Limits...
Statistical assessment of discriminative features for protein-coding and non coding cross-species conserved sequence elements.

Creanza TM, Horner DS, D'Addabbo A, Maglietta R, Mignone F, Ancona N, Pesole G - BMC Bioinformatics (2009)

Bottom Line: We found that the most discriminant feature was a comparative measure indicating the proportion of synonymous nucleotide substitutions per synonymous sites.Finally, the prediction accuracy of classifiers trained on comparative features increased significantly by adding intrinsic features to the set of input variables, independently on sequence length (Kolmogorov-Smirnov P-value <or= 0.05).In particular, we noted that comparative features tend to be more accurate in the classification of coding sequences - this is likely related to the fact that such features capture deviations from strictly neutral evolution expected as a consequence of the characteristics of the genetic code.

View Article: PubMed Central - HTML - PubMed

Affiliation: Istituto di Studi sui Sistemi Intelligenti per l'Automazione, CNR, Via Amendola 122/D-I, Bari, Italy. creanza@ba.issia.cnr.it

ABSTRACT

Background: The identification of protein coding elements in sets of mammalian conserved elements is one of the major challenges in the current molecular biology research. Many features have been proposed for automatically distinguishing coding and non coding conserved sequences, making so necessary a systematic statistical assessment of their differences. A comprehensive study should be composed of an association study, i.e. a comparison of the distributions of the features in the two classes, and a prediction study in which the prediction accuracies of classifiers trained on single and groups of features are analyzed, conditionally to the compared species and to the sequence lengths.

Results: In this paper we compared distributions of a set of comparative and non comparative features and evaluated the prediction accuracy of classifiers trained for discriminating sequence elements conserved among human, mouse and rat species. The association study showed that the analyzed features are statistically different in the two classes. In order to study the influence of the sequence lengths on the feature performances, a predictive study was performed on different data sets composed of coding and non coding alignments in equal number and equally long with an ascending average length. We found that the most discriminant feature was a comparative measure indicating the proportion of synonymous nucleotide substitutions per synonymous sites. Moreover, linear discriminant classifiers trained by using comparative features in general outperformed classifiers based on intrinsic ones. Finally, the prediction accuracy of classifiers trained on comparative features increased significantly by adding intrinsic features to the set of input variables, independently on sequence length (Kolmogorov-Smirnov P-value

Conclusion: We observed distinct and consistent patterns for individual and combined use of comparative and intrinsic classifiers, both with respect to different lengths of sequences/alignments and with respect to error rates in the classification of coding and non-coding elements. In particular, we noted that comparative features tend to be more accurate in the classification of coding sequences - this is likely related to the fact that such features capture deviations from strictly neutral evolution expected as a consequence of the characteristics of the genetic code.

Show MeSH
Sensitivity and specificity. The plots refer to the sequences of the H. sapiens and their alignments with rat and mouse genomes: in particular on the right the are the three plots of prediction accuracy of the combination of the only comparative a), of the only intrinsic c) and of all metrics e) as function of sequence lengths, on the left the respective plots b), d), f) for the sensitivity and the specificity.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2697643&req=5

Figure 5: Sensitivity and specificity. The plots refer to the sequences of the H. sapiens and their alignments with rat and mouse genomes: in particular on the right the are the three plots of prediction accuracy of the combination of the only comparative a), of the only intrinsic c) and of all metrics e) as function of sequence lengths, on the left the respective plots b), d), f) for the sensitivity and the specificity.

Mentions: The features depending on the reading frame were evaluated by using the frame suggested by the most accurate univariate classifier, i. e. the classifier based on SRRM. The empirical distributions (median and interquartile range) of prediction accuracies of comparative and intrinsic classifiers are depicted respectively in Figure 5a) and 5c). Both learning curves are ascending for increasing sequence length: the accuracies vary in [70%, 97%] and are statistically significant for each sequence length (P-value < 0.005 and π > 0.88). Although these learning curves exhibit a similar qualitative behavior, they result statistically different. In fact, Kolmogorov-Smirnov tests show that the error rates of comparative classifiers are significantly smaller than ones of non comparative classifiers in 68% of the length classes for the human, in 65% for the mouse and in 94% for the rat.


Statistical assessment of discriminative features for protein-coding and non coding cross-species conserved sequence elements.

Creanza TM, Horner DS, D'Addabbo A, Maglietta R, Mignone F, Ancona N, Pesole G - BMC Bioinformatics (2009)

Sensitivity and specificity. The plots refer to the sequences of the H. sapiens and their alignments with rat and mouse genomes: in particular on the right the are the three plots of prediction accuracy of the combination of the only comparative a), of the only intrinsic c) and of all metrics e) as function of sequence lengths, on the left the respective plots b), d), f) for the sensitivity and the specificity.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2697643&req=5

Figure 5: Sensitivity and specificity. The plots refer to the sequences of the H. sapiens and their alignments with rat and mouse genomes: in particular on the right the are the three plots of prediction accuracy of the combination of the only comparative a), of the only intrinsic c) and of all metrics e) as function of sequence lengths, on the left the respective plots b), d), f) for the sensitivity and the specificity.
Mentions: The features depending on the reading frame were evaluated by using the frame suggested by the most accurate univariate classifier, i. e. the classifier based on SRRM. The empirical distributions (median and interquartile range) of prediction accuracies of comparative and intrinsic classifiers are depicted respectively in Figure 5a) and 5c). Both learning curves are ascending for increasing sequence length: the accuracies vary in [70%, 97%] and are statistically significant for each sequence length (P-value < 0.005 and π > 0.88). Although these learning curves exhibit a similar qualitative behavior, they result statistically different. In fact, Kolmogorov-Smirnov tests show that the error rates of comparative classifiers are significantly smaller than ones of non comparative classifiers in 68% of the length classes for the human, in 65% for the mouse and in 94% for the rat.

Bottom Line: We found that the most discriminant feature was a comparative measure indicating the proportion of synonymous nucleotide substitutions per synonymous sites.Finally, the prediction accuracy of classifiers trained on comparative features increased significantly by adding intrinsic features to the set of input variables, independently on sequence length (Kolmogorov-Smirnov P-value <or= 0.05).In particular, we noted that comparative features tend to be more accurate in the classification of coding sequences - this is likely related to the fact that such features capture deviations from strictly neutral evolution expected as a consequence of the characteristics of the genetic code.

View Article: PubMed Central - HTML - PubMed

Affiliation: Istituto di Studi sui Sistemi Intelligenti per l'Automazione, CNR, Via Amendola 122/D-I, Bari, Italy. creanza@ba.issia.cnr.it

ABSTRACT

Background: The identification of protein coding elements in sets of mammalian conserved elements is one of the major challenges in the current molecular biology research. Many features have been proposed for automatically distinguishing coding and non coding conserved sequences, making so necessary a systematic statistical assessment of their differences. A comprehensive study should be composed of an association study, i.e. a comparison of the distributions of the features in the two classes, and a prediction study in which the prediction accuracies of classifiers trained on single and groups of features are analyzed, conditionally to the compared species and to the sequence lengths.

Results: In this paper we compared distributions of a set of comparative and non comparative features and evaluated the prediction accuracy of classifiers trained for discriminating sequence elements conserved among human, mouse and rat species. The association study showed that the analyzed features are statistically different in the two classes. In order to study the influence of the sequence lengths on the feature performances, a predictive study was performed on different data sets composed of coding and non coding alignments in equal number and equally long with an ascending average length. We found that the most discriminant feature was a comparative measure indicating the proportion of synonymous nucleotide substitutions per synonymous sites. Moreover, linear discriminant classifiers trained by using comparative features in general outperformed classifiers based on intrinsic ones. Finally, the prediction accuracy of classifiers trained on comparative features increased significantly by adding intrinsic features to the set of input variables, independently on sequence length (Kolmogorov-Smirnov P-value

Conclusion: We observed distinct and consistent patterns for individual and combined use of comparative and intrinsic classifiers, both with respect to different lengths of sequences/alignments and with respect to error rates in the classification of coding and non-coding elements. In particular, we noted that comparative features tend to be more accurate in the classification of coding sequences - this is likely related to the fact that such features capture deviations from strictly neutral evolution expected as a consequence of the characteristics of the genetic code.

Show MeSH