ゲノムネットワークプロジェクト

ヒトゲノムネットワークプラットフォーム構築
研究課題 生命科学文献からの情報抽出とテキストマイニング技術の開発
研究期間 平成16年度〜20年度
研究課題代表者 宮尾 祐介
所属機関 東京大学大学院情報理工学系研究科
公開システム Info PubMed (Interaction Network over the sea of MEDLINE)
MEDIE
研究目的 ゲノムネットワーク構築に有用な情報の多くが、膨大な論文群の中に埋もれている。また、論文から人手によってデータベース化されたあとも、生命科学研究者がそれを有効に活用できるためには、原著論文での情報の出現箇所だけでなく、新しい論文とも有機的に関連付けられていることが必須となる。 本研究では、言語処理技術、とくに、情報抽出(IE)技術、オントロジー技術を生命科学文献に適用することで、データベースと文献ベースを有機的に統合する技術を開発する。
研究概要 具体的には、生命科学の専門用語は複雑な構造を持つと同時に、新語の生成、類義語・関連語・異表記語・略語も頻繁に形成されることから、(1)論文からの用語の自動抽出、用語の意味クラスや用語間の意味関係の自動認定の技術を開発し、これと我々が従来から研究してきたテキスト構造の解析技術とを組み合わせることで、(2)論文からの事象情報の自動抽出(IE)技術の開発、(3)知的なテキストマイニングと情報検索システムの構築、を行う。研究結果は、すでに生命科学者が使うための知的な検索システム(Info-Pubmed、MEDIE)として一部公開されている。この2つのシステムの高度化を通じて、ゲノムネットワークのデータキュレーションとそれを活用する研究の効率化に寄与する。
研究成果 タンパク質間相互作用に関する情報抽出システムInfo-Pubmedにおいて、各種の二項関係を取り扱えるように再実装して、新たに疾患と遺伝子の関係情報を検索対象として追加した。また、論文アブストラクトから関係概念を高精度・高速に検索するシステムMEDIEにおいて取り扱える動詞の意味クラスを拡張すると共に、事象認識プログラムを用いて関係を分類した。
データ種別 -
対象生物 -
組織・細胞株 -
対象遺伝子 -
実験情報 -
産出データ
(ダウンロード)
-
XMLデータ -
研究論文・特許出願・
学術発表など
------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:989
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of IWPT 2007. Prague, Czech Republic, June
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2007-01-01
TITLE: Evaluating Impact of Re-training a Lexical Disambiguation Model on Domain Adaptation of an HPSG Parser.
STATUS: Presented
AUTHOR NAME: Hara, Tadayoshi, Yusuke Miyao and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:990
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the Twentieth International Joint Conference on Artificial Intelligence.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2007-01-01
TITLE: Ambiguous Part-of-Speech Tagging for Improving Accuracy and Domain Portability of Syntactic Parsers.
STATUS: Presented
AUTHOR NAME: Yoshida, Kazuhiro.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:991
PUBLICATION TYPE: journal
PUBLICATION NAME: BMC-Bioinformatics.
ARTICLE TITLE: Automatic Recognition of Topic-Classified Relations between Prostate Cancer and Genes using MEDLINE Abstracts.
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-11-01
TITLE: Automatic Recognition of Topic-Classified Relations between Prostate Cancer and Genes using MEDLINE Abstracts.
STATUS: Published
AUTHOR NAME: Chun, Hong-woo, Yoshimasa Tsuruoka, Jin-Dong Kim, Rie Shiba, Naoki Nagata, Teruyoshi Hishiki and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:992
PUBLICATION TYPE: journal
PUBLICATION NAME: Trends in Biotechmology.
ARTICLE TITLE: Text Mining and its potential applications in systems biology.
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-01-01
TITLE: Text Mining and its potential applications in systems biology.
STATUS: Published
AUTHOR NAME: Ananiadou, Sophia, Douglous Kell and Junichi Tsujii.
AUTHOR AFFILIATION: National Center for Text Mining

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:993
PUBLICATION TYPE: Book
PUBLICATION NAME: Text Mining for Biology and Biomedicine.
ARTICLE TITLE: Corpora and their Annotation
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-01-01
TITLE: Corpora and their Annotation
STATUS: Published
AUTHOR NAME: Kim, Jin-Dong and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:994
PUBLICATION TYPE: Conference
PUBLICATION NAME: The Pacific Symposium on Biocomputing (PSB)
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-01-01
TITLE: Extraction of Gene-Disease Relations from MedLine using Domain Dictionaries and Machine Learning.
STATUS: Presented
AUTHOR NAME: Chun, Hong-woo, Yoshimasa Tsuruoka, Jin-Dong Kim, Rie Shiba, Naoki Nagata, Teruyoshi Hishiki and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:995
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of COLING-ACL 2006.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-07-01
TITLE: Semantic Retrieval for the Accurate Identification of Relational Concepts in Massive Textbases.
STATUS: Presented
AUTHOR NAME: Miyao, Yusuke, Tomoko Ohta, Katsuya Masuda, Yoshimasa Tsuruoka, Kazuhiro Yoshida, Takashi Ninomiya and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:996
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of The Fifth International Conference on Language Resource and Evaluation (LREC 2006).
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-05-01
TITLE: Linguistic and Biological Annotations of Biological Interaction Events.
STATUS: Presented
AUTHOR NAME: Ohta, Tomoko, Yuka Tateisi, Jin-Dong Kim, Akane Yakushiji and Jun-ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:997
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. Sydney, Australia
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-07-01
TITLE: Automatic Construction of Predicate-argument Structure Patterns for Biomedical Information Extraction.
STATUS: Presented
AUTHOR NAME: Yakushiji, Akane, Miyao Yusuke, Tomoko Ohta, Yuka Tateisi and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:998
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions. Sydney, Australia,
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-07-01
TITLE: An Intelligent Search Engine and GUI-based Efficient MEDLINE Search Tool Based on Deep Syntactic Parsing.
STATUS: Presented
AUTHOR NAME: Ohta, Tomoko, Yusuke Miyao, Takashi Ninomiya, Yoshimasa Tsuruoka, Akane Yakushiji, Katsuya Masuda, Jumpei Takeuchi, Kazuhiro Yoshida, Tadayoshi Hara, Jin-Dong Kim, Yuka Tateisi and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:999
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-06-01
TITLE: Subdomain adaptation of a POS tagger with a small corpus.
STATUS: Presented
AUTHOR NAME: Tateisi, Yuka, Yoshimasa Tsuruoka and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1000
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the second international symposium on semantic mining in Biomedicine.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2006-04-01
TITLE: Automatic Recognition of Topic-Classified Relations between Prostate Cancer and Genes from Medline Abstracts.
STATUS: Presented
AUTHOR NAME: Chun, Hong-woo, Yoshimasa Tsuruoka, Jin-Dong Kim, Rie Shiba, Naoki Nagata, Teruyoshi Hishiki and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1001
PUBLICATION TYPE: journal
PUBLICATION NAME: Language Resources and Evaluation
ARTICLE TITLE: Thesaurus or logical ontology, which do we need for mining text?.
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-09-01
TITLE: Thesaurus or logical ontology, which do we need for mining text?.
STATUS: Published
AUTHOR NAME: Tsujii, Jun-ichi and Sophia Ananiadou.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1002
PUBLICATION TYPE: journal
PUBLICATION NAME: Natural Language Processing - IJCNLP
ARTICLE TITLE: Iterative CKY Parsing for Probabilistic Context-Free Grammars.
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-01-01
TITLE: Iterative CKY Parsing for Probabilistic Context-Free Grammars.
STATUS: Published
AUTHOR NAME: Tsuruoka, Yoshimasa and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1003
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Advances in Informatics - 10th Panhellenic Conference on Informatics.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-11-01
TITLE: Developing a Robust Part-of-Speech Tagger for Biomedical Text.
STATUS: Presented
AUTHOR NAME: Tsuruoka, Yoshimasa, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1004
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Lecture Notes in Artificial Intelligence.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-01-01
TITLE: Unsupervised Event Extraction from Biomedical Literature using Co-occurrence Information and Basic Patterns.
STATUS: Presented
AUTHOR NAME: Chun, Hong-Woo, Young-Sook Hwang and Hae-Chang Rim.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1005
PUBLICATION TYPE: Conference
PUBLICATION NAME: Natural Language Processing – IJCNLP 2005. Lecture Notes in Artificial Intelligence3651. Jeju Island, Korea,
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-10-01
TITLE: Adapting a probabilistic disambiguation model of an HPSG parser to a new domain.
STATUS: Presented
AUTHOR NAME: Hara, Tadayoshi, Yusuke Miyao and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1006
PUBLICATION TYPE: Conference
PUBLICATION NAME: Natural Language Processing - IJCNLP
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-01-01
TITLE: Word Folding: Taking the Snapshot of Words Instead of the Whole.
STATUS: Presented
AUTHOR NAME: Kim, Jin-Dong and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1007
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the ACL-ISMB Workshop on Linking Biological Literature, Ontologies and Databases: Mining Biological Semantics.
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-06-01
TITLE: A Machine Learning Approach to Acronym Generation.
STATUS: Presented
AUTHOR NAME: Tsuruoka, Yoshimasa, Sophia Ananiadou and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1008
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the Proceedings of the IJCNLP 2005,
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-10-01
TITLE: Syntax Annotation for the GENIA corpus.
STATUS: Presented
AUTHOR NAME: Tateisi, Yuka, Akane Yakushiji, Tomoko Ohta and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1009
PUBLICATION TYPE: Conference
PUBLICATION NAME: In the the Proceedings of the First International Symposium on Semantic Mining in Biomedicine. Hinxton,
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2005-01-01
TITLE: Biomedical Information Extraction with Predicate-Argument Structure Patterns.
STATUS: Presented
AUTHOR NAME: Yakushiji, Akane, Yusuke Miyao, Yuka Tateisi and Jun'ichi Tsujii.
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1898
PUBLICATION TYPE: Conference
PUBLICATION NAME: the Third International Symposium on Semantic Mining in Biomedicine (SMBM 2008)
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-09-03
TITLE: Exploring the Compatibility of Heterogeneous Protein Annotations Toward Corpus Integration
STATUS: Presented
AUTHOR NAME: Wang, Yue, Jin-Dong Kim, Rune Sætre and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1899
PUBLICATION TYPE: Conference
PUBLICATION NAME: the Third International Symposium on Semantic Mining in Biomedicine (SMBM 2008)
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-09-02
TITLE: Combining Multiple Layers of Syntactic Information for Protein-Protein Interaction Extraction
STATUS: Presented
AUTHOR NAME: Miwa, Makoto, Rune Satre, Yusuke Miyao, Tomoko Ohta and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1900
PUBLICATION TYPE: Conference
PUBLICATION NAME: the 6th Asia Pacific Bioinformatics Conference. Series on Advances in Bioinformatics and Computational Biology6
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-01-15
TITLE: From Text to Pathway: Corpus Annotation for Knowledge Acquisition from Biomedical Literature
STATUS: Presented
AUTHOR NAME: Kim, Jin-Dong, Ohta, Tomoko, Oda, Kanae and Tsujii, Jun'ichi
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1901
PUBLICATION TYPE: Conference
PUBLICATION NAME: the 5th International Conference on Language Resources and Evaluation
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-05-29
TITLE: GENIA-GR: a Grammatical Relation Corpus for Parser Evaluation in the Biomedical Domain
STATUS: Presented
AUTHOR NAME: Tateisi, Yuka, Yusuke Miyao, Kenji Sagae and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1902
PUBLICATION TYPE: Conference
PUBLICATION NAME: LREC-2008 Workshop: Building and evaluating resources for biotext mining
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-05-26
TITLE: A Comparison of Knowledge Resource Designs: Supporting Term-level Text Annotation
STATUS: Presented
AUTHOR NAME: Alicia, Tribble, Jin-Dong Kim, Tomoko Ohta, Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1903
PUBLICATION TYPE: Conference
PUBLICATION NAME: ACL-08:HLT
ARTICLE TITLE:
SUBMIT DATE:
ACCEPT DATE:
PUBLICATION DATE: 2008-06-16
TITLE: Task-Oriented Evaluation of Syntactic Parsers and Their Representations
STATUS: Presented
AUTHOR NAME: Miyao, Yusuke, Rune Sætre, Kenji Sagae, Takuya Matsuzaki and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1904
PUBLICATION TYPE: journal
PUBLICATION NAME: BMC Bioinformatics. 9(Suppl 3)
ARTICLE TITLE: New challenges for text mining: Mapping between text and manually curated pathways
SUBMIT DATE: 2007-10-20
ACCEPT DATE: 2007-11-02
PUBLICATION DATE: 2008-04-11
TITLE: New challenges for text mining: Mapping between text and manually curated pathways
STATUS: Published
AUTHOR NAME: Oda, Kanae, Jin-Dong Kim, Tomoko Ohta, Daisuke Okanohara, Takuya Matsuzaki, Yuka Tateisi and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1905
PUBLICATION TYPE: journal
PUBLICATION NAME: BMC Bioinformatics. 9(1)
ARTICLE TITLE: Corpus annotation for mining biomedical events from lterature
SUBMIT DATE: 2007-07-26
ACCEPT DATE: 2008-01-08
PUBLICATION DATE: 2008-01-08
TITLE: Corpus annotation for mining biomedical events from lterature
STATUS: Published
AUTHOR NAME: Kim, Jin-Dong, Tomoko Ohta and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

------------------------------ PUBLICATION ------------------------------
PUBLICATION ID:1906
PUBLICATION TYPE: journal
PUBLICATION NAME: Bioinformatics. 25(3)
ARTICLE TITLE: Evaluating Contributions of Natural Language Parsers to Protein-Protein Interaction Extraction
SUBMIT DATE: 2008-09-18
ACCEPT DATE: 2008-12-03
PUBLICATION DATE: 2008-12-09
TITLE: Evaluating Contributions of Natural Language Parsers to Protein-Protein Interaction Extraction
STATUS: Published
AUTHOR NAME: Miyao, Yusuke, Kenji Sagae, Rune Saetre, Takuya Matsuzaki and Jun'ichi Tsujii
AUTHOR AFFILIATION: University of Tokyo

その他 -
btn_close02_j.gif