Publications-Periodical Articles
Article View/Open
Publication Export
-
題名 MeInfoText 2.0: gene methylation and cancer relation extraction from biomedical literature 作者 Lai, Po-Ting
賴柏廷
Hsu, Wen-Lian
Dai, Hong-Jie
Fang, Yu-Ching貢獻者 資訊科學系 日期 2011-12 上傳時間 5-Aug-2015 14:29:53 (UTC+8) 摘要 Background DNA methylation is regarded as a potential biomarker in the diagnosis and treatment of cancer. The relations between aberrant gene methylation and cancer development have been identified by a number of recent scientific studies. In a previous work, we used co-occurrences to mine those associations and compiled the MeInfoText 1.0 database. To reduce the amount of manual curation and improve the accuracy of relation extraction, we have now developed MeInfoText 2.0, which uses a machine learning-based approach to extract gene methylation-cancer relations. Description Two maximum entropy models are trained to predict if aberrant gene methylation is related to any type of cancer mentioned in the literature. After evaluation based on 10-fold cross-validation, the average precision/recall rates of the two models are 94.7/90.1 and 91.8/90% respectively. MeInfoText 2.0 provides the gene methylation profiles of different types of human cancer. The extracted relations with maximum probability, evidence sentences, and specific gene information are also retrievable. The database is available at http://bws.iis.sinica.edu.tw:8081/MeInfoText2/. Conclusion The previous version, MeInfoText, was developed by using association rules, whereas MeInfoText 2.0 is based on a new framework that combines machine learning, dictionary lookup and pattern matching for epigenetics information extraction. The results of experiments show that MeInfoText 2.0 outperforms existing tools in many respects. To the best of our knowledge, this is the first study that uses a hybrid approach to extract gene methylation-cancer relations. It is also the first attempt to develop a gene methylation and cancer relation corpus. 關聯 BMC Bioinformatics,12:471 資料類型 article DOI http://dx.doi.org/10.1186/1471-2105-12-471 dc.contributor 資訊科學系 - dc.creator (作者) Lai, Po-Ting - dc.creator (作者) 賴柏廷 zh_TW dc.creator (作者) Hsu, Wen-Lian en_US dc.creator (作者) Dai, Hong-Jie en_US dc.creator (作者) Fang, Yu-Ching en_US dc.date (日期) 2011-12 - dc.date.accessioned 5-Aug-2015 14:29:53 (UTC+8) - dc.date.available 5-Aug-2015 14:29:53 (UTC+8) - dc.date.issued (上傳時間) 5-Aug-2015 14:29:53 (UTC+8) - dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/77424 - dc.description.abstract (摘要) Background DNA methylation is regarded as a potential biomarker in the diagnosis and treatment of cancer. The relations between aberrant gene methylation and cancer development have been identified by a number of recent scientific studies. In a previous work, we used co-occurrences to mine those associations and compiled the MeInfoText 1.0 database. To reduce the amount of manual curation and improve the accuracy of relation extraction, we have now developed MeInfoText 2.0, which uses a machine learning-based approach to extract gene methylation-cancer relations. Description Two maximum entropy models are trained to predict if aberrant gene methylation is related to any type of cancer mentioned in the literature. After evaluation based on 10-fold cross-validation, the average precision/recall rates of the two models are 94.7/90.1 and 91.8/90% respectively. MeInfoText 2.0 provides the gene methylation profiles of different types of human cancer. The extracted relations with maximum probability, evidence sentences, and specific gene information are also retrievable. The database is available at http://bws.iis.sinica.edu.tw:8081/MeInfoText2/. Conclusion The previous version, MeInfoText, was developed by using association rules, whereas MeInfoText 2.0 is based on a new framework that combines machine learning, dictionary lookup and pattern matching for epigenetics information extraction. The results of experiments show that MeInfoText 2.0 outperforms existing tools in many respects. To the best of our knowledge, this is the first study that uses a hybrid approach to extract gene methylation-cancer relations. It is also the first attempt to develop a gene methylation and cancer relation corpus. - dc.format.extent 540843 bytes - dc.format.mimetype application/pdf - dc.relation (關聯) BMC Bioinformatics,12:471 - dc.title (題名) MeInfoText 2.0: gene methylation and cancer relation extraction from biomedical literature - dc.type (資料類型) article en dc.identifier.doi (DOI) 10.1186/1471-2105-12-471 - dc.doi.uri (DOI) http://dx.doi.org/10.1186/1471-2105-12-471 -
