def run():
file_step1 = './02-pipeline/step6.fna'
"""Retrieve known sequences"""
knownseqfile = known()
"""Check if a BLAST DB of step7_knownseq already exists; Make BLAST DB if it doesn't"""
blastdb = blast.check(knownseqfile)
"""BLAST unique mature peptides against known sequences"""
blastoutfile = './02-pipeline/step7_blastp.csv'
blast.blastp(blastdb, file_step1, blastoutfile)
"""Parse the BLASTp output file"""
print 'Parsing BLASTp output...\n'
blastout = []
for b in blast.parse(
blastoutfile): #[cds_id, known sequence, %ID, length, evalue]
blastout.append([str(b[0]), b[1], b[2], b[3], b[4]])
"""Populate the SQLite Annotated table with BLASTp results"""
print 'Populating the Annotated table in the SQLite DB.'
count = 0
for b in blastout:
c = mysqlpop.annotated(b)
count += c
print '{} hits have been entered in the SQLite annotated table.'.format(
count)
print 'DATA ENTRY INTO MYSQL ANNOTATED TABLE IS COMPLETE'
filename = './02-pipeline/step7.csv'
header = ['cds_id', 'knownNP id', 'PID', 'length', 'evalue']
output.csv(filename, header, blastout)
print 'The BLASTp results have were written to {}.\n'.format(filename)
def main():
"""
Función que ejecuta todas las demas funciones
"""
# Control de argumentos
try:
query, subject, prosite, cov, ide = ctrl_arguments()
es_fasta(query)
results()
except:
sys.exit()
# Blastp
try:
print("EJECUTANDO MODULO BLASTP...")
multifasta = bl.convert(subject)
db = bl.data_base(multifasta)
dict_query = bl.dictionary(query)
output = bl.blastp(query, db)
bl.blastp_final(output, cov, ide, dict_query)
print("\n~ Se ha realizado Blastp\n")
except:
print("\n~ No se ha realizado Blastp\n")
sys.exit()
# Muscle
try:
print("EJECUTANDO MODULO MUSCLE...")
mu.muscle()
print("\n~ Se ha realizado Muscle\n")
except:
print("\n~ No se ha realizado Muscle\n")
sys.exit()
# Dominios
try:
print("EJECUTANDO MODULO DOMINIOS...")
db = do.parseo_dat(prosite)
dict_pattern = do.dictionary_patterns(db)
do.search_pattern(dict_pattern)
print("\n~ Se ha realizado la busqueda de dominios\n")
except:
print("\n~ No se ha realizado la busqueda de dominios\n")
sys.exit()
# Graficos de Blastp
try:
print("EJECUTANDO MODULO GRAFICACIÓN...")
gr.result_blast(output, cov, ide, dict_query)
gr.graph_blast()
gr.archivos_heatmap()
gr.graph_heatmap()
print("\n~ Se ha realizado la grafiaccion de los resultados"
" del Blastp")
except:
print("\n~ No se ha realizado la graficacion de los resultados"
" del Blastp")
sys.exit()
# Eliminar residuos
clear()
# Concluir
message = ("""
-------------------------------------------------------------\n
SE HA EJECUTADO EL PROGRAMA CON EXITO\n
-------------------------------------------------------------
""")
print(message)
#Definición argumentos obligatorios
query = sys.argv[1]
subject = sys.argv[2]
#Definición argumentos opcionales
if len(sys.argv) == 3:
cov = 50
identity = 25
elif len(sys.argv) == 5:
cov = sys.argv[3]
identity = sys.argv[4]
else:
print("Error: number of arguments introduced is not valid")
help()
sys.exist()
#Ejecución del blast.py:
bs.multifasta(subject)
bs.database()
dicti = bs.dictionary(query)
output = bs.blastp(query)
bs.finalblast(cov, identity, dicti)
#Ejecución de muscle.py:
mc.muscle()
#Ejecución de dominios.py:
a = dm.parsear()
dictionary = dm.dicti()
dm.search(dictionary)
try:
subject_info_allDB = pickle.load(open(blast_all_pickle, 'rb'))
except (EOFError, KeyError) as e:
repr(e)
print('Removing pickle file, redoing blast')
os.remove(blast_all_pickle)
###### use if not instead of else incase the error above got thrown, and file got removed
if not developing or not os.path.isfile(blast_all_pickle):
print 'blasting against all'
blast.makeBLASTdb(script_path + 'fasta_files' + os.sep + organism_name +
'_all_proteins_smaller_than_500aa.fasta', script_path +
'databases' + os.sep + 'allDB_' + organism_name,
blast_folder) # make all proteins database
blast_records = blast.blastp(
interest_proteins_path,
script_path + 'databases' + os.sep + 'allDB_' + organism_name,
args['eval_all'], blast_folder, script_path + 'blast_results/' +
organism_name + '_blastpAllOutput.xml')
subject_info_allDB = blast.getSubjectInfo(blast_records,
proteins_of_interest,
args['eval_all'])
if developing:
print 'saving in ' + blast_all_pickle
if not os.path.exists(script_path + 'blast_results'):
os.makedirs(script_path + 'blast_results')
f = open(blast_all_pickle, 'wb')
pickle.dump(subject_info_allDB, f)
print('len subject_info_allDB after < ' + str(args['all_size']) +
'a.a. Protein blast: ' + str(len(subject_info_allDB)) + '\n')
subject_info_total = dict(subject_info_allDB.items())
os.makedirs(script_path+'blast_results')
blast_all_pickle = script_path+'blast_results'+os.sep+fix_file_names(organism_name+'_blast_all_'+str(args['eval_all'])+'.p')
if developing:
if os.path.isfile(blast_all_pickle):
print 'BLAST records with this e-value against ALL database already exists, loading: '+blast_all_pickle
try:
subject_info_allDB = pickle.load( open(blast_all_pickle, 'rb' ))
except (EOFError, KeyError) as e:
repr(e)
print('Renoving pickle file, redoing blast')
os.remove(blast_all_pickle)
###### use if not instead of else incase the error above got thrown, and file got removed
if not developing or not os.path.isfile(blast_all_pickle):
print 'blasting against all'
blast.makeBLASTdb(script_path+'fasta_files'+os.sep+organism_name + '_all_proteins_smaller_than_500aa.fasta', script_path+'databases'+os.sep+'allDB_'+organism_name, blast_folder) # make all proteins database
blast_records = blast.blastp(interest_proteins_path, script_path+'databases'+os.sep+'allDB_'+organism_name, args['eval_all'], blast_folder, script_path+'blast_results/'+organism_name+'_blastpAllOutput.xml')
subject_info_allDB = blast.getSubjectInfo(blast_records, proteins_of_interest, args['eval_all'])
if developing:
print 'saving in '+blast_all_pickle
if not os.path.exists(script_path+'blast_results'):
os.makedirs(script_path+'blast_results')
f = open(blast_all_pickle, 'wb' )
pickle.dump( subject_info_allDB, f )
print('len subject_info_allDB after < '+str(args['all_size'])+'a.a. Protein blast: '+str(len(subject_info_allDB))+'\n')
#if developing:
# for subject in subject_info_allDB: # Loop over all
# print subject_info_allDB[subject]['query_title']
# for prot in not_found:
# if prot.lower() in subject.lower():
# print('found in allDb')