbour unannotated cis-regulatory data. Additionally, we show that DNA sequences can be automatically extracted from full-text articles with high cis-regulatory content and accurately mapped to genome sequences as a means of identifying the location, organism and target gene information that is critical to the cis-regulatory annotation process. CONCLUSIONS:Our results demonstrate that text-mining technologies can be successfully integrated with genome annotation systems, thereby increasing the availability of annotated cis-regulatory data needed to catalyze advances in the field of gene regulation.}, author = {Aerts, Stein and Haeussler, Maximilian and van Vooren, Steven and Griffith, Obi and Hulpiau, Paco and Jones, Steven and Montgomery, Stephen and Bergman, Casey and The}, citeulike-article-id = {2369777}, doi = {http://dx.doi.org/10.1186/gb-2008-9-2-r31}, journal = {Genome Biology}, keywords = {database, genomics, text-mining}, number = {2}, posted-at = {2008-07-18 06:19:23}, priority = {2}, title = {Text-mining assisted regulatory annotation}, url = {http://dx.doi.org/10.1186/gb-2008-9-2-r31}, volume = {9}, year = {2008} }

TY - JOUR ID - citeulike:2369777 L3 - citeulike-article-id:2369777 TI - Text-mining assisted regulatory annotation JF - Genome Biology VL - 9 IS - 2 N2 - BACKGROUND:Decoding transcriptional regulatory networks and the genomic cis-regulatory logic implemented in their control nodes are fundamental challenges in genome biology. High-throughput computational and experimental analyses of regulatory networks and sequences rely heavily on positive control data from prior small-scale experiments, but the vast majority of previously discovered regulatory data remains locked in the biomedical literature. RESULTS:We develop text-mining strategies to identify relevant publications and extract sequence information to assist the regulatory annotation process. Using a vector space model to identify Medline abstracts from papers likely to have high cis-regulatory content, we demonstrate that document relevance ranking can assist the curation of transcriptional regulatory networks and estimate that over 30,000 papers harbour unannotated cis-regulatory data. Additionally, we show that DNA sequences can be automatically extracted from full-text articles with high cis-regulatory content and accurately mapped to genome sequences as a means of identifying the location, organism and target gene information that is critical to the cis-regulatory annotation process. CONCLUSIONS:Our results demonstrate that text-mining technologies can be successfully integrated with genome annotation systems, thereby increasing the availability of annotated cis-regulatory data needed to catalyze advances in the field of gene regulation. KW - database KW - genomics KW - text-mining AU - Aerts, Stein AU - Haeussler, Maximilian AU - van Vooren, Steven AU - Griffith, Obi AU - Hulpiau, Paco AU - Jones, Steven AU - Montgomery, Stephen AU - Bergman, Casey AU - The PY - 2008/// UR - http://dx.doi.org/10.1186/gb-2008-9-2-r31 ER -