0.3.0: Getting ready for pypi release

MANIFEST.in

@@ -1,2 +1,3 @@
 include README.md
 include LICENSE
+recursive-include tobias *.c

setup.py

@@ -1,49 +1,84 @@
+import os
+import sys
+import re
 from setuptools import setup, Extension
-import numpy as np
 
-def readme():
-    with open('README.md') as f:
-        return f.read()
+#Test if numpy is installed
+try:
+	import numpy as np
+except:
+	sys.exit("ERROR: Numpy needed for TOBIAS installation. Numpy can be installed using the command \"pip install numpy\"")
+
+cmdclass = {}
+
+#Add cython modules depending on the availability of cython
+try:
+	from Cython.Distutils import build_ext
+except ImportError:
+	use_cython = False
+else:
+	use_cython = True
+
+if use_cython:
+	ext_modules = [Extension("tobias.utils.ngs", ["tobias/utils/ngs.pyx"], include_dirs=[np.get_include()]),
+					Extension("tobias.utils.sequences", ["tobias/utils/sequences.pyx"], include_dirs=[np.get_include()]),
+					Extension("tobias.utils.signals", ["tobias/utils/signals.pyx"], include_dirs=[np.get_include()])]
+	cmdclass.update({'build_ext': build_ext})
+
+else:
+	ext_modules = [Extension("tobias.utils.ngs", ["tobias/utils/ngs.c"], include_dirs=[np.get_include()]),
+						Extension("tobias.utils.sequences", ["tobias/utils/sequences.c"], include_dirs=[np.get_include()]),
+						Extension("tobias.utils.signals", ["tobias/utils/signals.c"], include_dirs=[np.get_include()])]
 
-ext_modules = [Extension("tobias.utils.ngs", ["tobias/utils/ngs.pyx"], include_dirs=[np.get_include()]),
-              Extension("tobias.utils.sequences", ["tobias/utils/sequences.pyx"], include_dirs=[np.get_include()]),
-               Extension("tobias.utils.signals", ["tobias/utils/signals.pyx"], include_dirs=[np.get_include()])]
+#Path of setup file to establish version
+setupdir = os.path.abspath(os.path.dirname(__file__))
+
+def find_version(init_file):
+	version_file = open(init_file).read()
+	version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", version_file, re.M)
+	if version_match:
+		return version_match.group(1)
+	else:
+		raise RuntimeError("Unable to find version string.")
+
+def readme():
+	with open('README.md') as f:
+		return f.read()
 
 setup(name='tobias',
-      version='0.2',
-      description='Transcription factor Occupancy prediction By Investigation of ATAC-seq Signal',
-      long_description=readme(),
-      url='https://github.molgen.mpg.de/loosolab/TOBIAS',
-      author='Mette Bentsen',
-      author_email='mette.bentsen@mpi-bn.mpg.de',
-      license='MIT',
-      packages=['tobias', 'tobias.footprinting', 'tobias.plotting', 'tobias.motifs', 'tobias.misc', 'tobias.utils'],
-      entry_points = {
-        'console_scripts': ['TOBIAS=tobias.TOBIAS:main']
-      },
-      install_requires=[
-        'setuptools_cython',
-        'numpy',
-        'scipy',
-        'pyBigWig',
-        'pysam',
-        'pybedtools',
-        'matplotlib>=2',
-        'scikit-learn',
-        'pandas',
-        'pypdf2',
-        'xlsxwriter',
-        'adjustText',
-      ],
-      #dependency_links=['https://github.com/jhkorhonen/MOODS/tarball/master'],
-      classifiers = [
-        'License :: OSI Approved :: MIT License',
-        'Intended Audience :: Science/Research',
-        'Topic :: Scientific/Engineering :: Bio-Informatics',
-        'Programming Language :: Python :: 3'
-      ],
-      zip_safe=False,
-      include_package_data=True,
-      ext_modules = ext_modules,
-      scripts=["tobias/utils/peak_annotation.sh"]
-      )
+		version=find_version(os.path.join(setupdir, "tobias", "__init__.py")),	#get version from __init__.py
+		description='Transcription factor Occupancy prediction By Investigation of ATAC-seq Signal',
+		long_description=readme(),
+		url='https://github.molgen.mpg.de/loosolab/TOBIAS',
+		author='Mette Bentsen',
+		author_email='mette.bentsen@mpi-bn.mpg.de',
+		license='MIT',
+		packages=['tobias', 'tobias.footprinting', 'tobias.plotting', 'tobias.motifs', 'tobias.misc', 'tobias.utils'],
+		entry_points={
+			'console_scripts': ['TOBIAS=tobias.TOBIAS:main']
+		},
+		ext_modules=ext_modules,
+		cmdclass = cmdclass,
+		#dependency_links=['https://github.com/jhkorhonen/MOODS/releases/download/v1.9.3/MOODS-python-1.9.3.tar.gz#egg=MOODS-python-1.9.3'],	
+		install_requires=[
+			'numpy',
+			'scipy',
+			'pysam',
+			'pybedtools',
+			'matplotlib>=2',
+			'scikit-learn',
+			'pandas',
+			'pypdf2',
+			'xlsxwriter',
+			'adjustText',
+			'pyBigWig',
+		],
+
+		classifiers=[
+			'License :: OSI Approved :: MIT License',
+			'Intended Audience :: Science/Research',
+			'Topic :: Scientific/Engineering :: Bio-Informatics',
+			'Programming Language :: Python :: 3'
+		],
+		zip_safe=True,
+		)

tobias/TOBIAS.py

@@ -9,6 +9,18 @@
 """
 
 import sys
+
+#Import extra dependencies
+try:
+	import MOODS
+except:
+	sys.exit("ERROR: Package MOODS is not installed and is needed by TOBIAS. You can install it using:\n" +
+			"$ wget https://github.com/jhkorhonen/MOODS/releases/download/v1.9.3/MOODS-python-1.9.3.tar.gz\n" +
+			"$ tar xzvf MOODS-python-1.9.3.tar.gz\n" + 
+			"$ cd  MOODS-python-1.9.3\n"
+			"$ python setup.py install")
+
+#Import general 
 import argparse
 from argparse import SUPPRESS
 import textwrap
@@ -23,7 +35,7 @@
 
 from tobias.motifs.tfbscan import * 
 from tobias.motifs.format_motifs import * 
-from tobias.motifs.cluster_tfbs import *
+#from tobias.motifs.cluster_tfbs import *
 from tobias.motifs.score_bed import *
 
 from tobias.misc.subsample_bam import *
@@ -32,8 +44,7 @@
 #from tobias.misc.create_network import *
 from tobias.misc.log2table import *
 
-
-TOBIAS_VERSION = "0.2"  #<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< Change here :-)
+from tobias import __version__ as TOBIAS_VERSION
 
 def main():
 
@@ -43,14 +54,14 @@ def main():
 							{
 							"ATACorrect":{"help":"Correct reads with regards to Tn5 sequence bias", "add_arguments": add_atacorrect_arguments, "function":run_atacorrect},
 							"FootprintScores":{"help":"Calculate footprint scores from cutsites", "add_arguments": add_footprint_arguments, "function":run_footprinting, "space":"\t"},
-							"BINDetect":{"help":"Detect TF binding from footprints", "add_arguments": add_bindetect_arguments, "function":run_bindetect},
+							"BINDetect":{"help":"Detect TF binding from footprints and motifs", "add_arguments": add_bindetect_arguments, "function":run_bindetect},
 							},
 
 						"Tools for working with motifs/TFBS":
 							{
 							"TFBScan": {"help":"Identify positions of TFBS given sequence and motifs", "add_arguments": add_tfbscan_arguments, "function": run_tfbscan},
 							"FormatMotifs": {"help": "Utility to deal with motif files", "add_arguments": add_formatmotifs_arguments, "function": run_formatmotifs},
-							"ClusterTFBS": {"help": "Cluster TFs based on overlap of sites", "add_arguments": add_clustering_arguments, "function": run_clustering},
+							#"ClusterTFBS": {"help": "Cluster TFs based on overlap of sites", "add_arguments": add_clustering_arguments, "function": run_clustering},
 							"ScoreBed": {"help":"Score .bed-file with signal from .bigwig-file(s)", "add_arguments": add_scorebed_arguments, "function": run_scorebed},
 							},
 

tobias/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.0"

tobias/footprinting/ATACorrect.py

@@ -30,7 +30,6 @@
 from collections import OrderedDict
 import logging
 import itertools
-from scipy.optimize import curve_fit
 from matplotlib.backends.backend_pdf import PdfPages
 
 #Bio-specific packages
@@ -116,11 +115,6 @@ def run_atacorrect(args):
 	if args.peaks == None:
 		sys.exit("Error: No .peaks-file given")
 
-	#Adjust input files to full path
-	#args.bam = os.path.abspath(args.bam)
-	#args.genome = os.path.abspath(args.genome)
-	#args.peaks = os.path.abspath(args.peaks) if args.peaks != None else None
-
 	#Adjust some parameters depending on input
 	args.prefix = os.path.splitext(os.path.basename(args.bam))[0] if args.prefix == None else args.prefix
 	args.outdir = os.path.abspath(args.outdir) if args.outdir != None else os.path.abspath(os.getcwd())
@@ -168,31 +162,12 @@ def run_atacorrect(args):
 
 	logger.info("----- Processing input data -----")
 
-	#Todo: use TOBIAS functions
-
-	#Input test
 	logger.debug("Testing input file availability")
-	file_list = [args.bam, args.genome, args.peaks]
-	file_list = [file for file in file_list if file != None]				#some files can be None depending on choice
-	for path in file_list:
-		if not os.path.exists(path):
-			logger.error("\nError: {0} does not exist.".format(path))
-			sys.exit(1)
+	check_files([args.bam, args.genome, args.peaks], "r")
 
 	logger.debug("Testing output directory/file writeability")
 	make_directory(args.outdir)
-	if not os.access(args.outdir, os.W_OK):
-		logger.error("Error: {0} does not exist or is not writeable.".format(args.outdir))
-		sys.exit(1)
-
-	#Output write test
-	for path in output_files[:-1]:	#Do not include log-file as this is managed by logger
-		if path == None:
-			continue
-		if os.path.exists(path):
-			if not os.access(path, os.W_OK):
-				logger.error("Error: {0} could not be opened for writing.".format(path))
-				sys.exit(1)
+	check_files(output_files, "w")
 
 	#Open pdf for figures
 	figure_pdf = PdfPages(figures_f, keep_empty=True)
@@ -368,10 +343,8 @@ def run_atacorrect(args):
 	logger.info("Finalizing bias motif for scoring")
 	for strand in strands:
 		bias_obj.bias[strand].prepare_mat()
-
 		figure_pdf.savefig(plot_pssm(bias_obj.bias[strand].pssm, "Tn5 insertion bias of reads ({0})".format(strand)))
 
-
 	#----------------------------------------------------------------------------------------------------#
 	# Correct read bias and write to bigwig
 	#----------------------------------------------------------------------------------------------------#

tobias/footprinting/ATACorrect_functions.py

@@ -16,7 +16,6 @@
 import multiprocessing as mp
 import time
 from datetime import datetime
-
 import matplotlib.pyplot as plt
 import matplotlib.ticker as ticker
 from scipy.optimize import curve_fit
@@ -135,7 +134,7 @@ def bias_estimation(regions_list, params):
 				for read in read_lst_strand[strand]:
 					if read.cigartuples is not None:
 						first_tuple = read.cigartuples[-1] if read.is_reverse else read.cigartuples[0]
-						if first_tuple[0] == 0 and first_tuple[1] > params.k_flank + max(np.abs(params.read_shift)):
+						if first_tuple[0] == 0 and first_tuple[1] > params.k_flank + max(np.abs(params.read_shift)):	#Only include non-clipped reads
 							read_per_pos[read.cutsite] = read_per_pos.get(read.cutsite, []) + [read]
 
 				for cutsite in read_per_pos: