def __init__(self, pdb_code, sequence_annotations, SurfRes=False,
pocket=False, lpocket=False):
self.filename = pdb_code
self.sequence_annotations = sequence_annotations
if SurfRes:
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if (self.filename + '_SurfRes.txt') == \
file_handlers.get_file_name(txt_file):
self.surfres_file = txt_file
else:
self.surfres_file = ''
if pocket:
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if (self.filename + '_pocketres.txt') == \
file_handlers.get_file_name(txt_file):
self.pocketres_file = txt_file
else:
self.pocketres_file = ''
if lpocket:
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if (self.filename + '_lpocket.txt') == \
file_handlers.get_file_name(txt_file):
self.lpocket_file = txt_file
else:
self.lpocket_file = ''
def _get_outfile(self):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
out_files = file_handlers.find_files(file_paths, 'out')
if (self.pdb_code != '' and self.psiblast != ''):
for out_file in out_files:
if (self.pdb_code + '_mutants') == \
file_handlers.get_file_name(out_file).split('.')[0]:
self.ddG_results_filepath = out_file
elif (self.psiblast + '_mutants') == \
file_handlers.get_file_name(out_file).split('.')[0]:
self.llikelihood_filepath = out_file
elif (self.pdb_code != '' and self.psiblast == ''):
for out_file in out_files:
if (self.pdb_code + '_mutants') == \
file_handlers.get_file_name(out_file).split('.')[0]:
self.ddG_results_filepath = out_file
print "Fetching data from %s ....." % \
file_handlers.get_file_name(out_file)
elif (self.pdb_code == '' and self.psiblast != ''):
for out_file in out_files:
if (self.psiblast + '_mutants') == \
file_handlers.get_file_name(out_file).split('.')[0]:
self.llikelihood_filepath = out_file
else:
print "You have not specified any results data to parse."
exit(1)
def main(): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() fasta_files = file_handlers.find_files(file_paths, 'fasta') for path in fasta_files: file_name = file_handlers.get_file_name(path) get_dm_raxml(path, file_name, 4)
def _get_downloaded_file_path(self, pdb_code):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
ent_files = file_handlers.find_files(file_paths, 'ent')
for ent_file in ent_files:
if pdb_code == file_handlers.get_file_name(ent_file).split('.')[0].lstrip('pdb').upper():
return ent_file
class PickleFasta:
def __init__(self):
self.file_handlers = FileHandlers()
def _get_fasta_files(self):
file_paths = self.file_handlers.search_directory()
fasta_files = self.file_handlers.find_files(file_paths, 'faa')
print "There are %d .faa files in this directory" % len(fasta_files)
return fasta_files
def pickle_organism_fasta(self):
fasta_files = self._get_fasta_files()
fasta_dictionary = {}
for fasta_file in fasta_files:
file_name = self.file_handlers.get_file_name(fasta_file)
name_list = file_name.split('.')
Data = open(fasta_file)
D = Data.readlines()
Data.close()
for d in D:
if d.startswith('>'):
d_list = d.split(' ')
if name_list[0] in fasta_dictionary:
fasta_dictionary[name_list[0]].append(d_list[0].lstrip('>'))
else:
fasta_dictionary[name_list[0]] = [d_list[0].lstrip('>')]
else:
pass
return fasta_dictionary
def main(): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() fasta_files = file_handlers.find_files(file_paths, 'fasta') for path in fasta_files: file_name, file_list, interval = find_indices(path) write_fasta_new_names(path, file_name, file_list, interval)
def _get_pdb_file_path(self):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if (self.filename + '_0001') == file_handlers.get_file_name(pdb_file).split('.')[0]:
self.file_path = pdb_file
def main():
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pep_files = file_handlers.find_files(file_paths, "pep")
for pep_file in pep_files:
file_name = file_handlers.get_file_name(pep_file)
run_muscle(pep_file, file_name)
def _get_downloaded_file_path(self, pdb_code):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
ent_files = file_handlers.find_files(file_paths, 'ent')
for ent_file in ent_files:
if pdb_code == file_handlers.get_file_name(ent_file).split(
'.')[0].lstrip('pdb').upper():
return ent_file
def _open_file(self):
#os.chdir("../src/database/pdbs")
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split('.')[0]:
Data = open(pdb_file)
self.data = Data.readlines()
Data.close
def _get_file_path(self):
os.chdir("./database/pdbs/pdb")
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split(
'.')[0]:
self.file_path = pdb_file
os.chdir("../../../")
def _get_data(self, filename):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if filename == file_handlers.get_file_name(txt_file):
TXT = open(txt_file)
data = TXT.readlines()
TXT.close()
return data
def _get_pdb(self):
#os.chdir("./database/pdbs/pdb")
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split('.')[0]:
PDB = open(pdb_file)
self.pdb = PDB.readlines()
PDB.close()
def _get_data(self, file_tag):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if self.filename == file_handlers.get_file_name(txt_file).split('_')[0]:
if (file_tag.split('_')[1] + '.txt') == file_handlers.get_file_name(txt_file).split('_')[1]:
TXT = open(txt_file)
self.data = TXT.readlines()
TXT.close()
def _get_output(self): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() out_files = file_handlers.find_files(file_paths, 'out') for out_file in out_files: TXT = open(out_file) data = TXT.readlines() TXT.close() os.remove(out_file) return data
def _get_file_path(self):
os.chdir("./database/pdbs/pdb")
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if (self.filename + '_0001') == file_handlers.get_file_name(pdb_file).split('.')[0]:
self.file_path = pdb_file
self.out_file = file_handlers.get_file_name(pdb_file).split('.')[0] + '_pops.out'
self.out_file_path = self.dir_path + '/' + self.out_file
def _get_data(self, filename): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() txt_files = file_handlers.find_files(file_paths, 'txt') for txt_file in txt_files: if filename == file_handlers.get_file_name(txt_file): TXT = open(txt_file) data = TXT.readlines() TXT.close() return data
def _get_gb_record(self):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
gb_files = file_handlers.find_files(file_paths, 'gb')
print gb_files
print self.genbank_id
for gb_file in gb_files:
if self.genbank_id == file_handlers.get_file_name(gb_file).split(
'.')[0]:
self.gb_file_path = gb_file
print self.gb_file_path
def _get_pdb(self):
#os.chdir("./database/pdbs/pdb")
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split(
'.')[0]:
PDB = open(pdb_file)
self.pdb = PDB.readlines()
PDB.close()
def _get_filename(self):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, "pdb")
if self.tag == "":
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split(".")[0]:
return file_handlers.get_file_name(pdb_file).split(".")[0]
else:
for pdb_file in pdb_files:
if (self.filename + self.tag) == file_handlers.get_file_name(pdb_file).split(".")[0]:
return file_handlers.get_file_name(pdb_file).split(".")[0]
def _get_data(self, file_tag):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
txt_files = file_handlers.find_files(file_paths, 'txt')
for txt_file in txt_files:
if self.filename == file_handlers.get_file_name(txt_file).split(
'_')[0]:
if (file_tag.split('_')[1] + '.txt'
) == file_handlers.get_file_name(txt_file).split('_')[1]:
TXT = open(txt_file)
self.data = TXT.readlines()
TXT.close()
def _get_file_path(self, ligand=False, pdb=False):
#os.chdir("./database/pdbs/pdb")
self.file_path = ''
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
if ligand == True:
for pdb_file in pdb_files:
if self.filename == file_handlers.get_file_name(pdb_file).split('.')[0]:
self.file_path = pdb_file
elif pdb == True:
for pdb_file in pdb_files:
if (self.filename + '_0001') == file_handlers.get_file_name(pdb_file).split('.')[0]:
self.file_path = pdb_file
def _get_filepath(self, data_file=False, pdb_file=False):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
if data_file == True:
files = file_handlers.find_files(file_paths, 'txt')
for path in files:
if (self.filename + '_mutant_list') == file_handlers.get_file_name(path).split('.')[0]:
return path
elif pdb_file == True:
files = file_handlers.find_files(file_paths, 'pdb')
for path in files:
if (self.filename + '_0001') == file_handlers.get_file_name(path).split('.')[0]:
return path
else:
print "Specify file type"
def _get_pdb(self, rosetta_min=False, refined_pocket=False):
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
pdb_files = file_handlers.find_files(file_paths, 'pdb')
for pdb_file in pdb_files:
if rosetta_min == True and refined_pocket == True:
print "Invalid input"
elif rosetta_min == True:
if (self.filename + '_0001') == file_handlers.get_file_name(pdb_file).split('.')[0]:
print "Found ", (self.filename + '_0001.pdb')
filepath = pdb_file
elif refined_pocket == True:
if ('pocket0') == file_handlers.get_file_name(pdb_file).split('.')[0]:
print "Found pocket0.pdb"
filepath = pdb_file
else:
if self.filename == file_handlers.get_file_name(pdb_file).split('.')[0]:
print "Found ", (self.filename + '.pdb')
filepath = pdb_file
return filepath
def LoadFiles(extention): """Get the paths to the .txt files listed in the current directory Useful when you have a set of custom .txt files that need to be loaded and parsed prior to some calculation or data analysis Parameters ---------- none Returns ------- list List of strings corresponding to the path/to/file.txt for each txt file found in the current directory Examples -------- >>> all_files = LoadFiles() """ file_handlers = FileHandlers() file_paths = file_handlers.search_directory() files = file_handlers.find_files(file_paths, extention) return files
def get_dm_files(): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() dm_files = file_handlers.find_files(file_paths, 'dm') return dm_files
import subprocess
from util import FileHandlers
from Bio.Phylo.TreeConstruction import DistanceCalculator
from Bio import AlignIO
file_handlers = FileHandlers()
file_paths = file_handlers.search_directory()
# fasta_files = file_handlers.find_files(file_paths, 'faa')
# for path in fasta_files:
# cmd = ['perl ./Scripts/MarkerScanner.pl -Bacteria ' + path]
# subprocess.call(cmd, shell=True)
# file_paths = file_handlers.search_directory()
# pep_files = file_handlers.find_files(file_paths, 'pep')
#
# for path in pep_files:
# file_name = file_handlers.get_file_name(path)
# name_list = file_name.split('.')
# out_file = ''.join([name_list[0] + '_out.' + name_list[1]])
# cmd = ['muscle -in ' + path + ' -out ' + out_file]
# subprocess.call(cmd, shell=True)
def run_muscle(path):
file_name = file_handlers.get_file_name(path)
name_list = file_name.split(".")
out_file = "".join(name_list[0] + "_out." + name_list[1])
cmd = ["muscle -in " + path + " -out " + out_file]
subprocess.call(cmd, shell=True)
import subprocess
from util import FileHandlers
from Bio.Phylo.TreeConstruction import DistanceCalculator
from Bio import AlignIO
file_handlers = FileHandlers()
#file_paths = file_handlers.search_directory()
#fasta_files = file_handlers.find_files(file_paths, 'faa')
#for path in fasta_files:
# cmd = ['perl ./Scripts/MarkerScanner.pl -Bacteria ' + path]
# subprocess.call(cmd, shell=True)
file_paths = file_paths = file_handlers.search_directory()
pep_files = file_handlers.find_files(file_paths, 'pep')
for path in pep_files:
file_name = file_handlers.get_file_name(path)
name_list = file_name.split('.')
out_file = ''.join([name_list[0] + '_out.' + name_list[1]])
cmd = ['muscle -in ' + path + ' -out ' + out_file]
subprocess.call(cmd, shell=True)
#aln = AlignIO.read('path/to/alignnment/file', 'format (i.e. phylip)')
#calculator = DistanceCalculator('identity') # identity is the name of the model(scoring matrix) to calculate the distance. The identity model is the default one and can be used both for DNA and protein sequence.
#dm = calculator.get_distance(aln)
def load_out_files(): file_handlers = FileHandlers() file_paths = file_handlers.search_directory() out_files = file_handlers.find_files(file_paths, 'out') return out_files
