Closes issue #4

MANIFEST.in

@@ -0,0 +1,2 @@
+graft kleborate/data
+graft kleborate/ICEKp_references

Kleborate.py → kleborate/Kleborate.py

@@ -4,17 +4,18 @@
 import os, sys, subprocess
 import gzip
 from optparse import OptionParser
-
-def main():
+from pkg_resources import resource_string, resource_filename
+
+def parse_options():
 
 	usage = "usage: %prog [options]"
 	parser = OptionParser(usage=usage)
 
 	# options
-	parser.add_option("-p", "--path", action="store", dest="repo_path", help="Path to Kleborate directory (default Kleborate)", default="Kleborate")
+	#parser.add_option("-p", "--path", action="store", dest="repo_path", help="Path to Kleborate directory (default Kleborate)", default="Kleborate")
 	parser.add_option("-o", "--outfile", action="store", dest="outfile", help="File for detailed output (default Kleborate_results.txt)", default="Kleborate_results.txt")
 	parser.add_option("-r", "--resistance", action="store", dest="resistance", help="Resistance genes screening (default off, set to on)", default="off")
-	
+
 	return parser.parse_args()
 
 
@@ -48,25 +49,31 @@ def decompress_file(in_file, out_file):
 		o.write(s)
 
 
-if __name__ == "__main__":
+def kleborate():
+	(options, args) = parse_options()
 
-	(options, args) = main()
+	# find necessary resources
+	data_folder = resource_filename(__name__, 'data')
+	mlstblast = resource_filename(__name__, 'mlstBLAST.py')
+	resblast = resource_filename(__name__, 'resBLAST.py')
+	clusterblast = resource_filename(__name__, 'clusterBLAST.py')
 
 	header_string = "\t".join(["strain","ST","Yersiniabactin","YbST","Colibactin","CbST","aerobactin","salmochelin","hypermucoidy","wzi","KL"])
 	print header_string,
-	
+
 	res_header_string = ""
 	if options.resistance == "on":
-		f = os.popen("python "+ options.repo_path + "/resBLAST.py -s " + options.repo_path + "/data/ARGannot.r1.fasta -t " + options.repo_path + "/data/ARGannot_clustered80.csv") 
+
+		f = os.popen("python "+ resblast + " -s " + data_folder + "/ARGannot.r1.fasta -t " +  data_folder + "/ARGannot_clustered80.csv")
 		fields = f.readline().rstrip().split("\t")
 		res_header_string = "\t".join(fields[1:])
 		f.close()
 		print "\t" + res_header_string,
-	
+
 	print "" # end header
-		
+
 	mlst_header_string = "\t".join(["Chr_ST","gapA","infB","mdh","pgi","phoE","rpoB","tonB","YbST","ybtS","ybtX","ybtQ","ybtP","ybtA","irp2","irp1","ybtU","ybtT","ybtE","fyuA","CbST","clbA","clbB","clbC","clbD","clbE","clbF","clbG","clbH","clbI","clbL","clbM","clbN","clbO","clbP","clbQ"])
-	
+
 	o = file(options.outfile, "w")
 	o.write("\t".join([header_string,mlst_header_string]))
 	if options.resistance == "on":
@@ -76,7 +83,7 @@ def decompress_file(in_file, out_file):
 	for contigs in args:
 		(dir,fileName) = os.path.split(contigs)
 		(name,ext) = os.path.splitext(fileName)
-		
+
 		# If the contigs are in a gz file, make a temporary decompressed FASTA file.
 		if get_compression_type(contigs) == 'gz':
 			new_contigs = contigs + '_temp_decompress.fasta'
@@ -86,12 +93,13 @@ def decompress_file(in_file, out_file):
 		else:
 			temp_decompress = False
 
-		f = os.popen("python "+ options.repo_path + "/mlstBLAST.py -s "+ options.repo_path + "/data/Klebsiella_pneumoniae.fasta -d "+ options.repo_path + "/data/kpneumoniae.txt -i no --maxmissing 3 " + contigs) 
+
+		f = os.popen("python "+  mlstblast + " -s "+  data_folder + "/Klebsiella_pneumoniae.fasta -d "+  data_folder +"/kpneumoniae.txt -i no --maxmissing 3 " + contigs)
 
 		# run chromosome MLST
 		chr_ST = ""
 		chr_ST_detail = []
-		
+
 		for line in f:
 			fields = line.rstrip().split("\t")
 			if fields[1] != "ST":
@@ -101,15 +109,15 @@ def decompress_file(in_file, out_file):
 				if chr_ST != "0":
 					chr_ST = "ST"+chr_ST
 		f.close()
-		
+
 		# run ybt MLST
-		
-		f = os.popen("python "+ options.repo_path + "/mlstBLAST.py -s "+ options.repo_path + "/data/ybt_alleles.fasta -d "+ options.repo_path + "/data/YbST_profiles.txt -i yes --maxmissing 3 " + contigs) 
+
+		f = os.popen("python "+  mlstblast + " -s "+  data_folder +"/ybt_alleles.fasta -d "+  data_folder + "/YbST_profiles.txt -i yes --maxmissing 3 " + contigs)
 
 		Yb_ST = ""
 		Yb_group = ""
 		Yb_ST_detail = []
-		
+
 		for line in f:
 			fields = line.rstrip().split("\t")
 			if fields[2] != "ST":
@@ -119,15 +127,15 @@ def decompress_file(in_file, out_file):
 				if Yb_group == "":
 					Yb_group = "-"
 		f.close()
-		
+
 		# run colibactin MLST
-		
-		f = os.popen("python "+ options.repo_path + "/mlstBLAST.py -s "+ options.repo_path + "/data/colibactin_alleles.fasta -d "+ options.repo_path + "/data/CbST_profiles.txt -i yes --maxmissing 3 " + contigs) 
+
+		f = os.popen("python "+  mlstblast + " -s "+  data_folder + "/colibactin_alleles.fasta -d "+  data_folder + "/CbST_profiles.txt -i yes --maxmissing 3 " + contigs)
 
 		Cb_ST = ""
 		Cb_group = ""
 		Cb_ST_detail = []
-		
+
 		for line in f:
 			fields = line.rstrip().split("\t")
 			if fields[2] != "ST":
@@ -137,19 +145,19 @@ def decompress_file(in_file, out_file):
 				if Cb_group == "":
 					Cb_group = "-"
 		f.close()
-		
+
 		# screen for other virulence genes (binary calls)
 
-		f = os.popen("python "+ options.repo_path + "/clusterBLAST.py -s "+ options.repo_path + "/data/other_vir_clusters.fasta " + contigs) 
+		f = os.popen("python "+  clusterblast + " -s "+  data_folder + "/other_vir_clusters.fasta " + contigs)
 		for line in f:
 			fields = line.rstrip().split("\t")
 			if fields[1] != "aerobactin":
 				# skip header
 				(strain,vir_hits) = (fields[0],"\t".join(fields[1:]))
 		f.close()
-		
+
 		# screen for wzi allele
-		f = os.popen("python "+ options.repo_path + "/mlstBLAST.py -s " + options.repo_path + "/data/wzi.fasta -d " + options.repo_path + "/data/wzi.txt -i yes --maxmissing 0 -m 99 " + contigs) 
+		f = os.popen("python "+  mlstblast + " -s " +  data_folder + "/wzi.fasta -d " +  data_folder + "/wzi.txt -i yes --maxmissing 0 -m 99 " + contigs)
 		for line in f:
 			fields = line.rstrip().split("\t")
 			if fields[0] != "ST":
@@ -163,20 +171,20 @@ def decompress_file(in_file, out_file):
 		# screen for resistance genes
 		res_hits = ""
 		if options.resistance == "on":
-			f = os.popen("python "+ options.repo_path + "/resBLAST.py -s " + options.repo_path + "/data/ARGannot.r1.fasta -t " + options.repo_path + "/data/ARGannot_clustered80.csv -q" + options.repo_path + "/data/QRDR_120.aa " + contigs) 
+			f = os.popen("python "+  resblast + " -s " +  data_folder + "/ARGannot.r1.fasta -t " +  data_folder + "/ARGannot_clustered80.csv -q" +  data_folder + "/QRDR_120.aa " + contigs)
 			for line in f:
 				fields = line.rstrip().split("\t")
 				if fields[0] != "strain":
 					# skip header
-					res_hits = "\t".join(fields[1:])	
+					res_hits = "\t".join(fields[1:])
 			f.close()
 
 		# record results
 		print "\t".join([name,chr_ST,Yb_group,Yb_ST,Cb_group,Cb_ST,vir_hits,wzi_ST,Ktype]),
 		if options.resistance == "on":
 			print "\t" + res_hits,
 		print ""
-		
+
 		o.write("\t".join([name,chr_ST,Yb_group,Yb_ST,Cb_group,Cb_ST,vir_hits,wzi_ST,Ktype,chr_ST]+chr_ST_detail+[Yb_ST]+Yb_ST_detail + [Cb_ST] + Cb_ST_detail))
 		if options.resistance == "on":
 			o.write("\t" + res_hits)
@@ -190,5 +198,8 @@ def decompress_file(in_file, out_file):
 		# If we've been working on a temporary decompressed file, delete it now.
 		if temp_decompress:
 			os.remove(contigs)
-		
+
 	o.close()
+
+if __name__ == "__main__":
+	kleborate()

setup.py

@@ -0,0 +1,35 @@
+from setuptools import setup
+
+
+def readme():
+    with open('README.md') as f:
+        return f.read()
+
+
+setup(name='Kleborate',
+      version='0.0.1',
+      description='Kleborate',
+      long_description=readme(),
+      classifiers=[
+        'Development Status :: 4 - Beta',
+        'License :: OSI Approved :: GPLv3',
+        'Programming Language :: Python :: 2.7',
+        'Topic :: Scientific/Engineering :: Bio-Informatics',
+        'Topic :: Scientific/Engineering :: Medical Science Apps.',
+        'Intended Audience :: Science/Research',
+      ],
+      keywords='microbial genomics sequence typing',
+      url='https://github.com/katholt/Kleborate',
+      author='Kathryn Holt',
+      author_email='',
+      license='GPLv2',
+      packages=['kleborate'],
+      install_requires=[
+      ],
+      test_suite='nose.collector',
+      tests_require=[],
+      entry_points={
+          'console_scripts': ['kleborate=kleborate.Kleborate:kleborate'],
+      },
+      include_package_data=True,
+      zip_safe=False)

test.sh

@@ -20,4 +20,4 @@ mv GCA_000016305.1_ASM1630v1_genomic.fna MGH78578.fna
 
 # run typing
 # NOTE: -p must point to the Kleborate directory
-python Kleborate.py -p . -o details.txt *.fna
+kleborate -p . -o details.txt *.fna