| Classifying "kinase inhibitor-likeness" by using machine-learning methods. | |
| | |
MedLine Citation:
|
PMID: 15696507 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
By using an in-house data set of small-molecule structures, encoded by Ghose-Crippen parameters, several machine learning techniques were applied to distinguish between kinase inhibitors and other molecules with no reported activity on any protein kinase. All four approaches pursued--support-vector machines (SVM), artificial neural networks (ANN), k nearest neighbor classification with GA-optimized feature selection (GA/kNN), and recursive partitioning (RP)--proved capable of providing a reasonable discrimination. Nevertheless, substantial differences in performance among the methods were observed. For all techniques tested, the use of a consensus vote of the 13 different models derived improved the quality of the predictions in terms of accuracy, precision, recall, and F1 value. Support-vector machines, followed by the GA/kNN combination, outperformed the other techniques when comparing the average of individual models. By using the respective majority votes, the prediction of neural networks yielded the highest F1 value, followed by SVMs. |
| | |
Authors:
|
Hans Briem; Judith Günther |
Related Documents
:
|
15573817 - Semisupervised learning of classifiers: theory, algorithms, and their application to hu... 14734317 - Is cross-validation better than resubstitution for ranking genes? 18532497 - The question of disguised voice. 20634557 - Object detection with discriminatively trained part-based models. 21167287 - Voxel-wise information theoretic eeg-fmri feature integration. 3175047 - The field integrated dose modification (fidm): three typical clinical applications of a... |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: Chembiochem : a European journal of chemical biology Volume: 6 ISSN: 1439-4227 ISO Abbreviation: Chembiochem Publication Date: 2005 Mar |
Date Detail:
|
Created Date: 2005-03-09 Completed Date: 2005-06-22 Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 100937360 Medline TA: Chembiochem Country: Germany |
Other Details:
|
Languages: eng Pagination: 558-66 Citation Subset: IM |
Affiliation:
|
Schering AG, Research Center Europe, CDCC/Computational Chemistry, Muellerstrasse 178, 13342 Berlin, Germany. hans.briem@schering.de |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Algorithms Computational Biology / methods* Computer Simulation* Molecular Structure Neural Networks (Computer) Protein Kinase Inhibitors / chemistry*, classification* Reproducibility of Results Sensitivity and Specificity |
| Chemical | |
Reg. No./Substance:
|
0/Protein Kinase Inhibitors |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Analysing child mortality in Nigeria with geoadditive discrete-time survival models.
Next Document: Small-molecule kinase-inhibitor target assessment.