Learning on knowledge graph dynamics provides an early warning of impactful research

The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for ‘impactfu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Nature biotechnology Ročník 39; číslo 10; s. 1300 - 1307
Hlavní autoři:	Weis, James W., Jacobson, Joseph M.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York Nature Publishing Group US 01.10.2021 Nature Publishing Group
Témata:	631/114/1305 631/114/2406 706/648/1496 Agriculture Analysis Artificial intelligence Bibliometrics Bioinformatics Biomedical and Life Sciences Biomedical Engineering/Biotechnology Biomedicine Biotechnology Datasets Funding Graph theory Knowledge representation Learning algorithms Life Sciences Machine learning Mathematical analysis Scientific papers Warning systems United States
ISSN:	1087-0156, 1546-1696, 1546-1696
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for ‘impactful’ research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework’s performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios. Biotechnology-related papers predicted to be of long-term impact are identified in a machine learning framework (DELPHI) that analyzes relationships among a range of features from the scientific literature over time.
AbstractList	The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for 'impactful' research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework's performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios. The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for 'impactful' research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework's performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios. Biotechnology-related papers predicted to be of long-term impact are identified in a machine learning framework (DELPHI) that analyzes relationships among a range of features from the scientific literature over time. The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for ‘impactful’ research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework’s performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios. Biotechnology-related papers predicted to be of long-term impact are identified in a machine learning framework (DELPHI) that analyzes relationships among a range of features from the scientific literature over time. The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for 'impactful' research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework's performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios.The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here we describe DELPHI (Dynamic Early-warning by Learning to Predict High Impact), a framework that provides an early-warning signal for 'impactful' research by autonomously learning high-dimensional relationships among features calculated across time from the scientific literature. We prototype this framework and deduce its performance and scaling properties on time-structured publication graphs from 1980 to 2019 drawn from 42 biotechnology-related journals, including over 7.8 million individual nodes, 201 million relationships and 3.8 billion calculated metrics. We demonstrate the framework's performance by correctly identifying 19/20 seminal biotechnologies from 1980 to 2014 via a blinded retrospective study and provide 50 research papers from 2018 that DELPHI predicts will be in the top 5% of time-rescaled node centrality in the future. We propose DELPHI as a tool to aid in the construction of diversified, impact-optimized funding portfolios.
Audience	Academic
Author	Weis, James W. Jacobson, Joseph M.
Author_xml	– sequence: 1 givenname: James W. orcidid: 0000-0003-3735-0365 surname: Weis fullname: Weis, James W. email: jww@mit.edu organization: MIT Media Lab, Massachusetts Institute of Technology, Department of Computational and Systems Biology, Massachusetts Institute of Technology – sequence: 2 givenname: Joseph M. surname: Jacobson fullname: Jacobson, Joseph M. organization: MIT Media Lab, Massachusetts Institute of Technology, MIT Center for Bits and Atoms, Massachusetts Institute of Technology
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/34002098$$D View this record in MEDLINE/PubMed
BookMark	eNqNkl1vFCEUhompsR_6B7wwJN7YxKkwHwxcNo3VJps00eotYeDMLHWWWWHGuv_es05r3cY0hmQg8DzMAd5DsheGAIS85OyEs0K-SyWvZJ2xnGeMKVZn4gk54FUpMi6U2MMx2y7zSuyTw5SuGWOiFOIZ2S9KxnKm5AG5WoCJwYeODoF-C8NND64D2kWzXlK3CWblbaLrOPzwDhI1gSLfb-jNndVSv1obO7ZTTyMkXLXL5-Rpa_oEL277I_Ll_P3V2cdscfnh4ux0kdmqrMesls7gCQSYHKwCnCsLBcoBmEa5mkkr8qYqsS-4dVy0LXOykk0JyrYFM8UReTPvi_V9nyCNeuWThb43AYYp6bzKpeQFVxLR1w_Q62GKAatDqlZSiIoV91RnetA-tMMYjd1uqk9FLXOhKpEjdfIPCpsDvC18o9bj_I5wvCMgM8LPsTNTSvri86f_Zy-_7rJv_2KbKfkACT_Jd8sxzcoO_ur2DqZmBU6vo1-ZuNF3aUAgnwEbh5QitH8QzvQ2cnqOnMbI6d-R0wIl-UCyfjSjx7qj8f3jajGrCf8TOoj3j_KI9QtL2ebL
CitedBy_id	crossref_primary_10_1038_s41562_024_02041_0 crossref_primary_10_1162_qss_a_00221 crossref_primary_10_1186_s40580_021_00282_7 crossref_primary_10_1109_RITA_2023_3301510 crossref_primary_10_3390_modelling5020024 crossref_primary_10_1073_pnas_2427157122 crossref_primary_10_3390_mca29040059 crossref_primary_10_1016_j_jik_2025_100778 crossref_primary_10_1016_j_joi_2024_101596 crossref_primary_10_1007_s11192_025_05345_8 crossref_primary_10_1039_D4NP00008K crossref_primary_10_1016_j_joi_2022_101290 crossref_primary_10_1209_0295_5075_ac6bbb crossref_primary_10_1061_JITSE4_ISENG_2399 crossref_primary_10_1371_journal_pone_0275192 crossref_primary_10_1016_j_techfore_2025_124053 crossref_primary_10_1007_s11192_022_04547_8 crossref_primary_10_1177_10597123231186432 crossref_primary_10_1016_j_jenvman_2022_115685 crossref_primary_10_1038_d41586_021_01358_4 crossref_primary_10_1007_s11390_022_2845_7 crossref_primary_10_1007_s11704_022_2078_5 crossref_primary_10_1038_s41598_024_52233_x crossref_primary_10_1080_01446193_2022_2164598 crossref_primary_10_1080_00207721_2023_2300149 crossref_primary_10_1007_s00146_021_01259_0 crossref_primary_10_1038_d41586_023_00183_1 crossref_primary_10_1088_2632_2153_add6ef crossref_primary_10_1371_journal_pone_0288469 crossref_primary_10_1016_j_joi_2022_101282 crossref_primary_10_1186_s13677_023_00585_6 crossref_primary_10_1038_s41524_025_01540_6 crossref_primary_10_4018_JDM_345400
Cites_doi	10.1016/j.joi.2019.101005 10.1136/bmj.314.7079.497 10.1038/s42254-018-0005-3 10.1101/gad.989402 10.1007/s11192-010-0160-5 10.1038/489201a 10.1016/j.jempfin.2009.11.001 10.1016/j.techfore.2018.01.036 10.1038/492034a 10.1073/pnas.1800485115 10.1109/MC.2013.374 10.1613/jair.953 10.1007/s11390-015-1518-1 10.1287/mnsc.2015.2366 10.1126/science.1212540 10.1038/s41586-019-0941-9 10.1209/0295-5075/116/30007 10.1016/j.stem.2007.05.015 10.1016/j.joi.2016.10.005 10.1126/science.aaa3796 10.1128/mBio.00694-16 10.1038/s41587-019-0362-1 10.3386/w22587 10.1109/JCDL.2017.7991559 10.1145/2939672.2939754 10.2139/ssrn.2053258 10.1038/4351003b
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Springer Nature America, Inc. 2021 COPYRIGHT 2021 Nature Publishing Group The Author(s), under exclusive licence to Springer Nature America, Inc. 2021. 2021. The Author(s), under exclusive licence to Springer Nature America, Inc.
Copyright_xml	– notice: The Author(s), under exclusive licence to Springer Nature America, Inc. 2021 – notice: COPYRIGHT 2021 Nature Publishing Group – notice: The Author(s), under exclusive licence to Springer Nature America, Inc. 2021. – notice: 2021. The Author(s), under exclusive licence to Springer Nature America, Inc.
DBID	AAYXX CITATION NPM N95 IOV ISR 3V. 7QO 7QP 7QR 7T7 7TK 7TM 7X7 7XB 88A 88E 88I 8AO 8FD 8FE 8FG 8FH 8FI 8FJ 8FK 8G5 ABJCF ABUWG AEUYN AFKRA AZQEC BBNVY BENPR BGLVJ BHPHI C1K CCPQU DWQXO FR3 FYUFA GHDGH GNUQQ GUQSH HCIFZ K9. L6V LK8 M0S M1P M2O M2P M7P M7S MBDVC P64 PHGZM PHGZT PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PTHSS Q9U RC3 7X8
DOI	10.1038/s41587-021-00907-6
DatabaseName	CrossRef PubMed Gale Business: Insights Gale In Context: Opposing Viewpoints Gale In Context: Science ProQuest Central (Corporate) Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Chemoreception Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) Neurosciences Abstracts Nucleic Acids Abstracts ProQuest Health & Medical Collection ProQuest Central (purchase pre-March 2016) Biology Database (Alumni Edition) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest Pharma Collection Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Journals Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) Research Library ProQuest Materials Science & Engineering Collection ProQuest Central (Alumni) One Sustainability ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection ProQuest Central Technology Collection Natural Science Collection Environmental Sciences and Pollution Management ProQuest One Community College ProQuest Central Engineering Research Database Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student Research Library Prep SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) ProQuest Engineering Collection Biological Sciences ProQuest Health & Medical Collection Medical Database Proquest Research Library ProQuest Science Database (NC LIVE) Biological Science Database Engineering Database Research Library (Corporate) Biotechnology and BioEngineering Abstracts ProQuest Central Premium ProQuest One Academic ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition Engineering Collection ProQuest Central Basic Genetics Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Research Library Prep ProQuest Central Student ProQuest Central Essentials Nucleic Acids Abstracts SciTech Premium Collection Environmental Sciences and Pollution Management ProQuest One Applied & Life Sciences ProQuest One Sustainability Health Research Premium Collection Natural Science Collection Health & Medical Research Collection Biological Science Collection Chemoreception Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) ProQuest Central (New) ProQuest Medical Library (Alumni) Engineering Collection Engineering Database ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest One Academic Eastern Edition ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) Biological Science Database Neurosciences Abstracts ProQuest Hospital Collection (Alumni) Biotechnology and BioEngineering Abstracts ProQuest Health & Medical Complete ProQuest One Academic UKI Edition Engineering Research Database ProQuest One Academic Calcium & Calcified Tissue Abstracts ProQuest One Academic (New) Technology Collection Technology Research Database ProQuest One Academic Middle East (New) ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing Research Library (Alumni Edition) ProQuest Natural Science Collection ProQuest Pharma Collection ProQuest Biology Journals (Alumni Edition) ProQuest Central ProQuest Health & Medical Research Collection Genetics Abstracts ProQuest Engineering Collection Biotechnology Research Abstracts Health and Medicine Complete (Alumni Edition) ProQuest Central Korea ProQuest Research Library ProQuest Central Basic ProQuest Science Journals ProQuest SciTech Collection ProQuest Medical Library Materials Science & Engineering Collection ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	PubMed MEDLINE - Academic Research Library Prep
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: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Engineering Agriculture Biology
EISSN	1546-1696
EndPage	1307
ExternalDocumentID	A678269562 34002098 10_1038_s41587_021_00907_6
Genre	Journal Article
GeographicLocations	United States
GeographicLocations_xml	– name: United States
GrantInformation_xml	– fundername: MIT Media Lab, MIT Center for Bits and Atoms
GroupedDBID	--- -~X .55 .GJ 0R~ 123 29M 2FS 2XV 36B 39C 3V. 4.4 4R4 53G 5BI 5M7 5RE 5S5 70F 7X7 88A 88E 88I 8AO 8CJ 8FE 8FG 8FH 8FI 8FJ 8G5 8R4 8R5 A8Z AAEEF AAHBH AAIKC AAMNW AARCD AAYOK AAYZH AAZLF ABAWZ ABDBF ABDPE ABEFU ABJCF ABJNI ABLJU ABOCM ABUWG ACBTR ACBWK ACGFO ACGFS ACGOD ACIWK ACMJI ACPRK ACUHS ADBBV ADFRT AENEX AEUYN AFANA AFBBN AFFNX AFKRA AFRAH AFSHS AGAYW AGHTU AHBCP AHMBA AHOSX AHSBF AIBTJ ALFFA ALIPV ALMA_UNASSIGNED_HOLDINGS AMTXH ARMCB ASPBG AVWKF AXYYD AZFZN AZQEC BAAKF BBNVY BENPR BGLVJ BHPHI BKKNO BKOMP BPHCQ BVXVI C0K CCPQU D1J DB5 DU5 DWQXO EAD EAP EAS EBC EBS EE. EJD EMB EMK EMOBN ESX EXGXG F5P FA8 FEDTE FQGFK FSGXE FYUFA GNUQQ GUQSH GX1 HCIFZ HMCUK HVGLF HZ~ IAG IAO IEA IEP IH2 IHR INH INR IOV ISR ITC KOO L6V LGEZI LK8 LOTEE M0L M1P M2O M2P M7P M7S ML0 MVM N95 NADUK NEJ NNMJJ NXXTH O9- ODYON P2P PKN PQQKQ PROAC PSQYO PTHSS Q2X QF4 QM4 QN7 QO4 RNS RNT RNTTT RVV RXW SHXYY SIXXV SJN SNYQT SOJ SV3 TAE TAOOD TBHMF TDRGL TN5 TSG TUS U5U UKHRP X7M XI7 XOL Y6R YZZ ZGI ZHY ZXP ~KM AAYXX ABFSG ACSTC AEZWR AFFHD AFHIU AGSTI AHWEU AIXLP ALPWD ATHPR CITATION PHGZM PHGZT PJZUB PPXIY PQGLB NPM 7QO 7QP 7QR 7T7 7TK 7TM 7XB 8FD 8FK C1K FR3 K9. MBDVC P64 PKEHL PQEST PQUKI Q9U RC3 7X8 PUEGO
ID	FETCH-LOGICAL-c547t-78da1586ea2ec9e547439e9deeab9d708c62b5408c31cd16ff0d858b4e9cf30a3
IEDL.DBID	M2P
ISICitedReferencesCount	47
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000651336800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1087-0156 1546-1696
IngestDate	Sun Sep 28 11:00:24 EDT 2025 Tue Oct 07 05:33:32 EDT 2025 Sat Nov 29 13:14:04 EST 2025 Sat Nov 29 09:53:09 EST 2025 Wed Nov 26 10:41:16 EST 2025 Wed Nov 26 09:37:16 EST 2025 Sat Nov 29 08:34:02 EST 2025 Thu Apr 03 07:00:53 EDT 2025 Sat Nov 29 06:22:26 EST 2025 Tue Nov 18 22:25:18 EST 2025 Fri Feb 21 02:38:19 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c547t-78da1586ea2ec9e547439e9deeab9d708c62b5408c31cd16ff0d858b4e9cf30a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-3735-0365
PMID	34002098
PQID	2579866503
PQPubID	47191
PageCount	8
ParticipantIDs	proquest_miscellaneous_2528813198 proquest_journals_2579866503 gale_infotracmisc_A678269562 gale_infotracacademiconefile_A678269562 gale_incontextgauss_ISR_A678269562 gale_incontextgauss_IOV_A678269562 gale_businessinsightsgauss_A678269562 pubmed_primary_34002098 crossref_primary_10_1038_s41587_021_00907_6 crossref_citationtrail_10_1038_s41587_021_00907_6 springer_journals_10_1038_s41587_021_00907_6
PublicationCentury	2000
PublicationDate	2021-10-01
PublicationDateYYYYMMDD	2021-10-01
PublicationDate_xml	– month: 10 year: 2021 text: 2021-10-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York – name: United States
PublicationSubtitle	The Science and Business of Biotechnology
PublicationTitle	Nature biotechnology
PublicationTitleAbbrev	Nat Biotechnol
PublicationTitleAlternate	Nat Biotechnol
PublicationYear	2021
Publisher	Nature Publishing Group US Nature Publishing Group
Publisher_xml	– name: Nature Publishing Group US – name: Nature Publishing Group
References	Dykstra (CR20) 2007; 1 CR18 Battiston (CR12) 2019; 1 CR15 Acuna, Allesina, Kording (CR13) 2012; 489 Nicholson, Ioannidis (CR26) 2012; 492 Mariani, Medo, Zhang (CR17) 2016; 10 Wu, Wang, Evans (CR10) 2019; 566 Ma, Uzzi (CR11) 2018; 115 Funk, Owen-Smith (CR8) 2017; 63 Fu, Aliferis (CR14) 2010; 85 Zhang, Liu, Xu (CR24) 2015; 30 Wilhite, Fong (CR3) 2012; 335 Xu, Mariani, Lü, Medo (CR22) 2020; 14 CR2 Seglen (CR4) 1997; 314 CR6 Tachibana (CR19) 2002; 16 CR7 Cumming, Dai (CR5) 2010; 17 CR25 Metcalfe (CR23) 2013; 46 Mariani, Medo, Lafond (CR9) 2019; 146 McNutt (CR1) 2014; 346 CR21 Vidmer, Medo (CR16) 2016; 116 Chawla, Bowyer, Hall, Kegelmeyer (CR27) 2002; 16 Y Ma (907_CR11) 2018; 115 B Dykstra (907_CR20) 2007; 1 907_CR21 F Battiston (907_CR12) 2019; 1 907_CR25 NV Chawla (907_CR27) 2002; 16 B Metcalfe (907_CR23) 2013; 46 DE Acuna (907_CR13) 2012; 489 A Vidmer (907_CR16) 2016; 116 MS Mariani (907_CR17) 2016; 10 MS Mariani (907_CR9) 2019; 146 LD Fu (907_CR14) 2010; 85 S Xu (907_CR22) 2020; 14 DJ Cumming (907_CR5) 2010; 17 907_CR15 M Tachibana (907_CR19) 2002; 16 AW Wilhite (907_CR3) 2012; 335 L Wu (907_CR10) 2019; 566 JM Nicholson (907_CR26) 2012; 492 907_CR7 907_CR18 907_CR6 907_CR2 X-Z Zhang (907_CR24) 2015; 30 M McNutt (907_CR1) 2014; 346 PO Seglen (907_CR4) 1997; 314 RJ Funk (907_CR8) 2017; 63
References_xml	– volume: 14 start-page: 101005 year: 2020 ident: CR22 article-title: Unbiased evaluation of ranking metrics reveals consistent performance in science and technology citation data publication-title: J. Informetrics doi: 10.1016/j.joi.2019.101005 – ident: CR18 – volume: 314 start-page: 498 year: 1997 end-page: 502 ident: CR4 article-title: Why the impact factor of journals should not be used for evaluating research publication-title: BMJ doi: 10.1136/bmj.314.7079.497 – ident: CR2 – volume: 1 start-page: 89 year: 2019 end-page: 97 ident: CR12 article-title: Taking census of physics publication-title: Nat. Rev. Physics doi: 10.1038/s42254-018-0005-3 – volume: 16 start-page: 1779 year: 2002 end-page: 1791 ident: CR19 article-title: G9a histone methyltransferase plays a dominant role in euchromatic histone h3 lysine 9 methylation and is essential for early embryogenesis publication-title: Genes Dev. doi: 10.1101/gad.989402 – volume: 85 start-page: 257 year: 2010 end-page: 270 ident: CR14 article-title: Using content-based and bibliometric features for machine learning models to predict citation counts in the biomedical literature publication-title: Scientometrics doi: 10.1007/s11192-010-0160-5 – ident: CR6 – volume: 489 start-page: 201 year: 2012 end-page: 202 ident: CR13 article-title: Predicting scientific success publication-title: Nature doi: 10.1038/489201a – volume: 17 start-page: 362 year: 2010 end-page: 380 ident: CR5 article-title: Local bias in venture capital investments publication-title: J. Empirical Finance doi: 10.1016/j.jempfin.2009.11.001 – ident: CR25 – volume: 146 start-page: 644 year: 2019 end-page: 654 ident: CR9 article-title: Early identification of important patents: design and validation of citation network metrics publication-title: Technol. Forecast. Soc. Change doi: 10.1016/j.techfore.2018.01.036 – volume: 492 start-page: 34 year: 2012 end-page: 36 ident: CR26 article-title: Conform and be funded publication-title: Nature doi: 10.1038/492034a – volume: 115 start-page: 12608 year: 2018 end-page: 12615 ident: CR11 article-title: Scientific prize network predicts who pushes the boundaries of science publication-title: Proc. Natl Acad. Sci. USA doi: 10.1073/pnas.1800485115 – ident: CR21 – volume: 46 start-page: 26 year: 2013 end-page: 31 ident: CR23 article-title: Metcalfe’s law after 40 years of ethernet publication-title: Computer doi: 10.1109/MC.2013.374 – volume: 16 start-page: 321 year: 2002 end-page: 357 ident: CR27 article-title: SMOTE: synthetic minority over-sampling technique publication-title: J. Artificial Intell. Res. doi: 10.1613/jair.953 – ident: CR15 – volume: 30 start-page: 246 year: 2015 end-page: 251 ident: CR24 article-title: Tencent and Facebook data validate Metcalfe’s law publication-title: J. Comput. Sci. Technol. doi: 10.1007/s11390-015-1518-1 – volume: 63 start-page: 791 year: 2017 end-page: 817 ident: CR8 article-title: A dynamic network measure of technological change publication-title: Management Sci. doi: 10.1287/mnsc.2015.2366 – volume: 335 start-page: 542 year: 2012 end-page: 543 ident: CR3 article-title: Coercive citation in academic publishing publication-title: Science doi: 10.1126/science.1212540 – ident: CR7 – volume: 566 start-page: 378 year: 2019 end-page: 382 ident: CR10 article-title: Large teams develop and small teams disrupt science and technology publication-title: Nature doi: 10.1038/s41586-019-0941-9 – volume: 116 start-page: 30007 year: 2016 ident: CR16 article-title: The essential role of time in network-based recommendation publication-title: Europhysics Lett. doi: 10.1209/0295-5075/116/30007 – volume: 1 start-page: 218 year: 2007 end-page: 229 ident: CR20 article-title: Long-term propagation of distinct hematopoietic differentiation programs in vivo publication-title: Cell Stem Cell doi: 10.1016/j.stem.2007.05.015 – volume: 10 start-page: 1207 year: 2016 end-page: 1223 ident: CR17 article-title: Identification of milestone papers through time-balanced network centrality publication-title: J. Informetrics doi: 10.1016/j.joi.2016.10.005 – volume: 346 start-page: 1155 year: 2014 ident: CR1 article-title: The measure of research merit publication-title: Science doi: 10.1126/science.aaa3796 – volume: 116 start-page: 30007 year: 2016 ident: 907_CR16 publication-title: Europhysics Lett. doi: 10.1209/0295-5075/116/30007 – volume: 63 start-page: 791 year: 2017 ident: 907_CR8 publication-title: Management Sci. doi: 10.1287/mnsc.2015.2366 – volume: 85 start-page: 257 year: 2010 ident: 907_CR14 publication-title: Scientometrics doi: 10.1007/s11192-010-0160-5 – ident: 907_CR25 doi: 10.1128/mBio.00694-16 – volume: 314 start-page: 498 year: 1997 ident: 907_CR4 publication-title: BMJ doi: 10.1136/bmj.314.7079.497 – ident: 907_CR21 doi: 10.1038/s41587-019-0362-1 – ident: 907_CR6 doi: 10.3386/w22587 – volume: 346 start-page: 1155 year: 2014 ident: 907_CR1 publication-title: Science doi: 10.1126/science.aaa3796 – volume: 335 start-page: 542 year: 2012 ident: 907_CR3 publication-title: Science doi: 10.1126/science.1212540 – volume: 492 start-page: 34 year: 2012 ident: 907_CR26 publication-title: Nature doi: 10.1038/492034a – volume: 489 start-page: 201 year: 2012 ident: 907_CR13 publication-title: Nature doi: 10.1038/489201a – volume: 17 start-page: 362 year: 2010 ident: 907_CR5 publication-title: J. Empirical Finance doi: 10.1016/j.jempfin.2009.11.001 – ident: 907_CR15 doi: 10.1109/JCDL.2017.7991559 – volume: 30 start-page: 246 year: 2015 ident: 907_CR24 publication-title: J. Comput. Sci. Technol. doi: 10.1007/s11390-015-1518-1 – ident: 907_CR18 doi: 10.1145/2939672.2939754 – volume: 1 start-page: 218 year: 2007 ident: 907_CR20 publication-title: Cell Stem Cell doi: 10.1016/j.stem.2007.05.015 – volume: 16 start-page: 321 year: 2002 ident: 907_CR27 publication-title: J. Artificial Intell. Res. doi: 10.1613/jair.953 – ident: 907_CR7 doi: 10.2139/ssrn.2053258 – ident: 907_CR2 doi: 10.1038/4351003b – volume: 16 start-page: 1779 year: 2002 ident: 907_CR19 publication-title: Genes Dev. doi: 10.1101/gad.989402 – volume: 14 start-page: 101005 year: 2020 ident: 907_CR22 publication-title: J. Informetrics doi: 10.1016/j.joi.2019.101005 – volume: 46 start-page: 26 year: 2013 ident: 907_CR23 publication-title: Computer doi: 10.1109/MC.2013.374 – volume: 1 start-page: 89 year: 2019 ident: 907_CR12 publication-title: Nat. Rev. Physics doi: 10.1038/s42254-018-0005-3 – volume: 10 start-page: 1207 year: 2016 ident: 907_CR17 publication-title: J. Informetrics doi: 10.1016/j.joi.2016.10.005 – volume: 566 start-page: 378 year: 2019 ident: 907_CR10 publication-title: Nature doi: 10.1038/s41586-019-0941-9 – volume: 146 start-page: 644 year: 2019 ident: 907_CR9 publication-title: Technol. Forecast. Soc. Change doi: 10.1016/j.techfore.2018.01.036 – volume: 115 start-page: 12608 year: 2018 ident: 907_CR11 publication-title: Proc. Natl Acad. Sci. USA doi: 10.1073/pnas.1800485115
SSID	ssj0006466
Score	2.552019
Snippet	The scientific ecosystem relies on citation-based metrics that provide only imperfect, inconsistent and easily manipulated measures of research quality. Here...
SourceID	proquest gale pubmed crossref springer
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1300
SubjectTerms	631/114/1305 631/114/2406 706/648/1496 Agriculture Analysis Artificial intelligence Bibliometrics Bioinformatics Biomedical and Life Sciences Biomedical Engineering/Biotechnology Biomedicine Biotechnology Datasets Funding Graph theory Knowledge representation Learning algorithms Life Sciences Machine learning Mathematical analysis Scientific papers Warning systems
Title	Learning on knowledge graph dynamics provides an early warning of impactful research
URI	https://link.springer.com/article/10.1038/s41587-021-00907-6 https://www.ncbi.nlm.nih.gov/pubmed/34002098 https://www.proquest.com/docview/2579866503 https://www.proquest.com/docview/2528813198
Volume	39
WOSCitedRecordID	wos000651336800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: M7P dateStart: 20210101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: M7S dateStart: 20210101 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: BENPR dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Health & Medical Collection customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: 7X7 dateStart: 20210101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Proquest Research Library customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: M2O dateStart: 20210101 isFulltext: true titleUrlDefault: https://search.proquest.com/pqrl providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Science Database (NC LIVE) customDbUrl: eissn: 1546-1696 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0006466 issn: 1087-0156 databaseCode: M2P dateStart: 20210101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7RFhAceCyvQFkZBOIAUfP044QKagWHbldtQXuzEtspSFVSml0Q_x5P7KRNJSokLpY2Hq8Sz3hm7Bl_A_AqTXLrBWV5yGJDw6wweShUyUJWxMyOoFTnVVdsgs1mfLEQc3_g1vq0yl4ndopaNwrPyLesaAnEZovS96c_QqwahdFVX0JjDTasZxNjStdeMh80MXWxyjjimF6ZU39pJkr5VmsNFz5N7GY6shvEkI4M02X1fME-XQqYdnZo9-7_fsE9uOM9ULLtROY-XDP1BG64mpS_J3D7AkLhBG7u-dj7AzjyUKzHpKnJcBRHOsRrol1h-5b4m30tKWpiEDyZ_OpHVcRdyaxWJ8RjDH17CF92d44-fgp9TYZQ5Rlbhozrws4cNUVilDD2mfVojNDGFKXQLOKKJqX1ArlKY6VjWlWR5jkvMyNUlUZF-gjW66Y2T4Bw-1MbptKS60zrSpQqVyoTseGCVjkLIO4ZIpUHLMe6GSeyC5ynXDomSstE2TFR0gDeDmNOHVzHldSvkc_S1_u0TYsnIu1xsWpbuW3teELt_jEJ4GVHh3gZNSbkOILP-1__gejwYET0xhNVjf0WVfhLEHZGEIdrRLk5orSrXo27eyGTXuu08lzCAngxdONIzKSrTbNCmoTz2CpeHsBjJ9PDTKUZ7h6w510v5Od__vdpfHr1uzyDWwmusy4DchPWl2cr8xyuq5_L7-3ZFNbYgnUtn8LGh53Z_GCKq3i_a-fYMtce_gF4ukne
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6V8j7wWF6BAgZRcYCoiZM4zgGhCqi6artUsKDeTGI7pVLJlmaXav8Uv5GZxNl2K1Fx6YFLpMTjKHbm4bFnvgF4EfEEV0Fx4qehFX6c28TPdJH6aR6m2EMIk5RNsYl0MJA7O9n2AvzucmEorLLTiY2iNiNNe-QryFoZYbMF0duDnz5VjaLT1a6ERssWG3Z6hC5b_ab_Hv_vMudrH4bv1n1XVcDXSZyO_VSaPEyksDm3OrP4DG2yzYy1eZGZNJBa8ALXMVJHoTahKMvAyEQWsc10GQV5hO-9ABdjQhajUEG-PdP8oj0bDQNJ4ZyJcEk6QSRXajSU9JSj8x6gQ-qLOUN42hycsIenDmgbu7d283-bsVtww62w2WorErdhwVY9uNzW3Jz24PoJBMYeXNlysQV3YOigZnfZqGKzrUbWIHozM63yH3u6Zi5zsWZ5xSyBQ7OjrlfJ2pTTcrLPHIbS97vw5VzGeg8Wq1FlHwCTeGtsqqNCmtiYMit0onWchVZmokxSD8KOAZR2gOxUF2RfNYEBkVQt0yhkGtUwjRIevJr1OWjhSM6kXia-Uq6eKV5q2vGpd_NJXatVXKdwgf4x9-B5Q0d4IBUFHLUE_Y9f_4Ho86c5opeOqBzhWHTukjxwRghnbI5yaY4StZqeb-6YWjmtWqtjjvbg2ayZelKkYGVHE6LhUoZoWKQH91sZms1UFJN3RC2vO6E6fvnfp_Hh2d_yFK6uD7c21WZ_sPEIrnGS8SbacwkWx4cT-xgu6V_jvfrwSaMtGHw7b2H7A-zhoi4
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLVRw4LG8AgUMouIA0eZpOweECu2KVWFZtQX1ZhLbKZUgKc0u1f41fh3jxEm7lai49MAlUuJxtJn9xjNjzwPgeRjEaAVFsct8Td0o1bGbyIy5LPUZzqBUxXndbIKNx3xvL5kswe82F8aEVbZrYr1Qq1KaPfIBQisxtdm8cJDbsIjJxvDN4U_XdJAyJ61tO40GIlt6fozuW_V6tIH_9VoQDDd33713bYcBV8YRm7qMq9SPOdVpoGWi8RnqZ50ordMsUczjkgYZ2jRchr5UPs1zT_GYZ5FOZB56aYjvvQTLDI2MqAfLbzfHk-1OD9DmpNT3uAnujKlN2fFCPqhQbZqnAbryHrqnLl1Qi2eVwynteOa4ttaCwxv_M_9uwnVre5P1RlhuwZIu-nCl6cY578O1U7UZ-7Dy0UYd3IZdW4R2n5QF6TYhSV3rm6h5kf44kBWxOY0VSQuiTdloctzOykmTjIosIba60rc78PlCvvUu9Iqy0PeBcLxVmskw4ypSKk8yGUsZJb7mCc1j5oDfgkFIW6rddAz5LuqQgZCLBkACASRqAAnqwMtuzmFTqORc6jWDMWE7neKlMntB1X46qyqxjhZMQNFzDhx4VtOZSiGFwUxDMPr05R-IdrYXiF5YorzEb5GpTf9AjpgKZAuUqwuUuN7JxeEW4MKut5U4QbcDT7thM9PEEBa6nBmagHMfVQ534F4jTx2nwsj4TWbkVStgJy__OxsfnP9bnsAKypj4MBpvPYSrgRH3Ogx0FXrTo5l-BJflr-lBdfTYLh0Evl60tP0BoyysSA
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=Learning+on+knowledge+graph+dynamics+provides+an+early+warning+of+impactful+research&rft.jtitle=Nature+biotechnology&rft.au=Weis%2C+James+W.&rft.au=Jacobson%2C+Joseph+M.&rft.date=2021-10-01&rft.issn=1087-0156&rft.eissn=1546-1696&rft.volume=39&rft.issue=10&rft.spage=1300&rft.epage=1307&rft_id=info:doi/10.1038%2Fs41587-021-00907-6&rft.externalDBID=n%2Fa&rft.externalDocID=10_1038_s41587_021_00907_6
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1087-0156&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1087-0156&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1087-0156&client=summon