Deep learning model for accurately predicting protein-protein interactions from sequence data alone

• Item type: SIG Technical Reports(1)
• 公開日: 2023-08-30
• タイトル: Deep learning model for accurately predicting protein-protein interactions from sequence data alone
• タイトル / 言語: en
• タイトル: Deep learning model for accurately predicting protein-protein interactions from sequence data alone
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: ディスカッショントラック
• 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: Kyushu Institute of Technology
• 著者所属: Kyushu Institute of Technology
• 著者所属(英): en
• 著者所属(英): Kyushu Institute of Technology
• 著者所属(英): en
• 著者所属(英): Kyushu Institute of Technology
• 著者名: Hiroyuki, Kurata; Sho, Tsukiyama
• 著者名(英): Hiroyuki, Kurata; Sho, Tsukiyama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Viral infection involves a large number of protein-protein interactions (PPIs) between human and virus. Few interspecies PPIs have been identified, because experimental methods including mass spectrometry are time-consuming and expensive, and molecular dynamic simulation is limited only to the proteins whose 3D structures are solved. Sequence-based machine learning methods are expected to overcome these problems. We have developed the (Long Short Term Memory) LSTM model with word2vec to predict PPIs between human and virus, named LSTM-PHV by using amino acid sequences and further developed a computational predictor, named cross-attention PHV, by implementing two key technologies of the cross-attention mechanism and a one-dimensional convolutional neural network.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Viral infection involves a large number of protein-protein interactions (PPIs) between human and virus. Few interspecies PPIs have been identified, because experimental methods including mass spectrometry are time-consuming and expensive, and molecular dynamic simulation is limited only to the proteins whose 3D structures are solved. Sequence-based machine learning methods are expected to overcome these problems. We have developed the (Long Short Term Memory) LSTM model with word2vec to predict PPIs between human and virus, named LSTM-PHV by using amino acid sequences and further developed a computational predictor, named cross-attention PHV, by implementing two key technologies of the cross-attention mechanism and a one-dimensional convolutional neural network.
• 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: AA12055912
• 書誌情報: 研究報告バイオ情報学（BIO）; 巻 2023-BIO-75, 号 6, p. 1-1, 発行日 2023-08-30
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8590
• 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