Inferring feature importance with uncertainties with application to large genotype data
Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generatin...
Uloženo v:
| Vydáno v: | PLoS computational biology Ročník 19; číslo 3; s. e1010963 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
Public Library of Science
01.03.2023
Public Library of Science (PLoS) |
| Témata: | |
| ISSN: | 1553-7358, 1553-734X, 1553-7358 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley-value-based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published model-agnostic feature importance score of SAGE (Shapley additive global importance) and introduce Sub-SAGE. For tree-based models, it has the advantage that it can be estimated without computationally expensive resampling. We argue that for all model types the uncertainties in our Sub-SAGE estimator can be estimated using bootstrapping and demonstrate the approach for tree ensemble methods. The framework is exemplified on synthetic data as well as large genotype data for predicting feature importance with respect to obesity. |
|---|---|
| AbstractList | Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley-value-based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published model-agnostic feature importance score of SAGE (Shapley additive global importance) and introduce Sub-SAGE. For tree-based models, it has the advantage that it can be estimated without computationally expensive resampling. We argue that for all model types the uncertainties in our Sub-SAGE estimator can be estimated using bootstrapping and demonstrate the approach for tree ensemble methods. The framework is exemplified on synthetic data as well as large genotype data for predicting feature importance with respect to obesity. Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley-value-based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published model-agnostic feature importance score of SAGE (Shapley additive global importance) and introduce Sub-SAGE. For tree-based models, it has the advantage that it can be estimated without computationally expensive resampling. We argue that for all model types the uncertainties in our Sub-SAGE estimator can be estimated using bootstrapping and demonstrate the approach for tree ensemble methods. The framework is exemplified on synthetic data as well as large genotype data for predicting feature importance with respect to obesity.Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley-value-based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published model-agnostic feature importance score of SAGE (Shapley additive global importance) and introduce Sub-SAGE. For tree-based models, it has the advantage that it can be estimated without computationally expensive resampling. We argue that for all model types the uncertainties in our Sub-SAGE estimator can be estimated using bootstrapping and demonstrate the approach for tree ensemble methods. The framework is exemplified on synthetic data as well as large genotype data for predicting feature importance with respect to obesity. Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley-value-based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published model-agnostic feature importance score of SAGE (Shapley additive global importance) and introduce Sub-SAGE. For tree-based models, it has the advantage that it can be estimated without computationally expensive resampling. We argue that for all model types the uncertainties in our Sub-SAGE estimator can be estimated using bootstrapping and demonstrate the approach for tree ensemble methods. The framework is exemplified on synthetic data as well as large genotype data for predicting feature importance with respect to obesity. Artificial intelligence and machine learning have been increasingly popular tools for modelling complex relationships in medicine and genomics. For example a machine learning model for predicting the likelihood of a particular person developing some disease. The prediction model can for instance be based on genomics data, which consists of a large number of features for each single person. Such prediction models can be very complex and difficult to interpret, hence they are often denoted black-box models. However, to exploit the knowledge the prediction model has gained, we must be able to interpret it, and explain which features are important for the model, but also for the underlying data. We investigate a theoretical approach for extracting feature importance, even when the model input consists of many features. Lastly, we emphasize the need for estimating the uncertainty of the individual feature importance, and provide a bootstrap procedure for doing so. |
| Audience | Academic |
| Author | Strümke, Inga Langaas, Mette Riemer-Sørensen, Signe DeWan, Andrew Thomas Johnsen, Pål Vegard |
| AuthorAffiliation | 1 SINTEF DIGITAL, Oslo, Norway 5 Department of Chronic Disease Epidemiology and Center for Perinatal, Pediatric and Environmental Epidemiology, Yale School of Public Health, New Haven, Connecticut, United States of America 4 Department of Holistic Systems, SimulaMet, Oslo, Norway Pennsylvania State University, UNITED STATES 2 Department of Mathematical Sciences, Norwegian University of Science and Technology, Trondheim, Norway 3 Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway |
| AuthorAffiliation_xml | – name: 1 SINTEF DIGITAL, Oslo, Norway – name: 4 Department of Holistic Systems, SimulaMet, Oslo, Norway – name: 5 Department of Chronic Disease Epidemiology and Center for Perinatal, Pediatric and Environmental Epidemiology, Yale School of Public Health, New Haven, Connecticut, United States of America – name: 2 Department of Mathematical Sciences, Norwegian University of Science and Technology, Trondheim, Norway – name: Pennsylvania State University, UNITED STATES – name: 3 Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway |
| Author_xml | – sequence: 1 givenname: Pål Vegard orcidid: 0000-0002-2599-7914 surname: Johnsen fullname: Johnsen, Pål Vegard – sequence: 2 givenname: Inga orcidid: 0000-0003-1820-6544 surname: Strümke fullname: Strümke, Inga – sequence: 3 givenname: Mette orcidid: 0000-0002-5714-0288 surname: Langaas fullname: Langaas, Mette – sequence: 4 givenname: Andrew Thomas surname: DeWan fullname: DeWan, Andrew Thomas – sequence: 5 givenname: Signe orcidid: 0000-0002-5308-7651 surname: Riemer-Sørensen fullname: Riemer-Sørensen, Signe |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36917581$$D View this record in MEDLINE/PubMed |
| BookMark | eNqVkltv1DAQhSNURC_wDxBE4gUedvEtccILqiouK1UgQSUerYkzSb3K2sF2gP57vN206lYVEslDJpNvjjNH5zg7sM5ilj2nZEm5pG_XbvIWhuWoG7OkhJK65I-yI1oUfCF5UR3cqQ-z4xDWhKSyLp9kh7ysqSwqepT9WNkOvTe2zzuEOHnMzWZ0PoLVmP828TKfUpXejY0Gw64F4zgYDdE4m0eXD-B7zHu0Ll6NmLcQ4Wn2uIMh4LP5eZJdfPxwcfZ5cf710-rs9Hyhy5LFRdugKDpdgJSU0oITILpAkCixbgvZCGg0F6LmZSOYpJVgXJalThgwTQk_yV7uZMfBBTVbEhSrCCMlr2qeiNWOaB2s1ejNBvyVcmDUdcP5XoGPRg-oCCuQcIKQvBEN5TUVuk4X69q2pm2btN7Pp03NBluNNnoY9kT3v1hzqXr3S9FkfcUqmRRezwre_ZwwRLUxQeMwgEU3pR-XVVlRxsot-uoe-vB6M9VD2sDYzqWD9VZUnUohpKCU00QtH6DS3eLG6JSrzqT-3sCbvYHERPwTe5hCUKvv3_6D_bLPvrjr4K11N4FMgNgB2rsQPHa3CCVqm_sbF9Q292rOfRp7d29Mm3idz7SoGf49_Bdhegi4 |
| CitedBy_id | crossref_primary_10_1007_s10867_023_09640_4 crossref_primary_10_1016_j_jad_2024_10_019 crossref_primary_10_1007_s00439_025_02768_4 |
| Cites_doi | 10.1002/sim.6082 10.1038/nature14177 10.1038/35075590 10.1038/hdy.2010.91 10.1038/s42003-022-03812-z 10.1038/s41591-019-0563-7 10.1038/s41588-020-0622-5 10.1038/s41588-018-0184-y 10.1186/s12859-021-04041-7 10.1145/2939672.2939785 10.1007/s10115-013-0679-x 10.1038/s41576-018-0018-x 10.1214/12-EJS710 10.1007/978-0-387-84858-7 10.1162/0899766041336387 10.1080/01621459.1987.10478410 10.1161/CIRCRESAHA.116.305697 10.1002/9781118555552 10.1137/15M1048070 10.1007/BF01769885 10.21105/joss.02027 10.1038/s42256-020-00236-4 10.1016/j.ajhg.2017.06.005 10.7717/peerj-cs.582 10.1371/journal.pmed.1001779 10.1038/s41586-021-03205-y 10.1093/bioinformatics/btv153 10.1038/s41586-018-0579-z 10.1038/s42256-019-0138-9 |
| ContentType | Journal Article |
| Copyright | Copyright: © 2023 Johnsen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. COPYRIGHT 2023 Public Library of Science 2023 Johnsen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 Johnsen et al 2023 Johnsen et al |
| Copyright_xml | – notice: Copyright: © 2023 Johnsen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. – notice: COPYRIGHT 2023 Public Library of Science – notice: 2023 Johnsen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 Johnsen et al 2023 Johnsen et al |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM ISN ISR 3V. 7QO 7QP 7TK 7TM 7X7 7XB 88E 8AL 8FD 8FE 8FG 8FH 8FI 8FJ 8FK ABUWG AEUYN AFKRA ARAPS AZQEC BBNVY BENPR BGLVJ BHPHI CCPQU DWQXO FR3 FYUFA GHDGH GNUQQ HCIFZ JQ2 K7- K9. LK8 M0N M0S M1P M7P P5Z P62 P64 PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI Q9U RC3 7X8 5PM DOA |
| DOI | 10.1371/journal.pcbi.1010963 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Gale In Context: Canada Gale In Context: Science ProQuest Central (Corporate) Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Neurosciences Abstracts Nucleic Acids Abstracts ProQuest Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Computing Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability (subscription) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials Biological Science Database (Proquest) ProQuest Central Technology collection Natural Science Collection ProQuest One Community College ProQuest Central Engineering Research Database Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database ProQuest Health & Medical Complete (Alumni) Biological Sciences Computing Database Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) Biological Science Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Biotechnology and BioEngineering Abstracts ProQuest Central Premium ProQuest One Academic ProQuest Publicly Available Content ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central Basic Genetics Abstracts 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) Publicly Available Content Database Computer Science Database ProQuest Central Student ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Nucleic Acids Abstracts SciTech Premium Collection ProQuest One Applied & Life Sciences ProQuest One Sustainability Health Research Premium Collection Natural Science Collection Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) Advanced Technologies & Aerospace Collection ProQuest Biological Science Collection ProQuest One Academic Eastern Edition ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) Biological Science Database Neurosciences Abstracts ProQuest Hospital Collection (Alumni) Biotechnology and BioEngineering Abstracts ProQuest Health & Medical Complete ProQuest One Academic UKI Edition Engineering Research Database ProQuest One Academic Calcium & Calcified Tissue Abstracts ProQuest One Academic (New) Technology Collection Technology Research Database ProQuest One Academic Middle East (New) ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central ProQuest Health & Medical Research Collection Genetics Abstracts Biotechnology Research Abstracts Health and Medicine Complete (Alumni Edition) ProQuest Central Korea ProQuest Computing ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest SciTech Collection Advanced Technologies & Aerospace Database ProQuest Medical Library ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic CrossRef Publicly Available Content Database |
| 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: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| DocumentTitleAlternate | Inferring feature importance with uncertainties |
| EISSN | 1553-7358 |
| ExternalDocumentID | 2802063893 oai_doaj_org_article_025e030ea1754b13914c99992fdd91dd PMC10038287 A744741131 36917581 10_1371_journal_pcbi_1010963 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GeographicLocations | Norway United Kingdom--UK |
| GeographicLocations_xml | – name: Norway – name: United Kingdom--UK |
| GrantInformation_xml | – fundername: ; grantid: 272402 |
| GroupedDBID | --- 123 29O 2WC 53G 5VS 7X7 88E 8FE 8FG 8FH 8FI 8FJ AAFWJ AAKPC AAUCC AAWOE AAYXX ABDBF ABUWG ACCTH ACGFO ACIHN ACIWK ACPRK ACUHS ADBBV AEAQA AENEX AEUYN AFFHD AFKRA AFPKN AFRAH AHMBA ALMA_UNASSIGNED_HOLDINGS AOIJS ARAPS AZQEC B0M BAIFH BAWUL BBNVY BBTPI BCNDV BENPR BGLVJ BHPHI BPHCQ BVXVI BWKFM CCPQU CITATION CS3 DIK DWQXO E3Z EAP EAS EBD EBS EJD EMK EMOBN ESX F5P FPL FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HMCUK HYE IAO IGS INH INR ISN ISR ITC J9A K6V K7- KQ8 LK8 M1P M48 M7P O5R O5S OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO PV9 RNS RPM RZL SV3 TR2 TUS UKHRP WOW XSB ~8M 3V. ADRAZ ALIPV C1A CGR CUY CVF ECM EIF H13 IPNFZ M0N M~E NPM PGMZT RIG WOQ 7QO 7QP 7TK 7TM 7XB 8AL 8FD 8FK FR3 JQ2 K9. P64 PKEHL PQEST PQUKI Q9U RC3 7X8 5PM AAPBV ABPTK N95 UMP |
| ID | FETCH-LOGICAL-c662t-dbe45fc5a77111530a0c5ea7e7e9d57b4abc344936b42718423766c0a0a2c103 |
| IEDL.DBID | FPL |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000949868800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1553-7358 1553-734X |
| IngestDate | Sun May 07 16:29:17 EDT 2023 Fri Oct 03 12:42:33 EDT 2025 Tue Nov 04 02:07:50 EST 2025 Sun Nov 09 13:28:16 EST 2025 Sat Nov 29 15:02:35 EST 2025 Tue Nov 11 11:12:27 EST 2025 Tue Nov 04 18:38:40 EST 2025 Wed Nov 26 11:27:09 EST 2025 Wed Nov 26 11:31:20 EST 2025 Wed Feb 19 02:24:48 EST 2025 Tue Nov 18 22:19:01 EST 2025 Sat Nov 29 02:56:00 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | Copyright: © 2023 Johnsen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Creative Commons Attribution License |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c662t-dbe45fc5a77111530a0c5ea7e7e9d57b4abc344936b42718423766c0a0a2c103 |
| Notes | new_version ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 The authors declare that they have no competing interests. |
| ORCID | 0000-0002-5714-0288 0000-0002-2599-7914 0000-0002-5308-7651 0000-0003-1820-6544 |
| OpenAccessLink | http://dx.doi.org/10.1371/journal.pcbi.1010963 |
| PMID | 36917581 |
| PQID | 2802063893 |
| PQPubID | 1436340 |
| PageCount | e1010963 |
| ParticipantIDs | plos_journals_2802063893 doaj_primary_oai_doaj_org_article_025e030ea1754b13914c99992fdd91dd pubmedcentral_primary_oai_pubmedcentral_nih_gov_10038287 proquest_miscellaneous_2786812267 proquest_journals_2802063893 gale_infotracmisc_A744741131 gale_infotracacademiconefile_A744741131 gale_incontextgauss_ISR_A744741131 gale_incontextgauss_ISN_A744741131 pubmed_primary_36917581 crossref_primary_10_1371_journal_pcbi_1010963 crossref_citationtrail_10_1371_journal_pcbi_1010963 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-03-01 |
| PublicationDateYYYYMMDD | 2023-03-01 |
| PublicationDate_xml | – month: 03 year: 2023 text: 2023-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: San Francisco – name: San Francisco, CA USA |
| PublicationTitle | PLoS computational biology |
| PublicationTitleAlternate | PLoS Comput Biol |
| PublicationYear | 2023 |
| Publisher | Public Library of Science Public Library of Science (PLoS) |
| Publisher_xml | – name: Public Library of Science – name: Public Library of Science (PLoS) |
| References | HP Young (pcbi.1010963.ref022) 1985; 14 DE Reich (pcbi.1010963.ref031) 2001; 411 MJ Sillanpää (pcbi.1010963.ref032) 2011; 106 pcbi.1010963.ref028 J Jiménez-Luna (pcbi.1010963.ref001) 2020; 2 J Grau (pcbi.1010963.ref033) 2015; 31 K Aas (pcbi.1010963.ref003) 2021; 298 E Strumbelj (pcbi.1010963.ref008) 2010; 11 F Huettner (pcbi.1010963.ref023) 2012; 6 SM Lundberg (pcbi.1010963.ref004) 2020; 2 E Song (pcbi.1010963.ref012) 2016; 4 T Karlsson (pcbi.1010963.ref034) 2019; 25 NE Karoui (pcbi.1010963.ref038) 2018; 19 E Strumbelj (pcbi.1010963.ref007) 2013; 41 JJ Goeman (pcbi.1010963.ref030) 2014; 33 C Sudlow (pcbi.1010963.ref019) 2015; 12 PM Visscher (pcbi.1010963.ref029) 2017; 101 DV Fryer (pcbi.1010963.ref016) 2021; 7 I Covert (pcbi.1010963.ref017) 2020 N Moehle (pcbi.1010963.ref013) 2021 M Elgart (pcbi.1010963.ref041) 2022; 5 SM Lundberg (pcbi.1010963.ref009) 2019 T Hastie (pcbi.1010963.ref026) 2009 B Efron (pcbi.1010963.ref027) 1987; 82 A Torkamani (pcbi.1010963.ref040) 2018; 19 A Keinan (pcbi.1010963.ref015) 2003; 16 W Zhou (pcbi.1010963.ref024) 2018; 50 PV Johnsen (pcbi.1010963.ref025) 2021; 22 GH Givens (pcbi.1010963.ref039) 2012 D Taliun (pcbi.1010963.ref036) 2021; 590 N Sellereite (pcbi.1010963.ref005) 2019; 5 A Redelmeier (pcbi.1010963.ref010) 2020 I Covert (pcbi.1010963.ref014) 2020 LS Shapley (pcbi.1010963.ref002) 1953; Volume II Y Kwon (pcbi.1010963.ref011) 2021 JE Hall (pcbi.1010963.ref037) 2015; 116 D Fryer (pcbi.1010963.ref018) 2021 SM Lundberg (pcbi.1010963.ref006) 2017 AE Locke (pcbi.1010963.ref021) 2015; 518 C Bycroft (pcbi.1010963.ref020) 2018; 562 SA Gagliano Taliun (pcbi.1010963.ref035) 2020; 52 |
| References_xml | – year: 2020 ident: pcbi.1010963.ref014 publication-title: Explaining by Removing: A Unified Framework for Model Explanation – year: 2021 ident: pcbi.1010963.ref018 publication-title: Shapley values for feature selection: The good, the bad, and the axioms – volume: 33 start-page: 1946 issue: 11 year: 2014 ident: pcbi.1010963.ref030 article-title: Multiple hypothesis testing in genomics publication-title: Statistics in Medicine doi: 10.1002/sim.6082 – volume: 518 start-page: 197 issue: 7538 year: 2015 ident: pcbi.1010963.ref021 article-title: Genetic studies of body mass index yield new insights for obesity biology publication-title: Nature doi: 10.1038/nature14177 – volume: 411 start-page: 199 year: 2001 ident: pcbi.1010963.ref031 article-title: Linkage disequilibrium in the human genome publication-title: Nature doi: 10.1038/35075590 – volume: 106 start-page: 511 issue: 4 year: 2011 ident: pcbi.1010963.ref032 article-title: Overview of techniques to account for confounding due to population stratification and cryptic relatedness in genomic data association analyses publication-title: Heredity doi: 10.1038/hdy.2010.91 – volume: 5 start-page: 1 issue: 1 year: 2022 ident: pcbi.1010963.ref041 article-title: Non-linear machine learning models incorporating SNPs and PRS improve polygenic prediction in diverse human populations publication-title: Communications Biology doi: 10.1038/s42003-022-03812-z – volume: 25 start-page: 1390 issue: 9 year: 2019 ident: pcbi.1010963.ref034 article-title: Contribution of genetics to visceral adiposity and its relation to cardiovascular and metabolic disease publication-title: Nature medicine doi: 10.1038/s41591-019-0563-7 – volume: 19 start-page: 66 year: 2018 ident: pcbi.1010963.ref038 article-title: Can We Trust the Bootstrap in High-dimensions? The Case of Linear Models publication-title: Journal of Machine Learning Research – volume: 52 issue: 6 year: 2020 ident: pcbi.1010963.ref035 article-title: Exploring and visualizing large-scale genetic associations by using PheWeb publication-title: Nature Genetics doi: 10.1038/s41588-020-0622-5 – year: 2020 ident: pcbi.1010963.ref017 publication-title: Understanding Global Feature Contributions With Additive Importance Measures – volume: 50 issue: 9 year: 2018 ident: pcbi.1010963.ref024 article-title: Efficiently controlling for case-control imbalance and sample relatedness in large-scale genetic association studies publication-title: Nature Genetics doi: 10.1038/s41588-018-0184-y – year: 2021 ident: pcbi.1010963.ref013 publication-title: Portfolio Performance Attribution via Shapley Value – volume: 22 issue: 1 year: 2021 ident: pcbi.1010963.ref025 article-title: A new method for exploring gene–gene and gene–environment interactions in GWAS with tree ensemble methods and SHAP values publication-title: BMC Bioinformatics doi: 10.1186/s12859-021-04041-7 – ident: pcbi.1010963.ref028 doi: 10.1145/2939672.2939785 – volume: 41 start-page: 647 year: 2013 ident: pcbi.1010963.ref007 article-title: Explaining prediction models and individual predictions with feature contributions publication-title: Knowledge and Information Systems doi: 10.1007/s10115-013-0679-x – volume: 19 start-page: 581 issue: 9 year: 2018 ident: pcbi.1010963.ref040 article-title: The personal and clinical utility of polygenic risk scores publication-title: Nature Reviews Genetics doi: 10.1038/s41576-018-0018-x – volume: 6 start-page: 1239 year: 2012 ident: pcbi.1010963.ref023 article-title: Axiomatic arguments for decomposiing goodness of fit according to Shapley and Owen values publication-title: Electronic Journal of Statistics doi: 10.1214/12-EJS710 – year: 2019 ident: pcbi.1010963.ref009 publication-title: Consistent Individualized Feature Attribution for Tree Ensembles – start-page: 223 volume-title: The Elements of Statistical Learning year: 2009 ident: pcbi.1010963.ref026 doi: 10.1007/978-0-387-84858-7 – volume: 16 start-page: 1887 year: 2003 ident: pcbi.1010963.ref015 article-title: Fair Attribution of Functional Contribution in Artificial and Biological Networks publication-title: Neural Computation doi: 10.1162/0899766041336387 – volume: 82 start-page: 171 issue: 397 year: 1987 ident: pcbi.1010963.ref027 article-title: Better Bootstrap Confidence Intervals publication-title: Journal of the American Statistical Association doi: 10.1080/01621459.1987.10478410 – volume: 116 start-page: 991 issue: 6 year: 2015 ident: pcbi.1010963.ref037 article-title: Obesity-Induced Hypertension publication-title: Circulation Research doi: 10.1161/CIRCRESAHA.116.305697 – start-page: 4765 volume-title: Advances in Neural Information Processing Systems 30 year: 2017 ident: pcbi.1010963.ref006 – volume: 11 start-page: 1 year: 2010 ident: pcbi.1010963.ref008 article-title: An Efficient Explanation of Individual Classifications using Game Theory publication-title: Journal of Machine Learning Research – start-page: 287 volume-title: Computational Statistics year: 2012 ident: pcbi.1010963.ref039 doi: 10.1002/9781118555552 – year: 2020 ident: pcbi.1010963.ref010 publication-title: Explaining predictive models with mixed features using Shapley values and conditional inference trees – volume: 4 start-page: 1060 year: 2016 ident: pcbi.1010963.ref012 article-title: Shapley Effects for Global Sensitivity Analysis: Theory and Computation publication-title: SIAM/ASA Journal on Uncertainty Quantification doi: 10.1137/15M1048070 – volume: 14 start-page: 65 year: 1985 ident: pcbi.1010963.ref022 article-title: Monotonic solutions of cooperative games publication-title: International Journal of Game Theory doi: 10.1007/BF01769885 – volume: 5 start-page: 2027 issue: 46 year: 2019 ident: pcbi.1010963.ref005 article-title: shapr: An R-package for explaining machine learning models with dependence-aware Shapley values publication-title: Journal of Open Source Software doi: 10.21105/joss.02027 – volume: 2 start-page: 573 issue: 10 year: 2020 ident: pcbi.1010963.ref001 article-title: Drug discovery with explainable artificial intelligence publication-title: Nature Machine Intelligence doi: 10.1038/s42256-020-00236-4 – volume: 101 start-page: 5 issue: 1 year: 2017 ident: pcbi.1010963.ref029 article-title: 10 Years of GWAS Discovery: Biology, Function, and Translation publication-title: American Journal of Human Genetics doi: 10.1016/j.ajhg.2017.06.005 – volume: 7 start-page: e582 year: 2021 ident: pcbi.1010963.ref016 article-title: Model independent feature attributions: Shapley values that uncover non-linear dependencies publication-title: PeerJ Computer Science doi: 10.7717/peerj-cs.582 – volume: 12 start-page: e1001779 issue: 3 year: 2015 ident: pcbi.1010963.ref019 article-title: UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age publication-title: PLoS medicine doi: 10.1371/journal.pmed.1001779 – volume: 590 start-page: 290 issue: 7845 year: 2021 ident: pcbi.1010963.ref036 article-title: Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program publication-title: Nature doi: 10.1038/s41586-021-03205-y – volume: 31 start-page: 2595 issue: 15 year: 2015 ident: pcbi.1010963.ref033 article-title: PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R publication-title: Bioinformatics doi: 10.1093/bioinformatics/btv153 – volume: 562 start-page: 203 issue: 7726 year: 2018 ident: pcbi.1010963.ref020 article-title: The UK Biobank resource with deep phenotyping and genomic data publication-title: Nature doi: 10.1038/s41586-018-0579-z – volume: Volume II year: 1953 ident: pcbi.1010963.ref002 article-title: A Value for n-Person Games publication-title: Contributions to the Theory of Games (AM-28) – year: 2021 ident: pcbi.1010963.ref011 publication-title: Efficient computation and analysis of distributional Shapley values – volume: 298 year: 2021 ident: pcbi.1010963.ref003 article-title: Explaining individual predictions when features are dependent: More accurate approximations to Shapley values publication-title: Artificial Intelligence – volume: 2 issue: 1 year: 2020 ident: pcbi.1010963.ref004 article-title: From local explanations to global understanding with explainable AI for trees publication-title: Nature Machine Intelligence doi: 10.1038/s42256-019-0138-9 |
| SSID | ssj0035896 |
| Score | 2.4237244 |
| Snippet | Estimating feature importance, which is the contribution of a prediction or several predictions due to a feature, is an essential aspect of explaining... |
| SourceID | plos doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | e1010963 |
| SubjectTerms | Artificial intelligence Biobanks Biology and Life Sciences Computer and Information Sciences Confidence intervals Decomposition Engineering and Technology Estimation theory Expected values Game theory Genotype Genotype & phenotype Genotypes Genotyping Techniques Machine learning Neural networks Obesity Physical Sciences Random variables Resampling Research and Analysis Methods Synthetic data Tree structures (Computers) Uncertainty Values |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3di9QwEA-yKPgien7c6nlEEXyqt2nSpnk8xeMOjkX0wH0L-aou7LXLdVfwv3cm6ZatnNyLr820JTOT-UgmvyHkHaTRilmOV5SZyYSyZVaVTmYKOyNFfPAk6Us5n1eLhfqy1-oLa8ISPHBi3An45ACKGAz4OWEhXmHCQVCj8tp7xbxH6wtRzy6ZSjaYF1XszIVNcTLJxaK_NMclO-ll9GHt7BJzV4jh-cgpRez-wUJP1qu2uy38_LuKcs8tnT0mj_p4kp6meTwh90JzQB6kDpO_n5LvF3ihD_fuaB0ihiddXseQG4RNcROWgmNLZQEIrZoe7Z1q001LV1gtThHNFTdsKRaVPiNXZ5-vPp1nfS-FzJVlvsm8DaKoXWGkBOtW8JmZuSIYGWRQvpBWGOu4EIqXVuTgr2K1TOmAzOSOzfhzMmnaJhwSqizzRuW-wAbizBlrfHA1MwHWs3V5MSV8x0vtepxxbHex0vHwTEK-kVijUQK6l8CUZMNb64SzcQf9RxTTQIso2fEB6I7udUffpTtT8haFrBEHo8FCmx9m23X64ttcn0ohINhinP2T6OuI6H1PVLcwWWf6yw3AMsTXGlEejShhNbvR8CEq3G7Onc4rCOhjWAlv7pTw9uE3wzB-FIvnmtBugUZWiDKXl3JKXiSdHfjGS8jXiwr-W420ecTY8Uiz_BlhyBmeKkPC_fJ_iOIVeQi2gafqviMy2dxsw2ty3_3aLLub47i4_wA1U1Eh priority: 102 providerName: Directory of Open Access Journals – databaseName: Computer Science Database dbid: K7- link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwELaggMSF97KFBQWExCls_UicnNCCWLECVQhWojfLryyVSlKaFol_z4zjhA1a4MA1nqS1Zzwvj78h5BmE0SU1HK8oU52K0uRpkVuZltgZKeCDd5x-L-fzYrEoP8SEWxvLKnudGBS1ayzmyA9ZAY5NMK8v199S7BqFp6uxhcZlcoUyRlHO38m018Q8K0J_LmyNk0ouFvHqHJf0MHLqxdqaJUaw4MnzkWkKCP6Dnp6sV017kRP6ey3lOeN0fPN_p3WL3IhuaXLUydFtcsnXd8i1rlHlj7vk8wneC8QUYFL5AAWaLL8Gzx1kJsFcbgL2sasuQITW7tG5w_Fk2yQrLDpPEBQW874J1qbeI6fHb05fv01jS4bU5jnbps54kVU201KCksz4TM9s5rX00pcuk0ZoY7kQJc-NYGD2QtFNboFMM0tnfI9M6qb2-yQpDXW6ZC7DPuTUaqOdtxXVHtSCsSybEt4zQ9kIV45dM1YqnMFJCFu6pVHIQhVZOCXp8Na6g-v4B_0r5PNAi2Db4UGzOVNx7ypwCz3oQq_B1RIGXGYqLPjVJaucK6lzU_IUpUQhnEaN9Tpnete26uTTXB1JIcBno5z-kejjiOh5JKoamKzV8Y4ELBnCdI0oD0aUoBTsaHgfJbafc6t-yRm82UvixcNPhmH8KNbg1b7ZAY0sEKyO5XJK7ndCP6wbzyHszwr43WK0HUYLOx6pl18CmjnFw2mI2x_8_X89JNdBefCu_O-ATLabnX9Ertrv22W7eRz2_U89j1-Q priority: 102 providerName: ProQuest |
| Title | Inferring feature importance with uncertainties with application to large genotype data |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/36917581 https://www.proquest.com/docview/2802063893 https://www.proquest.com/docview/2786812267 https://pubmed.ncbi.nlm.nih.gov/PMC10038287 https://doaj.org/article/025e030ea1754b13914c99992fdd91dd http://dx.doi.org/10.1371/journal.pcbi.1010963 |
| Volume | 19 |
| WOSCitedRecordID | wos000949868800001&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: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: DOA dateStart: 20050101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: AAdvanced Technologies & Aerospace Database (subscription) customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: P5Z dateStart: 20050601 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: M7P dateStart: 20050601 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: K7- dateStart: 20050601 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central - New (Subscription) customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: BENPR dateStart: 20050601 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Proquest Health and Medical Complete customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: 7X7 dateStart: 20050601 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: PIMPY dateStart: 20050601 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVATS databaseName: Public Library of Science (PLoS) Journals Open Access customDbUrl: eissn: 1553-7358 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0035896 issn: 1553-7358 databaseCode: FPL dateStart: 20050101 isFulltext: true titleUrlDefault: http://www.plos.org/publications/ providerName: Public Library of Science |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwELZYBxIv_IYVRhUQEk9hdZzY8eOGVlExqmhMovBi2Y4DlUpSLS0S_z13ThqWaRXixQ_xuU3OZ_s7-_wdIW_AjZbUMLyiTHUYS8PDlFsRSsyM5PnBm54-E7NZOp_L7K-jeO0Enwl61Or03cqaBfqagLnZHtmPGOcYwjXJzrYzL0tSydvrcbta9pYfz9LfzcWD1bKqbwKa1-MlryxAk_v_--oPyL0WagbHjW08JLdc-YjcaZJP_n5Mvkzxrh9u6wWF8_SeweKnR-NgBwHuzwaw5jURA8i62jy6cuAdrKtgiYHkARK94l5ugPGmT8jF5PTi_YewTbMQWs6jdZgbFyeFTbQQMPElbKzHNnFaOOFknggTa2NZHEvGTRzBUuYDabgFMR1ZOmZPyaCsSndAAmlormWUJ5hbnFptdO5sQbWDoW5slAwJ2ypf2ZaCHDNhLJU_VxPgijSqUagx1WpsSMKu1aqh4PiH_An2ayeLBNr-AXSNasejAqjnYH5zGuBTbAAG09gCVpZRkeeS5vmQvEarUEiRUWIMzne9qWs1_TxTxyKOAYdRRncKnfeE3rZCRQUfa3V77wFUhtRbPcnDniQMdNurPkAL3X5zraIUsL5HnNBya7U3V7_qqvFHMa6udNUGZESKBHQRF0PyrDHyTm-MgyufpPC_ac_8e4rt15SLH56hnOKBM_jiz3e_8gtyFyYD1oTzHZLB-nLjXpLb9td6UV-OyJ6YC1-mI7J_cjrLzkd-u2TkRzyUH0U4wkDdDMos-QZS2fRT9vUPPzJU1A |
| linkProvider | Public Library of Science |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELaWAoILb9jCAgaBOIWt4ySODwgtj9VWWyoElejNsh13qVSS0rSg_VH8R2acBxu0wGkPXONJWo_naY-_IeQJpNGSGY5XlJkOImmSIE2sCCR2RvL44NVKj8R4nE6n8v0W-dHchcGyysYmekOdFRb3yHfDFAIb715fLr8G2DUKT1ebFhqVWBy64--QspUvhm9gfZ-G4f7byeuDoO4qENgkCddBZlwUz2yshQA9j_lAD2zstHDCySwWJtLG8iiSPDFRCJbb140kFsh0aNmAw2fPkfNgxgVWkIlpm9_xOPXtwLATTyB4NK1v6nHBdmvBeL60Zo4JMyQOvOMJfcOA1i30louiPC3m_b1084Qv3L_6n3HxGrlSB910r9KS62TL5TfIxaoN5_FN8mmItx5xg5POnAc6pfMvPi8BjaC4U03B-1e1E4g_Wz06cfRP1wVdYEk9Rchb3NWmWHl7i0zOYlK3SS8vcrdNqDQs0zLMYuyyzqw2OnN2xrQDo2dsGPcJb9Ze2RqMHXuCLJQ_YRSQlFWsUSgxqpaYPgnat5YVGMk_6F-hWLW0CCXuHxSrI1VbJgVBrwNL7zQEkpGBhIBFFrIGGc6yTLIs65PHKJQKwUJyrEY60puyVMOPY7UnoggiUsbZH4k-dIie1USzAiZrdX0DBFiGIGQdyp0OJZg82xneRgVp5lyqX2INbzaCf_rwo3YYP4oVhrkrNkAjUoTiCxPRJ3cqHWv5xhMJzEnhd9OO9nUY2x3J5589VjvDo_cwFXf__r8ekksHk3cjNRqOD--Ry2AmeVXouEN669XG3ScX7Lf1vFw98CaHEnXGyvkTMiq6XA |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELaW8hAX3rCFBQwCcQqt7SRODggtLBXVrqoKVqLai-U4zlKpJKVpQfvT-HfMOA82aIHTHrjGk4cn87TH3xDyDNLomCUCjygz7flxEnpRaKQXY2ckhw9e_ekDOZlEs1k83SI_mrMwWFbZ2ERnqNPC4Br5gEcQ2Dj3Osjqsojp3uj18quHHaRwp7Vpp1GJyL49-Q7pW_lqvAf_-jnno3eHb997dYcBz4QhX3tpYv0gM4GWEnQ-EEM9NIHV0kobp4FMfJ0Y4fuxCBOfgxV3NSShATLNDRsKeOwFclFCiol53zQ4apyACCLXGgy78nhS-LP61J6QbFALyculSeaYPEMSITpe0TUPaF1Eb7koyrPi39_LOE_5xdH1_5ijN8i1Ohinu5X23CRbNr9FLlftOU9uk09jPA2JC580sw4Alc6_uHwFNIXiCjaFqKCqqUBc2urSqZIAui7oAkvtKULh4mo3xYrcO-TwPCZ1l_TyIrfbhMYJS3XM0wC7rzOjE51akzFtwRgmhgd9Iho5UKYGacdeIQvldh4lJGsVaxRKj6qlp0-89q5lBVLyD_o3KGItLUKMuwvF6ljVFktBMGzBA1gNAaafQKLAfAPZRMyzNI1ZmvbJUxRQhSAiOQrPsd6UpRp_nKhd6fsQqTLB_kj0oUP0oibKCpis0fXJEGAZgpN1KHc6lGAKTWd4G5WlmXOpfok43NkowdnDT9phfChWHua22ACNjBCij4eyT-5V-tbyTYQxMCeC90YdTewwtjuSzz87DHeGW_I8kvf__l2PyRXQSXUwnuw_IFfBeoqq_nGH9NarjX1ILplv63m5euSsDyXqnHXzJ2Vfw08 |
| 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=Inferring+feature+importance+with+uncertainties+with+application+to+large+genotype+data&rft.jtitle=PLoS+computational+biology&rft.au=Johnsen%2C+P%C3%A5l+Vegard&rft.au=Str%C3%BCmke%2C+Inga&rft.au=Langaas%2C+Mette&rft.au=DeWan%2C+Andrew+Thomas&rft.date=2023-03-01&rft.pub=Public+Library+of+Science&rft.issn=1553-734X&rft.eissn=1553-7358&rft.volume=19&rft.issue=3&rft_id=info:doi/10.1371%2Fjournal.pcbi.1010963&rft_id=info%3Apmid%2F36917581&rft.externalDocID=PMC10038287 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1553-7358&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1553-7358&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1553-7358&client=summon |