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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE/ACM transactions on computational biology and bioinformatics Ročník 6; číslo 3; s. 427 - 437
Hlavní autoři:	Hulsman, M., Reinders, M.J.T., de Ridder, D.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.07.2009 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	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
ISSN:	1545-5963, 1557-9964, 1557-9964
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23
ISSN:	1545-5963 1557-9964 1557-9964
DOI:	10.1109/TCBB.2008.137