Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions
Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested...
Gespeichert in:
| Veröffentlicht in: | Journal of chemical information and modeling 2021-01, Vol.61 (1), p.156-166 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 166 |
|---|---|
| container_issue | 1 |
| container_start_page | 156 |
| container_title | Journal of chemical information and modeling |
| container_volume | 61 |
| creator | Maser, Michael R Cui, Alexander Y Ryou, Serim DeLano, Travis J Yue, Yisong |
| description | Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model. |
| doi_str_mv | 10.1021/acs.jcim.0c01234 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2476564234</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2483640867</sourcerecordid><originalsourceid>FETCH-LOGICAL-a406t-5c279e30911a1c9ebc3d05e4a0de816aa71f52c75c15b0c49ed28586126f457e3</originalsourceid><addsrcrecordid>eNp1kM1LwzAYh4Mobk7vnqTgxYOdSfPR5ijFL9hQREFPJU3fakbazKY9-N_brpsHwVNeeJ_fL8mD0CnBc4IjcqW0n6-0qeZYYxJRtoemhDMZSoHf9nczl2KCjrxfYUypFNEhmlDKSMyYnKL3ZWdbY1UONkit8t6URqvWuDpYugKsD0rXBO0nBE8NFEZvNq4M0sZ5H6auW1tTfwTPoMZV6urCDJM_Rgelsh5OtucMvd7evKT34eLx7iG9XoSKYdGGXEexBIolIYpoCbmmBebAFC4gIUKpmJQ80jHXhOdYMwlFlPBEkEiUjMdAZ-hi7F037qsD32aV8RqsVTW4zmcRiwUXrLfTo-d_0JXrmrp_XU8lVDCciLin8Ejp4Y8NlNm6MZVqvjOCs0F71mvPBu3ZVnsfOdsWd3kFxW9g57kHLkdgE91d-m_fD4w_jfc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2483640867</pqid></control><display><type>article</type><title>Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions</title><source>ACS Publications</source><creator>Maser, Michael R ; Cui, Alexander Y ; Ryou, Serim ; DeLano, Travis J ; Yue, Yisong</creator><creatorcontrib>Maser, Michael R ; Cui, Alexander Y ; Ryou, Serim ; DeLano, Travis J ; Yue, Yisong</creatorcontrib><description>Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model.</description><identifier>ISSN: 1549-9596</identifier><identifier>EISSN: 1549-960X</identifier><identifier>DOI: 10.1021/acs.jcim.0c01234</identifier><identifier>PMID: 33417449</identifier><language>eng</language><publisher>United States: American Chemical Society</publisher><subject>Chemical reactions ; Cognitive tasks ; Couplings ; Cross coupling ; Datasets ; Machine Learning and Deep Learning ; Reagents ; Substrates</subject><ispartof>Journal of chemical information and modeling, 2021-01, Vol.61 (1), p.156-166</ispartof><rights>2021 American Chemical Society</rights><rights>Copyright American Chemical Society Jan 25, 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a406t-5c279e30911a1c9ebc3d05e4a0de816aa71f52c75c15b0c49ed28586126f457e3</citedby><cites>FETCH-LOGICAL-a406t-5c279e30911a1c9ebc3d05e4a0de816aa71f52c75c15b0c49ed28586126f457e3</cites><orcidid>0000-0001-8244-9300 ; 0000-0001-7895-7804</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://pubs.acs.org/doi/pdf/10.1021/acs.jcim.0c01234$$EPDF$$P50$$Gacs$$H</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/acs.jcim.0c01234$$EHTML$$P50$$Gacs$$H</linktohtml><link.rule.ids>314,778,782,2754,27059,27907,27908,56721,56771</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33417449$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Maser, Michael R</creatorcontrib><creatorcontrib>Cui, Alexander Y</creatorcontrib><creatorcontrib>Ryou, Serim</creatorcontrib><creatorcontrib>DeLano, Travis J</creatorcontrib><creatorcontrib>Yue, Yisong</creatorcontrib><title>Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions</title><title>Journal of chemical information and modeling</title><addtitle>J. Chem. Inf. Model</addtitle><description>Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model.</description><subject>Chemical reactions</subject><subject>Cognitive tasks</subject><subject>Couplings</subject><subject>Cross coupling</subject><subject>Datasets</subject><subject>Machine Learning and Deep Learning</subject><subject>Reagents</subject><subject>Substrates</subject><issn>1549-9596</issn><issn>1549-960X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp1kM1LwzAYh4Mobk7vnqTgxYOdSfPR5ijFL9hQREFPJU3fakbazKY9-N_brpsHwVNeeJ_fL8mD0CnBc4IjcqW0n6-0qeZYYxJRtoemhDMZSoHf9nczl2KCjrxfYUypFNEhmlDKSMyYnKL3ZWdbY1UONkit8t6URqvWuDpYugKsD0rXBO0nBE8NFEZvNq4M0sZ5H6auW1tTfwTPoMZV6urCDJM_Rgelsh5OtucMvd7evKT34eLx7iG9XoSKYdGGXEexBIolIYpoCbmmBebAFC4gIUKpmJQ80jHXhOdYMwlFlPBEkEiUjMdAZ-hi7F037qsD32aV8RqsVTW4zmcRiwUXrLfTo-d_0JXrmrp_XU8lVDCciLin8Ejp4Y8NlNm6MZVqvjOCs0F71mvPBu3ZVnsfOdsWd3kFxW9g57kHLkdgE91d-m_fD4w_jfc</recordid><startdate>20210125</startdate><enddate>20210125</enddate><creator>Maser, Michael R</creator><creator>Cui, Alexander Y</creator><creator>Ryou, Serim</creator><creator>DeLano, Travis J</creator><creator>Yue, Yisong</creator><general>American Chemical Society</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SR</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-8244-9300</orcidid><orcidid>https://orcid.org/0000-0001-7895-7804</orcidid></search><sort><creationdate>20210125</creationdate><title>Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions</title><author>Maser, Michael R ; Cui, Alexander Y ; Ryou, Serim ; DeLano, Travis J ; Yue, Yisong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a406t-5c279e30911a1c9ebc3d05e4a0de816aa71f52c75c15b0c49ed28586126f457e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Chemical reactions</topic><topic>Cognitive tasks</topic><topic>Couplings</topic><topic>Cross coupling</topic><topic>Datasets</topic><topic>Machine Learning and Deep Learning</topic><topic>Reagents</topic><topic>Substrates</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Maser, Michael R</creatorcontrib><creatorcontrib>Cui, Alexander Y</creatorcontrib><creatorcontrib>Ryou, Serim</creatorcontrib><creatorcontrib>DeLano, Travis J</creatorcontrib><creatorcontrib>Yue, Yisong</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</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>MEDLINE - Academic</collection><jtitle>Journal of chemical information and modeling</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Maser, Michael R</au><au>Cui, Alexander Y</au><au>Ryou, Serim</au><au>DeLano, Travis J</au><au>Yue, Yisong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions</atitle><jtitle>Journal of chemical information and modeling</jtitle><addtitle>J. Chem. Inf. Model</addtitle><date>2021-01-25</date><risdate>2021</risdate><volume>61</volume><issue>1</issue><spage>156</spage><epage>166</epage><pages>156-166</pages><issn>1549-9596</issn><eissn>1549-960X</eissn><abstract>Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published reactions were curated for Suzuki, Negishi, and C–N couplings, as well as Pauson–Khand reactions. String, descriptor, and graph encodings were tested as input representations, and models were trained to predict the set of conditions used in a reaction as a binary vector. Unique reagent dictionaries categorized by expert-crafted reaction roles were constructed for each data set, leading to context-aware predictions. We find that relational graph convolutional networks and gradient-boosting machines are very effective for this learning task, and we disclose a novel reaction-level graph attention operation in the top-performing model.</abstract><cop>United States</cop><pub>American Chemical Society</pub><pmid>33417449</pmid><doi>10.1021/acs.jcim.0c01234</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0001-8244-9300</orcidid><orcidid>https://orcid.org/0000-0001-7895-7804</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1549-9596 |
| ispartof | Journal of chemical information and modeling, 2021-01, Vol.61 (1), p.156-166 |
| issn | 1549-9596 1549-960X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2476564234 |
| source | ACS Publications |
| subjects | Chemical reactions Cognitive tasks Couplings Cross coupling Datasets Machine Learning and Deep Learning Reagents Substrates |
| title | Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T12%3A28%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multilabel%20Classification%20Models%20for%20the%20Prediction%20of%20Cross-Coupling%20Reaction%20Conditions&rft.jtitle=Journal%20of%20chemical%20information%20and%20modeling&rft.au=Maser,%20Michael%20R&rft.date=2021-01-25&rft.volume=61&rft.issue=1&rft.spage=156&rft.epage=166&rft.pages=156-166&rft.issn=1549-9596&rft.eissn=1549-960X&rft_id=info:doi/10.1021/acs.jcim.0c01234&rft_dat=%3Cproquest_cross%3E2483640867%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2483640867&rft_id=info:pmid/33417449&rfr_iscdi=true |