Please use this identifier to cite or link to this item: https://doi.org/10.1002/jcc.21347
DC FieldValue
dc.titleIdentification of small molecule aggregators from large compound libraries by support vector machines
dc.contributor.authorRao, H.
dc.contributor.authorLi, Z.
dc.contributor.authorLi, X.
dc.contributor.authorMa, X.
dc.contributor.authorUng, C.
dc.contributor.authorLi, H.
dc.contributor.authorLiu, X.
dc.contributor.authorChen, Y.
dc.date.accessioned2014-10-27T08:31:04Z
dc.date.available2014-10-27T08:31:04Z
dc.date.issued2010-03
dc.identifier.citationRao, H., Li, Z., Li, X., Ma, X., Ung, C., Li, H., Liu, X., Chen, Y. (2010-03). Identification of small molecule aggregators from large compound libraries by support vector machines. Journal of Computational Chemistry 31 (4) : 752-763. ScholarBank@NUS Repository. https://doi.org/10.1002/jcc.21347
dc.identifier.issn01928651
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/100877
dc.description.abstractSmall molecule aggregators non-specifically inhibit multiple unrelated proteins, rendering them therapeutically useless. They frequently appear as false hits and thus need to be eliminated in high-throughput screening campaigns. Computational methods have been explored for identifying aggregators, which have not been tested in screening large compound libraries. We used 1319 aggregators and 128,325 non-aggregators to develop a support vector machines (SVM) aggregator identification model, which was tested by four methods. The first is five fold cross-validation, which showed comparable aggregator and significantly improved non-aggregator identification rates against earlier studies. The second is the independent test of .17 aggregators discovered independently from the training aggregators, 71% of which were correctly identified. The third is retrospective screening of 13M PUBCHEM and 168K MDDR. compounds, which predicted 97.9% and 98.7% of the PUBCHEM and MDDR compounds as non-aggregators. The fourth is retrospective screening of 5527 MDDR compounds similar to the known aggregators, 1,14% of which were predicted as aggregators. SVM showed slightly better overall performance against two other machine learning methods based on five fold cross-validation studies of the same settings. Molecular features of aggregation, extracted by a feature selection method, are consistent with published profiles. SVM showed substantial capability in identifying aggregators from large libraries at low false-hit rates. © 2009 Wiley Periodicals, Inc.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1002/jcc.21347
dc.sourceScopus
dc.subjectActive compound
dc.subjectAggregation
dc.subjectAggregator
dc.subjectDrug discovery
dc.subjectHigh throughput screening
dc.subjectMachine learning method
dc.subjectRecursive feature elimination
dc.subjectSupport vector machine
dc.subjectVirtual screening
dc.typeArticle
dc.contributor.departmentPHARMACY
dc.contributor.departmentBIOLOGICAL SCIENCES
dc.description.doi10.1002/jcc.21347
dc.description.sourcetitleJournal of Computational Chemistry
dc.description.volume31
dc.description.issue4
dc.description.page752-763
dc.description.codenJCCHD
dc.identifier.isiut000274922000008
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

15
checked on Mar 30, 2020

WEB OF SCIENCETM
Citations

13
checked on Mar 30, 2020

Page view(s)

63
checked on Mar 28, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.