def load_gff_file():
create_go_table()
src = os.path.abspath(os.path.join(os.pardir, 'data', reference_go))
dest = os.path.abspath(os.path.join('data', reference_go))
shutil.copyfile(src, dest)
delete_first_line(dest)
load_table('gotable', dest)
def load_promoters_to_mysql(self):
ls = ['10000', '5000', '2000', '1000', '500']
for l in ls:
filename = 'data/promoters.sql.' + l + '.txt'
tname = "promoter_" + l
print(filename, tname)
create_promoter_table(tname)
load_table(tname, filename)
def get_first_line():
src = os.path.abspath(os.path.join(os.pardir, 'data', reference_ortholog))
cmd = 'head -n 1 ' + src
p = subprocess.Popen(["head", "-n", "1", src],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
out, err = p.communicate()
#a = os.system(cmd)
line = out.decode("utf-8")
line = line.rstrip("\r|\n")
ortho = []
for col in line.split("\t"):
if ('gene_id' in col):
continue
if ('_desc' in col):
continue
ortho.append(col)
a = os.path.abspath(
os.path.join(os.pardir, 'bin', 'php', 'settings', 'ortholog.php'))
php = "<?php\n$ortholog = ['{0}'];\n?>".format("','".join(ortho))
with open(a, "w") as outfile:
outfile.write(php)
create_ortholog(ortho)
if __name__ == '__main__':
get_first_line()
a = os.path.abspath(os.path.join(os.pardir, 'data', reference_ortholog))
load_table('ortholog', a)
print(filename)
## define original source
src = os.path.join(rnaseq_dir, filename)
## define path of destination
dest = os.path.abspath(os.path.join('data', filename))
## copy source to destination
shutil.copyfile(src, dest)
## delete the first line
delete_first_line(dest)
## remove inf and -inf and replace it with 100000
parse_infinity(dest)
## Make a R file with only the experiments
a = create_R_file(dest)
## Get the experiments list
print(a)
## Collect the R file list
outfiles.append(dest)
create_rnaseq_table()
for file in outfiles:
load_table('rnaseq', file)
expslist, hash = combine_rnaseq(outfiles)
rnaseq_combine_file = os.path.abspath(
os.path.join('data', 'rnaseq.combine'))
rnaseqcombine(expslist, hash, rnaseq_combine_file)
update_rnaseq(expslist, rnaseq_combine_file)
delete_first_line(rnaseq_combine_file)
create_rnaseq_expression_table(expslist)
load_table('rnaseq_expression', rnaseq_combine_file)
from mysql_tables import create_pathway_table, load_table
sys.path.append(os.path.abspath('../'))
from data import *
def genfile(boo):
b = os.getcwd()
a = os.path.abspath(os.path.join(os.pardir, 'bin', 'php', 'settings', 'pathway.php'))
php = "<?php\n$available_pathway = {0};\n?>".format(boo)
with open(a, "w") as outfile:
outfile.write(php)
def add_description():
print('add pathway')
genfile('TRUE')
def no_description():
print('no pathway')
genfile('FALSE')
if __name__ == '__main__':
print(reference_pathway)
if reference_pathway:
create_pathway_table()
a = os.path.abspath(os.path.join(os.pardir, 'data', reference_pathway))
load_table('pathway', a)
add_description()
else:
no_description()
gene_id, gene_name = extract_gene_id_name(cols[8])
return gene_id, chr, gene_start, gene_end, gene_length, gene_strand, gene_name
def parse_gff(filename, outfile):
fh = open(filename)
out = open(outfile, 'w')
for rec in fh:
if rec[0] == '#':
continue
rec = rec.rstrip("\r|\n")
cols = rec.split("\t")
if cols[2] != 'gene':
continue
if 'scaffold' in cols[0]:
continue
#print(">> ", rec)
#print("\t".join(extract_gene_info(cols)))
out.write("\t".join(extract_gene_info(cols)) + "\n")
fh.close()
out.close()
if __name__ == '__main__':
#filename = 'data/Homo_sapiens.GRCh37.75.gtf'
#filename = 'data/test'
#filename = 'data/Zea_mays.AGPv3.31.gtf'
parse_gff('../data/' + reference_gtf, 'data/' + reference_gtf + '.parse')
create_gff_table()
load_table('gfftest', 'data/' + reference_gtf + '.parse')
def genfile(boo):
b = os.getcwd()
a = os.path.abspath(
os.path.join(os.pardir, 'bin', 'php', 'settings', 'descriptions.php'))
php = "<?php\n$available_description = {0};\n?>".format(boo)
with open(a, "w") as outfile:
outfile.write(php)
def add_description():
print('add description')
genfile('TRUE')
def no_description():
print('no description')
genfile('FALSE')
if __name__ == '__main__':
print(reference_description)
if reference_description:
create_gene_descriptions()
a = os.path.abspath(
os.path.join(os.pardir, 'data', reference_description))
load_table('gene_descriptions', a)
add_description()
else:
no_description()
def parse_exp(filename, modfilename):
cmd = 'sed -i "s/,/\\t/g;s/$/\\t' + modfilename + '/g" ' + filename
os.system(cmd)
if __name__ == '__main__':
filename = '../data_chipseq/RA1_all_high_confidence_peaks.xls'
chipseq_dir = os.path.abspath(os.path.join(os.pardir, 'data_chipseq'))
files = [f for f in os.listdir(chipseq_dir) if re.match(r'.*\.csv', f)]
for filename in files:
## define original source
src = os.path.join(chipseq_dir, filename)
## define path of destination
dest = os.path.abspath(os.path.join('data', filename))
print(filename, src, dest)
## copy source to destination
shutil.copyfile(src, dest)
## Create table and load it
modfilename = filename.replace('.csv', '')
modfilename = modfilename.replace('\.', '')
create_chipseq()
## delete the first line
delete_first_line(dest)
parse_comma(dest)
parse_exp(dest, modfilename)
load_table('chipseq', dest)
#create_chipseq_table(filename)
#get_peak_seqs()
def load_cluster():
ref_dir = os.path.abspath(os.path.join(os.pardir, 'data'))
cluster = os.path.join(ref_dir, 'cluster.txt')
create_cluster
load_table('cluster', cluster)