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 _build_data_dict(self, file_tag):
self.data_dict = {}
self._get_data(file_tag)
file_handlers = FileHandlers()
for line in self.data:
fields = line.split('\t')
cleaned = file_handlers.clean(fields)
self.data_dict[cleaned[0]] = float(cleaned[1])
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_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_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_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 _build_SASA_dict(self):
file_handlers = FileHandlers()
self.SASA_dict[self.filename] = {}
self._run_POPS()
self._get_data()
for line in self.data:
fields = line.split('\t')
cleaned = file_handlers.clean(fields)
if len(cleaned) == 9:
(position, aa, tot_SA, SASA, frac_SASA, phob,
phil) = (cleaned[2], cleaned[0], cleaned[8], cleaned[5],
cleaned[6], cleaned[3], cleaned[4])
self.SASA_dict[self.filename][position] = [
aa, tot_SA, SASA, frac_SASA, phob, phil
]
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 _mkdir(self):
file_handlers = FileHandlers()
file_handlers.make_results_folder(self.dir_path.split('/')[-1])
