Predicting protein and pathway associations for understudied dark kinases using pattern-constrained knowledge graph embedding

The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied “dark” members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the e...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:PeerJ (San Francisco, CA) Ročník 11; s. e15815
Hlavní autoři: Salcedo, Mariah V., Gravel, Nathan, Keshavarzi, Abbas, Huang, Liang-Chin, Kochut, Krzysztof J., Kannan, Natarajan
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States PeerJ. Ltd 18.10.2023
PeerJ Inc
Témata:
ISSN:2167-8359, 2167-8359
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied “dark” members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the evolutionary and functional context encoded in knowledge graphs (KGs) to predict protein and pathway associations for understudied kinases. We propose a new scalable graph embedding approach, RegPattern2Vec, which employs regular pattern constrained random walks to sample diverse aspects of node context within a KG flexibly. RegPattern2Vec learns functional representations of kinases, interacting partners, post-translational modifications, pathways, cellular localization, and chemical interactions from a kinase-centric KG that integrates and conceptualizes data from curated heterogeneous data resources. By contextualizing information relevant to prediction, RegPattern2Vec improves accuracy and efficiency in comparison to other random walk-based graph embedding approaches. We show that the predictions produced by our model overlap with pathway enrichment data produced using experimentally validated Protein-Protein Interaction (PPI) data from both publicly available databases and experimental datasets not used in training. Our model also has the advantage of using the collected random walks as biological context to interpret the predicted protein-pathway associations. We provide high-confidence pathway predictions for 34 dark kinases and present three case studies in which analysis of meta-paths associated with the prediction enables biological interpretation. Overall, RegPattern2Vec efficiently samples multiple node types for link prediction on biological knowledge graphs and the predicted associations between understudied kinases, pseudokinases, and known pathways serve as a conceptual starting point for hypothesis generation and testing.
AbstractList The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied "dark" members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the evolutionary and functional context encoded in knowledge graphs (KGs) to predict protein and pathway associations for understudied kinases. We propose a new scalable graph embedding approach, RegPattern2Vec, which employs regular pattern constrained random walks to sample diverse aspects of node context within a KG flexibly. RegPattern2Vec learns functional representations of kinases, interacting partners, post-translational modifications, pathways, cellular localization, and chemical interactions from a kinase-centric KG that integrates and conceptualizes data from curated heterogeneous data resources. By contextualizing information relevant to prediction, RegPattern2Vec improves accuracy and efficiency in comparison to other random walk-based graph embedding approaches. We show that the predictions produced by our model overlap with pathway enrichment data produced using experimentally validated Protein-Protein Interaction (PPI) data from both publicly available databases and experimental datasets not used in training. Our model also has the advantage of using the collected random walks as biological context to interpret the predicted protein-pathway associations. We provide high-confidence pathway predictions for 34 dark kinases and present three case studies in which analysis of meta-paths associated with the prediction enables biological interpretation. Overall, RegPattern2Vec efficiently samples multiple node types for link prediction on biological knowledge graphs and the predicted associations between understudied kinases, pseudokinases, and known pathways serve as a conceptual starting point for hypothesis generation and testing.
The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied "dark" members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the evolutionary and functional context encoded in knowledge graphs (KGs) to predict protein and pathway associations for understudied kinases. We propose a new scalable graph embedding approach, RegPattern2Vec, which employs regular pattern constrained random walks to sample diverse aspects of node context within a KG flexibly. RegPattern2Vec learns functional representations of kinases, interacting partners, post-translational modifications, pathways, cellular localization, and chemical interactions from a kinase-centric KG that integrates and conceptualizes data from curated heterogeneous data resources. By contextualizing information relevant to prediction, RegPattern2Vec improves accuracy and efficiency in comparison to other random walk-based graph embedding approaches. We show that the predictions produced by our model overlap with pathway enrichment data produced using experimentally validated Protein-Protein Interaction (PPI) data from both publicly available databases and experimental datasets not used in training. Our model also has the advantage of using the collected random walks as biological context to interpret the predicted protein-pathway associations. We provide high-confidence pathway predictions for 34 dark kinases and present three case studies in which analysis of meta-paths associated with the prediction enables biological interpretation. Overall, RegPattern2Vec efficiently samples multiple node types for link prediction on biological knowledge graphs and the predicted associations between understudied kinases, pseudokinases, and known pathways serve as a conceptual starting point for hypothesis generation and testing.The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied "dark" members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the evolutionary and functional context encoded in knowledge graphs (KGs) to predict protein and pathway associations for understudied kinases. We propose a new scalable graph embedding approach, RegPattern2Vec, which employs regular pattern constrained random walks to sample diverse aspects of node context within a KG flexibly. RegPattern2Vec learns functional representations of kinases, interacting partners, post-translational modifications, pathways, cellular localization, and chemical interactions from a kinase-centric KG that integrates and conceptualizes data from curated heterogeneous data resources. By contextualizing information relevant to prediction, RegPattern2Vec improves accuracy and efficiency in comparison to other random walk-based graph embedding approaches. We show that the predictions produced by our model overlap with pathway enrichment data produced using experimentally validated Protein-Protein Interaction (PPI) data from both publicly available databases and experimental datasets not used in training. Our model also has the advantage of using the collected random walks as biological context to interpret the predicted protein-pathway associations. We provide high-confidence pathway predictions for 34 dark kinases and present three case studies in which analysis of meta-paths associated with the prediction enables biological interpretation. Overall, RegPattern2Vec efficiently samples multiple node types for link prediction on biological knowledge graphs and the predicted associations between understudied kinases, pseudokinases, and known pathways serve as a conceptual starting point for hypothesis generation and testing.
ArticleNumber e15815
Audience Academic
Author Huang, Liang-Chin
Kannan, Natarajan
Keshavarzi, Abbas
Salcedo, Mariah V.
Kochut, Krzysztof J.
Gravel, Nathan
Author_xml – sequence: 1
  givenname: Mariah V.
  surname: Salcedo
  fullname: Salcedo, Mariah V.
  organization: Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA, United States of America
– sequence: 2
  givenname: Nathan
  surname: Gravel
  fullname: Gravel, Nathan
  organization: Institute of Bioinformatics, University of Georgia, Athens, GA, United States of America
– sequence: 3
  givenname: Abbas
  surname: Keshavarzi
  fullname: Keshavarzi, Abbas
  organization: School of Computing, University of Georgia, Athens, GA, United States of America
– sequence: 4
  givenname: Liang-Chin
  surname: Huang
  fullname: Huang, Liang-Chin
  organization: Institute of Bioinformatics, University of Georgia, Athens, GA, United States of America
– sequence: 5
  givenname: Krzysztof J.
  surname: Kochut
  fullname: Kochut, Krzysztof J.
  organization: School of Computing, University of Georgia, Athens, GA, United States of America
– sequence: 6
  givenname: Natarajan
  surname: Kannan
  fullname: Kannan, Natarajan
  organization: Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA, United States of America, Institute of Bioinformatics, University of Georgia, Athens, GA, United States of America
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37868056$$D View this record in MEDLINE/PubMed
BookMark eNptkl1rHCEUhoeS0qTbXPW-DBRKoexWnS_nKoTQj0CgvWiv5YweZ93M6lSdhlz0v9edTcNuiSKKPuflHM_7MjuxzmKWvaZk1TS0-Tgi-s2KVpxWz7IzRutmyYuqPTk4n2bnIWxIGpzVhBcvstOi4TUnVX2W_fnuURkZje3z0buIxuZgVT5CXN_BfQ4hOGkgGmdDrp3PJ6vQhzgpgypX4G_zW2MhYMinMItAjOjtUqaA6MHYhN1adzeg6jHvPYzrHLcdKpXoV9lzDUPA84d9kf38_OnH1dflzbcv11eXN0tZlXVc0q6WmqhKKVoWRHeq0Aw0VEBLrqRuWlpSLLqKYcFIXRDSMdkxpqtWFp1KT4vseq-rHGzE6M0W_L1wYMR84XwvwEcjBxS6hVpzQCAayvSHLSkL1VCWpHTB0lpkF3utceq2qCTaVOZwJHr8Ys1a9O63oKRqCU35LbL3Dwre_ZowRLE1QeIwgEU3BcE4T60iLW0S-naP9pByM1a7JCl3uLjktCR1zfhOcPUElabCrUmNQG3S_VHAu4OANcIQ18EN09zmY_DNYbGPVf4zUAI-7AHpXQge9SNCidg5VMwOFbNDE03_o6WJs7l2VhmejPkLGxfsDQ
CitedBy_id crossref_primary_10_1039_D5MD00306G
crossref_primary_10_1016_j_csbj_2024_06_022
crossref_primary_10_1016_j_drudis_2024_103894
Cites_doi 10.1093/nar/gkaa1100
10.1182/blood-2014-01-551820
10.7717/peerj-cs.341
10.1093/nar/gkab540
10.1093/nar/gkac1033
10.1002/humu.22726
10.1016/j.jbi.2020.103624
10.1093/nar/gkaa993
10.1093/nar/gkab1028
10.1016/j.str.2009.12.012
10.1109/TKDE.2020.2982898
10.1042/bcj20220474
10.1021/acs.jmedchem.1c00963
10.1007/978-3-030-10928-8_3
10.1038/nrd.2018.14
10.1109/TKDE.2017.2754499
10.1093/nar/gkq985
10.15252/msb.20177651
10.1109/JPROC.2015.2483592
10.1016/j.bbagen.2022.130242
10.3389/fbioe.2020.00338
10.3892/ijmm.2017.3036
10.1016/j.steroids.2017.11.007
10.3389/fonc.2017.00140
10.1016/j.ceb.2009.01.028
10.1101/2020.04.02.022277
10.1021/acsomega.9b04195
10.1021/acs.biochem.1c00251
10.1093/nar/gkaa891
10.1091/mbc.e02-07-0391
10.1093/nar/gkaa895
10.1007/s12079-020-00592-1
10.1016/j.cell.2009.09.035
10.1021/acs.jmedchem.9b02170
10.1038/s41573-021-00252-y
10.1038/s41587-019-0344-3
10.1016/j.neucom.2021.05.093
10.1093/nar/gkaa913
10.1038/nrg2707
10.1016/j.knosys.2021.107310
10.1093/nargab/lqab113
10.1016/j.eswa.2019.01.015
10.1109/TKDE.2016.2598561
10.3389/fgene.2019.00163
10.1093/nar/gkz1031
10.1371/journal.pcbi.1007578
10.1093/nar/gkaa853
10.1016/j.bbabio.2018.04.005
10.1021/acs.jmedchem.0c01511
10.1006/geno.2000.6365
10.18632/oncotarget.24337
10.3389/fgene.2019.00226
10.1016/j.gde.2010.10.012
10.1093/nar/gkaa1113
10.1080/21541264.2018.1556915
10.3390/electronics9050750
10.1038/s41598-018-24457-1
10.1016/j.ajhg.2020.09.005
10.1142/S0218213020500013
10.1093/nar/gkt1079
10.1016/j.tips.2020.09.007
10.1093/nar/gky1015
10.1145/3487553.3524238
10.1093/nar/gky1131
10.1039/d1mo00521a
10.1038/s41586-022-05575-3
10.1007/978-1-4939-6783-4_16
10.1093/bib/bbac279
10.1109/JBHI.2020.2998906
10.1007/978-1-4939-2537-7_11
10.1186/gb-2014-15-1-r1
10.1093/nar/gks1111
10.1609/aaai.v29i1.9491
10.1038/s41385-021-00426-2
10.24963/ijcai.2019/592
ContentType Journal Article
Copyright 2023 Salcedo et al.
COPYRIGHT 2023 PeerJ. Ltd.
2023 Salcedo et al. 2023 Salcedo et al.
Copyright_xml – notice: 2023 Salcedo et al.
– notice: COPYRIGHT 2023 PeerJ. Ltd.
– notice: 2023 Salcedo et al. 2023 Salcedo et al.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
DOA
DOI 10.7717/peerj.15815
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE

CrossRef


MEDLINE - Academic

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2167-8359
ExternalDocumentID oai_doaj_org_article_f9a6f8aea0fa42169043d7129c3f323f
PMC10590106
A814066286
37868056
10_7717_peerj_15815
Genre Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NCI NIH HHS
  grantid: U01 CA239106
– fundername: National Institutes of Health
  grantid: U01CA239106
GroupedDBID 53G
5VS
88I
8FE
8FH
AAFWJ
AAYXX
ABUWG
ADBBV
ADRAZ
AENEX
AFFHD
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
AZQEC
BAWUL
BBNVY
BCNDV
BENPR
BHPHI
BPHCQ
CCPQU
CITATION
DIK
DWQXO
ECGQY
GNUQQ
GROUPED_DOAJ
GX1
HCIFZ
HYE
IAO
IEA
IHR
IHW
ITC
KQ8
LK8
M2P
M48
M7P
M~E
OK1
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
RPM
W2D
YAO
CGR
CUY
CVF
ECM
EIF
H13
NPM
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c546t-1b6cf0d5dd1430fbd3f2afa5a148dcf79141e3b52e3206300b2cb22f59c3bd1e3
IEDL.DBID DOA
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001096495400011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2167-8359
IngestDate Fri Oct 03 12:44:37 EDT 2025
Tue Nov 04 02:06:28 EST 2025
Thu Sep 04 19:08:50 EDT 2025
Tue Nov 11 10:53:59 EST 2025
Tue Nov 04 18:14:33 EST 2025
Thu May 22 21:24:20 EDT 2025
Sun Jul 20 01:30:23 EDT 2025
Sat Nov 29 03:40:05 EST 2025
Tue Nov 18 20:47:25 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Link prediction
Illuminating Druggable Genome (IDG)
Data integration
Random walk
Classification
Pathway prediction
Ontologies
Evolution
Drug discovery
Signaling networks
Language English
License https://creativecommons.org/licenses/by/4.0
2023 Salcedo et al.
This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c546t-1b6cf0d5dd1430fbd3f2afa5a148dcf79141e3b52e3206300b2cb22f59c3bd1e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://doaj.org/article/f9a6f8aea0fa42169043d7129c3f323f
PMID 37868056
PQID 2880820917
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_f9a6f8aea0fa42169043d7129c3f323f
pubmedcentral_primary_oai_pubmedcentral_nih_gov_10590106
proquest_miscellaneous_2880820917
gale_infotracmisc_A814066286
gale_infotracacademiconefile_A814066286
gale_healthsolutions_A814066286
pubmed_primary_37868056
crossref_primary_10_7717_peerj_15815
crossref_citationtrail_10_7717_peerj_15815
PublicationCentury 2000
PublicationDate 2023-10-18
PublicationDateYYYYMMDD 2023-10-18
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-10-18
  day: 18
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: San Diego, USA
PublicationTitle PeerJ (San Francisco, CA)
PublicationTitleAlternate PeerJ
PublicationYear 2023
Publisher PeerJ. Ltd
PeerJ Inc
Publisher_xml – name: PeerJ. Ltd
– name: PeerJ Inc
References Gillespie (10.7717/peerj.15815/ref-31) 2022; 50
Alshahrani (10.7717/peerj.15815/ref-3) 2021; 7
Weber (10.7717/peerj.15815/ref-94) 2018; 133
Wan (10.7717/peerj.15815/ref-91) 2020
Koncel-Kedziorski (10.7717/peerj.15815/ref-46) 2019
Szklarczyk (10.7717/peerj.15815/ref-83) 2019; 47
Omar (10.7717/peerj.15815/ref-63) 2020; 41
Brognard (10.7717/peerj.15815/ref-16) 2011; 21
Tang (10.7717/peerj.15815/ref-85) 2019
Abboud (10.7717/peerj.15815/ref-1) 2020; 33
Samizadeh (10.7717/peerj.15815/ref-75) 2020; 29
Zhang (10.7717/peerj.15815/ref-105) 2019
Lin (10.7717/peerj.15815/ref-50) 2015
Velankar (10.7717/peerj.15815/ref-88) 2010; 39
Minervini (10.7717/peerj.15815/ref-56) 2015
Tang (10.7717/peerj.15815/ref-84) 2021; 49
UniProt (10.7717/peerj.15815/ref-87) 2021; 49
Keshavarzi (10.7717/peerj.15815/ref-45) 2021
Hunter (10.7717/peerj.15815/ref-38) 2009; 21
Fant (10.7717/peerj.15815/ref-24) 2019; 10
Alarcón (10.7717/peerj.15815/ref-2) 2009; 139
Yang (10.7717/peerj.15815/ref-101) 2013; 41
Oprea (10.7717/peerj.15815/ref-64) 2018; 17
Ravanmehr (10.7717/peerj.15815/ref-72) 2021; 3
Berginski (10.7717/peerj.15815/ref-10) 2021; 49
Sarma (10.7717/peerj.15815/ref-76) 2010; 18
Sun (10.7717/peerj.15815/ref-82) 2019
Brede (10.7717/peerj.15815/ref-15) 2000; 70
Bi (10.7717/peerj.15815/ref-11) 2022
Hamilton (10.7717/peerj.15815/ref-35) 2017; 30
Huang (10.7717/peerj.15815/ref-36) 2018; 8
Shi (10.7717/peerj.15815/ref-79) 2020; 34
Tate (10.7717/peerj.15815/ref-86) 2019; 47
Wong (10.7717/peerj.15815/ref-96) 2020; 5
Ardito (10.7717/peerj.15815/ref-5) 2017; 40
Gene Ontology (10.7717/peerj.15815/ref-30) 2021; 49
Kultgen (10.7717/peerj.15815/ref-47) 2002; 13
Palencia-Campos (10.7717/peerj.15815/ref-66) 2020; 107
Pei (10.7717/peerj.15815/ref-67) 2020
Peng (10.7717/peerj.15815/ref-68) 2019; 10
Ross (10.7717/peerj.15815/ref-73) 2017
Sadeghian (10.7717/peerj.15815/ref-74) 2021
Moret (10.7717/peerj.15815/ref-58) 2021
Bachman (10.7717/peerj.15815/ref-8) 2022
Fu (10.7717/peerj.15815/ref-26) 2020
Wang (10.7717/peerj.15815/ref-93) 2021; 458
Johnson (10.7717/peerj.15815/ref-40) 2023
Pham (10.7717/peerj.15815/ref-71) 2019; 123
Manchev (10.7717/peerj.15815/ref-53) 2014; 124
Gyori (10.7717/peerj.15815/ref-33) 2017; 13
Long (10.7717/peerj.15815/ref-51) 2020; 25
Shi (10.7717/peerj.15815/ref-78) 2016; 29
Fu (10.7717/peerj.15815/ref-25) 2017
Kelleher (10.7717/peerj.15815/ref-43) 2023; 51
Yang (10.7717/peerj.15815/ref-99) 2018; vol. 11052
Zhang (10.7717/peerj.15815/ref-104) 2018
Najar (10.7717/peerj.15815/ref-59) 2021; 15
Ould Amer (10.7717/peerj.15815/ref-65) 2018; 1859
Dong (10.7717/peerj.15815/ref-23) 2017
Gao (10.7717/peerj.15815/ref-27) 2020
Anil (10.7717/peerj.15815/ref-4) 2019
Cyganiak (10.7717/peerj.15815/ref-20) 2014; 25
Nováček (10.7717/peerj.15815/ref-61) 2020; 16
Yao (10.7717/peerj.15815/ref-102) 2019
Li (10.7717/peerj.15815/ref-49) 2020; 112
Dai (10.7717/peerj.15815/ref-21) 2020; 9
Meng (10.7717/peerj.15815/ref-55) 2015
Velickovic (10.7717/peerj.15815/ref-89) 2017
Jassal (10.7717/peerj.15815/ref-39) 2020; 48
Wang (10.7717/peerj.15815/ref-92) 2017; 29
Nickel (10.7717/peerj.15815/ref-60) 2015; 104
Xie (10.7717/peerj.15815/ref-98) 2021; 64
Zhou (10.7717/peerj.15815/ref-106) 2021
Ha (10.7717/peerj.15815/ref-34) 2022
Yelland (10.7717/peerj.15815/ref-103) 2021; 60
Davis (10.7717/peerj.15815/ref-22) 2021; 49
Huang (10.7717/peerj.15815/ref-37) 2021; 229
Collins (10.7717/peerj.15815/ref-19) 2018; 9
Kennedy (10.7717/peerj.15815/ref-44) 2015; 1294
Blohm (10.7717/peerj.15815/ref-12) 2014; 42
Mistry (10.7717/peerj.15815/ref-57) 2021; 49
Yang (10.7717/peerj.15815/ref-100) 2021
W3C (10.7717/peerj.15815/ref-90) 2014
Peng (10.7717/peerj.15815/ref-69) 2020; 63
Xie (10.7717/peerj.15815/ref-97) 2022
Kania (10.7717/peerj.15815/ref-42) 2017; 7
Lahiry (10.7717/peerj.15815/ref-48) 2010; 11
Kanev (10.7717/peerj.15815/ref-41) 2021; 49
McSkimming (10.7717/peerj.15815/ref-54) 2015; 36
Gavali (10.7717/peerj.15815/ref-28) 2022; 18
Attwood (10.7717/peerj.15815/ref-6) 2021; 20
Byrne (10.7717/peerj.15815/ref-17) 2022; 480
Soleymani (10.7717/peerj.15815/ref-80) 2022
Bonner (10.7717/peerj.15815/ref-13) 2022; 23
Barodia (10.7717/peerj.15815/ref-9) 2022; 1866
Ge (10.7717/peerj.15815/ref-29) 2022
Grover (10.7717/peerj.15815/ref-32) 2016
Ayala-Aguilera (10.7717/peerj.15815/ref-7) 2022; 65
Bordes (10.7717/peerj.15815/ref-14) 2013; 26
Chen (10.7717/peerj.15815/ref-18) 2020; 8
Ochoa (10.7717/peerj.15815/ref-62) 2020; 38
Perozzi (10.7717/peerj.15815/ref-70) 2014
Wei (10.7717/peerj.15815/ref-95) 2021; 14
Malumbres (10.7717/peerj.15815/ref-52) 2014; 15
Stroukov (10.7717/peerj.15815/ref-81) 2019; 10
Sheils (10.7717/peerj.15815/ref-77) 2021; 49
References_xml – volume: 49
  start-page: D480
  year: 2021
  ident: 10.7717/peerj.15815/ref-87
  article-title: UniProt: the universal protein knowledgebase in 2021
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa1100
– volume: 124
  start-page: 2554
  year: 2014
  ident: 10.7717/peerj.15815/ref-53
  article-title: A new form of macrothrombocytopenia induced by a germ-line mutation in the PRKACG gene
  publication-title: Blood
  doi: 10.1182/blood-2014-01-551820
– volume: 7
  start-page: e341
  year: 2021
  ident: 10.7717/peerj.15815/ref-3
  article-title: Application and evaluation of knowledge graph embeddings in biomedical data
  publication-title: PeerJ Computer Science
  doi: 10.7717/peerj-cs.341
– volume: 49
  start-page: 7476
  year: 2021
  ident: 10.7717/peerj.15815/ref-84
  article-title: Genome-wide CRISPR screens reveal cyclin C as synthetic survival target of BRCA2
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkab540
– volume: 51
  start-page: D1405
  year: 2023
  ident: 10.7717/peerj.15815/ref-43
  article-title: Pharos 2023: an integrated resource for the understudied human proteome
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkac1033
– volume: 36
  start-page: 175
  year: 2015
  ident: 10.7717/peerj.15815/ref-54
  article-title: ProKinO: a unified resource for mining the cancer kinome
  publication-title: Human Mutation
  doi: 10.1002/humu.22726
– volume: 112
  start-page: 103624
  year: 2020
  ident: 10.7717/peerj.15815/ref-49
  article-title: Potential circRNA-disease association prediction using DeepWalk and network consistency projection
  publication-title: Journal of biomedical informatics
  doi: 10.1016/j.jbi.2020.103624
– volume: 49
  start-page: D1334
  year: 2021
  ident: 10.7717/peerj.15815/ref-77
  article-title: TCRD and Pharos 2021: mining the human proteome for disease biology
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa993
– start-page: 1
  year: 2021
  ident: 10.7717/peerj.15815/ref-45
  article-title: RegPattern2Vec: link prediction in knowledge graphs
– start-page: 385
  year: 2020
  ident: 10.7717/peerj.15815/ref-27
  article-title: Rotate3d: representing relations as rotations in three-dimensional space for knowledge graph embedding
– volume: 50
  start-page: D687
  year: 2022
  ident: 10.7717/peerj.15815/ref-31
  article-title: The reactome pathway knowledgebase 2022
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkab1028
– start-page: 162
  year: 2015
  ident: 10.7717/peerj.15815/ref-56
  article-title: Scalable learning of entity and predicate embeddings for knowledge graph completion
– volume: 18
  start-page: 155
  year: 2010
  ident: 10.7717/peerj.15815/ref-76
  article-title: Structure of D-AKAP2:PKA RI complex: insights into AKAP specificity and selectivity
  publication-title: Structure
  doi: 10.1016/j.str.2009.12.012
– volume: 34
  start-page: 433
  year: 2020
  ident: 10.7717/peerj.15815/ref-79
  article-title: Rhine: relation structure-aware heterogeneous information network embedding
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2020.2982898
– volume: 480
  start-page: 141
  year: 2022
  ident: 10.7717/peerj.15815/ref-17
  article-title: Evolutionary and cellular analysis of the ’dark’ pseudokinase PSKH2
  publication-title: Biochemical Journal
  doi: 10.1042/bcj20220474
– start-page: 905
  year: 2021
  ident: 10.7717/peerj.15815/ref-106
  article-title: Path-RotatE: knowledge graph embedding by relational rotation of path in complex space
– volume: 65
  start-page: 1047
  year: 2022
  ident: 10.7717/peerj.15815/ref-7
  article-title: Small molecule kinase inhibitor drugs (1995-2021): medical indication, pharmacology, and synthesis
  publication-title: Journal of Medicinal Chemistry
  doi: 10.1021/acs.jmedchem.1c00963
– volume: vol. 11052
  volume-title: Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2018
  year: 2018
  ident: 10.7717/peerj.15815/ref-99
  article-title: Similarity modeling on heterogeneous networks via automatic path discovery
  doi: 10.1007/978-3-030-10928-8_3
– volume: 17
  start-page: 317
  year: 2018
  ident: 10.7717/peerj.15815/ref-64
  article-title: Unexplored therapeutic opportunities in the human genome
  publication-title: Nature Reviews Drug Discovery
  doi: 10.1038/nrd.2018.14
– volume: 29
  start-page: 2724
  year: 2017
  ident: 10.7717/peerj.15815/ref-92
  article-title: Knowledge graph embedding: a survey of approaches and applications
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2017.2754499
– volume: 39
  start-page: D402
  year: 2010
  ident: 10.7717/peerj.15815/ref-88
  article-title: PDBe: protein data bank in Europe
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkq985
– volume: 13
  start-page: 954
  year: 2017
  ident: 10.7717/peerj.15815/ref-33
  article-title: From word models to executable models of signaling networks using automated assembly
  publication-title: Molecular Systems Biology
  doi: 10.15252/msb.20177651
– volume: 104
  start-page: 11
  year: 2015
  ident: 10.7717/peerj.15815/ref-60
  article-title: A review of relational machine learning for knowledge graphs
  publication-title: Proceedings of the IEEE
  doi: 10.1109/JPROC.2015.2483592
– volume: 1866
  start-page: 130242
  year: 2022
  ident: 10.7717/peerj.15815/ref-9
  article-title: A(2A) R mediated modulation in IP(3) levels altering the [Ca(2+)](i) through cAMP-dependent PKA signalling pathway
  publication-title: Biochimica et Biophysica Acta (BBA) - General Subjects
  doi: 10.1016/j.bbagen.2022.130242
– year: 2019
  ident: 10.7717/peerj.15815/ref-82
  article-title: Rotate: knowledge graph embedding by relational rotation in complex space
– volume: 30
  start-page: 1
  year: 2017
  ident: 10.7717/peerj.15815/ref-35
  article-title: Inductive representation learning on large graphs
  publication-title: Advances in Neural Information Processing Systems
– year: 2022
  ident: 10.7717/peerj.15815/ref-8
  article-title: Automated assembly of molecular mechanisms at scale from text mining and curated databases
  publication-title: bioRxiv
– volume: 8
  start-page: 338
  year: 2020
  ident: 10.7717/peerj.15815/ref-18
  article-title: Prediction of drug–target interactions from multi-molecular network based on deep walk embedding model
  publication-title: Frontiers in Bioengineering and Biotechnology
  doi: 10.3389/fbioe.2020.00338
– start-page: 1797
  year: 2017
  ident: 10.7717/peerj.15815/ref-25
  article-title: Hin2vec: explore meta-paths in heterogeneous information networks for representation learning
– volume: 40
  start-page: 271
  year: 2017
  ident: 10.7717/peerj.15815/ref-5
  article-title: The crucial role of protein phosphorylation in cell signaling and its use as targeted therapy (Review)
  publication-title: International Journal of Molecular Medicine
  doi: 10.3892/ijmm.2017.3036
– volume: 133
  start-page: 8
  year: 2018
  ident: 10.7717/peerj.15815/ref-94
  article-title: The mediator complex in genomic and non-genomic signaling in cancer
  publication-title: Steroids
  doi: 10.1016/j.steroids.2017.11.007
– volume: 7
  start-page: 140
  year: 2017
  ident: 10.7717/peerj.15815/ref-42
  article-title: IP(3) receptor-mediated calcium signaling and its role in autophagy in cancer
  publication-title: Frontiers in Oncology
  doi: 10.3389/fonc.2017.00140
– year: 2019
  ident: 10.7717/peerj.15815/ref-46
  article-title: Text generation from knowledge graphs with graph transformers
– volume: 21
  start-page: 140
  year: 2009
  ident: 10.7717/peerj.15815/ref-38
  article-title: Tyrosine phosphorylation: thirty years and counting
  publication-title: Current Opinion in Cell Biology
  doi: 10.1016/j.ceb.2009.01.028
– year: 2021
  ident: 10.7717/peerj.15815/ref-58
  article-title: A resource for exploring the understudied human kinome for research and therapeutic opportunities
  publication-title: BioRxiv
  doi: 10.1101/2020.04.02.022277
– volume: 5
  start-page: 17022
  year: 2020
  ident: 10.7717/peerj.15815/ref-96
  article-title: MIPDH: a novel computational model for predicting microRNA–mRNA interactions by DeepWalk on a heterogeneous network
  publication-title: ACS Omega
  doi: 10.1021/acsomega.9b04195
– volume: 60
  start-page: 1952
  year: 2021
  ident: 10.7717/peerj.15815/ref-103
  article-title: The structural and biochemical characterization of UNC119B cargo binding and release mechanisms
  publication-title: Biochemistry
  doi: 10.1021/acs.biochem.1c00251
– volume: 49
  start-page: D1138
  year: 2021
  ident: 10.7717/peerj.15815/ref-22
  article-title: Comparative toxicogenomics database (CTD): update 2021
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa891
– start-page: 855
  year: 2016
  ident: 10.7717/peerj.15815/ref-32
  article-title: node2vec: scalable feature learning for networks
– volume: 13
  start-page: 4156
  year: 2002
  ident: 10.7717/peerj.15815/ref-47
  article-title: Characterization of an A-kinase anchoring protein in human ciliary axonemes
  publication-title: Molecular Biology of the Cell
  doi: 10.1091/mbc.e02-07-0391
– volume: 49
  start-page: D562
  year: 2021
  ident: 10.7717/peerj.15815/ref-41
  article-title: KLIFS: an overhaul after the first 5 years of supporting kinase research
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa895
– volume: 15
  start-page: 283
  year: 2021
  ident: 10.7717/peerj.15815/ref-59
  article-title: A complete map of the calcium/calmodulin-dependent protein kinase kinase 2 (CAMKK2) signaling pathway
  publication-title: Cell Communication and Signaling
  doi: 10.1007/s12079-020-00592-1
– volume: 139
  start-page: 757
  year: 2009
  ident: 10.7717/peerj.15815/ref-2
  article-title: Nuclear CDKs drive Smad transcriptional activation and turnover in BMP and TGF-beta pathways
  publication-title: Cell
  doi: 10.1016/j.cell.2009.09.035
– volume: 63
  start-page: 10594
  year: 2020
  ident: 10.7717/peerj.15815/ref-69
  article-title: Advances in the development of phosphodiesterase-4 inhibitors
  publication-title: Journal of Medicinal Chemistry
  doi: 10.1021/acs.jmedchem.9b02170
– volume: 20
  start-page: 839
  year: 2021
  ident: 10.7717/peerj.15815/ref-6
  article-title: Trends in kinase drug discovery: targets, indications and inhibitor design
  publication-title: Nature Reviews Drug Discovery
  doi: 10.1038/s41573-021-00252-y
– volume: 38
  start-page: 365
  year: 2020
  ident: 10.7717/peerj.15815/ref-62
  article-title: The functional landscape of the human phosphoproteome
  publication-title: Nature Biotechnology
  doi: 10.1038/s41587-019-0344-3
– start-page: 754
  year: 2015
  ident: 10.7717/peerj.15815/ref-55
  article-title: Discovering meta-paths in large heterogeneous information networks
– year: 2019
  ident: 10.7717/peerj.15815/ref-85
  article-title: ChebNet: efficient and stable constructions of deep neural networks with rectified power units using chebyshev approximations
– volume: 458
  start-page: 259
  year: 2021
  ident: 10.7717/peerj.15815/ref-93
  article-title: Hierarchical-aware relation rotational knowledge graph embedding for link prediction
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.05.093
– volume: 49
  start-page: D412
  year: 2021
  ident: 10.7717/peerj.15815/ref-57
  article-title: Pfam: the protein families database in 2021
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa913
– volume: 33
  start-page: 9649
  year: 2020
  ident: 10.7717/peerj.15815/ref-1
  article-title: Boxe: a box embedding model for knowledge base completion
  publication-title: Advances in Neural Information Processing Systems
– volume: 11
  start-page: 60
  year: 2010
  ident: 10.7717/peerj.15815/ref-48
  article-title: Kinase mutations in human disease: interpreting genotype-phenotype relationships
  publication-title: Nature Reviews Genetics
  doi: 10.1038/nrg2707
– year: 2022
  ident: 10.7717/peerj.15815/ref-29
  article-title: Compounde: knowledge graph embedding with translation, rotation and scaling compound operations
– volume: 229
  start-page: 107310
  year: 2021
  ident: 10.7717/peerj.15815/ref-37
  article-title: Knowledge graph embedding by relational and entity rotation
  publication-title: Knowledge-Based Systems
  doi: 10.1016/j.knosys.2021.107310
– volume: 3
  start-page: lqab113
  year: 2021
  ident: 10.7717/peerj.15815/ref-72
  article-title: Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer
  publication-title: NAR Genomics and Bioinformatics
  doi: 10.1093/nargab/lqab113
– volume: 123
  start-page: 328
  year: 2019
  ident: 10.7717/peerj.15815/ref-71
  article-title: W-MetaPath2Vec: the topic-driven meta-path-based model for large-scaled content-based heterogeneous information network representation learning
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2019.01.015
– start-page: 701
  year: 2014
  ident: 10.7717/peerj.15815/ref-70
  article-title: Deepwalk: online learning of social representations
– volume: 29
  start-page: 17
  year: 2016
  ident: 10.7717/peerj.15815/ref-78
  article-title: A survey of heterogeneous information network analysis
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2016.2598561
– year: 2022
  ident: 10.7717/peerj.15815/ref-11
  article-title: Relphormer: relational graph transformer for knowledge graph representation
– volume: 25
  start-page: 1
  year: 2014
  ident: 10.7717/peerj.15815/ref-20
  article-title: RDF 1.1 concepts and abstract syntax
  publication-title: W3C Recommendation
– volume: 10
  start-page: 163
  year: 2019
  ident: 10.7717/peerj.15815/ref-81
  article-title: Synchronizing protein traffic to the primary cilium
  publication-title: Frontiers in Genetics
  doi: 10.3389/fgene.2019.00163
– volume: 48
  start-page: D498
  year: 2020
  ident: 10.7717/peerj.15815/ref-39
  article-title: The reactome pathway knowledgebase
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkz1031
– start-page: 2311
  year: 2021
  ident: 10.7717/peerj.15815/ref-100
  article-title: Knowledge graph representation learning as groupoid: unifying TransE, RotatE, QuatE, ComplEx
– volume: 16
  start-page: e1007578
  year: 2020
  ident: 10.7717/peerj.15815/ref-61
  article-title: Accurate prediction of kinase-substrate networks using knowledge graphs
  publication-title: PLOS Computational Biology
  doi: 10.1371/journal.pcbi.1007578
– volume: 49
  start-page: D529
  year: 2021
  ident: 10.7717/peerj.15815/ref-10
  article-title: The Dark Kinase Knowledgebase: an online compendium of knowledge and experimental results of understudied kinases
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa853
– volume: 1859
  start-page: 868
  year: 2018
  ident: 10.7717/peerj.15815/ref-65
  article-title: Mitochondrial cAMP-PKA signaling: what do we really know?
  publication-title: Biochimica et Biophysica Acta - Bioenergetics
  doi: 10.1016/j.bbabio.2018.04.005
– start-page: 135
  year: 2017
  ident: 10.7717/peerj.15815/ref-23
  article-title: metapath2vec: scalable representation learning for heterogeneous networks
– start-page: 6094
  year: 2020
  ident: 10.7717/peerj.15815/ref-91
  article-title: Reinforcement learning based meta-path discovery in large-scale heterogeneous information networks
– year: 2018
  ident: 10.7717/peerj.15815/ref-104
  article-title: Gaan: gated attention networks for learning on large and spatiotemporal graphs
– year: 2022
  ident: 10.7717/peerj.15815/ref-80
  article-title: Dark kinase annotation, mining and visualization using the Protein Kinase Ontology
  publication-title: bioRxiv
– volume: 64
  start-page: 1283
  year: 2021
  ident: 10.7717/peerj.15815/ref-98
  article-title: Small-molecule kinase inhibitors for the treatment of nononcologic diseases
  publication-title: Journal of Medicinal Chemistry
  doi: 10.1021/acs.jmedchem.0c01511
– volume: 70
  start-page: 82
  year: 2000
  ident: 10.7717/peerj.15815/ref-15
  article-title: Characterization of PSKH1, a novel human protein serine kinase with centrosomal, golgi, and nuclear localization
  publication-title: Genomics
  doi: 10.1006/geno.2000.6365
– volume: 9
  start-page: 15480
  year: 2018
  ident: 10.7717/peerj.15815/ref-19
  article-title: Proteomic analysis defines kinase taxonomies specific for subtypes of breast cancer
  publication-title: Oncotarget
  doi: 10.18632/oncotarget.24337
– volume: 10
  start-page: 226
  year: 2019
  ident: 10.7717/peerj.15815/ref-68
  article-title: Predicting parkinson’s disease genes based on node2vec and autoencoder
  publication-title: Frontiers in Genetics
  doi: 10.3389/fgene.2019.00226
– volume: 21
  start-page: 4
  year: 2011
  ident: 10.7717/peerj.15815/ref-16
  article-title: Protein kinase signaling networks in cancer
  publication-title: Current Opinion in Genetics and Development
  doi: 10.1016/j.gde.2010.10.012
– volume: 49
  start-page: D325
  year: 2021
  ident: 10.7717/peerj.15815/ref-30
  article-title: The gene ontology resource: enriching a gold mine
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkaa1113
– volume: 26
  start-page: 1
  year: 2013
  ident: 10.7717/peerj.15815/ref-14
  article-title: Translating embeddings for modeling multi-relational data
  publication-title: Advances in Neural Information Processing Systems
– volume: 10
  start-page: 76
  year: 2019
  ident: 10.7717/peerj.15815/ref-24
  article-title: Regulatory functions of the Mediator kinases CDK8 and CDK19
  publication-title: Transcription
  doi: 10.1080/21541264.2018.1556915
– volume: 9
  start-page: 750
  year: 2020
  ident: 10.7717/peerj.15815/ref-21
  article-title: A survey on knowledge graph embedding: approaches, applications and benchmarks
  publication-title: Electronics
  doi: 10.3390/electronics9050750
– volume: 8
  start-page: 6518
  year: 2018
  ident: 10.7717/peerj.15815/ref-36
  article-title: Integrative annotation and knowledge discovery of kinase post-translational modifications and cancer-associated mutations through federated protein ontologies and resources
  publication-title: Scientific Reports
  doi: 10.1038/s41598-018-24457-1
– volume: 107
  start-page: 977
  year: 2020
  ident: 10.7717/peerj.15815/ref-66
  article-title: Germline and mosaic variants in PRKACA and PRKACB cause a multiple congenital malformation syndrome
  publication-title: American Journal of Human Genetics
  doi: 10.1016/j.ajhg.2020.09.005
– volume: 29
  start-page: 2050001
  year: 2020
  ident: 10.7717/peerj.15815/ref-75
  article-title: Drug-target interaction prediction by Metapath2vec node embedding in heterogeneous network of interactions
  publication-title: International Journal on Artificial Intelligence Tools
  doi: 10.1142/S0218213020500013
– start-page: 2331
  year: 2020
  ident: 10.7717/peerj.15815/ref-26
  article-title: Magnn: metapath aggregated graph neural network for heterogeneous graph embedding
– volume: 42
  start-page: D396
  year: 2014
  ident: 10.7717/peerj.15815/ref-12
  article-title: Negatome 2.0: a database of non-interacting proteins derived by literature mining, manual annotation and protein structure analysis
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gkt1079
– volume: 41
  start-page: 933
  year: 2020
  ident: 10.7717/peerj.15815/ref-63
  article-title: AKAP signaling Islands: venues for precision pharmacology
  publication-title: Trends in Pharmacological Sciences
  doi: 10.1016/j.tips.2020.09.007
– volume: 47
  start-page: D941
  year: 2019
  ident: 10.7717/peerj.15815/ref-86
  article-title: COSMIC: the catalogue of somatic mutations in cancer
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gky1015
– start-page: 354
  year: 2019
  ident: 10.7717/peerj.15815/ref-4
  article-title: Network sampling using k-hop random walks for heterogeneous network embedding
– year: 2017
  ident: 10.7717/peerj.15815/ref-89
  article-title: Graph attention networks
– year: 2022
  ident: 10.7717/peerj.15815/ref-97
  article-title: From discrimination to generation: knowledge graph completion with generative transformer
  doi: 10.1145/3487553.3524238
– volume: 47
  start-page: D607
  year: 2019
  ident: 10.7717/peerj.15815/ref-83
  article-title: STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gky1131
– volume: 18
  start-page: 853
  year: 2022
  ident: 10.7717/peerj.15815/ref-28
  article-title: A knowledge graph representation learning approach to predict novel kinase-substrate interactions
  publication-title: Molecular Omics Journal
  doi: 10.1039/d1mo00521a
– year: 2022
  ident: 10.7717/peerj.15815/ref-34
  article-title: NCMD: Node2vec-based neural collaborative filtering for predicting miRNA-disease association
– year: 2023
  ident: 10.7717/peerj.15815/ref-40
  article-title: An atlas of substrate specificities for the human serine/threonine kinome
  publication-title: Nature
  doi: 10.1038/s41586-022-05575-3
– start-page: 333
  volume-title: Protein Bioinformatics: From Protein Modifications and Networks to Proteomics
  year: 2017
  ident: 10.7717/peerj.15815/ref-73
  article-title: iPTMnet: integrative bioinformatics for studying PTM networks
  doi: 10.1007/978-1-4939-6783-4_16
– volume: 23
  start-page: bbac279
  year: 2022
  ident: 10.7717/peerj.15815/ref-13
  article-title: Implications of topological imbalance for representation learning on biomedical knowledge graphs
  publication-title: Briefings in Bioinformatics
  doi: 10.1093/bib/bbac279
– volume: 25
  start-page: 266
  year: 2020
  ident: 10.7717/peerj.15815/ref-51
  article-title: Association mining to identify microbe drug interactions based on heterogeneous network embedding representation
  publication-title: IEEE Journal of Biomedical and Health Informatics
  doi: 10.1109/JBHI.2020.2998906
– start-page: 6471
  year: 2021
  ident: 10.7717/peerj.15815/ref-74
  article-title: Chronor: rotation based temporal knowledge graph embedding
– volume: 1294
  start-page: 137
  year: 2015
  ident: 10.7717/peerj.15815/ref-44
  article-title: Selective disruption of the AKAP signaling complexes
  publication-title: Methods in Molecular Biology
  doi: 10.1007/978-1-4939-2537-7_11
– volume: 15
  start-page: 1
  year: 2014
  ident: 10.7717/peerj.15815/ref-52
  article-title: Cyclin-dependent kinases
  publication-title: Genome Biology
  doi: 10.1186/gb-2014-15-1-r1
– year: 2020
  ident: 10.7717/peerj.15815/ref-67
  article-title: Geom-gcn: geometric graph convolutional networks
– volume: 41
  start-page: D955
  year: 2013
  ident: 10.7717/peerj.15815/ref-101
  article-title: Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells
  publication-title: Nucleic Acids Research
  doi: 10.1093/nar/gks1111
– year: 2015
  ident: 10.7717/peerj.15815/ref-50
  article-title: Learning entity and relation embeddings for knowledge graph completion
  doi: 10.1609/aaai.v29i1.9491
– volume: 14
  start-page: 1282
  year: 2021
  ident: 10.7717/peerj.15815/ref-95
  article-title: PRKAR2A deficiency protects mice from experimental colitis by increasing IFN-stimulated gene expression and modulating the intestinal microbiota
  publication-title: Mucosal Immunology
  doi: 10.1038/s41385-021-00426-2
– year: 2019
  ident: 10.7717/peerj.15815/ref-102
  article-title: KG-BERT: BERT for knowledge graph completion
– year: 2014
  ident: 10.7717/peerj.15815/ref-90
  article-title: RDF Schema 1.1
– year: 2019
  ident: 10.7717/peerj.15815/ref-105
  article-title: Star-gcn: stacked and reconstructed graph convolutional networks for recommender systems
  doi: 10.24963/ijcai.2019/592
SSID ssj0000826083
Score 2.3172977
Snippet The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied “dark”...
The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied "dark"...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage e15815
SubjectTerms Biochemistry
Bioinformatics
Case studies
Computational Biology
Computational linguistics
Computational Science
Data integration
Data Mining and Machine Learning
Data Science
Genomics
Humans
Illuminating Druggable Genome (IDG)
Knowledge
Language processing
Learning
Link prediction
Natural language interfaces
Ontologies
Pathway prediction
Pattern Recognition, Automated
Protein kinases
Protein-protein interactions
Proteins
Proteins - genetics
Random walk
Title Predicting protein and pathway associations for understudied dark kinases using pattern-constrained knowledge graph embedding
URI https://www.ncbi.nlm.nih.gov/pubmed/37868056
https://www.proquest.com/docview/2880820917
https://pubmed.ncbi.nlm.nih.gov/PMC10590106
https://doaj.org/article/f9a6f8aea0fa42169043d7129c3f323f
Volume 11
WOSCitedRecordID wos001096495400011&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: M7P
  dateStart: 20130212
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: BENPR
  dateStart: 20130212
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database (ProQuest)
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: PIMPY
  dateStart: 20130212
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 2167-8359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000826083
  issn: 2167-8359
  databaseCode: M2P
  dateStart: 20130212
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3di9QwEA96J3Iv4rfVc41wIAjlmvQj6eOd3KHgLkVU1qeST11Oe0d398QH_3dn0l5tUfDFl1CaKSSZycykmfkNIQeIGG4V4zEzUsdZWqhYS8liK7nTmnlnwg3-x7disZDLZVmNSn1hTFgHD9wt3KEvVeGlcirxKuN4qZOlVoCVMqlPeepR-yaiHB2mgg4Grxmciy4hT8CR5fDCuRb0Qi6xAO7IBAWk_j_18cggTYMlR9bn9Da51buN9Kgb7h1yzTV3yc15fzF-j_ysWnzGGGYaoBdWDVWNpVhw-Lv6QdVvLqwp-Kl02yW1YBChpVa1Z_Rs1YBFW1OMhP-MH-Kvwtig_4hlJIBs-P9GA8w1dd-0s2j77pMPpyfvX72O-8oKscmzYhMzXRif2NxacJcSr23qufIqV3A4ssaLkmXMpTrnLuUBlEtzozn3Oay6ttD1gOw05417RGiZayWy0nFf-iwThVKKaZflsNDWsIxH5OXVYtemhx3HYX-t4fiBnKkDZ-rAmYgcDMQXHdrG38mOkWsDCUJkhxcgOHUvOPW_BCciz5DndZdvOmz0-ggxwArM2I3Ii0CBWx2GbFSfsQATR9CsCeX-hBK2qJl0P7-Sqxq7MK6tcefbdc1BfYIPBmfmiDzs5GyYVSpkIcE_jYicSOBk2tOeZvUlIISzkFKcFI__x0I9IXscPDs02Ezuk51Nu3VPyQ1zuVmt2xm5LpZyRnaPTxbVu1nYhdDOeYWtgHa3ejOvPv0CMe0-Jw
linkProvider Directory of Open Access Journals
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=Predicting+protein+and+pathway+associations+for+understudied+dark+kinases+using+pattern-constrained+knowledge+graph+embedding&rft.jtitle=PeerJ+%28San+Francisco%2C+CA%29&rft.au=Salcedo%2C+Mariah+V&rft.au=Gravel%2C+Nathan&rft.au=Keshavarzi%2C+Abbas&rft.au=Huang%2C+Liang-Chin&rft.date=2023-10-18&rft.eissn=2167-8359&rft.volume=11&rft.spage=e15815&rft_id=info:doi/10.7717%2Fpeerj.15815&rft_id=info%3Apmid%2F37868056&rft.externalDocID=37868056
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2167-8359&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2167-8359&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2167-8359&client=summon