Machine-learning approach to the design of OSDAs for zeolite beta
We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction....
Gespeichert in:
| Veröffentlicht in: | Proceedings of the National Academy of Sciences - PNAS 2019-02, Vol.116 (9), p.3413-3418 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3418 |
|---|---|
| container_issue | 9 |
| container_start_page | 3413 |
| container_title | Proceedings of the National Academy of Sciences - PNAS |
| container_volume | 116 |
| creator | Daeyaert, Frits Deem, Michael W. |
| description | We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below −17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta. |
| doi_str_mv | 10.1073/pnas.1818763116 |
| format | Article |
| fullrecord | <record><control><sourceid>jstor_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6397530</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>26672082</jstor_id><sourcerecordid>26672082</sourcerecordid><originalsourceid>FETCH-LOGICAL-c536t-4bb8a32a689e255c4520c10e91cbab364b14dcf0f16a410767f63c4c37e06b0a3</originalsourceid><addsrcrecordid>eNpdkc1vEzEQxS0EoqFw5gRa0QuXbWdsr72-IEUtX1JRD8DZ8jrexNHGXmwHCf56HKWEj9NIM7954-dHyHOESwTJruZg8iX22EvBEMUDskBQ2Aqu4CFZAFDZ9pzyM_Ik5y0AqK6Hx-SM1V1GFSzI8pOxGx9cOzmTgg_rxsxzirXZlNiUjWtWLvt1aOLY3H2-WeZmjKn56eLki2sGV8xT8mg0U3bP7us5-fru7ZfrD-3t3fuP18vb1nZMlJYPQ28YNaJXjnad5R0Fi-AU2sEMTPAB-cqOMKIwvHoTchTMcsukAzGAYefkzVF33g87t7IulGQmPSe_M-mHjsbrfyfBb_Q6fteCKdkxqAKvjgIxF6-zrQbsxsYQnC0aBTKUskKv76-k-G3vctE7n62bJhNc3GdNsReCouKiohf_odu4T6H-wYGSiKrDw9WrI2VTzDm58fRiBH3IUB8y1H8yrBsv_zZ64n-HVoEXR2CbS0ynORVCUugp-wXKIZ_4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2187119510</pqid></control><display><type>article</type><title>Machine-learning approach to the design of OSDAs for zeolite beta</title><source>Jstor Complete Legacy</source><source>PubMed Central</source><source>Alma/SFX Local Collection</source><source>Free Full-Text Journals in Chemistry</source><creator>Daeyaert, Frits ; Deem, Michael W.</creator><creatorcontrib>Daeyaert, Frits ; Deem, Michael W. ; Rice Univ., Houston, TX (United States)</creatorcontrib><description>We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below −17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta.</description><identifier>ISSN: 0027-8424</identifier><identifier>EISSN: 1091-6490</identifier><identifier>DOI: 10.1073/pnas.1818763116</identifier><identifier>PMID: 30733290</identifier><language>eng</language><publisher>United States: National Academy of Sciences</publisher><subject>Design ; ENGINEERING ; Evolutionary algorithms ; Learning algorithms ; Machine learning ; Molecular dynamics ; neural network ; Neural networks ; Organic chemistry ; OSDA ; Physical Sciences ; Predictions ; science & technology - other topics ; Stabilization ; zeolite beta ; Zeolites</subject><ispartof>Proceedings of the National Academy of Sciences - PNAS, 2019-02, Vol.116 (9), p.3413-3418</ispartof><rights>Copyright © 2019 the Author(s). Published by PNAS.</rights><rights>Copyright National Academy of Sciences Feb 26, 2019</rights><rights>Copyright © 2019 the Author(s). Published by PNAS. 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c536t-4bb8a32a689e255c4520c10e91cbab364b14dcf0f16a410767f63c4c37e06b0a3</citedby><cites>FETCH-LOGICAL-c536t-4bb8a32a689e255c4520c10e91cbab364b14dcf0f16a410767f63c4c37e06b0a3</cites><orcidid>0000-0002-3896-4003 ; 0000-0002-4298-3450 ; 0000000238964003 ; 0000000242983450</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/26672082$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/26672082$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>230,314,723,776,780,799,881,27901,27902,53766,53768,57992,58225</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30733290$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/servlets/purl/1613177$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Daeyaert, Frits</creatorcontrib><creatorcontrib>Deem, Michael W.</creatorcontrib><creatorcontrib>Rice Univ., Houston, TX (United States)</creatorcontrib><title>Machine-learning approach to the design of OSDAs for zeolite beta</title><title>Proceedings of the National Academy of Sciences - PNAS</title><addtitle>Proc Natl Acad Sci U S A</addtitle><description>We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below −17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta.</description><subject>Design</subject><subject>ENGINEERING</subject><subject>Evolutionary algorithms</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Molecular dynamics</subject><subject>neural network</subject><subject>Neural networks</subject><subject>Organic chemistry</subject><subject>OSDA</subject><subject>Physical Sciences</subject><subject>Predictions</subject><subject>science & technology - other topics</subject><subject>Stabilization</subject><subject>zeolite beta</subject><subject>Zeolites</subject><issn>0027-8424</issn><issn>1091-6490</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNpdkc1vEzEQxS0EoqFw5gRa0QuXbWdsr72-IEUtX1JRD8DZ8jrexNHGXmwHCf56HKWEj9NIM7954-dHyHOESwTJruZg8iX22EvBEMUDskBQ2Aqu4CFZAFDZ9pzyM_Ik5y0AqK6Hx-SM1V1GFSzI8pOxGx9cOzmTgg_rxsxzirXZlNiUjWtWLvt1aOLY3H2-WeZmjKn56eLki2sGV8xT8mg0U3bP7us5-fru7ZfrD-3t3fuP18vb1nZMlJYPQ28YNaJXjnad5R0Fi-AU2sEMTPAB-cqOMKIwvHoTchTMcsukAzGAYefkzVF33g87t7IulGQmPSe_M-mHjsbrfyfBb_Q6fteCKdkxqAKvjgIxF6-zrQbsxsYQnC0aBTKUskKv76-k-G3vctE7n62bJhNc3GdNsReCouKiohf_odu4T6H-wYGSiKrDw9WrI2VTzDm58fRiBH3IUB8y1H8yrBsv_zZ64n-HVoEXR2CbS0ynORVCUugp-wXKIZ_4</recordid><startdate>20190226</startdate><enddate>20190226</enddate><creator>Daeyaert, Frits</creator><creator>Deem, Michael W.</creator><general>National Academy of Sciences</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QG</scope><scope>7QL</scope><scope>7QP</scope><scope>7QR</scope><scope>7SN</scope><scope>7SS</scope><scope>7T5</scope><scope>7TK</scope><scope>7TM</scope><scope>7TO</scope><scope>7U9</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>H94</scope><scope>M7N</scope><scope>P64</scope><scope>RC3</scope><scope>7X8</scope><scope>OIOZB</scope><scope>OTOTI</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-3896-4003</orcidid><orcidid>https://orcid.org/0000-0002-4298-3450</orcidid><orcidid>https://orcid.org/0000000238964003</orcidid><orcidid>https://orcid.org/0000000242983450</orcidid></search><sort><creationdate>20190226</creationdate><title>Machine-learning approach to the design of OSDAs for zeolite beta</title><author>Daeyaert, Frits ; Deem, Michael W.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c536t-4bb8a32a689e255c4520c10e91cbab364b14dcf0f16a410767f63c4c37e06b0a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Design</topic><topic>ENGINEERING</topic><topic>Evolutionary algorithms</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Molecular dynamics</topic><topic>neural network</topic><topic>Neural networks</topic><topic>Organic chemistry</topic><topic>OSDA</topic><topic>Physical Sciences</topic><topic>Predictions</topic><topic>science & technology - other topics</topic><topic>Stabilization</topic><topic>zeolite beta</topic><topic>Zeolites</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Daeyaert, Frits</creatorcontrib><creatorcontrib>Deem, Michael W.</creatorcontrib><creatorcontrib>Rice Univ., Houston, TX (United States)</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Animal Behavior Abstracts</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Ecology Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Immunology Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Nucleic Acids Abstracts</collection><collection>Oncogenes and Growth Factors Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Proceedings of the National Academy of Sciences - PNAS</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Daeyaert, Frits</au><au>Deem, Michael W.</au><aucorp>Rice Univ., Houston, TX (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine-learning approach to the design of OSDAs for zeolite beta</atitle><jtitle>Proceedings of the National Academy of Sciences - PNAS</jtitle><addtitle>Proc Natl Acad Sci U S A</addtitle><date>2019-02-26</date><risdate>2019</risdate><volume>116</volume><issue>9</issue><spage>3413</spage><epage>3418</epage><pages>3413-3418</pages><issn>0027-8424</issn><eissn>1091-6490</eissn><abstract>We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below −17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta.</abstract><cop>United States</cop><pub>National Academy of Sciences</pub><pmid>30733290</pmid><doi>10.1073/pnas.1818763116</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0002-3896-4003</orcidid><orcidid>https://orcid.org/0000-0002-4298-3450</orcidid><orcidid>https://orcid.org/0000000238964003</orcidid><orcidid>https://orcid.org/0000000242983450</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0027-8424 |
| ispartof | Proceedings of the National Academy of Sciences - PNAS, 2019-02, Vol.116 (9), p.3413-3418 |
| issn | 0027-8424 1091-6490 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6397530 |
| source | Jstor Complete Legacy; PubMed Central; Alma/SFX Local Collection; Free Full-Text Journals in Chemistry |
| subjects | Design ENGINEERING Evolutionary algorithms Learning algorithms Machine learning Molecular dynamics neural network Neural networks Organic chemistry OSDA Physical Sciences Predictions science & technology - other topics Stabilization zeolite beta Zeolites |
| title | Machine-learning approach to the design of OSDAs for zeolite beta |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T05%3A48%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine-learning%20approach%20to%20the%20design%20of%20OSDAs%20for%20zeolite%20beta&rft.jtitle=Proceedings%20of%20the%20National%20Academy%20of%20Sciences%20-%20PNAS&rft.au=Daeyaert,%20Frits&rft.aucorp=Rice%20Univ.,%20Houston,%20TX%20(United%20States)&rft.date=2019-02-26&rft.volume=116&rft.issue=9&rft.spage=3413&rft.epage=3418&rft.pages=3413-3418&rft.issn=0027-8424&rft.eissn=1091-6490&rft_id=info:doi/10.1073/pnas.1818763116&rft_dat=%3Cjstor_pubme%3E26672082%3C/jstor_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2187119510&rft_id=info:pmid/30733290&rft_jstor_id=26672082&rfr_iscdi=true |