Evolutionary Optimization of Kernel Weights Improves Protein Complex Comembership Prediction
In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based cla...
Uložené v:
| Vydané v: | IEEE/ACM transactions on computational biology and bioinformatics Ročník 6; číslo 3; s. 427 - 437 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
IEEE
01.07.2009
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 1545-5963, 1557-9964, 1557-9964 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy. |
|---|---|
| AbstractList | In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy.In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy. In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. |
| Author | de Ridder, D. Hulsman, M. Reinders, M.J.T. |
| Author_xml | – sequence: 1 givenname: M. surname: Hulsman fullname: Hulsman, M. organization: Inf. & Commun. Theor. Group, Delft Univ. of Technol., Delft, Netherlands – sequence: 2 givenname: M.J.T. surname: Reinders fullname: Reinders, M.J.T. organization: Inf. & Commun. Theor. Group, Delft Univ. of Technol., Delft, Netherlands – sequence: 3 givenname: D. surname: de Ridder fullname: de Ridder, D. organization: Inf. & Commun. Theor. Group, Delft Univ. of Technol., Delft, Netherlands |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/19644171$$D View this record in MEDLINE/PubMed |
| BookMark | eNqF0ktv1DAQAGALFdEHHDkhoYhDe8ri9-NIV6WtqFQORVyQLCeZUFdJnNpJBf31ON3SQyXYk23NNyPbM_toZwgDIPSW4BUh2Hy8Wh8fryjGekWYeoH2iBCqNEbynWXPRSmMZLtoP6UbjCk3mL9CuyTHOVFkD_04uQvdPPkwuPi7uBwn3_t7t5yL0BZfIA7QFd_B_7yeUnHejzHcQSq-xjCBH4p16McOfi0r9BXEdO3HHITG10uJ1-hl67oEbx7XA_Tt88nV-qy8uDw9X3-6KGsu2VQaLmSrdINbB4Ax8Epz0UgsKl1x4ySTqq5ZzUC0QvC2hboS0uFGEVE53TB2gI42dfP1bmdIk-19qqHr3ABhTlZLI7RWUmd5-F8pleCUK7kVMq4oNYRshZRQTolm2yFWShhsMvzwDN6EOQ75A_NDiBJU8gW9f0Rz1UNjx-j73EH7t7MZsA2oY0gpQmtrPz00dorOd5Zgu8yPXebHLvNj8_zkrPJZ1lPhf_h3G-8B4MlyxQjN0T-hDc59 |
| CODEN | ITCBCY |
| CitedBy_id | crossref_primary_10_1093_bib_bbt020 crossref_primary_10_1002_widm_1125 crossref_primary_10_1007_s00500_013_1080_0 |
| Cites_doi | 10.1145/1102351.1102399 10.1017/CBO9780511809682 10.1186/1471-2105-5-38 10.1023/A:1012450327387 10.1038/ng569 10.1073/pnas.242624799 10.1093/bioinformatics/bth294 10.1038/415180a 10.1109/CEC.2005.1554902 10.1126/science.1087361 10.1016/S0092-8674(00)00015-5 10.1093/nar/30.1.303 10.1073/pnas.0406614101 10.7551/mitpress/4057.001.0001 10.1089/10665270252935539 10.1145/1068009.1068160 10.1038/nature02800 10.1162/106365603321828970 10.1038/nature750 10.1186/1471-2105-4-2 10.1093/bioinformatics/btm187 10.1002/prot.20865 10.1093/bioinformatics/bti1016 10.1038/nbt1002-991 10.1371/journal.pcbi.1000173 10.7551/mitpress/1120.003.0052 10.1074/jbc.M410573200 10.1186/1471-2105-7-S1-S2 10.1038/415141a 10.1093/nar/28.1.37 10.1101/gr.1774904 10.1093/bioinformatics/bth483 10.1101/gr.3610305 10.1023/A:1022627411411 10.1093/bioinformatics/btl475 10.1016/j.mib.2004.08.012 10.1145/1015330.1015424 10.1162/089976604774201640 10.1142/S0219720007002953 10.1016/S1097-2765(04)00003-6 10.1093/nar/gkg078 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2009 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2009 |
| DBID | 97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| DOI | 10.1109/TCBB.2008.137 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Technology Research Database MEDLINE Engineering Research Database Materials Research Database Engineering Research Database Engineering Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 1557-9964 |
| EndPage | 437 |
| ExternalDocumentID | 2318964241 19644171 10_1109_TCBB_2008_137 4731237 |
| Genre | orig-research Journal Article |
| GroupedDBID | 0R~ 29I 4.4 53G 5GY 5VS 6IK 8US 97E AAJGR AAKMM AALFJ AARMG AASAJ AAWTH AAWTV ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACM ACPRK ADBCU ADL AEBYY AEFXT AEJOY AENEX AENSD AETIX AFRAH AFWIH AFWXC AGQYO AGSQL AHBIQ AIBXA AIKLT AKJIK AKQYR AKRVB ALMA_UNASSIGNED_HOLDINGS ASPBG ATWAV AVWKF BDXCO BEFXN BFFAM BGNUA BKEBE BPEOZ CCLIF CS3 DU5 EBS EJD FEDTE GUFHI HGAVV HZ~ I07 IEDLZ IFIPE IPLJI JAVBF LAI LHSKQ M43 O9- OCL P1C P2P PQQKQ RIA RIE RNI RNS ROL RZB TN5 XOL AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| ID | FETCH-LOGICAL-c463t-9456f78d0faee00e4b845d605b8b49a6367cc3c3e5f554ffecb56a0d715ba8d33 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 7 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000268356300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1545-5963 1557-9964 |
| IngestDate | Tue Oct 07 09:11:41 EDT 2025 Sun Sep 28 01:46:21 EDT 2025 Thu Oct 02 10:53:07 EDT 2025 Tue Oct 07 10:08:52 EDT 2025 Mon Oct 06 18:04:49 EDT 2025 Sun Nov 09 06:45:08 EST 2025 Mon Jul 21 05:54:36 EDT 2025 Tue Nov 18 21:27:19 EST 2025 Sat Nov 29 08:09:14 EST 2025 Tue Aug 26 16:38:05 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c463t-9456f78d0faee00e4b845d605b8b49a6367cc3c3e5f554ffecb56a0d715ba8d33 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23 |
| PMID | 19644171 |
| PQID | 861752649 |
| PQPubID | 23462 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1109_TCBB_2008_137 crossref_primary_10_1109_TCBB_2008_137 proquest_miscellaneous_21242183 pubmed_primary_19644171 proquest_miscellaneous_67542476 proquest_miscellaneous_20775909 proquest_miscellaneous_34722911 proquest_journals_861752649 ieee_primary_4731237 proquest_miscellaneous_869588768 |
| PublicationCentury | 2000 |
| PublicationDate | 2009-07-01 |
| PublicationDateYYYYMMDD | 2009-07-01 |
| PublicationDate_xml | – month: 07 year: 2009 text: 2009-07-01 day: 01 |
| PublicationDecade | 2000 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE/ACM transactions on computational biology and bioinformatics |
| PublicationTitleAbbrev | TCBB |
| PublicationTitleAlternate | IEEE/ACM Trans Comput Biol Bioinform |
| PublicationYear | 2009 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref14 Bousquet (ref19) 2003; 15 ref11 ref10 ref16 Duin (ref44) 2009 ref18 Chang (ref43) 2008 ref46 ref48 ref47 ref42 ref41 Friedrichs (ref25) Lanckriet (ref15) ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 Sonnenburg (ref17) 2006; 7 ref35 ref34 ref37 ref36 ref31 ref33 ref32 ref2 ref1 ref39 ref38 Hsu (ref45) 2003 ref24 ref23 ref26 ref20 ref22 ref21 ref28 ref27 ref29 Bach (ref30) 2004; 5 |
| References_xml | – ident: ref49 doi: 10.1145/1102351.1102399 – ident: ref2 doi: 10.1017/CBO9780511809682 – ident: ref12 doi: 10.1186/1471-2105-5-38 – start-page: 323 volume-title: Proc. 19th Int’l Conf. Machine Learning (ICML ’02) ident: ref15 article-title: Learning the Kernel Matrix with Semidefinite Programming – ident: ref18 doi: 10.1023/A:1012450327387 – ident: ref37 doi: 10.1038/ng569 – year: 2003 ident: ref45 article-title: A Practical Guide to Support Vector Classification – ident: ref36 doi: 10.1073/pnas.242624799 – ident: ref16 doi: 10.1093/bioinformatics/bth294 – ident: ref5 doi: 10.1038/415180a – ident: ref28 doi: 10.1109/CEC.2005.1554902 – ident: ref11 doi: 10.1126/science.1087361 – ident: ref34 doi: 10.1016/S0092-8674(00)00015-5 – ident: ref40 doi: 10.1093/nar/30.1.303 – ident: ref47 doi: 10.1073/pnas.0406614101 – ident: ref1 doi: 10.7551/mitpress/4057.001.0001 – volume: 7 start-page: 1531 year: 2006 ident: ref17 article-title: Large Scale Multiple Kernel Learning publication-title: J. Machine Learning Research – ident: ref21 doi: 10.1089/10665270252935539 – ident: ref24 doi: 10.1145/1068009.1068160 – ident: ref38 doi: 10.1038/nature02800 – ident: ref27 doi: 10.1162/106365603321828970 – ident: ref8 doi: 10.1038/nature750 – year: 2008 ident: ref43 article-title: LIBSVM: A Library for Support Vector Machine – ident: ref10 doi: 10.1186/1471-2105-4-2 – ident: ref26 doi: 10.1093/bioinformatics/btm187 – ident: ref14 doi: 10.1002/prot.20865 – ident: ref22 doi: 10.1093/bioinformatics/bti1016 – ident: ref7 doi: 10.1038/nbt1002-991 – volume: 15 start-page: 415 volume-title: Advances in Neural Information Processing Systems year: 2003 ident: ref19 article-title: On the Complexity of Learning the Kernel Matrix – ident: ref3 doi: 10.1371/journal.pcbi.1000173 – ident: ref20 doi: 10.7551/mitpress/1120.003.0052 – ident: ref35 doi: 10.1074/jbc.M410573200 – ident: ref32 doi: 10.1186/1471-2105-7-S1-S2 – year: 2009 ident: ref44 article-title: PRTools, A Matlab Toolbox for Pattern Recognition – ident: ref6 doi: 10.1038/415141a – ident: ref31 doi: 10.1093/nar/28.1.37 – ident: ref42 doi: 10.1101/gr.1774904 – ident: ref23 doi: 10.1093/bioinformatics/bth483 – ident: ref41 doi: 10.1101/gr.3610305 – ident: ref4 doi: 10.1023/A:1022627411411 – ident: ref46 doi: 10.1093/bioinformatics/btl475 – ident: ref9 doi: 10.1016/j.mib.2004.08.012 – ident: ref29 doi: 10.1145/1015330.1015424 – ident: ref48 doi: 10.1162/089976604774201640 – start-page: 519 volume-title: Proc. European Symp. Artificial Neural Networks (ESANN) ident: ref25 article-title: Evolutionary Tuning of Multiple SVM Parameters – ident: ref13 doi: 10.1142/S0219720007002953 – ident: ref39 doi: 10.1016/S1097-2765(04)00003-6 – ident: ref33 doi: 10.1093/nar/gkg078 – volume: 5 start-page: 1391 year: 2004 ident: ref30 article-title: Computing Regularization Paths for Learning Multiple Kernels publication-title: J. Machine Learning Research |
| SSID | ssj0024904 |
| Score | 1.8682715 |
| Snippet | In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression,... In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 427 |
| SubjectTerms | Algorithms Artificial Intelligence Bioinformatics biology and genetics Biology computing Classifier design and evaluation Evolution, Molecular Evolutionary computation evolutionary computing and genetic algorithms Kernel Large-scale systems Linear Models Models, Genetic Multiprotein Complexes - chemistry Nonlinear Dynamics Optimization methods Protein engineering Reproducibility of Results ROC Curve Sequences Studies Support vector machine classification Support vector machines |
| Title | Evolutionary Optimization of Kernel Weights Improves Protein Complex Comembership Prediction |
| URI | https://ieeexplore.ieee.org/document/4731237 https://www.ncbi.nlm.nih.gov/pubmed/19644171 https://www.proquest.com/docview/861752649 https://www.proquest.com/docview/20775909 https://www.proquest.com/docview/21242183 https://www.proquest.com/docview/34722911 https://www.proquest.com/docview/67542476 https://www.proquest.com/docview/869588768 |
| Volume | 6 |
| WOSCitedRecordID | wos000268356300006&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: PRVIEE databaseName: IEEE/IET Electronic Library customDbUrl: eissn: 1557-9964 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024904 issn: 1545-5963 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS9xAEB9UWuiLtbUfqdXuQ-mTqUn3-7GKUihYHyy9h0JINhMQzly53In-953ZxDsKjeBTAhmWzXzt7M7s_AA--krpPLg6pVgIaYOiMPWqKtM6a5z1XwJa30SwCXt-7iYTf7EBh6u7MIgYi8_wM7_GXH49C0s-KjtSVpKjtZuwaa3p72qt--r5CBXIEUGqSavW_TSPLk-Oj_uqyVxG0D3PQYDN_1mKIrbKeJgZl5uz54-b6A5sD2Gl-NrrwQvYwPYlPO2BJu924ffpzaBi5fxO_CA3cT3cvxSzRnzHeYtT8SueknaiP2fATlxwD4erVrDPmOItP5HxQ7jAiz5yioeHeAU_z04vT76lA65CGpSRCxKGNo11JI4SMctQVU7pmvY1lauUL400NgQZJOqGgg0uK6m0KbPa5roqXS3la9hqZy2-BZFJK3VJimCci2DlTai9s2WDkkKZyiRweM_iIgxNxxn7YlrEzUfmCxZOj4VJwkng04r8T99tY4xwl7m-IhoYnsDevfyKwRa7wlGQRlNTPoEPq69kRJwZKVucLTsa1lrts4cocs6dOzlOIbntJi0d4xSG0YaVJaaIEQpnvCavb1wCb3rtW7NhUNp3___zPXjW57m4kPg9bC3mS9yHJ-FmcdXND8hgJu4gGsxf7oYSwA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VAoILr_IIBeoD4tS0Sf0-0qpVUcvSwyJ6QIoSZyJVWrJos1vRf8-Mk-4KiUXilEgZWc7M2P7sGc8H8N5XSufB1SlhIaQNisLUq6pM66xx1h8EtL6JZBN2NHKXl_5iA3aXd2EQMSaf4R6_xlh-PQ0LPirbV1bSRGvvwF2t1EHW39ZaVdbzkSyQMUGqya9WFTX3x0eHh33eZC4j7Z5nGGDzPxajyK6yHmjGBefk8f919Qk8GoCl-Nh7wlPYwPYZ3O-pJm-24Pvx9eBk5exGfKGJ4sdwA1NMG3GGsxYn4ls8J-1Ef9KAnbjgKg5XreBZY4K_-InMIMIpXvSRgzzcxHP4enI8PjpNB2aFNCgj52QObRrryCAlYpahqpzSNe1sKlcpXxppbAgySNQNwQ1OLKm0KbPa5roqXS3lC9hspy2-ApFJK3VJrmCci3TlTai9s2WDksBMZRLYvVVxEYay48x-MSni9iPzBRunZ8Mk4yTwYSn-s6-3sU5wi7W-FBoUnsD2rf2KYTR2hSOYRl1TPoGd5VcaRhwbKVucLjpq1lrts39J5Bw9d3K9hOTCm7R4rJcwzDesLClFrJFwxmua941L4GXvfSs1DE77-u9_vgMPTsefz4vzT6OzbXjYR704rfgNbM5nC3wL98L1_KqbvYvD5jfZEhUf |
| 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=Evolutionary+optimization+of+kernel+weights+improves+protein+complex+comembership+prediction&rft.jtitle=IEEE%2FACM+transactions+on+computational+biology+and+bioinformatics&rft.au=Hulsman%2C+Marc&rft.au=Reinders%2C+Marcel+J+T&rft.au=de+Ridder%2C+Dick&rft.date=2009-07-01&rft.issn=1557-9964&rft.eissn=1557-9964&rft.volume=6&rft.issue=3&rft.spage=427&rft_id=info:doi/10.1109%2FTCBB.2008.137&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5963&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5963&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5963&client=summon |