droso

<p>The dataset contains 400 true donor sites, 400 false donor sites and 50 false sites as test set. Each sequence is of 40 nucleotides long. The conserved di-nucleotides GT are present at $21^st$ and $22^nd$ positions respectively.</p>

datasets

We describe fifteen different splice site sequence encoding schemes that have been used in earlier studies for mapping of splice site sequences into numeric feature vectors. These encoding schemes will also be helpful for transforming other nucleotide sequences into numeric forms, provided they are of equal length. These encoding schemes will help the computational biologist working in the field of classification (binary or multiclass) or prediction involving nucleic acid sequences of equal length.

Prabina Meher

EncDNA

Encoding of Nucleotide Sequences into Numeric Feature Vectors

droso function

<p>The dataset belongs to the class <code>DNAStringSet</code>.</p>

droso: An example dataset consisting of true and false donor splice sites of Drosophila melanogaster.

Description

Usage

Arguments

Format

References

Examples