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 _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, 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_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):
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
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_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_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"
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():
## THIS WORKED, DON'T ERASE
## Save organism data to pickled dictionary
#pickle_fasta = PickleFasta()
#fasta_dictionary = pickle_fasta.pickle_organism_fasta()
#print "There are %d entries in the fasta_dictionary" % len(fasta_dictionary)
#pickle.dump(fasta_dictionary, open('organism_dictionary.pkl', 'wb'))
file_handlers = FileHandlers()
dm_files = get_dm_files()
# Load the dictionary back from the pickle file
print "Loading fasta_dictionary..."
open_fasta = open('organism_dictionary.pkl', 'rb')
fasta_dictionary = pickle.load(open_fasta)
open_fasta.close()
print "Length of fasta dictionary: ", len(fasta_dictionary)
## THIS WORKED, DON'T ERASE
## Build mapping dictionary and pickle
dm_processing = dmDictionary()
dm_processing.init_mapping_dictionary(fasta_dictionary)
for path in dm_files:
file_name = file_handlers.get_file_name(path)
print "Opening %s..." % file_name
dm_dictionary = dm_processing.individual_dm_dictionary(path, file_name)
print "Length of dm_dictionary for %s is %d" % (file_name, len(dm_dictionary))
mapping_dictionary = dm_processing.build_mapping_dictionary(fasta_dictionary, dm_dictionary)
open_mapping = open('mapping_dictionary.pkl', 'wb')
pickle.dump(mapping_dictionary, open_mapping)
open_mapping.close()
print mapping_dictionary
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() 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 build_SASA_dict(out_files):
SASA_dict = {}
for path in out_files:
file_handlers = FileHandlers()
file_name = file_handlers.get_file_name(path)
SASA_dict[file_name] = {}
for line in open(path):
file_handlers2 = FileHandlers()
fields = line.split('\t')
cleaned = file_handlers2.clean(fields)
if len(cleaned) == 9: #and int(cleaned[2]) >= 1:
(position,
aa,
tot_SA,
SASA,
frac_SASA,
phob,
phil) = (cleaned[2],
cleaned[0],
cleaned[8],
cleaned[5],
cleaned[6],
cleaned[3],
cleaned[4])
SASA_dict[file_name][position] = [aa,
tot_SA,
SASA,
frac_SASA,
phob,
phil]
return SASA_dict
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 _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_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, 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_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_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 find_indices(path): file_handlers = FileHandlers() #for path in fasta_files: indices = [] open_file = open(path, 'rU') file_list = open_file.readlines() for line in file_list: if '>' in line: indices.append(file_list.index(line)) interval = indices[1] - indices[0] file_name = file_handlers.get_file_name(path) return file_name, file_list, interval
def build_distance_dict(dm_files, inverse_mapping_dict, organism_pairs):
file_handlers = FileHandlers()
for dm_file in dm_files:
file_name = file_handlers.get_file_name(dm_file)
print "Opening %s...." % file_name
data = open(dm_file)
D = data.readlines()
data.close()
for d in D:
data = d.strip().split(' ')
enz1 = data[0]
enz2 = data[1]
distance = data[-1]
for key in organism_pairs:
if enz1 in inverse_mapping_dict and enz2 in inverse_mapping_dict:
if inverse_mapping_dict[enz1] in key and inverse_mapping_dict[enz2] in key:
#print inverse_mapping_dict[enz1], inverse_mapping_dict[enz2], key
organism_pairs[key].append(distance)
#print organism_pairs[key]
#print "Length of distance list is %d" % len(organism_pairs[key])
else:
print "Could not find %s and %s in mapping_dict" % (enz1, enz2)
print "Finished parsing %s...." % file_name
return organism_pairs
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)
# sequences = open_file.readlines()
# i = 0
# while i < len(sequences):
# if sequences[i] in temp_dict:
# i += 14
# else:
# temp_dict[sequences[i]] = sequences[i + 1 : i + 13]
# new_file.write(str(i) + "\n")
# for item in temp_dict[sequences[i]]:
# new_file.write(item)
# i += 14
fasta_files = file_handlers.find_files(file_paths, "fasta")
for path in fasta_files:
file_name = file_handlers.get_file_name(path)
print file_name
name_list = file_name.split(".")
# derep_out_file = ''.join(name_list[0] + '_uniques.fasta')
dm_out_file = "".join(name_list[0] + "_dm.txt")
# cmd = ['usearch -derep_fulllength ' + path + ' -fastaout ' + derep_out_file]
# subprocess.call(cmd, shell=True)
new_file = open("/Users/andrea/repositories/AMPHORA2/muscle_alignments/" + dm_out_file, "w")
aln = AlignIO.read(path, "fasta")
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)
new_file.write(dm)
new_file.close()
