Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.molimm.2006.02.010
DC FieldValue
dc.titleComputer prediction of allergen proteins from sequence-derived protein structural and physicochemical properties
dc.contributor.authorCui, J.
dc.contributor.authorHan, L.Y.
dc.contributor.authorLi, H.
dc.contributor.authorUng, C.Y.
dc.contributor.authorTang, Z.Q.
dc.contributor.authorZheng, C.J.
dc.contributor.authorCao, Z.W.
dc.contributor.authorChen, Y.Z.
dc.date.accessioned2014-10-29T01:50:30Z
dc.date.available2014-10-29T01:50:30Z
dc.date.issued2007-01
dc.identifier.citationCui, J., Han, L.Y., Li, H., Ung, C.Y., Tang, Z.Q., Zheng, C.J., Cao, Z.W., Chen, Y.Z. (2007-01). Computer prediction of allergen proteins from sequence-derived protein structural and physicochemical properties. Molecular Immunology 44 (4) : 514-520. ScholarBank@NUS Repository. https://doi.org/10.1016/j.molimm.2006.02.010
dc.identifier.issn01615890
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/105768
dc.description.abstractBackground: Computational methods have been developed for predicting allergen proteins from sequence segments that show identity, homology, or motif match to a known allergen. These methods achieve good prediction accuracies, but are less effective for novel proteins with no similarity to any known allergen. Methods: This work tests the feasibility of using a statistical learning method, support vector machines, as such a method. The prediction system is trained and tested by using 1005 allergen proteins from the Allergome database and 22,469 non-allergen proteins from 7871 Pfam families. Results: Testing results by an independent set of 229 allergen and 6717 non-allergen proteins from 7871 Pfam families show that 93.0% and 99.9% of these are correctly predicted, which are comparable to the best results of other methods. Of the 18 novel allergen proteins non-homologous to any other proteins in the Swissprot database, 88.9% is correctly predicted. A further screening of 168,128 proteins in the Swissprot database finds that 2.9% of the proteins are predicted as allergen proteins, which is consistent with the estimated numbers from motif-based methods. Conclusions: Our study suggests that SVM is a potentially useful method for predicting allergen proteins and it has certain capability for predicting novel allergen proteins. Our software can be accessed at http://jing.cz3.nus.edu.sg/cgi-bin/APPEL. © 2006 Elsevier Ltd. All rights reserved.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/j.molimm.2006.02.010
dc.sourceScopus
dc.subjectAllergen
dc.subjectImmunology
dc.subjectStatistical learning method
dc.subjectSupport vector machine
dc.typeArticle
dc.contributor.departmentPHARMACY
dc.description.doi10.1016/j.molimm.2006.02.010
dc.description.sourcetitleMolecular Immunology
dc.description.volume44
dc.description.issue4
dc.description.page514-520
dc.description.codenIMCHA
dc.identifier.isiut000241460900027
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

49
checked on Oct 22, 2019

WEB OF SCIENCETM
Citations

45
checked on Oct 15, 2019

Page view(s)

46
checked on Oct 11, 2019

Google ScholarTM

Check

Altmetric


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