AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification
Abstract In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug–target interaction prediction. Our proposed model is inspired by sentence clas...
Gespeichert in:
Veröffentlicht in: | Briefings in bioinformatics 2022-07, Vol.23 (4) |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 4 |
container_start_page | |
container_title | Briefings in bioinformatics |
container_volume | 23 |
creator | Yazdani-Jahromi, Mehdi Yousefi, Niloofar Tayebi, Aida Kolanthai, Elayaraja Neal, Craig J Seal, Sudipta Garibay, Ozlem Ozmen |
description | Abstract
In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug–target interaction prediction. Our proposed model is inspired by sentence classification models in the field of Natural Language Processing, where the drug–target complex is treated as a sentence with relational meaning between its biochemical entities a.k.a. protein pockets and drug molecule. AttentionSiteDTI enables interpretability by identifying the protein binding sites that contribute the most toward the drug–target interaction. Results on three benchmark datasets show improved performance compared with the current state-of-the-art models. More significantly, unlike previous studies, our model shows superior performance, when tested on new proteins (i.e. high generalizability). Through multidisciplinary collaboration, we further experimentally evaluate the practical potential of our proposed approach. To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in the laboratory. The high agreement between the computationally predicted and experimentally observed (measured) drug–target interactions illustrates the potential of our method as an effective pre-screening tool in drug repurposing applications. |
doi_str_mv | 10.1093/bib/bbac272 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9294423</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/bib/bbac272</oup_id><sourcerecordid>2699592362</sourcerecordid><originalsourceid>FETCH-LOGICAL-c417t-4968035e91a7bab18e4f58baff6396df716527498c53b31b6c0fd4044d93dce13</originalsourceid><addsrcrecordid>eNp9kd1qFTEUhQdR7I9e-QIDgggybX4nEy-EUqstHFSwXocks2eaMieZJpmC79CHbk7nIOiFV9nZ-fbaWayqeoPRCUaSnhpnTo3RlgjyrDrETIiGIc6e7-pWNJy19KA6SukWIYJEh19WB5R3WFDZHlYPZzmDzy74ny7D5-urj7X2tfMZ4hwhazNBPUY93zRGJ-jrbehhqocQ6z4uY5N1HCGvvLY7mbqM9W4tl-T8WH_b_KhT2QHeQjPBfZmPMOknwk46JTc4-3R9Vb0Y9JTg9f48rn59ubg-v2w2379enZ9tGsuwyA2TbYcoB4m1MNrgDtjAO6OHoS2e-kHglhPBZGc5NRSb1qKhZ4ixXtLeAqbH1adVd17MFkrL56gnNUe31fG3Ctqpv1-8u1FjuFeSSMYILQLv9wIx3C2Qstq6ZGGatIewJEXaruOEIsQK-vYf9DYs0Rd7hZKSS0JbUqgPK2VjSCnC8OczGKldyqqkrPYpF_rdSodl_i_4CHXvqpM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2699592362</pqid></control><display><type>article</type><title>AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification</title><source>EBSCOhost Business Source Complete</source><source>Oxford Journals Open Access Collection</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Yazdani-Jahromi, Mehdi ; Yousefi, Niloofar ; Tayebi, Aida ; Kolanthai, Elayaraja ; Neal, Craig J ; Seal, Sudipta ; Garibay, Ozlem Ozmen</creator><creatorcontrib>Yazdani-Jahromi, Mehdi ; Yousefi, Niloofar ; Tayebi, Aida ; Kolanthai, Elayaraja ; Neal, Craig J ; Seal, Sudipta ; Garibay, Ozlem Ozmen</creatorcontrib><description>Abstract
In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug–target interaction prediction. Our proposed model is inspired by sentence classification models in the field of Natural Language Processing, where the drug–target complex is treated as a sentence with relational meaning between its biochemical entities a.k.a. protein pockets and drug molecule. AttentionSiteDTI enables interpretability by identifying the protein binding sites that contribute the most toward the drug–target interaction. Results on three benchmark datasets show improved performance compared with the current state-of-the-art models. More significantly, unlike previous studies, our model shows superior performance, when tested on new proteins (i.e. high generalizability). Through multidisciplinary collaboration, we further experimentally evaluate the practical potential of our proposed approach. To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in the laboratory. The high agreement between the computationally predicted and experimentally observed (measured) drug–target interactions illustrates the potential of our method as an effective pre-screening tool in drug repurposing applications.</description><identifier>ISSN: 1467-5463</identifier><identifier>EISSN: 1477-4054</identifier><identifier>DOI: 10.1093/bib/bbac272</identifier><identifier>PMID: 35817396</identifier><language>eng</language><publisher>Oxford: Oxford University Press</publisher><subject>Binding sites ; Classification ; Deep learning ; Machine learning ; Natural language processing ; Prediction models ; Problem Solving Protocol ; Proteins</subject><ispartof>Briefings in bioinformatics, 2022-07, Vol.23 (4)</ispartof><rights>The Author(s) 2022. Published by Oxford University Press. 2022</rights><rights>The Author(s) 2022. Published by Oxford University Press.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c417t-4968035e91a7bab18e4f58baff6396df716527498c53b31b6c0fd4044d93dce13</citedby><cites>FETCH-LOGICAL-c417t-4968035e91a7bab18e4f58baff6396df716527498c53b31b6c0fd4044d93dce13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9294423/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9294423/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,1604,27924,27925,53791,53793</link.rule.ids></links><search><creatorcontrib>Yazdani-Jahromi, Mehdi</creatorcontrib><creatorcontrib>Yousefi, Niloofar</creatorcontrib><creatorcontrib>Tayebi, Aida</creatorcontrib><creatorcontrib>Kolanthai, Elayaraja</creatorcontrib><creatorcontrib>Neal, Craig J</creatorcontrib><creatorcontrib>Seal, Sudipta</creatorcontrib><creatorcontrib>Garibay, Ozlem Ozmen</creatorcontrib><title>AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification</title><title>Briefings in bioinformatics</title><description>Abstract
In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug–target interaction prediction. Our proposed model is inspired by sentence classification models in the field of Natural Language Processing, where the drug–target complex is treated as a sentence with relational meaning between its biochemical entities a.k.a. protein pockets and drug molecule. AttentionSiteDTI enables interpretability by identifying the protein binding sites that contribute the most toward the drug–target interaction. Results on three benchmark datasets show improved performance compared with the current state-of-the-art models. More significantly, unlike previous studies, our model shows superior performance, when tested on new proteins (i.e. high generalizability). Through multidisciplinary collaboration, we further experimentally evaluate the practical potential of our proposed approach. To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in the laboratory. The high agreement between the computationally predicted and experimentally observed (measured) drug–target interactions illustrates the potential of our method as an effective pre-screening tool in drug repurposing applications.</description><subject>Binding sites</subject><subject>Classification</subject><subject>Deep learning</subject><subject>Machine learning</subject><subject>Natural language processing</subject><subject>Prediction models</subject><subject>Problem Solving Protocol</subject><subject>Proteins</subject><issn>1467-5463</issn><issn>1477-4054</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>TOX</sourceid><recordid>eNp9kd1qFTEUhQdR7I9e-QIDgggybX4nEy-EUqstHFSwXocks2eaMieZJpmC79CHbk7nIOiFV9nZ-fbaWayqeoPRCUaSnhpnTo3RlgjyrDrETIiGIc6e7-pWNJy19KA6SukWIYJEh19WB5R3WFDZHlYPZzmDzy74ny7D5-urj7X2tfMZ4hwhazNBPUY93zRGJ-jrbehhqocQ6z4uY5N1HCGvvLY7mbqM9W4tl-T8WH_b_KhT2QHeQjPBfZmPMOknwk46JTc4-3R9Vb0Y9JTg9f48rn59ubg-v2w2379enZ9tGsuwyA2TbYcoB4m1MNrgDtjAO6OHoS2e-kHglhPBZGc5NRSb1qKhZ4ixXtLeAqbH1adVd17MFkrL56gnNUe31fG3Ctqpv1-8u1FjuFeSSMYILQLv9wIx3C2Qstq6ZGGatIewJEXaruOEIsQK-vYf9DYs0Rd7hZKSS0JbUqgPK2VjSCnC8OczGKldyqqkrPYpF_rdSodl_i_4CHXvqpM</recordid><startdate>20220718</startdate><enddate>20220718</enddate><creator>Yazdani-Jahromi, Mehdi</creator><creator>Yousefi, Niloofar</creator><creator>Tayebi, Aida</creator><creator>Kolanthai, Elayaraja</creator><creator>Neal, Craig J</creator><creator>Seal, Sudipta</creator><creator>Garibay, Ozlem Ozmen</creator><general>Oxford University Press</general><general>Oxford Publishing Limited (England)</general><scope>TOX</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>7SC</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20220718</creationdate><title>AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification</title><author>Yazdani-Jahromi, Mehdi ; Yousefi, Niloofar ; Tayebi, Aida ; Kolanthai, Elayaraja ; Neal, Craig J ; Seal, Sudipta ; Garibay, Ozlem Ozmen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c417t-4968035e91a7bab18e4f58baff6396df716527498c53b31b6c0fd4044d93dce13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Binding sites</topic><topic>Classification</topic><topic>Deep learning</topic><topic>Machine learning</topic><topic>Natural language processing</topic><topic>Prediction models</topic><topic>Problem Solving Protocol</topic><topic>Proteins</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yazdani-Jahromi, Mehdi</creatorcontrib><creatorcontrib>Yousefi, Niloofar</creatorcontrib><creatorcontrib>Tayebi, Aida</creatorcontrib><creatorcontrib>Kolanthai, Elayaraja</creatorcontrib><creatorcontrib>Neal, Craig J</creatorcontrib><creatorcontrib>Seal, Sudipta</creatorcontrib><creatorcontrib>Garibay, Ozlem Ozmen</creatorcontrib><collection>Oxford Journals Open Access Collection</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Briefings in bioinformatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yazdani-Jahromi, Mehdi</au><au>Yousefi, Niloofar</au><au>Tayebi, Aida</au><au>Kolanthai, Elayaraja</au><au>Neal, Craig J</au><au>Seal, Sudipta</au><au>Garibay, Ozlem Ozmen</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification</atitle><jtitle>Briefings in bioinformatics</jtitle><date>2022-07-18</date><risdate>2022</risdate><volume>23</volume><issue>4</issue><issn>1467-5463</issn><eissn>1477-4054</eissn><abstract>Abstract
In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug–target interaction prediction. Our proposed model is inspired by sentence classification models in the field of Natural Language Processing, where the drug–target complex is treated as a sentence with relational meaning between its biochemical entities a.k.a. protein pockets and drug molecule. AttentionSiteDTI enables interpretability by identifying the protein binding sites that contribute the most toward the drug–target interaction. Results on three benchmark datasets show improved performance compared with the current state-of-the-art models. More significantly, unlike previous studies, our model shows superior performance, when tested on new proteins (i.e. high generalizability). Through multidisciplinary collaboration, we further experimentally evaluate the practical potential of our proposed approach. To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in the laboratory. The high agreement between the computationally predicted and experimentally observed (measured) drug–target interactions illustrates the potential of our method as an effective pre-screening tool in drug repurposing applications.</abstract><cop>Oxford</cop><pub>Oxford University Press</pub><pmid>35817396</pmid><doi>10.1093/bib/bbac272</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1467-5463 |
ispartof | Briefings in bioinformatics, 2022-07, Vol.23 (4) |
issn | 1467-5463 1477-4054 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9294423 |
source | EBSCOhost Business Source Complete; Oxford Journals Open Access Collection; EZB-FREE-00999 freely available EZB journals; PubMed Central |
subjects | Binding sites Classification Deep learning Machine learning Natural language processing Prediction models Problem Solving Protocol Proteins |
title | AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A05%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AttentionSiteDTI:%20an%20interpretable%20graph-based%20model%20for%20drug-target%20interaction%20prediction%20using%20NLP%20sentence-level%20relation%20classification&rft.jtitle=Briefings%20in%20bioinformatics&rft.au=Yazdani-Jahromi,%20Mehdi&rft.date=2022-07-18&rft.volume=23&rft.issue=4&rft.issn=1467-5463&rft.eissn=1477-4054&rft_id=info:doi/10.1093/bib/bbac272&rft_dat=%3Cproquest_pubme%3E2699592362%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2699592362&rft_id=info:pmid/35817396&rft_oup_id=10.1093/bib/bbac272&rfr_iscdi=true |