def do_eval2pct(eval_file, explained_file):
prog = 'eval2pct'
args = [ prog ]
args.append(eval_file)
with open(explained_file, 'w') as fh:
gd_util.run_program(prog, args, stdout=fh)
def do_coords2admix(coords_file):
prog = 'coords2admix'
args = [ prog ]
args.append(coords_file)
with open('fake', 'w') as fh:
gd_util.run_program(prog, args, stdout=fh)
shutil.copy2('fake', coords_file)
def do_ploteig(evec_file, population_names):
prog = 'gd_ploteig'
args = [ prog ]
args.append('-i')
args.append(evec_file)
args.append('-c')
args.append('1:2')
args.append('-p')
args.append(':'.join(population_names))
args.append('-x')
gd_util.run_program(prog, args)
def do_smartpca(par_file):
prog = 'smartpca'
args = [ prog ]
args.append('-p')
args.append(par_file)
stdoutdata, stderrdata = gd_util.run_program(prog, args)
stats = []
save_line = False
for line in stdoutdata.split('\n'):
if line.startswith(('## Average divergence', '## Anova statistics', '## Statistical significance')):
stats.append('')
save_line = True
if line.strip() == '':
save_line = False
if save_line:
stats.append(line)
return '\n'.join(stats[1:])
prog = 'offspring_heterozygosity'
args = [prog]
args.append(input) # a Galaxy SNP table
for tag in p1.tag_list():
column, name = tag.split(':')
if input_type == 'gd_genotype':
column = int(column) - 2
tag = '{0}:{1}:{2}'.format(column, 0, name)
args.append(tag)
for tag in p2.tag_list():
column, name = tag.split(':')
if input_type == 'gd_genotype':
column = int(column) - 2
tag = '{0}:{1}:{2}'.format(column, 1, name)
args.append(tag)
with open(output, 'w') as fh:
gd_util.run_program(prog, args, stdout=fh)
################################################################################
sys.exit(0)
################################################################################
prog = 'Fst_column'
args = [ prog ]
args.append(input)
args.append(data_source)
args.append(min_reads)
args.append(min_qual)
args.append(retain)
args.append(discard_fixed)
args.append(biased)
columns = p1.column_list()
for column in columns:
if input_type == 'gd_genotype':
column = int(column) - 2
args.append('{0}:1'.format(column))
columns = p2.column_list()
for column in columns:
if input_type == 'gd_genotype':
column = int(column) - 2
args.append('{0}:2'.format(column))
with open(output, 'w') as fh:
gd_util.run_program(prog, args, stdout=fh)
sys.exit(0)
prog = 'kinship_prep'
args = [ prog ]
args.append(input) # a Galaxy SNP table
args.append(0) # required number of reads for each individual to use a SNP
args.append(0) # required genotype quality for each individual to use a SNP
args.append(0) # minimum spacing between SNPs on the same scaffold
for tag in p1.tag_list():
if input_type == 'gd_genotype':
column, name = tag.split(':')
tag = '{0}:{1}'.format(int(column) - 2, name)
args.append(tag)
gd_util.run_program(prog, args)
# kinship.map
# kinship.ped
# kinship.dat
################################################################################
prog = 'king'
args = [ prog ]
args.append('-d')
args.append('kinship.dat')
args.append('-p')
args.append('kinship.ped')
args.append('-m')
prog = 'admix_prep'
args = [prog]
args.append(input_snp_filename)
args.append(min_reads)
args.append(min_qual)
args.append(min_spacing)
for tag in p1.tag_list():
if input_type == 'gd_genotype':
column, name = tag.split(':', 1)
tag = '{0}:{1}'.format(int(column) - 2, name)
args.append(tag)
stdoutdata, stderrdata = gd_util.run_program(prog, args)
using_info = stdoutdata.rstrip('\r\n')
################################################################################
gd_util.mkdir_p(output_files_path)
output_ped_filename = os.path.join(output_files_path, 'admix.ped')
output_map_filename = os.path.join(output_files_path, 'admix.map')
shutil.copy2('admix.ped', output_ped_filename)
shutil.copy2('admix.map', output_map_filename)
do_import(output_filename, output_files_path, min_reads, min_qual, min_spacing,
using_info, population_list)
sys.exit(0)
prog = 'kinship_prep'
args = [prog]
args.append(input) # a Galaxy SNP table
args.append(0) # required number of reads for each individual to use a SNP
args.append(0) # required genotype quality for each individual to use a SNP
args.append(0) # minimum spacing between SNPs on the same scaffold
for tag in p1.tag_list():
if input_type == 'gd_genotype':
column, name = tag.split(':')
tag = '{0}:{1}'.format(int(column) - 2, name)
args.append(tag)
gd_util.run_program(prog, args)
# kinship.map
# kinship.ped
# kinship.dat
################################################################################
prog = 'king'
args = [prog]
args.append('-d')
args.append('kinship.dat')
args.append('-p')
args.append('kinship.ped')
args.append('-m')
prog = 'admix_prep'
args = [ prog ]
args.append(input_snp_filename)
args.append(min_reads)
args.append(min_qual)
args.append(min_spacing)
for tag in p1.tag_list():
if input_type == 'gd_genotype':
column, name = tag.split(':', 1)
tag = '{0}:{1}'.format(int(column) - 2, name)
args.append(tag)
stdoutdata, stderrdata = gd_util.run_program(prog, args)
using_info = stdoutdata.rstrip('\r\n')
################################################################################
gd_util.mkdir_p(output_files_path)
output_ped_filename = os.path.join(output_files_path, 'admix.ped')
output_map_filename = os.path.join(output_files_path, 'admix.map')
shutil.copy2('admix.ped', output_ped_filename)
shutil.copy2('admix.map', output_map_filename)
do_import(output_filename, output_files_path, min_reads, min_qual, min_spacing, using_info, population_list)
sys.exit(0)