# HG changeset patch
# User test-svm
# Date 1344198723 14400
# Node ID e8dcc2ed0f9f59f6d2f931e58450a42fa798fd02
# Parent  a8cbea0008d4a211a514308805c347135a5f50eb
Included bugfix, README

diff -r a8cbea0008d4 -r e8dcc2ed0f9f kmersvm/README.txt
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/kmersvm/README.txt	Sun Aug 05 16:32:03 2012 -0400
@@ -0,0 +1,45 @@
+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 create a nullseq_indices.loc file according to the instructions
+in nullseq_indices.loc.sample, providing the path to the created indices. 
+
+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.
+
+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>
+
diff -r a8cbea0008d4 -r e8dcc2ed0f9f kmersvm/scripts/.nullseq_build_indices.py.swp
Binary file kmersvm/scripts/.nullseq_build_indices.py.swp has changed
diff -r a8cbea0008d4 -r e8dcc2ed0f9f kmersvm/scripts/make_profile.py
--- a/kmersvm/scripts/make_profile.py	Sun Aug 05 15:39:52 2012 -0400
+++ b/kmersvm/scripts/make_profile.py	Sun Aug 05 16:32:03 2012 -0400
@@ -73,8 +73,7 @@
 
 def main():
 	parser = optparse.OptionParser()
-		
-	if len(sys.argv) != 4:
+	if len(sys.argv) != 5:
 		print "Usage:", sys.argv[0], "BEDFILE BUILDNAME BASE_DIR OUT_FILE"
 		sys.exit()
 	parser.add_option("-o", dest="output", default="seq_profile.txt")
diff -r a8cbea0008d4 -r e8dcc2ed0f9f kmersvm/scripts/split_genome.py
--- a/kmersvm/scripts/split_genome.py	Sun Aug 05 15:39:52 2012 -0400
+++ b/kmersvm/scripts/split_genome.py	Sun Aug 05 16:32:03 2012 -0400
@@ -3,7 +3,6 @@
 import sys
 import optparse
 import math
-import struct
 import re
 from libkmersvm import *
 		
diff -r a8cbea0008d4 -r e8dcc2ed0f9f kmersvm/svm_enh/split_genome.pyc
Binary file kmersvm/svm_enh/split_genome.pyc has changed