The repDNA Python package can generate various modes of feature vectors for DNA sequences, this Python package could:
1) Calculate three nucleic acid composition features describing the local sequence information by means of kmers (subsequences of DNA sequences);
2) Calculate six autocorrelation features describing the level of correlation between two oligonucleotides along a DNA sequence in terms of their specific physicochemical properties;
3) Calculate six pseudo nucleotide composition features, which can be used to represent a DNA sequence with a discrete model or vector yet still keep considerable sequence order information, particularly the global or long-range sequence order information, via the physicochemical properties of its constituent oligonucleotides.
There are four modules in the repDNA package, including util, nac, ac and psenac. The util module contains several basic functions manipulating DNA data, including reading DNA data from files or lists (a data structure in Python), checking the validity and normalizing the user-defined physicochemical indices, etc. The three modules nac, ac and psenac respond to the calculation of the 15 different features from three feature categories. In order to use the repDNA package to calculate these features as needed, the users need to import the appropriate class from the corresponding module, construct a responding object, and then call the corresponding methods to calculate these features.
The structure of repDNA package
