ダウンロード数: 267
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
fmc-2016-0197.pdf | 4.81 MB | Adobe PDF | 見る/開く |
タイトル: | Active learning for computational chemogenomics |
著者: | Reker, Daniel Schneider, Petra Schneider, Gisbert Brown, JB |
キーワード: | chemogenomics computational chemistry and modeling virtual screening |
発行日: | Mar-2017 |
出版者: | Future Science |
誌名: | Future Medicinal Chemistry |
巻: | 9 |
号: | 4 |
開始ページ: | 381 |
終了ページ: | 402 |
抄録: | Aim: Computational chemogenomics models the compound–protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of proteins and ligands. As an alternative to modeling entire large datasets at once, active learning adaptively incorporates a minimum of informative examples for modeling, yielding compact but high quality models. Results/methodology: We assessed active learning for protein/target family-wide chemogenomic modeling by replicate experiment. Results demonstrate that small yet highly predictive models can be extracted from only 10–25% of large bioactivity datasets, irrespective of molecule descriptors used. Conclusion: Chemogenomic active learning identifies small subsets of ligand–target interactions in a large screening database that lead to knowledge discovery and highly predictive models. |
記述: | ビッグデータを使わない薬物候補探索モデルを開発 : 化合物の実験データから薬効予測に有効なものを選びとる新手法 |
著作権等: | © Daniel Reker et al. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 Unported License. |
URI: | http://hdl.handle.net/2433/218686 |
DOI(出版社版): | 10.4155/fmc-2016-0197 |
PubMed ID: | 28263088 |
関連リンク: | http://www.kyoto-u.ac.jp/ja/research/research_results/2016/170306_1.html |
出現コレクション: | 学術雑誌掲載論文等 |
このリポジトリに保管されているアイテムはすべて著作権により保護されています。