Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning
Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in hay...
Saved in:
| Published in: | Chemical reviews Vol. 121; no. 16; p. 9927 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
25.08.2021
|
| Subjects: | |
| ISSN: | 1520-6890, 1520-6890 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes. |
|---|---|
| AbstractList | Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes. Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes. |
| Author | Duan, Chenru Nandy, Aditya Kulik, Heather J Liu, Fang Taylor, Michael G Steeves, Adam H |
| Author_xml | – sequence: 1 givenname: Aditya orcidid: 0000-0001-7137-5449 surname: Nandy fullname: Nandy, Aditya organization: Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States – sequence: 2 givenname: Chenru orcidid: 0000-0003-2592-4237 surname: Duan fullname: Duan, Chenru organization: Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States – sequence: 3 givenname: Michael G orcidid: 0000-0003-4327-2746 surname: Taylor fullname: Taylor, Michael G organization: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States – sequence: 4 givenname: Fang orcidid: 0000-0003-1322-4997 surname: Liu fullname: Liu, Fang organization: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States – sequence: 5 givenname: Adam H orcidid: 0000-0001-5813-4659 surname: Steeves fullname: Steeves, Adam H organization: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States – sequence: 6 givenname: Heather J orcidid: 0000-0001-9342-0191 surname: Kulik fullname: Kulik, Heather J organization: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34260198$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkF9LwzAUxYNM3B_9BILk0ZfOm6xNU99kOidMfHA-lzS7XSNtMpN2uG9vhxN8Opdzfhy4Z0wG1lkk5JrBlAFnd0qHqa6w8bifMg0wi9MzMmIJh0jIDAb_7iEZh_AJAEnC0wsynMVcAMvkiJi5a3Zdq1rjrKrpowna7dEfqCvp2isbzDGJGmz79MjW-I3hni68a-jSbKuorbzrtlVfQt-1R7TGbmnr6KvSlbFIV6j80bsk56WqA16ddEI-Fk_r-TJavT2_zB9WkUriuI0YglCJTJFvUqmFhKIsNYc4K0DydKazQpcyK5MNZJpLjQJLlsWxLlKWAhSCT8jtb-_Ou68OQ5s3_VNY18qi60LO-w1AMJGwHr05oV3R4CbfedMof8j_5uE_3WVsyA |
| CitedBy_id | crossref_primary_10_1038_s43588_022_00393_z crossref_primary_10_1038_s41524_022_00922_4 crossref_primary_10_1038_s41598_024_62074_3 crossref_primary_10_1002_anie_202420204 crossref_primary_10_1002_jcc_27185 crossref_primary_10_1007_s13399_024_05604_3 crossref_primary_10_1039_D5BM00687B crossref_primary_10_3390_catal12020164 crossref_primary_10_1039_D5DD00216H crossref_primary_10_1038_s41570_022_00424_3 crossref_primary_10_1002_aoc_7077 crossref_primary_10_1039_D5NJ00827A crossref_primary_10_1007_s40820_023_01192_5 crossref_primary_10_1021_jacs_4c17015 crossref_primary_10_1002_anie_202116175 crossref_primary_10_1002_cctc_202301215 crossref_primary_10_1002_smll_202301037 crossref_primary_10_1021_jacs_2c08513 crossref_primary_10_1021_jacs_2c08876 crossref_primary_10_1063_5_0201701 crossref_primary_10_1038_s44160_022_00133_1 crossref_primary_10_1038_s43588_024_00616_5 crossref_primary_10_1002_asia_202500512 crossref_primary_10_1039_D5DD00093A crossref_primary_10_1016_j_polymer_2024_126997 crossref_primary_10_1039_D3SC03319H crossref_primary_10_3389_fphy_2025_1580425 crossref_primary_10_1016_j_talanta_2022_123228 crossref_primary_10_1186_s13321_024_00939_5 crossref_primary_10_1063_5_0248572 crossref_primary_10_1039_D4SC03647F crossref_primary_10_1021_acs_jcim_5c00815 crossref_primary_10_1038_d41586_025_00902_w crossref_primary_10_1002_ange_202116175 crossref_primary_10_1088_2632_2153_addc32 crossref_primary_10_1039_D2CY00200K crossref_primary_10_1021_acs_inorgchem_5c01726 crossref_primary_10_1021_jacsau_5c00502 crossref_primary_10_1002_cplu_202300702 crossref_primary_10_1088_1361_6463_ac6f97 crossref_primary_10_1021_jacs_2c11066 crossref_primary_10_1016_j_ica_2025_122894 crossref_primary_10_1016_j_ccr_2025_217187 crossref_primary_10_1142_S2810922825300028 crossref_primary_10_1016_j_nxmate_2025_100864 crossref_primary_10_1021_acs_jpclett_4c03568 crossref_primary_10_1007_s00214_023_02974_1 crossref_primary_10_1016_j_commatsci_2025_114121 crossref_primary_10_1016_j_pnsc_2025_05_002 crossref_primary_10_59324_ejaset_2025_3_4__13 crossref_primary_10_1016_j_apcatb_2024_124622 crossref_primary_10_1016_j_mcat_2023_113450 crossref_primary_10_1021_acsami_4c22658 crossref_primary_10_1039_D4SC05471G crossref_primary_10_1002_ange_202420204 crossref_primary_10_1016_j_molstruc_2023_136866 crossref_primary_10_1038_s43588_022_00384_0 crossref_primary_10_3233_JIFS_220781 crossref_primary_10_1063_5_0136526 crossref_primary_10_1002_adma_202502407 crossref_primary_10_1002_aoc_7021 crossref_primary_10_1021_acs_jpclett_5c01940 crossref_primary_10_1039_D5DT00812C crossref_primary_10_1007_s40843_025_3399_3 crossref_primary_10_1134_S1061934823070055 crossref_primary_10_1021_jacsau_5c00242 crossref_primary_10_1088_2632_2153_ad9f22 crossref_primary_10_1557_s43578_025_01568_w crossref_primary_10_1088_2515_7655_ade5cb crossref_primary_10_1039_D4SC05616G crossref_primary_10_1038_s42256_025_01010_0 crossref_primary_10_1002_cmtd_202400071 crossref_primary_10_1002_poc_4458 crossref_primary_10_1038_s44160_022_00128_y crossref_primary_10_1021_acs_jctc_5c00886 crossref_primary_10_1021_acs_jctc_5c00402 crossref_primary_10_1039_D5DT01438G crossref_primary_10_1103_PhysRevB_111_085110 crossref_primary_10_1002_chem_202201570 crossref_primary_10_1016_j_coche_2021_100752 crossref_primary_10_1016_j_fuel_2025_136132 crossref_primary_10_1039_D3SC04610A crossref_primary_10_1002_cjce_25437 crossref_primary_10_1038_s43588_024_00618_3 crossref_primary_10_1021_cbe_4c00170 crossref_primary_10_1038_s41524_024_01339_x crossref_primary_10_1016_j_jechem_2023_02_043 crossref_primary_10_1016_j_nxmate_2025_100713 crossref_primary_10_1039_D2SC05089G crossref_primary_10_1038_s41377_024_01734_5 crossref_primary_10_1016_j_compchemeng_2022_108022 crossref_primary_10_1002_jcc_27013 crossref_primary_10_1039_D2SC04251G crossref_primary_10_1002_advs_202506240 crossref_primary_10_1016_j_ccr_2023_215169 crossref_primary_10_3390_molecules28114477 crossref_primary_10_1038_s44160_024_00561_1 crossref_primary_10_1021_jacs_3c11399 crossref_primary_10_1039_D5TA01139F crossref_primary_10_1021_acs_jctc_5c00303 crossref_primary_10_1016_j_coche_2021_100778 crossref_primary_10_1146_annurev_chembioeng_092320_120230 crossref_primary_10_1002_cctc_202301475 crossref_primary_10_1016_j_jece_2025_118132 crossref_primary_10_1021_acs_jctc_5c01079 crossref_primary_10_1038_s41524_024_01466_5 crossref_primary_10_1134_S0036024423020188 crossref_primary_10_1002_cplu_202400686 crossref_primary_10_1007_s11243_024_00572_z crossref_primary_10_1002_adma_202306733 crossref_primary_10_1016_j_inoche_2024_113770 crossref_primary_10_30799_jacs_272_25110103 crossref_primary_10_3390_cancers17111828 crossref_primary_10_1002_idm2_12249 crossref_primary_10_1016_j_saa_2024_125138 crossref_primary_10_1021_jacs_4c14076 crossref_primary_10_1021_jacs_5c02097 crossref_primary_10_1021_acs_jpca_4c05718 crossref_primary_10_1016_j_jcat_2021_12_014 crossref_primary_10_1039_D5DD00129C crossref_primary_10_1016_j_mtener_2025_102002 crossref_primary_10_1038_s41524_025_01523_7 crossref_primary_10_1080_00194506_2024_2444394 crossref_primary_10_1007_s11244_021_01543_9 crossref_primary_10_1016_j_asoc_2024_111935 crossref_primary_10_1002_cssc_202300482 crossref_primary_10_1107_S2052252524000770 crossref_primary_10_1007_s42773_023_00225_x crossref_primary_10_1021_acs_jcim_5c00636 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1021/acs.chemrev.1c00347 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Chemistry |
| EISSN | 1520-6890 |
| ExternalDocumentID | 34260198 |
| Genre | Research Support, U.S. Gov't, Non-P.H.S Review Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- -DZ -~X .DC .K2 29B 4.4 53G 55A 5GY 5RE 5VS 6J9 7~N 85S AABXI AAHBH ABJNI ABMVS ABPPZ ABQRX ABUCX ACGFO ACGFS ACGOD ACIWK ACJ ACNCT ACS ADHLV AEESW AENEX AFEFF AFXLT AGXLV AHGAQ ALMA_UNASSIGNED_HOLDINGS AQSVZ BAANH BKOMP CGR CS3 CUPRZ CUY CVF D0L DU5 EBS ECM ED~ EIF F5P GGK GNL IH9 IHE JG~ LG6 NPM P2P PQQKQ ROL RWL TAE TN5 UI2 UKR UPT VF5 VG9 W1F WH7 XSW YZZ ~02 7X8 ABBLG ABLBI |
| ID | FETCH-LOGICAL-a544t-1e06a587e2d78c680bffc2049b08273c9bcf89f5d09c28ce6ef1944cb71700b62 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 219 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000691784200006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1520-6890 |
| IngestDate | Fri Jul 11 11:17:24 EDT 2025 Thu Apr 03 07:05:08 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 16 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a544t-1e06a587e2d78c680bffc2049b08273c9bcf89f5d09c28ce6ef1944cb71700b62 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 ObjectType-Review-3 content type line 23 |
| ORCID | 0000-0001-9342-0191 0000-0003-1322-4997 0000-0001-7137-5449 0000-0003-2592-4237 0000-0003-4327-2746 0000-0001-5813-4659 |
| OpenAccessLink | https://www.osti.gov/biblio/1808009 |
| PMID | 34260198 |
| PQID | 2552061651 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2552061651 pubmed_primary_34260198 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-08-25 |
| PublicationDateYYYYMMDD | 2021-08-25 |
| PublicationDate_xml | – month: 08 year: 2021 text: 2021-08-25 day: 25 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Chemical reviews |
| PublicationTitleAlternate | Chem Rev |
| PublicationYear | 2021 |
| SSID | ssj0005527 |
| Score | 2.6969266 |
| SecondaryResourceType | review_article |
| Snippet | Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 9927 |
| SubjectTerms | Coordination Complexes - chemistry High-Throughput Screening Assays Machine Learning Metals - chemistry Transition Elements - chemistry |
| Title | Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/34260198 https://www.proquest.com/docview/2552061651 |
| Volume | 121 |
| WOSCitedRecordID | wos000691784200006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dS8MwFA3qBH3x-2N-EcHXsDZtmsQXkenwZWOgwt5GkyY6cO1cp-i_96ZN2ZMg-NKnNrS5t_eeJIdzELrKUkgCaO3EwQ0SSxoSlVlFhDaKWZrR1IjKbIIPBmI0kkO_4VZ6WmVTE6tCnRXa7ZF3APpS6D0JC29m78S5RrnTVW-hsYpaEUAZR-nio6VaOKstW6FFwRJJyKBRHaJhJ9UQ0lczdUYvoXYqLfx3jFn1mt72f99yB215lIlv67TYRSsm30Mb3cbcbR9NajcHvxOI7yaldlzOb1xYXLWvislFpgawOXb3vpkvU17j3ryYYscNId7gBwbBj9qRd6AH4kWB-xU702Av3PpygJ5790_dB-JdF0jK4nhBQhMkKRPc0IwLnYhAWaspLCQUoAUeaam0FdKyLJCaQkgTY0MZx1pxJ_WnEnqI1vIiN8cIW4hAlMgMqkYaRyaWWkEKpJkQknHLVRtdNrM4hu93RxVpboqPcrycxzY6qkMxntXyG-PIieqHUpz84elTtEkdCSWAcsDOUMvCP23O0br-XEzK-UWVLnAdDPs_KLfM0g |
| linkProvider | ProQuest |
| 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=Computational+Discovery+of+Transition-metal+Complexes%3A+From+High-throughput+Screening+to+Machine+Learning&rft.jtitle=Chemical+reviews&rft.au=Nandy%2C+Aditya&rft.au=Duan%2C+Chenru&rft.au=Taylor%2C+Michael+G&rft.au=Liu%2C+Fang&rft.date=2021-08-25&rft.issn=1520-6890&rft.eissn=1520-6890&rft.volume=121&rft.issue=16&rft.spage=9927&rft_id=info:doi/10.1021%2Facs.chemrev.1c00347&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-6890&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-6890&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-6890&client=summon |