{"created":"2025-01-19T01:28:43.901508+00:00","updated":"2025-01-19T11:31:56.476446+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229524","sets":["1164:5352:11207:11373"]},"path":["11373"],"owner":"44499","recid":"229524","title":["リガンド結合による構造変化が大きいタンパク質の予測"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-22"},"_buckets":{"deposit":"cb0a1280-a1df-4cb5-ba35-878095242f7a"},"_deposit":{"id":"229524","pid":{"type":"depid","value":"229524","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"リガンド結合による構造変化が大きいタンパク質の予測","author_link":["617352","617353"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"リガンド結合による構造変化が大きいタンパク質の予測"},{"subitem_title":"Prediction of proteins with large conformational changes due to ligand binding","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2023-11-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業大学情報理工学院情報工学系知能情報コース"},{"subitem_text_value":"東京工業大学情報理工学院情報工学系知能情報コース"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, School of Computing, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, School of Computing, Tokyo Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/229524/files/IPSJ-BIO23076002.pdf","label":"IPSJ-BIO23076002.pdf"},"date":[{"dateType":"Available","dateValue":"2025-11-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-BIO23076002.pdf","filesize":[{"value":"4.5 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"41"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"615d73a7-1ccf-4d18-b7d3-f34b605ee6fc","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"酒居, 寛太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石田, 貴士"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12055912","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8590","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"タンパク質は本質的に柔軟性があり,同じタンパク質でも複数の構造形態を取ることができる.この多様性は,リガンドが結合した状態(ホロ構造)と非結合状態(アポ構造)の間で顕著な構造的差異を生じさせる.ドッキングシミュレーションでは,ホロ構造の使用が一般に予測精度を向上させるが,多くのタンパク質でホロ構造が未解明であり,これらのタンパク質のための効果的なホロ構造予測手法はまだ確立されていない.タンパク質の柔軟性は異なるため,ドッキングシミュレーションに与える影響もタンパク質ごとに異なる.本研究では,リガンド結合による顕著な構造変化を示し,ドッキングシミュレーションの精度に大きな影響を与える可能性のあるタンパク質を特定するための新しいアプローチを提案する.Graph Neural Network を使用し,アポ構造とポケットの重心座標を入力として,ホロとアポのリガンド結合部位(ポケット)のRMSD (Root Mean Square Deviation) に基づいて,大きな構造変化を示すタンパク質を予測する.初期結果は,この手法がランダム予測を上回る精度を示していることを示唆している.本研究は,どのようなタンパク質が大きな構造変化を起こすのかを理解し,またドッキングシミュレーションの精度向上に寄与するものである.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Proteins are inherently flexible, and the same protein can take on multiple structural forms. This diversity leads to marked structural differences between the ligand-bound state (holo structure) and the unbound state (apo structure). In docking simulations, the use of holo structures generally improves prediction accuracy, but holo structures are unresolved for many proteins, and effective holo structure prediction methods for these proteins have not yet been established. Since proteins vary in flexibility, the impact on docking simulations is also different for each protein. In this study, we propose a novel approach to identify proteins that exhibit significant conformational changes due to ligand binding and may have a significant impact on the accuracy of docking simulations, using Graph Neural Networks, with apo structure and pocket center of gravity coordinates as input, Based on the RMSD of the holo and apo ligand binding sites (pockets), we predict proteins that exhibit large conformational changes. Initial results suggest that this method is more accurate than random prediction. This study will contribute to our understanding of which proteins undergo large conformational changes and to improving the accuracy of docking simulations.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告バイオ情報学(BIO)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2023-BIO-76"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229524,"links":{}}