Discovery of novel reticular materials for carbon dioxide capture using GFlowNets
Artificial intelligence holds promise to improve materials discovery. GFlowNets are an emerging deep learning algorithm with many applications in AI-assisted discovery. Using GFlowNets, we generate porous reticular materials, such as Metal Organic Frameworks and Covalent Organic Frameworks, for appl...
Saved in:
Published in | Digital discovery Vol. 3; no. 3; pp. 449 - 455 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
13.03.2024
|
Online Access | Get full text |
Cover
Loading…
Abstract | Artificial intelligence holds promise to improve materials discovery. GFlowNets are an emerging deep learning algorithm with many applications in AI-assisted discovery. Using GFlowNets, we generate porous reticular materials, such as Metal Organic Frameworks and Covalent Organic Frameworks, for applications in carbon dioxide capture. We introduce a new Python package (matgfn) to train and sample GFlowNets. We use matgfn to generate the matgfn-rm dataset of novel and diverse reticular materials with gravimetric surface area above 5000 m
2
g
−1
. We calculate single- and two-component gas adsorption isotherms for the top-100 candidates in matgfn-rm. These candidates are novel compared to the state-of-art ARC-MOF dataset and rank in the 90th percentile in terms of working capacity compared to the CoRE2019 dataset. We identify 13 materials with CO
2
working capacity outperforming all materials in CoRE2019. After further analysis and structural relaxation, two outperforming materials remain.
GFlowNets discover reticular materials with simulated CO
2
working capacity outperforming all materials in CoRE2019. |
---|---|
AbstractList | Artificial intelligence holds promise to improve materials discovery. GFlowNets are an emerging deep learning algorithm with many applications in AI-assisted discovery. Using GFlowNets, we generate porous reticular materials, such as Metal Organic Frameworks and Covalent Organic Frameworks, for applications in carbon dioxide capture. We introduce a new Python package (matgfn) to train and sample GFlowNets. We use matgfn to generate the matgfn-rm dataset of novel and diverse reticular materials with gravimetric surface area above 5000 m
2
g
−1
. We calculate single- and two-component gas adsorption isotherms for the top-100 candidates in matgfn-rm. These candidates are novel compared to the state-of-art ARC-MOF dataset and rank in the 90th percentile in terms of working capacity compared to the CoRE2019 dataset. We identify 13 materials with CO
2
working capacity outperforming all materials in CoRE2019. After further analysis and structural relaxation, two outperforming materials remain. Artificial intelligence holds promise to improve materials discovery. GFlowNets are an emerging deep learning algorithm with many applications in AI-assisted discovery. Using GFlowNets, we generate porous reticular materials, such as Metal Organic Frameworks and Covalent Organic Frameworks, for applications in carbon dioxide capture. We introduce a new Python package (matgfn) to train and sample GFlowNets. We use matgfn to generate the matgfn-rm dataset of novel and diverse reticular materials with gravimetric surface area above 5000 m 2 g −1 . We calculate single- and two-component gas adsorption isotherms for the top-100 candidates in matgfn-rm. These candidates are novel compared to the state-of-art ARC-MOF dataset and rank in the 90th percentile in terms of working capacity compared to the CoRE2019 dataset. We identify 13 materials with CO 2 working capacity outperforming all materials in CoRE2019. After further analysis and structural relaxation, two outperforming materials remain. GFlowNets discover reticular materials with simulated CO 2 working capacity outperforming all materials in CoRE2019. |
Author | Steiner, Mathias Cipcigan, Flaviu Ribeiro dos Santos, Carine Booth, Jonathan Barros Ferreira, Rodrigo Neumann |
AuthorAffiliation | IBM Research IBM Research Europe Science and Technologies Facilities Council |
AuthorAffiliation_xml | – name: Science and Technologies Facilities Council – name: IBM Research Europe – name: IBM Research |
Author_xml | – sequence: 1 givenname: Flaviu surname: Cipcigan fullname: Cipcigan, Flaviu – sequence: 2 givenname: Jonathan surname: Booth fullname: Booth, Jonathan – sequence: 3 givenname: Rodrigo Neumann surname: Barros Ferreira fullname: Barros Ferreira, Rodrigo Neumann – sequence: 4 givenname: Carine surname: Ribeiro dos Santos fullname: Ribeiro dos Santos, Carine – sequence: 5 givenname: Mathias surname: Steiner fullname: Steiner, Mathias |
BookMark | eNpNkN9LwzAUhYNMcM69-C7kWagmbdIfj7K6qQxFUPCtpDc3ktE1I2l1--_tnKhP91z4znn4TsmodS0Scs7ZFWdJca2F1oyxmK2OyDhOExmxIn8b_csnZBrCas9kGedJOibPpQ3gPtDvqDO0HVJDPXYW-kZ5ulYdequaQI3zFJSvXUu1dVurcXg3Xe-R9sG273Qxb9znI3bhjByboYHTnzshr_Pbl9ldtHxa3M9ulhHEIu8iYLWATCZMcM1zY3gKWSw0l1BLFDFKlRYGtBQmVZlCiDNTC10bVptCIMhkQi4Pu-BdCB5NtfF2rfyu4qza-6hKUZbfPh4G-OIA-wC_3J-v5AuPqGBd |
Cites_doi | 10.1039/D0ME00060D 10.1021/acs.chemmater.2c02485 10.1038/s43246-023-00409-9 10.1038/s41597-023-02116-z 10.5281/zenodo.10246465 10.1021/ja3055639 10.1021/acs.chemmater.8b02257 10.48550/arXiv.1912.01703 10.1021/acs.jced.9b00835 10.46793/match.87-3.529W 10.1101/731877 10.1021/acsnano.1c00218 10.48550/arXiv.2303.14223 10.1039/D3DD00053B 10.1002/9783527821099 10.48550/arXiv.2306.03792 10.48550/arXiv.2302.00615 10.1038/s42256-020-00271-1 10.1016/j.micromeso.2011.08.020 10.1145/1963405.1963487 10.1021/acs.chemrev.0c01266 10.48550/arXiv.2106.04399 10.1002/anie.202101644 10.48550/arXiv.2111.09266 10.48550/arXiv.2306.17693 10.1021/ar800124u 10.1063/1.4946894 10.1126/sciadv.aat9180 10.1021/acs.jcim.0c00803 10.1038/s41551-021-00689-x 10.1038/s41586-019-1798-7 10.1038/s41467-020-17755-8 10.1021/acsami.1c02471 |
ContentType | Journal Article |
DBID | AAYXX CITATION |
DOI | 10.1039/d4dd00020j |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Chemistry |
EISSN | 2635-098X |
EndPage | 455 |
ExternalDocumentID | 10_1039_D4DD00020J d4dd00020j |
GroupedDBID | AAFWJ AFPKN AKBGW ALMA_UNASSIGNED_HOLDINGS ANUXI C6K EBS GROUPED_DOAJ M~E RRC 0R~ AARTK AAYXX CITATION H13 |
ID | FETCH-LOGICAL-c248t-c0b4c753041d18ff16c724d15cb5e42e5a69fcd54f6a7aec27fb4dbf0bf94ec53 |
ISSN | 2635-098X |
IngestDate | Fri Aug 23 03:24:45 EDT 2024 Thu Mar 14 07:25:52 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c248t-c0b4c753041d18ff16c724d15cb5e42e5a69fcd54f6a7aec27fb4dbf0bf94ec53 |
Notes | https://doi.org/10.1039/d4dd00020j Electronic supplementary information (ESI) available. See DOI |
ORCID | 0000-0002-5015-1443 |
OpenAccessLink | https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00020j |
PageCount | 7 |
ParticipantIDs | rsc_primary_d4dd00020j crossref_primary_10_1039_D4DD00020J |
PublicationCentury | 2000 |
PublicationDate | 2024-03-13 |
PublicationDateYYYYMMDD | 2024-03-13 |
PublicationDate_xml | – month: 03 year: 2024 text: 2024-03-13 day: 13 |
PublicationDecade | 2020 |
PublicationTitle | Digital discovery |
PublicationYear | 2024 |
References | Jain (D4DD00020J/cit39/1) 2022 Hey (D4DD00020J/cit1/1) 2009 Yaghi (D4DD00020J/cit8/1) 2019 Chung (D4DD00020J/cit19/1) 2019; 64 Freund (D4DD00020J/cit9/1) 2021; 60 Malkin (D4DD00020J/cit28/1) 2022; 35 Paszke (D4DD00020J/cit22/1) 2019 Widdowson (D4DD00020J/cit29/1) 2021; 87 Lahlou (D4DD00020J/cit24/1) 2023 Poličar (D4DD00020J/cit30/1) 2019 Pedregosa (D4DD00020J/cit32/1) 2011; 12 Burner (D4DD00020J/cit21/1) 2023; 35 Bengio (D4DD00020J/cit13/1) 2021 Jain (D4DD00020J/cit42/1) 2023 Dong (D4DD00020J/cit31/1) 2011 Rector-Brooks (D4DD00020J/cit40/1) 2023 Farha (D4DD00020J/cit11/1) 2012; 134 Cipcigan (D4DD00020J/cit12/1) 2023 Liu (D4DD00020J/cit43/1) 2023 Willems (D4DD00020J/cit25/1) 2012; 149 Agrawal (D4DD00020J/cit2/1) 2016; 4 Mohamed (D4DD00020J/cit45/1) 2023; 4 O'Keeffe (D4DD00020J/cit16/1) 2008; 41 Yao (D4DD00020J/cit18/1) 2021; 3 Yancy-Caballero (D4DD00020J/cit37/1) 2020; 5 Madan (D4DD00020J/cit41/1) 2022 Anderson (D4DD00020J/cit26/1) 2018; 30 Boyd (D4DD00020J/cit27/1) 2019; 576 Hammond (D4DD00020J/cit5/1) 2021; 15 Jain (D4DD00020J/cit15/1) 2023 Farmahini (D4DD00020J/cit38/1) 2021; 121 Bengio (D4DD00020J/cit14/1) 2021 He (D4DD00020J/cit44/1) 2022; 2022 Das (D4DD00020J/cit3/1) 2021; 5 McDonagh (D4DD00020J/cit7/1) 2023 Kalmutzki (D4DD00020J/cit10/1) 2018; 4 Crusius (D4DD00020J/cit4/1) 2023; 2 Cipcigan (D4DD00020J/cit6/1) 2020; 61 Lee (D4DD00020J/cit17/1) 2021; 13 Deng (D4DD00020J/cit36/1) 2023 Moosavi (D4DD00020J/cit20/1) 2020; 11 Neumann Barros Ferreira (D4DD00020J/cit33/1) 2022 Oliveira (D4DD00020J/cit34/1) 2023; 10 Jablonka (D4DD00020J/cit35/1) 2023 |
References_xml | – issn: 2023 publication-title: arXiv doi: Rector-Brooks Madan Jain Korablyov Liu Chandar Malkin Bengio – issn: 2022 publication-title: Biological Sequence Design with GFlowNets doi: Jain Bengio Garcia Rector-Brooks Dossou Ekbote Fu Zhang Kilgour Zhang Simine Das Bengio – issn: 2009 publication-title: The Fourth Paradigm: Data-Intensive Scientific Discovery doi: Hey Tansley Tolle – issn: 2019 publication-title: bioRxiv doi: Poli ar Stra ar Zupan – issn: 2022 issue: 2022 end-page: p 2205-2215 publication-title: Proceedings of the ACM Web Conference doi: He Feng Cheng Ji Guo Caverlee – issn: 2021 publication-title: arXiv doi: Bengio Jain Korablyov Precup Bengio – issn: 2023 end-page: p 14631-14653 publication-title: International Conference on Machine Learning doi: Jain Raparthy Hernández-Garc a Rector-Brooks Bengio Miret Bengio – issn: 2023 publication-title: Gymnasium doi: Towers Terry Kwiatkowski Balis Cola Deleu Goulão Kallinteris Arjun Krimmel Perez-Vicente Pierré Schulhoff Tai Shen Younis – issn: 2023 publication-title: Zenodo archive for flaviucipcigan/matgfn doi: Cipcigan – issn: 2023 publication-title: arXiv doi: McDonagh Wunsch Zavitsanou Harrison Elmegreen Gifford van Kessel Cipcigan – issn: 2019 publication-title: Introduction to reticular chemistry: metal-organic frameworks and covalent organic frameworks doi: Yaghi Kalmutzki Diercks – issn: 2023 doi: Jablonka – issn: 2022 publication-title: International Conference on Machine Learning doi: Madan Rector-Brooks Korablyov Bengio Jain Nica Bosc Bengio Malkin – issn: 2021 publication-title: arXiv doi: Bengio Deleu Hu Lahlou Tiwari Bengio – issn: 2023 publication-title: torchgfn, A PyTorch GFlowNet library doi: Lahlou Viviano Schmidt Bengio – issn: 2023 publication-title: arXiv doi: Liu Feng Stone Liu – issn: 2023 publication-title: arXiv doi: Jain Deleu Hartford Liu Hernández-García Bengio – issn: 2022 publication-title: Proceedings of the 16th Greenhouse Gas Control Technologies Conference doi: Neumann Barros Ferreira O Conchuir Elengikal Luan Ohta Lopes Oliveira Mhadeshwar Kalyanaraman Sundaram Falkowski – issn: 2011 end-page: p 577-586 publication-title: Proceedings of the 20th International Conference on World Wide Web doi: Dong Moses Li – issn: 2019 publication-title: arXiv doi: Paszke Gross Massa Lerer Bradbury Chanan Killeen Lin Gimelshein Antiga Desmaison Köpf Yang DeVito Raison Tejani Chilamkurthy Steiner Fang Bai Chintala – year: 2023 ident: D4DD00020J/cit35/1 contributor: fullname: Jablonka – volume-title: International Conference on Machine Learning year: 2022 ident: D4DD00020J/cit41/1 contributor: fullname: Madan – volume: 5 start-page: 1205 year: 2020 ident: D4DD00020J/cit37/1 publication-title: Mol. Syst. Des. Eng. doi: 10.1039/D0ME00060D contributor: fullname: Yancy-Caballero – volume: 35 start-page: 900 year: 2023 ident: D4DD00020J/cit21/1 publication-title: Chem. Mater. doi: 10.1021/acs.chemmater.2c02485 contributor: fullname: Burner – volume: 4 start-page: 79 year: 2023 ident: D4DD00020J/cit45/1 publication-title: Commun. Mater. doi: 10.1038/s43246-023-00409-9 contributor: fullname: Mohamed – volume: 10 start-page: 230 year: 2023 ident: D4DD00020J/cit34/1 publication-title: Sci. Data doi: 10.1038/s41597-023-02116-z contributor: fullname: Oliveira – volume: 35 start-page: 5955 year: 2022 ident: D4DD00020J/cit28/1 publication-title: Adv. Neural Inf. Process. contributor: fullname: Malkin – volume-title: Zenodo archive for flaviucipcigan/matgfn year: 2023 ident: D4DD00020J/cit12/1 doi: 10.5281/zenodo.10246465 contributor: fullname: Cipcigan – volume: 134 start-page: 15016 year: 2012 ident: D4DD00020J/cit11/1 publication-title: J. Am. Chem. Soc. doi: 10.1021/ja3055639 contributor: fullname: Farha – volume: 30 start-page: 6325 issue: 18 year: 2018 ident: D4DD00020J/cit26/1 publication-title: Chem. Mater. doi: 10.1021/acs.chemmater.8b02257 contributor: fullname: Anderson – volume-title: The Fourth Paradigm: Data-Intensive Scientific Discovery year: 2009 ident: D4DD00020J/cit1/1 contributor: fullname: Hey – volume-title: arXiv year: 2019 ident: D4DD00020J/cit22/1 doi: 10.48550/arXiv.1912.01703 contributor: fullname: Paszke – volume: 64 start-page: 5985 year: 2019 ident: D4DD00020J/cit19/1 publication-title: J. Chem. Eng. Data doi: 10.1021/acs.jced.9b00835 contributor: fullname: Chung – volume: 87 start-page: 529 year: 2021 ident: D4DD00020J/cit29/1 publication-title: MATCH Commun. Math. Comput. Chem. doi: 10.46793/match.87-3.529W contributor: fullname: Widdowson – volume-title: bioRxiv year: 2019 ident: D4DD00020J/cit30/1 doi: 10.1101/731877 contributor: fullname: Poličar – volume: 2022 start-page: 2205 volume-title: Proceedings of the ACM Web Conference year: 2022 ident: D4DD00020J/cit44/1 contributor: fullname: He – volume: 15 start-page: 9679 year: 2021 ident: D4DD00020J/cit5/1 publication-title: ACS Nano doi: 10.1021/acsnano.1c00218 contributor: fullname: Hammond – volume-title: arXiv year: 2023 ident: D4DD00020J/cit7/1 doi: 10.48550/arXiv.2303.14223 contributor: fullname: McDonagh – volume: 2 start-page: 1163 year: 2023 ident: D4DD00020J/cit4/1 publication-title: Digital Discovery doi: 10.1039/D3DD00053B contributor: fullname: Crusius – volume-title: Introduction to reticular chemistry: metal-organic frameworks and covalent organic frameworks year: 2019 ident: D4DD00020J/cit8/1 doi: 10.1002/9783527821099 contributor: fullname: Yaghi – start-page: 14631 volume-title: International Conference on Machine Learning year: 2023 ident: D4DD00020J/cit42/1 contributor: fullname: Jain – volume-title: arXiv year: 2023 ident: D4DD00020J/cit43/1 doi: 10.48550/arXiv.2306.03792 contributor: fullname: Liu – volume-title: Proceedings of the 16th Greenhouse Gas Control Technologies Conference year: 2022 ident: D4DD00020J/cit33/1 contributor: fullname: Neumann Barros Ferreira – volume-title: arXiv year: 2023 ident: D4DD00020J/cit15/1 doi: 10.48550/arXiv.2302.00615 contributor: fullname: Jain – volume: 3 start-page: 76 year: 2021 ident: D4DD00020J/cit18/1 publication-title: Nat. Mach. Intell. doi: 10.1038/s42256-020-00271-1 contributor: fullname: Yao – volume: 149 start-page: 134 year: 2012 ident: D4DD00020J/cit25/1 publication-title: Microporous Mesoporous Mater. doi: 10.1016/j.micromeso.2011.08.020 contributor: fullname: Willems – start-page: 577 volume-title: Proceedings of the 20th International Conference on World Wide Web year: 2011 ident: D4DD00020J/cit31/1 doi: 10.1145/1963405.1963487 contributor: fullname: Dong – start-page: 1 year: 2023 ident: D4DD00020J/cit36/1 publication-title: Nat. Mach. Intell. contributor: fullname: Deng – volume: 121 start-page: 10666 year: 2021 ident: D4DD00020J/cit38/1 publication-title: Chem. Rev. doi: 10.1021/acs.chemrev.0c01266 contributor: fullname: Farmahini – volume-title: arXiv year: 2021 ident: D4DD00020J/cit13/1 doi: 10.48550/arXiv.2106.04399 contributor: fullname: Bengio – volume: 60 start-page: 23946 issue: 45 year: 2021 ident: D4DD00020J/cit9/1 publication-title: Angew. Chem. doi: 10.1002/anie.202101644 contributor: fullname: Freund – volume-title: arXiv year: 2021 ident: D4DD00020J/cit14/1 doi: 10.48550/arXiv.2111.09266 contributor: fullname: Bengio – volume-title: arXiv year: 2023 ident: D4DD00020J/cit40/1 doi: 10.48550/arXiv.2306.17693 contributor: fullname: Rector-Brooks – volume-title: Biological Sequence Design with GFlowNets year: 2022 ident: D4DD00020J/cit39/1 contributor: fullname: Jain – volume: 41 start-page: 1782 year: 2008 ident: D4DD00020J/cit16/1 publication-title: Acc. Chem. Res. doi: 10.1021/ar800124u contributor: fullname: O'Keeffe – volume: 4 start-page: 053208 year: 2016 ident: D4DD00020J/cit2/1 publication-title: APL Mater. doi: 10.1063/1.4946894 contributor: fullname: Agrawal – volume: 4 start-page: eaat9180 year: 2018 ident: D4DD00020J/cit10/1 publication-title: Sci. Adv. doi: 10.1126/sciadv.aat9180 contributor: fullname: Kalmutzki – volume: 61 start-page: 263 year: 2020 ident: D4DD00020J/cit6/1 publication-title: J. Chem. Inf. Model. doi: 10.1021/acs.jcim.0c00803 contributor: fullname: Cipcigan – volume: 5 start-page: 613 year: 2021 ident: D4DD00020J/cit3/1 publication-title: Nat. Biomed. Eng. doi: 10.1038/s41551-021-00689-x contributor: fullname: Das – volume: 576 start-page: 253 year: 2019 ident: D4DD00020J/cit27/1 publication-title: Nature doi: 10.1038/s41586-019-1798-7 contributor: fullname: Boyd – volume-title: torchgfn, A PyTorch GFlowNet library year: 2023 ident: D4DD00020J/cit24/1 contributor: fullname: Lahlou – volume: 11 start-page: 4068 year: 2020 ident: D4DD00020J/cit20/1 publication-title: Nat. Commun. doi: 10.1038/s41467-020-17755-8 contributor: fullname: Moosavi – volume: 13 start-page: 23647 year: 2021 ident: D4DD00020J/cit17/1 publication-title: ACS Appl. Mater. Interfaces doi: 10.1021/acsami.1c02471 contributor: fullname: Lee – volume: 12 start-page: 2825 year: 2011 ident: D4DD00020J/cit32/1 publication-title: J. Mach. Learn. Res. contributor: fullname: Pedregosa |
SSID | ssj0002771136 |
Score | 2.297198 |
Snippet | Artificial intelligence holds promise to improve materials discovery. GFlowNets are an emerging deep learning algorithm with many applications in AI-assisted... |
SourceID | crossref rsc |
SourceType | Aggregation Database Publisher |
StartPage | 449 |
Title | Discovery of novel reticular materials for carbon dioxide capture using GFlowNets |
Volume | 3 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELa25QAXxKuiPCpLcFsFHMd5HVHDUlWiEqKVels5fqyMqvUq3YWqB_4Cf5mxHScL7aFwiSKvvYk8XzzjmfE3CL3Vkqicc55IltcJAwWQVKpKk0IImROdCe5d2Z9PiqMzdnyen08mv7ayljbr9p24vvVcyf9IFdpAru6U7D9IdvhTaIB7kC9cQcJwvZOMG3MpXApmYIWGO0fS79k0eDcFUzS8g88kFLxrQdDS2CsjXa7XyocONt5V8Gl2YX-cqEDqFE3VxixcQREXwgkPGcIVZiXMIjhOZxf8u9kMe3prg5sm-uRHP2kH2ng6U12nTBfsVSs7s7CwyrowwngezbTQw04ldP_qChxf9mkpMf7feygocyla4YBpWMgc301Cal9CGHTOLW39SpxtAS7bWlVZYDXtFTQLvL431n6SOerUhjWNj68ejxouRvX_UnxDOqIPxGf1fBy7g-5RxxzockF_jk47WpauBo4rWBjfP1LeZvX7cfgfRs5OF2vJeJvl9BF62G828IeAnMdoopZP0P3DWOPvKfoyIAhbjT2C8IAgPCAIA4JwQBDuEYR7BGGPIDwg6Bk6m308PTxK-iIbiaCsWieCtEzAnpWwVKaV1mkhSspkmos2V4zCh1zUGr5bpgteciVoqVsmW01aXTMl8mwP7S7tUj1HOGVCEyooKV1xea0rwomQtCiLQqS5yvfRmzgr81XgUpnfnPp9tAcTNnSQTEr_w7cXdxr-Ej0YMfgK7a67jXoNduO6PfD-lgMv0d85lnHo |
link.rule.ids | 315,783,787,867,27937,27938 |
linkProvider | ISSN International Centre |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Discovery+of+novel+reticular+materials+for+carbon+dioxide+capture+using+GFlowNets&rft.jtitle=Digital+discovery&rft.au=Cipcigan%2C+Flaviu&rft.au=Booth%2C+Jonathan&rft.au=Barros+Ferreira%2C+Rodrigo+Neumann&rft.au=Ribeiro+dos+Santos%2C+Carine&rft.date=2024-03-13&rft.issn=2635-098X&rft.eissn=2635-098X&rft.volume=3&rft.issue=3&rft.spage=449&rft.epage=455&rft_id=info:doi/10.1039%2FD4DD00020J&rft.externalDBID=n%2Fa&rft.externalDocID=10_1039_D4DD00020J |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2635-098X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2635-098X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2635-098X&client=summon |