MatchMaker: A Deep Learning Framework for Drug Synergy Prediction
Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable du...
Gespeichert in:
| Veröffentlicht in: | IEEE/ACM transactions on computational biology and bioinformatics 2022-07, Vol.19 (4), p.2334-2344 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2344 |
|---|---|
| container_issue | 4 |
| container_start_page | 2334 |
| container_title | IEEE/ACM transactions on computational biology and bioinformatics |
| container_volume | 19 |
| creator | Kuru, Halil Ibrahim Tastan, Oznur Cicek, A. Ercument |
| description | Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to \sim 15\% ∼15% correlation and \sim 33\% ∼33% mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker . |
| doi_str_mv | 10.1109/TCBB.2021.3086702 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TCBB_2021_3086702</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9447196</ieee_id><sourcerecordid>2700414620</sourcerecordid><originalsourceid>FETCH-LOGICAL-c369t-2dc1568c9dae8070497d7e7bbeb802aa36201d424a35440ab0371ff8d4351bf43</originalsourceid><addsrcrecordid>eNpdkLtOw0AQRVcIRCDwAYhmJRoah9mX10uXBwGkRCAR6tXaHgfnYYe1LZS_x1YiCqo7xbkzo0PIDYMBY2AeFuPRaMCBs4GAKNTAT8gFU0oHxoTytJulCpQJRY9cVtUKgEsD8pz0hGx5pcMLMpy7OvmauzX6RzqkE8QdnaHzRV4s6dS7Lf6Ufk2z0tOJb5b0Y1-gX-7pu8c0T-q8LK7IWeY2FV4fs08-p0-L8Uswe3t-HQ9nQSJCUwc8TZgKo8SkDiPQII1ONeo4xjgC7pwIObBUcumEkhJcDEKzLItSKRSLMyn65P6wd-fL7war2m7zKsHNxhVYNpXlSuhQgGmzT-7-oauy8UX7neUaQDLZHmspdqASX1aVx8zufL51fm8Z2M6v7fzazq89-m07t4dOjoh_vJFSs1bzL92ichI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2700414620</pqid></control><display><type>article</type><title>MatchMaker: A Deep Learning Framework for Drug Synergy Prediction</title><source>IEEE Electronic Library (IEL)</source><creator>Kuru, Halil Ibrahim ; Tastan, Oznur ; Cicek, A. Ercument</creator><creatorcontrib>Kuru, Halil Ibrahim ; Tastan, Oznur ; Cicek, A. Ercument</creatorcontrib><description><![CDATA[Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to <inline-formula><tex-math notation="LaTeX">\sim 15\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>15</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq1-3086702.gif"/> </inline-formula> correlation and <inline-formula><tex-math notation="LaTeX">\sim 33\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>33</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq2-3086702.gif"/> </inline-formula> mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker .]]></description><identifier>ISSN: 1545-5963</identifier><identifier>EISSN: 1557-9964</identifier><identifier>DOI: 10.1109/TCBB.2021.3086702</identifier><identifier>PMID: 34086576</identifier><identifier>CODEN: ITCBCY</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>cancer cell lines ; chemical features ; Chemicals ; Combinatorial analysis ; Computer applications ; Computer architecture ; Deep learning ; drug synergy ; Drugs ; Gene expression ; Microprocessors ; Prediction algorithms ; Predictive models ; Side effects</subject><ispartof>IEEE/ACM transactions on computational biology and bioinformatics, 2022-07, Vol.19 (4), p.2334-2344</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c369t-2dc1568c9dae8070497d7e7bbeb802aa36201d424a35440ab0371ff8d4351bf43</citedby><cites>FETCH-LOGICAL-c369t-2dc1568c9dae8070497d7e7bbeb802aa36201d424a35440ab0371ff8d4351bf43</cites><orcidid>0000-0001-8613-6619 ; 0000-0001-7058-5372 ; 0000-0003-4356-8846</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9447196$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9447196$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kuru, Halil Ibrahim</creatorcontrib><creatorcontrib>Tastan, Oznur</creatorcontrib><creatorcontrib>Cicek, A. Ercument</creatorcontrib><title>MatchMaker: A Deep Learning Framework for Drug Synergy Prediction</title><title>IEEE/ACM transactions on computational biology and bioinformatics</title><addtitle>TCBB</addtitle><description><![CDATA[Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to <inline-formula><tex-math notation="LaTeX">\sim 15\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>15</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq1-3086702.gif"/> </inline-formula> correlation and <inline-formula><tex-math notation="LaTeX">\sim 33\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>33</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq2-3086702.gif"/> </inline-formula> mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker .]]></description><subject>cancer cell lines</subject><subject>chemical features</subject><subject>Chemicals</subject><subject>Combinatorial analysis</subject><subject>Computer applications</subject><subject>Computer architecture</subject><subject>Deep learning</subject><subject>drug synergy</subject><subject>Drugs</subject><subject>Gene expression</subject><subject>Microprocessors</subject><subject>Prediction algorithms</subject><subject>Predictive models</subject><subject>Side effects</subject><issn>1545-5963</issn><issn>1557-9964</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkLtOw0AQRVcIRCDwAYhmJRoah9mX10uXBwGkRCAR6tXaHgfnYYe1LZS_x1YiCqo7xbkzo0PIDYMBY2AeFuPRaMCBs4GAKNTAT8gFU0oHxoTytJulCpQJRY9cVtUKgEsD8pz0hGx5pcMLMpy7OvmauzX6RzqkE8QdnaHzRV4s6dS7Lf6Ufk2z0tOJb5b0Y1-gX-7pu8c0T-q8LK7IWeY2FV4fs08-p0-L8Uswe3t-HQ9nQSJCUwc8TZgKo8SkDiPQII1ONeo4xjgC7pwIObBUcumEkhJcDEKzLItSKRSLMyn65P6wd-fL7war2m7zKsHNxhVYNpXlSuhQgGmzT-7-oauy8UX7neUaQDLZHmspdqASX1aVx8zufL51fm8Z2M6v7fzazq89-m07t4dOjoh_vJFSs1bzL92ichI</recordid><startdate>20220701</startdate><enddate>20220701</enddate><creator>Kuru, Halil Ibrahim</creator><creator>Tastan, Oznur</creator><creator>Cicek, A. Ercument</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-8613-6619</orcidid><orcidid>https://orcid.org/0000-0001-7058-5372</orcidid><orcidid>https://orcid.org/0000-0003-4356-8846</orcidid></search><sort><creationdate>20220701</creationdate><title>MatchMaker: A Deep Learning Framework for Drug Synergy Prediction</title><author>Kuru, Halil Ibrahim ; Tastan, Oznur ; Cicek, A. Ercument</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c369t-2dc1568c9dae8070497d7e7bbeb802aa36201d424a35440ab0371ff8d4351bf43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>cancer cell lines</topic><topic>chemical features</topic><topic>Chemicals</topic><topic>Combinatorial analysis</topic><topic>Computer applications</topic><topic>Computer architecture</topic><topic>Deep learning</topic><topic>drug synergy</topic><topic>Drugs</topic><topic>Gene expression</topic><topic>Microprocessors</topic><topic>Prediction algorithms</topic><topic>Predictive models</topic><topic>Side effects</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kuru, Halil Ibrahim</creatorcontrib><creatorcontrib>Tastan, Oznur</creatorcontrib><creatorcontrib>Cicek, A. Ercument</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</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>MEDLINE - Academic</collection><jtitle>IEEE/ACM transactions on computational biology and bioinformatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kuru, Halil Ibrahim</au><au>Tastan, Oznur</au><au>Cicek, A. Ercument</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MatchMaker: A Deep Learning Framework for Drug Synergy Prediction</atitle><jtitle>IEEE/ACM transactions on computational biology and bioinformatics</jtitle><stitle>TCBB</stitle><date>2022-07-01</date><risdate>2022</risdate><volume>19</volume><issue>4</issue><spage>2334</spage><epage>2344</epage><pages>2334-2344</pages><issn>1545-5963</issn><eissn>1557-9964</eissn><coden>ITCBCY</coden><abstract><![CDATA[Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to <inline-formula><tex-math notation="LaTeX">\sim 15\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>15</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq1-3086702.gif"/> </inline-formula> correlation and <inline-formula><tex-math notation="LaTeX">\sim 33\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>33</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="kuru-ieq2-3086702.gif"/> </inline-formula> mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker .]]></abstract><cop>New York</cop><pub>IEEE</pub><pmid>34086576</pmid><doi>10.1109/TCBB.2021.3086702</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0001-8613-6619</orcidid><orcidid>https://orcid.org/0000-0001-7058-5372</orcidid><orcidid>https://orcid.org/0000-0003-4356-8846</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1545-5963 |
| ispartof | IEEE/ACM transactions on computational biology and bioinformatics, 2022-07, Vol.19 (4), p.2334-2344 |
| issn | 1545-5963 1557-9964 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TCBB_2021_3086702 |
| source | IEEE Electronic Library (IEL) |
| subjects | cancer cell lines chemical features Chemicals Combinatorial analysis Computer applications Computer architecture Deep learning drug synergy Drugs Gene expression Microprocessors Prediction algorithms Predictive models Side effects |
| title | MatchMaker: A Deep Learning Framework for Drug Synergy Prediction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T03%3A24%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MatchMaker:%20A%20Deep%20Learning%20Framework%20for%20Drug%20Synergy%20Prediction&rft.jtitle=IEEE/ACM%20transactions%20on%20computational%20biology%20and%20bioinformatics&rft.au=Kuru,%20Halil%20Ibrahim&rft.date=2022-07-01&rft.volume=19&rft.issue=4&rft.spage=2334&rft.epage=2344&rft.pages=2334-2344&rft.issn=1545-5963&rft.eissn=1557-9964&rft.coden=ITCBCY&rft_id=info:doi/10.1109/TCBB.2021.3086702&rft_dat=%3Cproquest_RIE%3E2700414620%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2700414620&rft_id=info:pmid/34086576&rft_ieee_id=9447196&rfr_iscdi=true |