DEPENDENCIES:
*************
KmerSVM requires the following software:

  *Shogun Toolbox, v0.9.3 - v1.10
  *Swig
  *Numpy
  *Bitarray
  *R
  *ROCR R Package

Further, KmerSVM has been tested on Python 2.6, 2.7.

REQUIRED FILES:
***************
For efficient access to genome-wide data "Generate Null Sequence" and 
"Sequence Profiles" rely on access to binary files (indices)  generated 
by using the script 'nullseq_build_indices.py'.  Download the *.tar or 
*.zip files for each genome to be analyzed.  To create indices for a
specific genome, call nullseq_build_indices.py as follows:

python nullseq_build_indices.py <GENOME ARCHIVE FILE> <GENOME BUILD>

Next copy nullseq_indices.loc.sample to tool-data/nullseq_indices.loc 
and add the path to the created indices following the instructions 
included in that file.

To generate FASTA files for training or scoring purposes, KmerSVM uses
the built-in tool "Fetch Sequences", which looks for genomes in *.nib or
*.2bit format.  Download genomes related to your data and update the
'alignseq.loc' file to include the location of these genomes according
to directions in that file.

Move the file sample_roc_chen.png to the 'tool-data' file.

TOOL_CONF.XML:
**************
Add the following lines to tool_conf.xml:

  <section name="SVM Tools" id="kmersvm">
    <tool file="kmersvm/classify.xml"/>
    <tool file="kmersvm/nullseq.xml"/>
    <tool file="kmersvm/rocprcurve.xml"/>
    <tool file="kmersvm/train.xml"/>
    <tool file="kmersvm/split_genome.xml"/>
    <tool file="kmersvm/seqprofile.xml" />
  </section>

Tool Tests:
***********
To run tests on the tools "Train SVM", "Score Sequences of Interest" and
"Split Genome", move the following files to the 'test-data' directory:

  *classify_output.out
  *classify_test.fa
  *kmersvm_output_weights.out
  *test_positive.fa
  *test_negative.fa
  *test_weights.out
  *train_predictions.out

IDs for KmerSVM tests can be found by calling run_functional_tests.sh with the '-list' flag.
