FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments
Summary: Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S258900422302833X |
| _version_ | 1797372115205226496 |
|---|---|
| author | Zeyu Yin Yu Chen Yajie Hao Sanjeevi Pandiyan Jinsong Shao Li Wang |
| author_facet | Zeyu Yin Yu Chen Yajie Hao Sanjeevi Pandiyan Jinsong Shao Li Wang |
| author_sort | Zeyu Yin |
| collection | DOAJ |
| description | Summary: Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (a Fusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model’s understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications. |
| first_indexed | 2024-03-08T18:30:13Z |
| format | Article |
| id | doaj.art-ec33f8d55b724ad2a6abfc7f8a40a680 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-08T18:30:13Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-ec33f8d55b724ad2a6abfc7f8a40a6802023-12-30T04:44:39ZengElsevieriScience2589-00422024-01-01271108756FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragmentsZeyu Yin0Yu Chen1Yajie Hao2Sanjeevi Pandiyan3Jinsong Shao4Li Wang5School of Information Science and Technology, Nantong University, Nantong 226001, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226001, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226001, ChinaResearch Center for Intelligent Information Technology, Nantong University, Nantong 226001, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226001, ChinaSchool of Information Science and Technology, Nantong University, Nantong 226001, China; Research Center for Intelligent Information Technology, Nantong University, Nantong 226001, China; Corresponding authorSummary: Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (a Fusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model’s understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.http://www.sciencedirect.com/science/article/pii/S258900422302833XBiocomputational methodComputational bioinformaticsIn silico biology |
| spellingShingle | Zeyu Yin Yu Chen Yajie Hao Sanjeevi Pandiyan Jinsong Shao Li Wang FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments iScience Biocomputational method Computational bioinformatics In silico biology |
| title | FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments |
| title_full | FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments |
| title_fullStr | FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments |
| title_full_unstemmed | FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments |
| title_short | FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments |
| title_sort | fotf cpi a compound protein interaction prediction transformer based on the fusion of optimal transport fragments |
| topic | Biocomputational method Computational bioinformatics In silico biology |
| url | http://www.sciencedirect.com/science/article/pii/S258900422302833X |
| work_keys_str_mv | AT zeyuyin fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments AT yuchen fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments AT yajiehao fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments AT sanjeevipandiyan fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments AT jinsongshao fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments AT liwang fotfcpiacompoundproteininteractionpredictiontransformerbasedonthefusionofoptimaltransportfragments |