Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning
A new, accelerated design scheme for photoinitiators based on an advanced machine learning framework is studied. Design space for photoinitiators is set by over 120 unique oxime ester compounds synthesized and measured for their photosensitivity. Then, an automated machine learning algorithm is used...
Gespeichert in:
Veröffentlicht in: | Chemistry of materials 2022-01, Vol.34 (1), p.116-127 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 127 |
---|---|
container_issue | 1 |
container_start_page | 116 |
container_title | Chemistry of materials |
container_volume | 34 |
creator | Lee, Won Jung Kwak, H. Shaun Lee, Deuk-rak Oh, Chunrim Yum, Eul Kgun An, Yuling Halls, Mathew D Lee, Chi-Wan |
description | A new, accelerated design scheme for photoinitiators based on an advanced machine learning framework is studied. Design space for photoinitiators is set by over 120 unique oxime ester compounds synthesized and measured for their photosensitivity. Then, an automated machine learning algorithm is used for rapidly identifying the best quantitative structure–property relationship (QSPR) models among hundreds that are generated, ranked, and validated in an automated fashion to predict photosensitivity. Top-performing models are highly predictive with coefficients of determination of around 0.8 for compounds that are unknown to the models. Visual interpretation of the predictive models based on atom-site contributions offers a clear and intuitive direction to design new photoinitiators. Based on the machine learning-assisted analysis, three new oxime ester compounds were pushed for synthesis and further evaluation as novel photoinitiators. Experimental validation confirms high photosensitivity in all of the newly synthesized candidates. The work demonstrates the value of combining synthesis with the automated machine learning framework as a fast and reliable measure, which provides unbiased insights often hidden in high-dimensional data space. |
doi_str_mv | 10.1021/acs.chemmater.1c02871 |
format | Article |
fullrecord | <record><control><sourceid>acs_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1021_acs_chemmater_1c02871</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>a352438551</sourcerecordid><originalsourceid>FETCH-LOGICAL-a295t-c5eaa763e232a593a4f098bd48b3d726ec98bb479756afbfa37a6ee3e832e7ad3</originalsourceid><addsrcrecordid>eNqFkNtKw0AQhhdRsFYfQdgXSN1Dkk0uS60HqFZQr8MkmTRbml3Z3Yp9eze0eOvV8DN8c_gIueVsxpngd9D4WdPjMEBAN-MNE4XiZ2TCM8GSjDFxTiasKFWSqiy_JFfebxnjES0mBO7R642hYFr6fjChj9FT29FX-407uv7RA9Klj4PpW2-D1UYHDcE6T-f7zYAmYEvrQwzBjvtb-gJNrw3SFYIz2myuyUUHO483pzolnw_Lj8VTslo_Pi_mqwREmYWkyRBA5RKFFJCVEtKOlUXdpkUtWyVybGKqU1XGH6CrO5AKckSJhRSooJVTkh3nNs5677CrvpwewB0qzqrRUxU9VX-eqpOnyPEjN7a3du9MvPIf5hefmnLB</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning</title><source>American Chemical Society Journals</source><creator>Lee, Won Jung ; Kwak, H. Shaun ; Lee, Deuk-rak ; Oh, Chunrim ; Yum, Eul Kgun ; An, Yuling ; Halls, Mathew D ; Lee, Chi-Wan</creator><creatorcontrib>Lee, Won Jung ; Kwak, H. Shaun ; Lee, Deuk-rak ; Oh, Chunrim ; Yum, Eul Kgun ; An, Yuling ; Halls, Mathew D ; Lee, Chi-Wan</creatorcontrib><description>A new, accelerated design scheme for photoinitiators based on an advanced machine learning framework is studied. Design space for photoinitiators is set by over 120 unique oxime ester compounds synthesized and measured for their photosensitivity. Then, an automated machine learning algorithm is used for rapidly identifying the best quantitative structure–property relationship (QSPR) models among hundreds that are generated, ranked, and validated in an automated fashion to predict photosensitivity. Top-performing models are highly predictive with coefficients of determination of around 0.8 for compounds that are unknown to the models. Visual interpretation of the predictive models based on atom-site contributions offers a clear and intuitive direction to design new photoinitiators. Based on the machine learning-assisted analysis, three new oxime ester compounds were pushed for synthesis and further evaluation as novel photoinitiators. Experimental validation confirms high photosensitivity in all of the newly synthesized candidates. The work demonstrates the value of combining synthesis with the automated machine learning framework as a fast and reliable measure, which provides unbiased insights often hidden in high-dimensional data space.</description><identifier>ISSN: 0897-4756</identifier><identifier>EISSN: 1520-5002</identifier><identifier>DOI: 10.1021/acs.chemmater.1c02871</identifier><language>eng</language><publisher>American Chemical Society</publisher><ispartof>Chemistry of materials, 2022-01, Vol.34 (1), p.116-127</ispartof><rights>2021 American Chemical Society</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a295t-c5eaa763e232a593a4f098bd48b3d726ec98bb479756afbfa37a6ee3e832e7ad3</citedby><cites>FETCH-LOGICAL-a295t-c5eaa763e232a593a4f098bd48b3d726ec98bb479756afbfa37a6ee3e832e7ad3</cites><orcidid>0000-0002-9123-4464 ; 0000-0001-8989-8934 ; 0000-0003-4669-0986</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.chemmater.1c02871$$EPDF$$P50$$Gacs$$H</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/acs.chemmater.1c02871$$EHTML$$P50$$Gacs$$H</linktohtml><link.rule.ids>314,780,784,2765,27076,27924,27925,56738,56788</link.rule.ids></links><search><creatorcontrib>Lee, Won Jung</creatorcontrib><creatorcontrib>Kwak, H. Shaun</creatorcontrib><creatorcontrib>Lee, Deuk-rak</creatorcontrib><creatorcontrib>Oh, Chunrim</creatorcontrib><creatorcontrib>Yum, Eul Kgun</creatorcontrib><creatorcontrib>An, Yuling</creatorcontrib><creatorcontrib>Halls, Mathew D</creatorcontrib><creatorcontrib>Lee, Chi-Wan</creatorcontrib><title>Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning</title><title>Chemistry of materials</title><addtitle>Chem. Mater</addtitle><description>A new, accelerated design scheme for photoinitiators based on an advanced machine learning framework is studied. Design space for photoinitiators is set by over 120 unique oxime ester compounds synthesized and measured for their photosensitivity. Then, an automated machine learning algorithm is used for rapidly identifying the best quantitative structure–property relationship (QSPR) models among hundreds that are generated, ranked, and validated in an automated fashion to predict photosensitivity. Top-performing models are highly predictive with coefficients of determination of around 0.8 for compounds that are unknown to the models. Visual interpretation of the predictive models based on atom-site contributions offers a clear and intuitive direction to design new photoinitiators. Based on the machine learning-assisted analysis, three new oxime ester compounds were pushed for synthesis and further evaluation as novel photoinitiators. Experimental validation confirms high photosensitivity in all of the newly synthesized candidates. The work demonstrates the value of combining synthesis with the automated machine learning framework as a fast and reliable measure, which provides unbiased insights often hidden in high-dimensional data space.</description><issn>0897-4756</issn><issn>1520-5002</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNqFkNtKw0AQhhdRsFYfQdgXSN1Dkk0uS60HqFZQr8MkmTRbml3Z3Yp9eze0eOvV8DN8c_gIueVsxpngd9D4WdPjMEBAN-MNE4XiZ2TCM8GSjDFxTiasKFWSqiy_JFfebxnjES0mBO7R642hYFr6fjChj9FT29FX-407uv7RA9Klj4PpW2-D1UYHDcE6T-f7zYAmYEvrQwzBjvtb-gJNrw3SFYIz2myuyUUHO483pzolnw_Lj8VTslo_Pi_mqwREmYWkyRBA5RKFFJCVEtKOlUXdpkUtWyVybGKqU1XGH6CrO5AKckSJhRSooJVTkh3nNs5677CrvpwewB0qzqrRUxU9VX-eqpOnyPEjN7a3du9MvPIf5hefmnLB</recordid><startdate>20220111</startdate><enddate>20220111</enddate><creator>Lee, Won Jung</creator><creator>Kwak, H. Shaun</creator><creator>Lee, Deuk-rak</creator><creator>Oh, Chunrim</creator><creator>Yum, Eul Kgun</creator><creator>An, Yuling</creator><creator>Halls, Mathew D</creator><creator>Lee, Chi-Wan</creator><general>American Chemical Society</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-9123-4464</orcidid><orcidid>https://orcid.org/0000-0001-8989-8934</orcidid><orcidid>https://orcid.org/0000-0003-4669-0986</orcidid></search><sort><creationdate>20220111</creationdate><title>Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning</title><author>Lee, Won Jung ; Kwak, H. Shaun ; Lee, Deuk-rak ; Oh, Chunrim ; Yum, Eul Kgun ; An, Yuling ; Halls, Mathew D ; Lee, Chi-Wan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a295t-c5eaa763e232a593a4f098bd48b3d726ec98bb479756afbfa37a6ee3e832e7ad3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lee, Won Jung</creatorcontrib><creatorcontrib>Kwak, H. Shaun</creatorcontrib><creatorcontrib>Lee, Deuk-rak</creatorcontrib><creatorcontrib>Oh, Chunrim</creatorcontrib><creatorcontrib>Yum, Eul Kgun</creatorcontrib><creatorcontrib>An, Yuling</creatorcontrib><creatorcontrib>Halls, Mathew D</creatorcontrib><creatorcontrib>Lee, Chi-Wan</creatorcontrib><collection>CrossRef</collection><jtitle>Chemistry of materials</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lee, Won Jung</au><au>Kwak, H. Shaun</au><au>Lee, Deuk-rak</au><au>Oh, Chunrim</au><au>Yum, Eul Kgun</au><au>An, Yuling</au><au>Halls, Mathew D</au><au>Lee, Chi-Wan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning</atitle><jtitle>Chemistry of materials</jtitle><addtitle>Chem. Mater</addtitle><date>2022-01-11</date><risdate>2022</risdate><volume>34</volume><issue>1</issue><spage>116</spage><epage>127</epage><pages>116-127</pages><issn>0897-4756</issn><eissn>1520-5002</eissn><abstract>A new, accelerated design scheme for photoinitiators based on an advanced machine learning framework is studied. Design space for photoinitiators is set by over 120 unique oxime ester compounds synthesized and measured for their photosensitivity. Then, an automated machine learning algorithm is used for rapidly identifying the best quantitative structure–property relationship (QSPR) models among hundreds that are generated, ranked, and validated in an automated fashion to predict photosensitivity. Top-performing models are highly predictive with coefficients of determination of around 0.8 for compounds that are unknown to the models. Visual interpretation of the predictive models based on atom-site contributions offers a clear and intuitive direction to design new photoinitiators. Based on the machine learning-assisted analysis, three new oxime ester compounds were pushed for synthesis and further evaluation as novel photoinitiators. Experimental validation confirms high photosensitivity in all of the newly synthesized candidates. The work demonstrates the value of combining synthesis with the automated machine learning framework as a fast and reliable measure, which provides unbiased insights often hidden in high-dimensional data space.</abstract><pub>American Chemical Society</pub><doi>10.1021/acs.chemmater.1c02871</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-9123-4464</orcidid><orcidid>https://orcid.org/0000-0001-8989-8934</orcidid><orcidid>https://orcid.org/0000-0003-4669-0986</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0897-4756 |
ispartof | Chemistry of materials, 2022-01, Vol.34 (1), p.116-127 |
issn | 0897-4756 1520-5002 |
language | eng |
recordid | cdi_crossref_primary_10_1021_acs_chemmater_1c02871 |
source | American Chemical Society Journals |
title | Design and Synthesis of Novel Oxime Ester Photoinitiators Augmented by Automated Machine Learning |
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%3A23%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-acs_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Design%20and%20Synthesis%20of%20Novel%20Oxime%20Ester%20Photoinitiators%20Augmented%20by%20Automated%20Machine%20Learning&rft.jtitle=Chemistry%20of%20materials&rft.au=Lee,%20Won%20Jung&rft.date=2022-01-11&rft.volume=34&rft.issue=1&rft.spage=116&rft.epage=127&rft.pages=116-127&rft.issn=0897-4756&rft.eissn=1520-5002&rft_id=info:doi/10.1021/acs.chemmater.1c02871&rft_dat=%3Cacs_cross%3Ea352438551%3C/acs_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |