Limits...
Heterodimeric protein complex identification by naïve Bayes classifiers.

Maruyama O - BMC Bioinformatics (2013)

Bottom Line: It can be found that in databases of protein complexes of yeast like CYC2008, the major type of known protein complexes is heterodimeric complexes.However, it turns out that by designing features specialized for heterodimeric protein complexes, predictability of them can be improved.Thus, the design of more sophisticate features for heterodimeric protein complexes as well as the accumulation of more accurate and useful genome-wide data sets will lead to higher predictability of heterodimeric protein complexes.

View Article: PubMed Central - HTML - PubMed

Affiliation: Institute of Mathematics for Industry, Kyushu University, Fukuoka, Japan. om@imi.kyushu-u.ac.jp.

ABSTRACT

Background: Protein complexes are basic cellular entities that carry out the functions of their components. It can be found that in databases of protein complexes of yeast like CYC2008, the major type of known protein complexes is heterodimeric complexes. Although a number of methods for trying to predict sets of proteins that form arbitrary types of protein complexes simultaneously have been proposed, it can be found that they often fail to predict heterodimeric complexes.

Results: In this paper, we have designed several features characterizing heterodimeric protein complexes based on genomic data sets, and proposed a supervised-learning method for the prediction of heterodimeric protein complexes. This method learns the parameters of the features, which are embedded in the naïve Bayes classifier. The log-likelihood ratio derived from the naïve Bayes classifier with the parameter values obtained by maximum likelihood estimation gives the score of a given pair of proteins to predict whether the pair is a heterodimeric complex or not. A five-fold cross-validation shows good performance on yeast. The trained classifiers also show higher predictability than various existing algorithms on yeast data sets with approximate and exact matching criteria.

Conclusions: Heterodimeric protein complex prediction is a rather harder problem than heteromeric protein complex prediction because heterodimeric protein complex is topologically simpler. However, it turns out that by designing features specialized for heterodimeric protein complexes, predictability of them can be improved. Thus, the design of more sophisticate features for heterodimeric protein complexes as well as the accumulation of more accurate and useful genome-wide data sets will lead to higher predictability of heterodimeric protein complexes. Our tool can be downloaded from http://imi.kyushu-u.ac.jp/~om/.

Show MeSH
Overview of evaluation of trained classifiers by all known PPIs. This figure shows an overview of evaluation of the classifiers trained in a cross-validation by all PPIs in the WI-PHI database.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4219333&req=5

Figure 2: Overview of evaluation of trained classifiers by all known PPIs. This figure shows an overview of evaluation of the classifiers trained in a cross-validation by all PPIs in the WI-PHI database.

Mentions: Given a set of features, a five-fold cross-validation is carried out, in which classifiers are trained with training sets of positive and negative examples and those trained classifiers are evaluated with test sets of positive and negative examples (see Figure1). The trained classifiers are then used to predict whether each of known PPIs form a heterodimeric protein complex or not (see Figure2), and the resulting performance is compared with those of other methods.


Heterodimeric protein complex identification by naïve Bayes classifiers.

Maruyama O - BMC Bioinformatics (2013)

Overview of evaluation of trained classifiers by all known PPIs. This figure shows an overview of evaluation of the classifiers trained in a cross-validation by all PPIs in the WI-PHI database.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4219333&req=5

Figure 2: Overview of evaluation of trained classifiers by all known PPIs. This figure shows an overview of evaluation of the classifiers trained in a cross-validation by all PPIs in the WI-PHI database.
Mentions: Given a set of features, a five-fold cross-validation is carried out, in which classifiers are trained with training sets of positive and negative examples and those trained classifiers are evaluated with test sets of positive and negative examples (see Figure1). The trained classifiers are then used to predict whether each of known PPIs form a heterodimeric protein complex or not (see Figure2), and the resulting performance is compared with those of other methods.

Bottom Line: It can be found that in databases of protein complexes of yeast like CYC2008, the major type of known protein complexes is heterodimeric complexes.However, it turns out that by designing features specialized for heterodimeric protein complexes, predictability of them can be improved.Thus, the design of more sophisticate features for heterodimeric protein complexes as well as the accumulation of more accurate and useful genome-wide data sets will lead to higher predictability of heterodimeric protein complexes.

View Article: PubMed Central - HTML - PubMed

Affiliation: Institute of Mathematics for Industry, Kyushu University, Fukuoka, Japan. om@imi.kyushu-u.ac.jp.

ABSTRACT

Background: Protein complexes are basic cellular entities that carry out the functions of their components. It can be found that in databases of protein complexes of yeast like CYC2008, the major type of known protein complexes is heterodimeric complexes. Although a number of methods for trying to predict sets of proteins that form arbitrary types of protein complexes simultaneously have been proposed, it can be found that they often fail to predict heterodimeric complexes.

Results: In this paper, we have designed several features characterizing heterodimeric protein complexes based on genomic data sets, and proposed a supervised-learning method for the prediction of heterodimeric protein complexes. This method learns the parameters of the features, which are embedded in the naïve Bayes classifier. The log-likelihood ratio derived from the naïve Bayes classifier with the parameter values obtained by maximum likelihood estimation gives the score of a given pair of proteins to predict whether the pair is a heterodimeric complex or not. A five-fold cross-validation shows good performance on yeast. The trained classifiers also show higher predictability than various existing algorithms on yeast data sets with approximate and exact matching criteria.

Conclusions: Heterodimeric protein complex prediction is a rather harder problem than heteromeric protein complex prediction because heterodimeric protein complex is topologically simpler. However, it turns out that by designing features specialized for heterodimeric protein complexes, predictability of them can be improved. Thus, the design of more sophisticate features for heterodimeric protein complexes as well as the accumulation of more accurate and useful genome-wide data sets will lead to higher predictability of heterodimeric protein complexes. Our tool can be downloaded from http://imi.kyushu-u.ac.jp/~om/.

Show MeSH