def runProgram(Species,Array_type,mir_source,stringency,Force):
global species; global array_type; global force
process_microRNA_predictions = 'yes'
species = Species; array_type = Array_type; force = Force
import_dir = '/AltDatabase/'+species+'/'+array_type
filedir = import_dir[1:]+'/'
dir_list = read_directory(import_dir) #send a sub_directory to a function to identify all files in a directory
probeset_seq_file=''
for input_file in dir_list: #loop through each file in the directory to results
if 'critical-exon-seq_updated' in input_file: probeset_seq_file = filedir+input_file
elif 'critical-exon-seq' in input_file: probeset_seq_file2 = filedir+input_file
if len(probeset_seq_file)==0: probeset_seq_file=probeset_seq_file2
data_type = 'critical-exons'
try: splice_event_db = getParametersAndExecute(probeset_seq_file,array_type,species,data_type)
except UnboundLocalError:
probeset_seq_file = 'AltDatabase/'+species+'/'+array_type+'/'+array_type+'_critical-exon-seq_updated.txt'
update.downloadCurrentVersion(probeset_seq_file,array_type,'txt')
splice_event_db = getParametersAndExecute(probeset_seq_file,array_type,species,data_type)
if process_microRNA_predictions == 'yes':
print 'stringency:',stringency
try:
ensembl_mirna_db = ExonSeqModule.importmiRNATargetPredictionsAdvanced(species)
ExonSeqModule.alignmiRNAData(array_type,mir_source,species,stringency,ensembl_mirna_db,splice_event_db)
except Exception: pass
def runExtractUniProt(species,species_full,uniprot_filename_url,trembl_filename_url,force):
global uniprot_ensembl_db;uniprot_ensembl_db={}
global uniprot_db;uniprot_db={}; global species_name; global uniprot_fildir
global secondary_to_primary_db; secondary_to_primary_db={}
import update; reload(update)
species_name = species_full
import UI; species_names = UI.getSpeciesInfo()
species_full = species_names[species]
species_full = string.replace(species_full,' ','_')
uniprot_file = string.split(uniprot_filename_url,'/')[-1]; uniprot_file = string.replace(uniprot_file,'.gz','')
trembl_file = string.split(trembl_filename_url,'/')[-1]; trembl_file = string.replace(trembl_file,'.gz','')
uniprot_fildir = 'AltDatabase/uniprot/'+species+'/'
uniprot_download_fildir = 'AltDatabase/uniprot/'
uniprot_ens_file = species+'_Ensembl-UniProt.txt'; uniprot_ens_location = uniprot_fildir+uniprot_ens_file
uniprot_location = uniprot_download_fildir+uniprot_file
trembl_location = uniprot_download_fildir+trembl_file
add_trembl_annotations = 'no' ### Currently we don't need these annotations
try: importEnsemblUniprot(uniprot_ens_location)
except IOError:
try:
### Download the data from the AltAnalyze website (if there)
update.downloadCurrentVersion(uniprot_ens_location,species,'txt')
importEnsemblUniprot(uniprot_ens_location)
except Exception: null=[]
try:
uniprot_ens_location_built = string.replace(uniprot_ens_location,'UniProt','Uniprot-SWISSPROT')
uniprot_ens_location_built = string.replace(uniprot_ens_location_built,'uniprot','Uniprot-SWISSPROT')
importEnsemblUniprot(uniprot_ens_location_built)
except Exception: null=[]
### Import UniProt annotations
counts = update.verifyFile(uniprot_location,'counts')
if force == 'no' or counts > 8: import_uniprot_db(uniprot_location)
else:
### Directly download the data from UniProt
gz_filepath, status = update.download(uniprot_filename_url,uniprot_download_fildir,'')
if status == 'not-removed':
try: os.remove(gz_filepath) ### Not sure why this works now and not before
except OSError: status = status
import_uniprot_db(uniprot_location)
if add_trembl_annotations == 'yes':
### Import TreMBL annotations
try:
if force == 'yes': uniprot_location += '!!!!!' ### Force an IOError
import_uniprot_db(trembl_location)
except IOError:
### Directly download the data from UniProt
update.download(trembl_filename_url,uniprot_download_fildir,'')
import_uniprot_db(trembl_location)
export()
exportEnsemblUniprot(uniprot_ens_location)
def runExtractUniProt(species,species_full,uniprot_filename_url,trembl_filename_url,force):
global uniprot_ensembl_db;uniprot_ensembl_db={}
global uniprot_db;uniprot_db={}; global species_name; global uniprot_fildir
global secondary_to_primary_db; secondary_to_primary_db={}
import update; reload(update)
species_name = species_full
import UI; species_names = UI.getSpeciesInfo()
species_full = species_names[species]
species_full = string.replace(species_full,' ','_')
uniprot_file = string.split(uniprot_filename_url,'/')[-1]; uniprot_file = string.replace(uniprot_file,'.gz','')
trembl_file = string.split(trembl_filename_url,'/')[-1]; trembl_file = string.replace(trembl_file,'.gz','')
uniprot_fildir = 'AltDatabase/uniprot/'+species+'/'
uniprot_download_fildir = 'AltDatabase/uniprot/'
uniprot_ens_file = species+'_Ensembl-UniProt.txt'; uniprot_ens_location = uniprot_fildir+uniprot_ens_file
uniprot_location = uniprot_download_fildir+uniprot_file
trembl_location = uniprot_download_fildir+trembl_file
add_trembl_annotations = 'no' ### Currently we don't need these annotations
try: importEnsemblUniprot(uniprot_ens_location)
except IOError:
try:
### Download the data from the AltAnalyze website (if there)
update.downloadCurrentVersion(uniprot_ens_location,species,'txt')
importEnsemblUniprot(uniprot_ens_location)
except Exception: null=[]
try:
uniprot_ens_location_built = string.replace(uniprot_ens_location,'UniProt','Uniprot-SWISSPROT')
uniprot_ens_location_built = string.replace(uniprot_ens_location_built,'uniprot','Uniprot-SWISSPROT')
importEnsemblUniprot(uniprot_ens_location_built)
except Exception: null=[]
### Import UniProt annotations
counts = update.verifyFile(uniprot_location,'counts')
if force == 'no' or counts > 8: import_uniprot_db(uniprot_location)
else:
### Directly download the data from UniProt
gz_filepath, status = update.download(uniprot_filename_url,uniprot_download_fildir,'')
if status == 'not-removed':
try: os.remove(gz_filepath) ### Not sure why this works now and not before
except OSError: status = status
import_uniprot_db(uniprot_location)
if add_trembl_annotations == 'yes':
### Import TreMBL annotations
try:
if force == 'yes': uniprot_location += '!!!!!' ### Force an IOError
import_uniprot_db(trembl_location)
except IOError:
### Directly download the data from UniProt
update.download(trembl_filename_url,uniprot_download_fildir,'')
import_uniprot_db(trembl_location)
export()
exportEnsemblUniprot(uniprot_ens_location)
def checkProbesetSequenceFile(species):
""" Check to see if the probeset sequence file is present and otherwise download AltAnalyze hosted version"""
probeset_seq_file = getProbesetSequenceFile(species)
if probeset_seq_file == None:
dir = '/AltDatabase/'+species+'/'+array_type
filename = update.getFileLocations(species,'exon_seq')
filename = dir[1:]+'/'+ filename
update.downloadCurrentVersion(filename,'exon','.fa')
probeset_seq_file = getProbesetSequenceFile(species)
return probeset_seq_file
def runProgram(Species, Array_type, mir_source, stringency, Force):
global species
global array_type
global force
process_microRNA_predictions = 'yes'
species = Species
array_type = Array_type
force = Force
import_dir = '/AltDatabase/' + species + '/' + array_type
filedir = import_dir[1:] + '/'
dir_list = read_directory(
import_dir
) #send a sub_directory to a function to identify all files in a directory
probeset_seq_file = ''
for input_file in dir_list: #loop through each file in the directory to results
if 'critical-exon-seq_updated' in input_file:
probeset_seq_file = filedir + input_file
elif 'critical-exon-seq' in input_file:
probeset_seq_file2 = filedir + input_file
if len(probeset_seq_file) == 0: probeset_seq_file = probeset_seq_file2
data_type = 'critical-exons'
try:
splice_event_db = getParametersAndExecute(probeset_seq_file,
array_type, species,
data_type)
except UnboundLocalError:
probeset_seq_file = 'AltDatabase/' + species + '/' + array_type + '/' + array_type + '_critical-exon-seq_updated.txt'
update.downloadCurrentVersion(probeset_seq_file, array_type, 'txt')
splice_event_db = getParametersAndExecute(probeset_seq_file,
array_type, species,
data_type)
if process_microRNA_predictions == 'yes':
print 'stringency:', stringency
try:
ensembl_mirna_db = ExonSeqModule.importmiRNATargetPredictionsAdvanced(
species)
ExonSeqModule.alignmiRNAData(array_type, mir_source, species,
stringency, ensembl_mirna_db,
splice_event_db)
except Exception:
pass
def verifyFile(filename,species_name):
fn=filepath(filename); counts=0
try:
for line in open(fn,'rU').xreadlines():
counts+=1
if counts>10: break
except Exception:
counts=0
if species_name == 'counts': ### Used if the file cannot be downloaded from http://www.altanalyze.org
return counts
elif counts == 0:
if species_name in filename: server_folder = species_name ### Folder equals species unless it is a universal file
elif 'Mm' in filename: server_folder = 'Mm' ### For PicTar
else: server_folder = 'all'
print 'Downloading:',server_folder,filename
update.downloadCurrentVersion(filename,server_folder,'txt')
else:
return counts
def verifyFile(filename, species_name):
fn = filepath(filename)
counts = 0
try:
for line in open(fn, 'rU').xreadlines():
counts += 1
if counts > 10: break
except Exception:
counts = 0
if species_name == 'counts': ### Used if the file cannot be downloaded from http://www.altanalyze.org
return counts
elif counts == 0:
if species_name in filename:
server_folder = species_name ### Folder equals species unless it is a universal file
elif 'Mm' in filename:
server_folder = 'Mm' ### For PicTar
else:
server_folder = 'all'
print 'Downloading:', server_folder, filename
update.downloadCurrentVersion(filename, server_folder, 'txt')
else:
return counts