MicroRNA signature for interpretable breast cancer classification with subtype clue

MicroRNAs (miRNAs) are short non-coding RNAs engaged in cellular regulation by suppressing genes at their post-transcriptional stage. Evidence of their involvement in breast cancer and the possibility of quantifying the their concentration in the blood has sparked the hope of using them as reliable,...

Full description

Saved in:
Bibliographic Details
Published in:Journal of Computational Mathematics and Data Science Vol. 3; p. 100042
Main Authors: Andreini, Paolo, Bonechi, Simone, Bianchini, Monica, Geraci, Filippo
Format: Journal Article
Language:English
Published: Elsevier B.V 01.06.2022
Subjects:
Breast cancer subtype
Feature importance
MiRNA biomarkers
Supervised classification
Breast cancer subtype
Feature importance
MiRNA biomarkers
Supervised classification
ISSN:2772-4158, 2772-4158
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract MicroRNAs (miRNAs) are short non-coding RNAs engaged in cellular regulation by suppressing genes at their post-transcriptional stage. Evidence of their involvement in breast cancer and the possibility of quantifying the their concentration in the blood has sparked the hope of using them as reliable, inexpensive and non-invasive biomarkers. While differential expression analysis succeeded in identifying groups of disregulated miRNAs among tumor and healthy samples, its intrinsic dual nature makes it inadequate for cancer subtype detection. Using artificial intelligence or machine learning to uncover complex profiles of miRNA expression associated with different breast cancer subtypes has poorly been investigated and only few recent works have explored this possibility. However, the use of the same dataset both for training and testing leaves the issue of the robustness of these results still open. In this paper, we propose a two-stage method that leverages on two ad-hoc classifiers for tumor/healthy classification and subtype identification. We assess our results using two completely independent datasets: TGCA for training and GSE68085 for testing. Experiments show that our strategy is extraordinarily effective especially for tumor/healthy classification, where we achieved an accuracy of 0.99. Yet, by means of a feature importance mechanism, our method is able to display which miRNAs lead to every single sample classification so as to enable a personalized medicine approach to therapy as well as the algorithm explainability required by the EU GDPR regulation and other similar legislations.
AbstractList MicroRNAs (miRNAs) are short non-coding RNAs engaged in cellular regulation by suppressing genes at their post-transcriptional stage. Evidence of their involvement in breast cancer and the possibility of quantifying the their concentration in the blood has sparked the hope of using them as reliable, inexpensive and non-invasive biomarkers. While differential expression analysis succeeded in identifying groups of disregulated miRNAs among tumor and healthy samples, its intrinsic dual nature makes it inadequate for cancer subtype detection. Using artificial intelligence or machine learning to uncover complex profiles of miRNA expression associated with different breast cancer subtypes has poorly been investigated and only few recent works have explored this possibility. However, the use of the same dataset both for training and testing leaves the issue of the robustness of these results still open. In this paper, we propose a two-stage method that leverages on two ad-hoc classifiers for tumor/healthy classification and subtype identification. We assess our results using two completely independent datasets: TGCA for training and GSE68085 for testing. Experiments show that our strategy is extraordinarily effective especially for tumor/healthy classification, where we achieved an accuracy of 0.99. Yet, by means of a feature importance mechanism, our method is able to display which miRNAs lead to every single sample classification so as to enable a personalized medicine approach to therapy as well as the algorithm explainability required by the EU GDPR regulation and other similar legislations.
ArticleNumber 100042
Author Bianchini, Monica
Geraci, Filippo
Bonechi, Simone
Andreini, Paolo
Author_xml – sequence: 1
  givenname: Paolo
  surname: Andreini
  fullname: Andreini, Paolo
  organization: Department of Information Engineering and Mathematics, University of Siena, Siena, Italy
– sequence: 2
  givenname: Simone
  surname: Bonechi
  fullname: Bonechi, Simone
  organization: Department of Social, Political and Cognitive Sciences, University of Siena, Siena, Italy
– sequence: 3
  givenname: Monica
  surname: Bianchini
  fullname: Bianchini, Monica
  organization: Department of Information Engineering and Mathematics, University of Siena, Siena, Italy
– sequence: 4
  givenname: Filippo
  orcidid: 0000-0001-6993-6761
  surname: Geraci
  fullname: Geraci, Filippo
  email: filippo.geraci@iit.cnr.it
  organization: Institute for Informatics and Telematics, CNR, Pisa, Italy
BookMark eNqFkEtPwzAMgCM0JMbYL-CSP9CRR5u2Bw7TxEsaIPE4R0nqQKqunZIMtH9PtnFAHOBky_Zn2d8pGvVDDwidUzKjhIqLdtaaVRNmjDCWKoTk7AiNWVmyLKdFNfqRn6BpCG0aYSXPRV2M0fO9M354epjj4N56FTcesB08dn0Ev_YQle4Aaw8qRGxUb8Bj06kQnHVGRTf0-NPFdxw2Om7XkHobOEPHVnUBpt9xgl6vr14Wt9ny8eZuMV9mhgnOMibyQpSKEGpEU1pqRS6saOpaV8SahipocqgUq4pCVBXnaa4uuaGV4JoorfkE1Ye96YMQPFhpXNzfFL1ynaRE7gTJVu4FyZ0geRCUWP6LXXu3Un77D3V5oCC99eHAy2AcJCmN82CibAb3J_8FT-mC0A
CitedBy_id crossref_primary_10_3390_a15080274
crossref_primary_10_3390_app13148257
crossref_primary_10_3390_diagnostics13193072
crossref_primary_10_1016_j_asoc_2024_112270
Cites_doi 10.1016/j.bspc.2022.103545
10.1016/j.compbiomed.2021.104352
10.1093/bioinformatics/btp616
10.1016/j.lfs.2020.117865
10.1007/s10549-018-4899-3
10.1007/s12094-019-02103-0
10.1038/nature11412
10.1016/j.compbiolchem.2019.107191
10.1155/2015/281756
10.1093/nar/gkt1181
10.1002/hed.25866
10.1016/j.jmoldx.2013.07.005
10.1023/A:1010933404324
10.1371/journal.pone.0003148
10.1023/A:1022627411411
10.1200/JCO.2008.18.1370
10.1007/s12282-017-0814-8
10.1371/journal.pcbi.0030131
10.3390/cancers11030431
10.1634/theoncologist.2014-0108
10.1111/cpr.12913
10.1158/0008-5472.CAN-16-2574
10.1016/j.molmed.2011.01.006
10.3390/cancers12071785
10.1158/0008-5472.CAN-09-1201
10.1186/s12864-015-1899-0
10.1038/jhg.2016.89
10.1371/journal.pone.0260327
10.1016/j.gene.2018.07.057
10.1158/1055-9965.EPI-13-1023
10.1016/j.compbiomed.2021.104244
10.1016/j.humpath.2012.10.014
10.1038/nature03702
10.1001/jama.2015.13183
10.1038/nature10983
10.1371/journal.pone.0200353
10.1261/rna.1034808
10.1096/fj.15-271312
10.1371/journal.pone.0020769
10.1038/srep06566
10.7150/ijbs.16529
ContentType Journal Article
Copyright 2022 The Author(s)
Copyright_xml – notice: 2022 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.jcmds.2022.100042
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
EISSN 2772-4158
ExternalDocumentID 10_1016_j_jcmds_2022_100042
S2772415822000116
GroupedDBID 6I.
AAFTH
AAXUO
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
EBS
FDB
GROUPED_DOAJ
M41
M~E
OK1
ROL
0R~
AALRI
AAYWO
AAYXX
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AIGII
AITUG
AKBMS
AKYEP
APXCP
CITATION
ID FETCH-LOGICAL-c2632-264567a001c6d7f1f646f6d99b80fcd1aed4e8a28556883301c973c1863b0abb3
ISSN 2772-4158
IngestDate Tue Nov 18 21:47:20 EST 2025
Sat Nov 29 07:35:29 EST 2025
Tue Jul 25 20:57:54 EDT 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Breast cancer subtype
Feature importance
MiRNA biomarkers
Supervised classification
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2632-264567a001c6d7f1f646f6d99b80fcd1aed4e8a28556883301c973c1863b0abb3
ORCID 0000-0001-6993-6761
OpenAccessLink http://dx.doi.org/10.1016/j.jcmds.2022.100042
ParticipantIDs crossref_citationtrail_10_1016_j_jcmds_2022_100042
crossref_primary_10_1016_j_jcmds_2022_100042
elsevier_sciencedirect_doi_10_1016_j_jcmds_2022_100042
PublicationCentury 2000
PublicationDate June 2022
2022-06-00
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: June 2022
PublicationDecade 2020
PublicationTitle Journal of Computational Mathematics and Data Science
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Saha, Bhowmick, Geraci, Pellegrini, Bhattacharjee, Maulik, Plewczynski (b22) 2015
Myers, Moorman, Gierisch, Havrilesky, Grimm, Ghate, Davidson, Mongtomery, Crowley, McCrory (b7) 2015; 314
Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg, Vanderplas, Passos, Cournapeau, Brucher, Perrot, Duchesnay (b40) 2011; 12
Farshid, Walters (b8) 2018; 172
Sætrom, Biesinger, Li, Smith, Thomas, Majzoub, Rivas, Alluin, Rossi, Krontiris (b42) 2009; 69
Curtis, Shah, Chin, Turashvili, Rueda, Dunning, Speed, Lynch, Samarajiwa, Yuan (b6) 2012; 486
Amirfallah, Knutsdottir, Arason, Hilmarsdottir, Johannsson, Agnarsson, Barkardottir, Reynisdottir (b44) 2021; 16
Breiman (b27) 2001; 45
Netanely, Avraham, Ben-Baruch, Evron, Shamir (b35) 2016; 18
Yan, Huang, Shao, Huang, Deng, Wu, Zeng, Shao (b45) 2008; 14
Sweeney, Bernard, Factor, Kwan, Habel, Quesenberry, Shakespear, Weltzien, Stijleman, Davis (b3) 2014; 23
Rehman, Zhuang, Muhamed Ali, Ibrahim, Li (b20) 2019; 11
Siegel, Miller, Jemal (b1) 2019
Shalgi, Lieber, Oren, Pilpel (b12) 2007; 3
Wang, Ye, Zhao, Li, Wang, Tao, Wang, He (b51) 2013; 44
Jakob, Mattes, Küffer, Unger, Hess, Bertlich, Haubner, Ihler, Canis, Weiss (b48) 2019; 41
Peng, Theng, Le (b41) 2021; 54
Zhang, Xu, Wang, Tang, He (b47) 2019; 42
Wang, Yan, Zhang, Li (b52) 2019; 7
Mopidevi, Maharjan, Jain, Pandey, Kumar (b54) 2012
Kurozumi, Yamaguchi, Kurosumi, Ohira, Matsumoto, Horiguchi (b16) 2017; 62
Sarkar, Saha, Sarkar, Maulik (b25) 2021; 131
Tamilmani, Devi, Sujithra, Shajin, Rajesh (b31) 2022; 75
Holm, Eriksson, Ploner, Eriksson, Rantalainen, Li, Hall, Czene (b4) 2017; 77
Robinson, McCarthy, Smyth (b33) 2010; 26
Huang, Cai, Pacheco, Narrandes, Wang, Xu (b28) 2018; 15
Krishnan, Ghosh, Wang, Li, Narasimhan, Berendt, Graham, Mackey, Kovalchuk, Damaraju (b36) 2015; 16
Qi (b29) 2012
Lopez-Rincon, Mendoza-Maldonado, Martinez-Archundia, Schönhuth, Kraneveld, Garssen, Tonda (b24) 2020; 12
Andorfer, Necela, Thompson, Perez (b17) 2011; 17
Kozomara, Griffiths-Jones (b38) 2013; 42
Yang, Xu, Zhang, Wu, Xing, Ru, Xu, Cao (b49) 2015; 5
Sherafatian (b23) 2018; 677
Geraci, Manzini (b37) 2021; 133
Cortes, Vapnik (b26) 1995; 20
Kok, Halliani, Moerland, Meijers, Creemers, Pinto-Sietsma (b10) 2015; 29
Koboldt, Fulton, McLellan, Schmidt, Kalicki-Veizer, McMichael, Fulton, Dooling, Ding, Mardis (b32) 2012; 490
Zhang, Xu, Ni, Li, Zhou, Xu (b50) 2016; 12
Krist, Florczyk, Pietraszek-Gremplewicz, Józkowicz, Dulak (b53) 2015; 2015
Dai, Chen, Bai (b15) 2014; 4
Adhami, Haghdoost, Sadeghi, Malekpour Afshar (b18) 2018; 25
Lundberg, Lee (b30) 2017
Sourvinou, Markou, Lianidou (b9) 2013; 15
Dieci, Orvieto, Dominici, Conte, Guarneri (b5) 2014; 19
Khalili, Nouri-Vaskeh, Segherlou, Baghbanzadeh, Halimi, Rezaee, Baradaran (b46) 2020; 256
Lu, Getz, Miska, Saavedra, Lamb, Peck, Cordero, Ebert, Mak, Ferrando, Downing, Jacks, Horvitz, Golub (b11) 2005; 435
Gilad, Meiri, Yogev, Benjamin, Lebanony, Yerushalmi, Benjamin, Kushnir, Cholakh, Melamed (b14) 2008; 3
Duttagupta, Jiang, Gollub, Getts, Jones (b13) 2011; 6
Parker, Mullins, Cheang, Leung, Voduc, Vickery, Davies, Fauron, He, Hu (b2) 2009; 27
Cava, Colaprico, Bertoli, Bontempi, Mauri, Castiglioni (b55) 2016; 17
Bhowmick, Saha, Bhattacharjee, Genovese, Geraci (b19) 2018; 13
Brodersen, Ong, Stephan, Buhmann (b39) 2010
Dai, Li, Bai, Yang, Liu, Zhan, Shi (b34) 2015; 5
Bozgeyik (b43) 2020; 84
Tomczak, Czerwińska, Wiznerowicz (b21) 2015; 19
Zhang (10.1016/j.jcmds.2022.100042_b50) 2016; 12
Parker (10.1016/j.jcmds.2022.100042_b2) 2009; 27
Curtis (10.1016/j.jcmds.2022.100042_b6) 2012; 486
Farshid (10.1016/j.jcmds.2022.100042_b8) 2018; 172
Kozomara (10.1016/j.jcmds.2022.100042_b38) 2013; 42
Bozgeyik (10.1016/j.jcmds.2022.100042_b43) 2020; 84
Rehman (10.1016/j.jcmds.2022.100042_b20) 2019; 11
Siegel (10.1016/j.jcmds.2022.100042_b1) 2019
Sætrom (10.1016/j.jcmds.2022.100042_b42) 2009; 69
Zhang (10.1016/j.jcmds.2022.100042_b47) 2019; 42
Duttagupta (10.1016/j.jcmds.2022.100042_b13) 2011; 6
Dai (10.1016/j.jcmds.2022.100042_b15) 2014; 4
Sweeney (10.1016/j.jcmds.2022.100042_b3) 2014; 23
Lopez-Rincon (10.1016/j.jcmds.2022.100042_b24) 2020; 12
Cortes (10.1016/j.jcmds.2022.100042_b26) 1995; 20
Wang (10.1016/j.jcmds.2022.100042_b51) 2013; 44
Breiman (10.1016/j.jcmds.2022.100042_b27) 2001; 45
Amirfallah (10.1016/j.jcmds.2022.100042_b44) 2021; 16
Jakob (10.1016/j.jcmds.2022.100042_b48) 2019; 41
Kurozumi (10.1016/j.jcmds.2022.100042_b16) 2017; 62
Lundberg (10.1016/j.jcmds.2022.100042_b30) 2017
Adhami (10.1016/j.jcmds.2022.100042_b18) 2018; 25
Tomczak (10.1016/j.jcmds.2022.100042_b21) 2015; 19
Qi (10.1016/j.jcmds.2022.100042_b29) 2012
Yan (10.1016/j.jcmds.2022.100042_b45) 2008; 14
Tamilmani (10.1016/j.jcmds.2022.100042_b31) 2022; 75
Lu (10.1016/j.jcmds.2022.100042_b11) 2005; 435
Andorfer (10.1016/j.jcmds.2022.100042_b17) 2011; 17
Brodersen (10.1016/j.jcmds.2022.100042_b39) 2010
Saha (10.1016/j.jcmds.2022.100042_b22) 2015
Cava (10.1016/j.jcmds.2022.100042_b55) 2016; 17
Sourvinou (10.1016/j.jcmds.2022.100042_b9) 2013; 15
Holm (10.1016/j.jcmds.2022.100042_b4) 2017; 77
Pedregosa (10.1016/j.jcmds.2022.100042_b40) 2011; 12
Dieci (10.1016/j.jcmds.2022.100042_b5) 2014; 19
Kok (10.1016/j.jcmds.2022.100042_b10) 2015; 29
Khalili (10.1016/j.jcmds.2022.100042_b46) 2020; 256
Wang (10.1016/j.jcmds.2022.100042_b52) 2019; 7
Peng (10.1016/j.jcmds.2022.100042_b41) 2021; 54
Mopidevi (10.1016/j.jcmds.2022.100042_b54) 2012
Sherafatian (10.1016/j.jcmds.2022.100042_b23) 2018; 677
Geraci (10.1016/j.jcmds.2022.100042_b37) 2021; 133
Dai (10.1016/j.jcmds.2022.100042_b34) 2015; 5
Krist (10.1016/j.jcmds.2022.100042_b53) 2015; 2015
Myers (10.1016/j.jcmds.2022.100042_b7) 2015; 314
Krishnan (10.1016/j.jcmds.2022.100042_b36) 2015; 16
Yang (10.1016/j.jcmds.2022.100042_b49) 2015; 5
Bhowmick (10.1016/j.jcmds.2022.100042_b19) 2018; 13
Netanely (10.1016/j.jcmds.2022.100042_b35) 2016; 18
Shalgi (10.1016/j.jcmds.2022.100042_b12) 2007; 3
Koboldt (10.1016/j.jcmds.2022.100042_b32) 2012; 490
Huang (10.1016/j.jcmds.2022.100042_b28) 2018; 15
Gilad (10.1016/j.jcmds.2022.100042_b14) 2008; 3
Robinson (10.1016/j.jcmds.2022.100042_b33) 2010; 26
Sarkar (10.1016/j.jcmds.2022.100042_b25) 2021; 131
References_xml – volume: 17
  year: 2016
  ident: b55
  article-title: How interacting pathways are regulated by miRNAs in breast cancer subtypes
  publication-title: BMC Bioinformatics
– volume: 12
  start-page: 2825
  year: 2011
  end-page: 2830
  ident: b40
  article-title: Scikit-learn: Machine learning in python
  publication-title: J Mach Learn Res
– volume: 314
  start-page: 1615
  year: 2015
  end-page: 1634
  ident: b7
  article-title: Benefits and harms of breast cancer screening: a systematic review
  publication-title: JAMA
– volume: 25
  start-page: 198
  year: 2018
  end-page: 205
  ident: b18
  article-title: Candidate mirnas in human breast cancer biomarkers: a systematic review
  publication-title: Breast Cancer
– volume: 15
  start-page: 41
  year: 2018
  end-page: 51
  ident: b28
  article-title: Applications of support vector machine (SVM) learning in cancer genomics
  publication-title: Cancer Genomics Proteomics
– volume: 42
  start-page: D68
  year: 2013
  end-page: D73
  ident: b38
  article-title: MiRBase: annotating high confidence microRNAs using deep sequencing data
  publication-title: Nucleic Acids Res
– volume: 3
  year: 2007
  ident: b12
  article-title: Global and local architecture of the mammalian microRNA-transcription factor regulatory network
  publication-title: PLoS Comput Biol
– volume: 256
  year: 2020
  ident: b46
  article-title: Diagnostic, prognostic, and therapeutic significance of miR-139-5p in cancers
  publication-title: Life Sciences
– start-page: 3121
  year: 2010
  end-page: 3124
  ident: b39
  article-title: The balanced accuracy and its posterior distribution
  publication-title: 2010 20th International Conference on Pattern Recognition
– volume: 75
  year: 2022
  ident: b31
  article-title: Cancer MiRNA biomarker classification based on improved generative adversarial network optimized with mayfly optimization algorithm
  publication-title: Biomed Signal Process Control
– volume: 14
  start-page: 2348
  year: 2008
  end-page: 2360
  ident: b45
  article-title: MicroRNA miR-21 overexpression in human breast cancer is associated with advanced clinical stage, lymph node metastasis and patient poor prognosis
  publication-title: Rna
– volume: 131
  year: 2021
  ident: b25
  article-title: Machine learning integrated ensemble of feature selection methods followed by survival analysis for predicting breast cancer subtype specific miRNA biomarkers
  publication-title: Comput Biol Med
– volume: 84
  year: 2020
  ident: b43
  article-title: Bioinformatic analysis and in vitro validation of let-7b and let-7c in breast cancer
  publication-title: Comput Biol Chem
– volume: 19
  start-page: 805
  year: 2014
  end-page: 813
  ident: b5
  article-title: Rare breast cancer subtypes: histological, molecular, and clinical peculiarities
  publication-title: Oncol
– start-page: 116
  year: 2015
  end-page: 127
  ident: b22
  article-title: Analysis of next-generation sequencing data of mirna for the prediction of breast cancer
  publication-title: International Conference on Swarm, Evolutionary, and Memetic Computing
– volume: 69
  start-page: 7459
  year: 2009
  end-page: 7465
  ident: b42
  article-title: A risk variant in an miR-125b binding site in BMPR1B is associated with breast cancer pathogenesis
  publication-title: Cancer Res
– start-page: 4765
  year: 2017
  end-page: 4774
  ident: b30
  article-title: A unified approach to interpreting model predictions
  publication-title: Advances in Neural Information Processing Systems 30
– volume: 435
  start-page: 834
  year: 2005
  end-page: 838
  ident: b11
  article-title: MicroRNA expression profiles classify human cancers
  publication-title: Nature
– volume: 62
  start-page: 15
  year: 2017
  end-page: 24
  ident: b16
  article-title: Recent trends in microrna research into breast cancer with particular focus on the associations between micrornas and intrinsic subtypes
  publication-title: J Human Genetics
– volume: 2015
  year: 2015
  ident: b53
  article-title: The role of miR-378a in metabolism, angiogenesis, and muscle biology
  publication-title: Int J Endocrinol
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: b27
  article-title: Random forests
  publication-title: Mach Learn
– volume: 12
  start-page: 1437
  year: 2016
  ident: b50
  article-title: MiR-99a and MiR-491 regulate cisplatin resistance in human gastric cancer cells by targeting CAPNS1
  publication-title: Int J Biol Sci
– volume: 20
  start-page: 273
  year: 1995
  end-page: 297
  ident: b26
  article-title: Support-vector networks
  publication-title: Mach Learn
– volume: 54
  year: 2021
  ident: b41
  article-title: Essential functions of miR-125b in cancer
  publication-title: Cell Proliferation
– volume: 44
  start-page: 1278
  year: 2013
  end-page: 1285
  ident: b51
  article-title: Clinicopathologic significance of miR-10b expression in gastric carcinoma
  publication-title: Human Pathol
– volume: 490
  start-page: 61
  year: 2012
  end-page: 70
  ident: b32
  article-title: Comprehensive molecular portraits of human breast tumours
  publication-title: Nature
– volume: 6
  year: 2011
  ident: b13
  article-title: Impact of cellular mirnas on circulating mirna biomarker signatures
  publication-title: PLoS One
– year: 2019
  ident: b1
  article-title: Cancer statistics
  publication-title: CA: Cancer J Clin
– volume: 7
  year: 2019
  ident: b52
  article-title: Role of miR-10b-5p in the prognosis of breast cancer
  publication-title: PeerJ
– volume: 27
  start-page: 1160
  year: 2009
  ident: b2
  article-title: Supervised risk predictor of breast cancer based on intrinsic subtypes
  publication-title: J Clin Oncol
– volume: 41
  start-page: 3499
  year: 2019
  end-page: 3515
  ident: b48
  article-title: MicroRNA expression patterns in oral squamous cell carcinoma: hsa-mir-99b-3p and hsa-mir-100-5p as novel prognostic markers for oral cancer
  publication-title: Head Neck
– volume: 12
  start-page: 1785
  year: 2020
  ident: b24
  article-title: Machine learning-based ensemble recursive feature selection of circulating mirnas for cancer tumor classification
  publication-title: Cancers
– volume: 19
  start-page: A68
  year: 2015
  ident: b21
  article-title: The cancer genome atlas (TCGA): an immeasurable source of knowledge
  publication-title: Contem Oncol
– volume: 486
  start-page: 346
  year: 2012
  ident: b6
  article-title: The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups
  publication-title: Nature
– volume: 13
  year: 2018
  ident: b19
  article-title: Genome-wide analysis of NGS data to compile cancer-specific panels of mirna biomarkers
  publication-title: PLoS One
– volume: 133
  year: 2021
  ident: b37
  article-title: EZcount: An all-in-one software for microRNA expression quantification from NGS sequencing data
  publication-title: Comput Biol Med
– volume: 15
  start-page: 827
  year: 2013
  end-page: 834
  ident: b9
  article-title: Quantification of circulating mirnas in plasma: effect of preanalytical and analytical parameters on their isolation and stability
  publication-title: J Mol Diagnost
– volume: 17
  start-page: 313
  year: 2011
  end-page: 319
  ident: b17
  article-title: Microrna signatures: clinical biomarkers for the diagnosis and treatment of breast cancer
  publication-title: Trends Mol Med
– volume: 16
  year: 2021
  ident: b44
  article-title: Hsa-mir-21-3p associates with breast cancer patient survival and targets genes in tumor suppressive pathways
  publication-title: PLoS One
– volume: 5
  start-page: 545
  year: 2015
  ident: b49
  article-title: Role of miR-100 in the radioresistance of colorectal cancer cells
  publication-title: Amer J Cancer Res
– volume: 172
  start-page: 191
  year: 2018
  end-page: 199
  ident: b8
  article-title: Molecular subtypes of screen-detected breast cancer
  publication-title: Breast Cancer Res Treat
– volume: 16
  start-page: 1
  year: 2015
  end-page: 17
  ident: b36
  article-title: Next generation sequencing profiling identifies miR-574-3p and miR-660-5p as potential novel prognostic markers for breast cancer
  publication-title: BMC Genomics
– year: 2012
  ident: b54
  article-title: MicroRNAs hsa-miR-584 and hsa-mir-31 regulate expression of human angiotensnogen gene
– volume: 677
  start-page: 111
  year: 2018
  end-page: 118
  ident: b23
  article-title: Tree-based machine learning algorithms identified minimal set of mirna biomarkers for breast cancer diagnosis and molecular subtyping
  publication-title: Gene
– start-page: 307
  year: 2012
  end-page: 323
  ident: b29
  article-title: Random forest for bioinformatics
  publication-title: Ensemble Machine Learning
– volume: 42
  start-page: 1699
  year: 2019
  end-page: 1708
  ident: b47
  article-title: MiR-139-3p suppresses the invasion and migration properties of breast cancer cells by targeting RAB1a
  publication-title: Oncol Rep
– volume: 77
  start-page: 3708
  year: 2017
  end-page: 3717
  ident: b4
  article-title: Assessment of breast cancer risk factors reveals subtype heterogeneity
  publication-title: Cancer Res
– volume: 5
  start-page: 2929
  year: 2015
  ident: b34
  article-title: Breast cancer intrinsic subtype classification, clinical use and future trends
  publication-title: Amer J Cancer Res
– volume: 29
  start-page: 3853
  year: 2015
  end-page: 3862
  ident: b10
  article-title: Normalization panels for the reliable quantification of circulating microRNAs by RT-qPCR
  publication-title: FASEB J
– volume: 11
  start-page: 431
  year: 2019
  ident: b20
  article-title: Validation of mirnas as breast cancer biomarkers with a machine learning approach
  publication-title: Cancers
– volume: 4
  start-page: 1
  year: 2014
  end-page: 10
  ident: b15
  article-title: Integrative investigation on breast cancer in ER, PR and HER2-defined subgroups using mRNA and mirna expression profiling
  publication-title: Sci Rep
– volume: 18
  start-page: 1
  year: 2016
  end-page: 16
  ident: b35
  article-title: Expression and methylation patterns partition luminal-A breast tumors into distinct prognostic subgroups
  publication-title: Breast Cancer Res
– volume: 23
  start-page: 714
  year: 2014
  end-page: 724
  ident: b3
  article-title: Intrinsic subtypes from PAM50 gene expression assay in a population-based breast cancer cohort: differences by age, race, and tumor characteristics
  publication-title: Cancer Epidemiol Prevent Biomarkers
– volume: 26
  start-page: 139
  year: 2010
  end-page: 140
  ident: b33
  article-title: Edger: a bioconductor package for differential expression analysis of digital gene expression data
  publication-title: Bioinformatics
– volume: 3
  year: 2008
  ident: b14
  article-title: Serum microRNAs are promising novel biomarkers
  publication-title: PLoS One
– volume: 12
  start-page: 2825
  year: 2011
  ident: 10.1016/j.jcmds.2022.100042_b40
  article-title: Scikit-learn: Machine learning in python
  publication-title: J Mach Learn Res
– volume: 75
  year: 2022
  ident: 10.1016/j.jcmds.2022.100042_b31
  article-title: Cancer MiRNA biomarker classification based on improved generative adversarial network optimized with mayfly optimization algorithm
  publication-title: Biomed Signal Process Control
  doi: 10.1016/j.bspc.2022.103545
– volume: 133
  year: 2021
  ident: 10.1016/j.jcmds.2022.100042_b37
  article-title: EZcount: An all-in-one software for microRNA expression quantification from NGS sequencing data
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2021.104352
– volume: 26
  start-page: 139
  issue: 1
  year: 2010
  ident: 10.1016/j.jcmds.2022.100042_b33
  article-title: Edger: a bioconductor package for differential expression analysis of digital gene expression data
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btp616
– volume: 256
  year: 2020
  ident: 10.1016/j.jcmds.2022.100042_b46
  article-title: Diagnostic, prognostic, and therapeutic significance of miR-139-5p in cancers
  publication-title: Life Sciences
  doi: 10.1016/j.lfs.2020.117865
– volume: 172
  start-page: 191
  issue: 1
  year: 2018
  ident: 10.1016/j.jcmds.2022.100042_b8
  article-title: Molecular subtypes of screen-detected breast cancer
  publication-title: Breast Cancer Res Treat
  doi: 10.1007/s10549-018-4899-3
– volume: 42
  start-page: 1699
  issue: 5
  year: 2019
  ident: 10.1016/j.jcmds.2022.100042_b47
  article-title: MiR-139-3p suppresses the invasion and migration properties of breast cancer cells by targeting RAB1a
  publication-title: Oncol Rep
  doi: 10.1007/s12094-019-02103-0
– volume: 5
  start-page: 2929
  issue: 10
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b34
  article-title: Breast cancer intrinsic subtype classification, clinical use and future trends
  publication-title: Amer J Cancer Res
– start-page: 3121
  year: 2010
  ident: 10.1016/j.jcmds.2022.100042_b39
  article-title: The balanced accuracy and its posterior distribution
– volume: 490
  start-page: 61
  issue: 7418
  year: 2012
  ident: 10.1016/j.jcmds.2022.100042_b32
  article-title: Comprehensive molecular portraits of human breast tumours
  publication-title: Nature
  doi: 10.1038/nature11412
– volume: 84
  year: 2020
  ident: 10.1016/j.jcmds.2022.100042_b43
  article-title: Bioinformatic analysis and in vitro validation of let-7b and let-7c in breast cancer
  publication-title: Comput Biol Chem
  doi: 10.1016/j.compbiolchem.2019.107191
– start-page: 307
  year: 2012
  ident: 10.1016/j.jcmds.2022.100042_b29
  article-title: Random forest for bioinformatics
– volume: 2015
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b53
  article-title: The role of miR-378a in metabolism, angiogenesis, and muscle biology
  publication-title: Int J Endocrinol
  doi: 10.1155/2015/281756
– volume: 42
  start-page: D68
  issue: D1
  year: 2013
  ident: 10.1016/j.jcmds.2022.100042_b38
  article-title: MiRBase: annotating high confidence microRNAs using deep sequencing data
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkt1181
– volume: 41
  start-page: 3499
  issue: 10
  year: 2019
  ident: 10.1016/j.jcmds.2022.100042_b48
  article-title: MicroRNA expression patterns in oral squamous cell carcinoma: hsa-mir-99b-3p and hsa-mir-100-5p as novel prognostic markers for oral cancer
  publication-title: Head Neck
  doi: 10.1002/hed.25866
– volume: 15
  start-page: 827
  issue: 6
  year: 2013
  ident: 10.1016/j.jcmds.2022.100042_b9
  article-title: Quantification of circulating mirnas in plasma: effect of preanalytical and analytical parameters on their isolation and stability
  publication-title: J Mol Diagnost
  doi: 10.1016/j.jmoldx.2013.07.005
– volume: 45
  start-page: 5
  issue: 1
  year: 2001
  ident: 10.1016/j.jcmds.2022.100042_b27
  article-title: Random forests
  publication-title: Mach Learn
  doi: 10.1023/A:1010933404324
– volume: 3
  issue: 9
  year: 2008
  ident: 10.1016/j.jcmds.2022.100042_b14
  article-title: Serum microRNAs are promising novel biomarkers
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0003148
– volume: 20
  start-page: 273
  issue: 3
  year: 1995
  ident: 10.1016/j.jcmds.2022.100042_b26
  article-title: Support-vector networks
  publication-title: Mach Learn
  doi: 10.1023/A:1022627411411
– volume: 18
  start-page: 1
  issue: 1
  year: 2016
  ident: 10.1016/j.jcmds.2022.100042_b35
  article-title: Expression and methylation patterns partition luminal-A breast tumors into distinct prognostic subgroups
  publication-title: Breast Cancer Res
– volume: 27
  start-page: 1160
  issue: 8
  year: 2009
  ident: 10.1016/j.jcmds.2022.100042_b2
  article-title: Supervised risk predictor of breast cancer based on intrinsic subtypes
  publication-title: J Clin Oncol
  doi: 10.1200/JCO.2008.18.1370
– volume: 25
  start-page: 198
  issue: 2
  year: 2018
  ident: 10.1016/j.jcmds.2022.100042_b18
  article-title: Candidate mirnas in human breast cancer biomarkers: a systematic review
  publication-title: Breast Cancer
  doi: 10.1007/s12282-017-0814-8
– volume: 3
  issue: 7
  year: 2007
  ident: 10.1016/j.jcmds.2022.100042_b12
  article-title: Global and local architecture of the mammalian microRNA-transcription factor regulatory network
  publication-title: PLoS Comput Biol
  doi: 10.1371/journal.pcbi.0030131
– volume: 11
  start-page: 431
  issue: 3
  year: 2019
  ident: 10.1016/j.jcmds.2022.100042_b20
  article-title: Validation of mirnas as breast cancer biomarkers with a machine learning approach
  publication-title: Cancers
  doi: 10.3390/cancers11030431
– volume: 19
  start-page: 805
  issue: 8
  year: 2014
  ident: 10.1016/j.jcmds.2022.100042_b5
  article-title: Rare breast cancer subtypes: histological, molecular, and clinical peculiarities
  publication-title: Oncol
  doi: 10.1634/theoncologist.2014-0108
– volume: 54
  issue: 2
  year: 2021
  ident: 10.1016/j.jcmds.2022.100042_b41
  article-title: Essential functions of miR-125b in cancer
  publication-title: Cell Proliferation
  doi: 10.1111/cpr.12913
– volume: 77
  start-page: 3708
  issue: 13
  year: 2017
  ident: 10.1016/j.jcmds.2022.100042_b4
  article-title: Assessment of breast cancer risk factors reveals subtype heterogeneity
  publication-title: Cancer Res
  doi: 10.1158/0008-5472.CAN-16-2574
– volume: 17
  start-page: 313
  issue: 6
  year: 2011
  ident: 10.1016/j.jcmds.2022.100042_b17
  article-title: Microrna signatures: clinical biomarkers for the diagnosis and treatment of breast cancer
  publication-title: Trends Mol Med
  doi: 10.1016/j.molmed.2011.01.006
– volume: 12
  start-page: 1785
  issue: 7
  year: 2020
  ident: 10.1016/j.jcmds.2022.100042_b24
  article-title: Machine learning-based ensemble recursive feature selection of circulating mirnas for cancer tumor classification
  publication-title: Cancers
  doi: 10.3390/cancers12071785
– volume: 69
  start-page: 7459
  issue: 18
  year: 2009
  ident: 10.1016/j.jcmds.2022.100042_b42
  article-title: A risk variant in an miR-125b binding site in BMPR1B is associated with breast cancer pathogenesis
  publication-title: Cancer Res
  doi: 10.1158/0008-5472.CAN-09-1201
– volume: 16
  start-page: 1
  issue: 1
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b36
  article-title: Next generation sequencing profiling identifies miR-574-3p and miR-660-5p as potential novel prognostic markers for breast cancer
  publication-title: BMC Genomics
  doi: 10.1186/s12864-015-1899-0
– volume: 62
  start-page: 15
  issue: 1
  year: 2017
  ident: 10.1016/j.jcmds.2022.100042_b16
  article-title: Recent trends in microrna research into breast cancer with particular focus on the associations between micrornas and intrinsic subtypes
  publication-title: J Human Genetics
  doi: 10.1038/jhg.2016.89
– volume: 16
  issue: 11
  year: 2021
  ident: 10.1016/j.jcmds.2022.100042_b44
  article-title: Hsa-mir-21-3p associates with breast cancer patient survival and targets genes in tumor suppressive pathways
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0260327
– volume: 677
  start-page: 111
  year: 2018
  ident: 10.1016/j.jcmds.2022.100042_b23
  article-title: Tree-based machine learning algorithms identified minimal set of mirna biomarkers for breast cancer diagnosis and molecular subtyping
  publication-title: Gene
  doi: 10.1016/j.gene.2018.07.057
– volume: 23
  start-page: 714
  issue: 5
  year: 2014
  ident: 10.1016/j.jcmds.2022.100042_b3
  article-title: Intrinsic subtypes from PAM50 gene expression assay in a population-based breast cancer cohort: differences by age, race, and tumor characteristics
  publication-title: Cancer Epidemiol Prevent Biomarkers
  doi: 10.1158/1055-9965.EPI-13-1023
– volume: 131
  year: 2021
  ident: 10.1016/j.jcmds.2022.100042_b25
  article-title: Machine learning integrated ensemble of feature selection methods followed by survival analysis for predicting breast cancer subtype specific miRNA biomarkers
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2021.104244
– volume: 7
  year: 2019
  ident: 10.1016/j.jcmds.2022.100042_b52
  article-title: Role of miR-10b-5p in the prognosis of breast cancer
  publication-title: PeerJ
– volume: 44
  start-page: 1278
  issue: 7
  year: 2013
  ident: 10.1016/j.jcmds.2022.100042_b51
  article-title: Clinicopathologic significance of miR-10b expression in gastric carcinoma
  publication-title: Human Pathol
  doi: 10.1016/j.humpath.2012.10.014
– volume: 17
  issue: 348
  year: 2016
  ident: 10.1016/j.jcmds.2022.100042_b55
  article-title: How interacting pathways are regulated by miRNAs in breast cancer subtypes
  publication-title: BMC Bioinformatics
– volume: 435
  start-page: 834
  issue: 7043
  year: 2005
  ident: 10.1016/j.jcmds.2022.100042_b11
  article-title: MicroRNA expression profiles classify human cancers
  publication-title: Nature
  doi: 10.1038/nature03702
– volume: 314
  start-page: 1615
  issue: 15
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b7
  article-title: Benefits and harms of breast cancer screening: a systematic review
  publication-title: JAMA
  doi: 10.1001/jama.2015.13183
– start-page: 116
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b22
  article-title: Analysis of next-generation sequencing data of mirna for the prediction of breast cancer
– year: 2012
  ident: 10.1016/j.jcmds.2022.100042_b54
– volume: 486
  start-page: 346
  issue: 7403
  year: 2012
  ident: 10.1016/j.jcmds.2022.100042_b6
  article-title: The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups
  publication-title: Nature
  doi: 10.1038/nature10983
– volume: 13
  issue: 7
  year: 2018
  ident: 10.1016/j.jcmds.2022.100042_b19
  article-title: Genome-wide analysis of NGS data to compile cancer-specific panels of mirna biomarkers
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0200353
– volume: 14
  start-page: 2348
  issue: 11
  year: 2008
  ident: 10.1016/j.jcmds.2022.100042_b45
  article-title: MicroRNA miR-21 overexpression in human breast cancer is associated with advanced clinical stage, lymph node metastasis and patient poor prognosis
  publication-title: Rna
  doi: 10.1261/rna.1034808
– year: 2019
  ident: 10.1016/j.jcmds.2022.100042_b1
  article-title: Cancer statistics
  publication-title: CA: Cancer J Clin
– volume: 29
  start-page: 3853
  issue: 9
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b10
  article-title: Normalization panels for the reliable quantification of circulating microRNAs by RT-qPCR
  publication-title: FASEB J
  doi: 10.1096/fj.15-271312
– volume: 19
  start-page: A68
  issue: 1A
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b21
  article-title: The cancer genome atlas (TCGA): an immeasurable source of knowledge
  publication-title: Contem Oncol
– volume: 6
  issue: 6
  year: 2011
  ident: 10.1016/j.jcmds.2022.100042_b13
  article-title: Impact of cellular mirnas on circulating mirna biomarker signatures
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0020769
– start-page: 4765
  year: 2017
  ident: 10.1016/j.jcmds.2022.100042_b30
  article-title: A unified approach to interpreting model predictions
– volume: 15
  start-page: 41
  issue: 1
  year: 2018
  ident: 10.1016/j.jcmds.2022.100042_b28
  article-title: Applications of support vector machine (SVM) learning in cancer genomics
  publication-title: Cancer Genomics Proteomics
– volume: 5
  start-page: 545
  issue: 2
  year: 2015
  ident: 10.1016/j.jcmds.2022.100042_b49
  article-title: Role of miR-100 in the radioresistance of colorectal cancer cells
  publication-title: Amer J Cancer Res
– volume: 4
  start-page: 1
  issue: 1
  year: 2014
  ident: 10.1016/j.jcmds.2022.100042_b15
  article-title: Integrative investigation on breast cancer in ER, PR and HER2-defined subgroups using mRNA and mirna expression profiling
  publication-title: Sci Rep
  doi: 10.1038/srep06566
– volume: 12
  start-page: 1437
  issue: 12
  year: 2016
  ident: 10.1016/j.jcmds.2022.100042_b50
  article-title: MiR-99a and MiR-491 regulate cisplatin resistance in human gastric cancer cells by targeting CAPNS1
  publication-title: Int J Biol Sci
  doi: 10.7150/ijbs.16529
SSID ssj0002734695
Score 2.2386475
Snippet MicroRNAs (miRNAs) are short non-coding RNAs engaged in cellular regulation by suppressing genes at their post-transcriptional stage. Evidence of their...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 100042
SubjectTerms Breast cancer subtype
Feature importance
MiRNA biomarkers
Supervised classification
Title MicroRNA signature for interpretable breast cancer classification with subtype clue
URI https://dx.doi.org/10.1016/j.jcmds.2022.100042
Volume 3
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2772-4158
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002734695
  issn: 2772-4158
  databaseCode: DOA
  dateStart: 20210101
  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: 2772-4158
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002734695
  issn: 2772-4158
  databaseCode: M~E
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1NTxsxELUC7YELagUVUIp84JZulXh3vd4jooVeElUEJG4r22uLRGGJtgFx4h_wn5mx9yOBCBWkXlaRFTuJ58kevzy_IeRQM5vaSPEgdtQNHCoCYeDUKnpKCrzsGFvpik0kw6G4vEz_dDqP9V2Yu2lSFOL-Pp3911BDGwQbr86-IdzNoNAAryHo8ISww_OfAj9Aid3Z8KiL0gxn2-mkhONGXYh3pRRq0eco-dKm7GpMoVEz5NFQydaVo2f19HZZLdRmsL4iRM0mDhoDWG_7_FPOZb10tGRDXpqxqyIFuSusuw0bcFMY7eoLd0eAnoX_-pF0uaq64ALUSotOTSm1az9BUmh2s8hgwOG3UVp5Wu3F1Rpc_Rik_QFkF35xNivaquU7XLkReE5i8mOir3N0ZWcM9SA97-T1zGF7hOPisIy5FJmvkQ8siVNUCA4eWsoOnYC4q-PTfJHax8opBl981upcZyF_Of9ENquw0SMPmM-kY4otMqrBQhuwUAALXQIL9WChHix0GSwUwUIrsFAEyza5OPl1fvw7qMpsBBrN-lHjGPNEwi_XPE9s3_KIW56nqRI9q_O-NHlkhGQCzepECDuCTpNQ9wUPVU8qFX4h6wUAY4fQXAgdm1jLSMURVzmyAcraxMC2AYlxf5ewekIyXXnQYymUaVaLDSeZm8UMZzHzs7hLvjedZt6C5fW383qmsyqL9NlhBth4rePeezt-JRstrPfJ-ry8Nd_IR303H_8tDxzLc-CQ9ASD25o5
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=MicroRNA+signature+for+interpretable+breast+cancer+classification+with+subtype+clue&rft.jtitle=Journal+of+Computational+Mathematics+and+Data+Science&rft.au=Andreini%2C+Paolo&rft.au=Bonechi%2C+Simone&rft.au=Bianchini%2C+Monica&rft.au=Geraci%2C+Filippo&rft.date=2022-06-01&rft.pub=Elsevier+B.V&rft.issn=2772-4158&rft.eissn=2772-4158&rft.volume=3&rft_id=info:doi/10.1016%2Fj.jcmds.2022.100042&rft.externalDocID=S2772415822000116
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2772-4158&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2772-4158&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2772-4158&client=summon