SAE.Feature function

Encoding of nucleotide sequences based on sum of absolute error (SAE) of each sequence.

The sum of absolute error (SAE) concept was introduced by Meher et al. (2014) for prediction of donor splice sites, and was subsequently used by the same authors (Meher et al., 2016) for encoding of splice site motif for prediction using supervised learning model. In this encoding technique also all possible pair-wise nucleotide dependencies are considered.

SAE.Feature(positive_class, negative_class, test_seq)

Arguments

• positive_class: Sequence dataset of the positive class, must be an object of class DNAStringSet.
• negative_class: Sequence dataset of the negative class, must be an object of class DNAStringSet.
• test_seq: Sequences to be encoded into numeric vectors, must be an object of class DNAStringSet.

Details

In this encoding approach a vector of two observations will be obtained for each sequence. This two values correspond to the values obtained, when only positive class and both positive & neagtive datasets are used for encoding. This encoding scheme is invariant to the length of the sequence. Thus, both positive and negative classes datasets are required for encoding of sequence.

Returns

A numeric matrix of order $m*2$, where $m$ is the number of sequences in test_seq.

References

1. Meher, P.K., Sahu, T.K., Rao, A.R. and Wahi, S.D. (2014). A statistical approach for 5' splice site prediction using short sequence motifs and without encoding sequence data. BMC Bioinformatics, 15(1), 362.
2. Meher, P.K., Sahu, T.K., Rao, A.R. and Wahi, S.D. (2016). Identification of donor splice sites using support vector machine: a computational approach based on positional, compositional and dependency features. Algorithms for Molecular Biology, 11(1), 16.

Author(s)

Prabina Kumar Meher, Indian Agricultural Statistics Research Institute, New Delhi-110012, INDIA

See Also

MM1.Feature, WAM.Feature

Examples

data(droso)
positive <- droso$positive
negative <- droso$negative
test <- droso$test
pos <- positive[1:200]
neg <- negative[1:200]
tst <- test
enc <- SAE.Feature(positive_class=pos, negative_class=neg, test_seq=tst)
enc