Semi-Supervised Ligand Finding Using Formal Concept Analysis

• Item type: SIG Technical Reports(1)
• 公開日: 2011-11-24
• タイトル: Semi-Supervised Ligand Finding Using Formal Concept Analysis
• タイトル / 言語: en
• タイトル: Semi-Supervised Ligand Finding Using Formal Concept Analysis
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Graduate School of Informatics, Kyoto University／Presently with Research Fellow of the Japan Society for the Promotion of Science
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University / Presently with Research Fellow of the Japan Society for the Promotion of Science
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者名: Mahito, Sugiyama; Kentaro, Imajo; Keisuke, Otaki; Akihiro, Yamamoto
• 著者名(英): Mahito, Sugiyama; Kentaro, Imajo; Keisuke, Otaki; Akihiro, Yamamoto
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: To date, enormous studies have been devoted to investigate biochemical functions of receptors, which have crucial roles for signal processing in organisms, and ligands are key tools in experiments since receptor specificity with respect to them enables us to control activity of receptors. However, finding ligands is difficult; choosing ligand candidates relies on expert knowledge of biologists and conducting test experiments in vivo or in vitro costs high. Here we challenge to ligand finding with a machine learning approach by formalizing the problem as multi-label classification mainly discussed in the area of preference learning. We develop in this paper a new algorithm LIFT (Ligand FInding via Formal ConcepT Analysis) for multi-label classification, which can treat ligand data in databases in the semi-supervised manner. The key to LIFT is to realize clustering by putting an original dataset on lattices using the data analysis technique of Formal Concept Analysis (FCA), followed by obtaining the preference for each label using the lattice structure. Experiments using real data of ligands and receptors in the IUPHAR database show that LIFT effectively solves our task compared to other machine learning algorithms.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: To date, enormous studies have been devoted to investigate biochemical functions of receptors, which have crucial roles for signal processing in organisms, and ligands are key tools in experiments since receptor specificity with respect to them enables us to control activity of receptors. However, finding ligands is difficult; choosing ligand candidates relies on expert knowledge of biologists and conducting test experiments in vivo or in vitro costs high. Here we challenge to ligand finding with a machine learning approach by formalizing the problem as multi-label classification mainly discussed in the area of preference learning. We develop in this paper a new algorithm LIFT (Ligand FInding via Formal ConcepT Analysis) for multi-label classification, which can treat ligand data in databases in the semi-supervised manner. The key to LIFT is to realize clustering by putting an original dataset on lattices using the data analysis technique of Formal Concept Analysis (FCA), followed by obtaining the preference for each label using the lattice structure. Experiments using real data of ligands and receptors in the IUPHAR database show that LIFT effectively solves our task compared to other machine learning algorithms.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10505667
• 書誌情報: 研究報告数理モデル化と問題解決（MPS）; 巻 2011-MPS-86, 号 28, p. 1-6, 発行日 2011-11-24
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会