added tar.gz download within get_results.py
This commit is contained in:
parent
80f7e039ab
commit
56f5479c0b
4 changed files with 32 additions and 9 deletions
|
@ -1,7 +0,0 @@
|
||||||
mutationinformation,ddg_dynamut,ddg_encom,ddg_mcsm,ddg_sdm,ddg_duet,dds_encom
|
|
||||||
G13V,0.006 kcal/mol (Stabilizing),-0.053 kcal/mol (Destabilizing),-0.261 kcal/mol (Destabilizing),-0.120 kcal/mol (Destabilizing),0.120 kcal/mol (Stabilizing),0.066 kcal.mol-1.K-1 (Increase of molecule flexibility)
|
|
||||||
A19T,-0.077 kcal/mol (Destabilizing),0.224 kcal/mol (Destabilizing),-0.631 kcal/mol (Destabilizing),-2.620 kcal/mol (Destabilizing),-0.758 kcal/mol (Destabilizing),-0.280 kcal.mol-1.K-1 (Decrease of molecule flexibility)
|
|
||||||
I4N,-0.239 kcal/mol (Destabilizing),-0.720 kcal/mol (Destabilizing),-0.728 kcal/mol (Destabilizing),-0.550 kcal/mol (Destabilizing),-0.461 kcal/mol (Destabilizing),0.900 kcal.mol-1.K-1 (Increase of molecule flexibility)
|
|
||||||
P3S,0.727 kcal/mol (Stabilizing),0.334 kcal/mol (Destabilizing),-0.672 kcal/mol (Destabilizing),0.010 kcal/mol (Stabilizing),-0.252 kcal/mol (Destabilizing),-0.418 kcal.mol-1.K-1 (Decrease of molecule flexibility)
|
|
||||||
F12S,-0.270 kcal/mol (Destabilizing),0.048 kcal/mol (Destabilizing),-1.028 kcal/mol (Destabilizing),-0.930 kcal/mol (Destabilizing),-0.993 kcal/mol (Destabilizing),-0.060 kcal.mol-1.K-1 (Decrease of molecule flexibility)
|
|
||||||
A19V,2.389 kcal/mol (Stabilizing),0.450 kcal/mol (Destabilizing),0.659 kcal/mol (Stabilizing),-0.170 kcal/mol (Destabilizing),1.040 kcal/mol (Stabilizing),-0.562 kcal.mol-1.K-1 (Decrease of molecule flexibility)
|
|
|
|
@ -61,7 +61,7 @@ get_results(url_file = my_url_file_multiple
|
||||||
# example 2: single url in a file
|
# example 2: single url in a file
|
||||||
#----------------------------------------------
|
#----------------------------------------------
|
||||||
my_url_file_single = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_single.txt'
|
my_url_file_single = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_single.txt'
|
||||||
print(my_url_file_multiple)
|
print(my_url_file_single)
|
||||||
my_suffix = 'single'
|
my_suffix = 'single'
|
||||||
|
|
||||||
get_results(my_url_file_single
|
get_results(my_url_file_single
|
||||||
|
@ -69,3 +69,18 @@ get_results(my_url_file_single
|
||||||
, output_dir = my_outdir
|
, output_dir = my_outdir
|
||||||
, outfile_suffix = my_suffix)
|
, outfile_suffix = my_suffix)
|
||||||
#%%###################################################################
|
#%%###################################################################
|
||||||
|
url = 'http://biosig.unimelb.edu.au/dynamut/results_prediction/161296287365'
|
||||||
|
host_url = 'http://biosig.unimelb.edu.au'
|
||||||
|
prediction_number = re.search(r'([0-9]+$)', url).group(0)
|
||||||
|
print(prediction_number)
|
||||||
|
dynamut_results_dir = '/home/tanu/git/LSHTM_analysis/dynamut/dynamut_results'
|
||||||
|
tgz_url = f"{host_url}/dynamut/results_file/results_" + prediction_number + '.tar.gz'
|
||||||
|
print(tgz_url)
|
||||||
|
outfile_suffix = 'foo'
|
||||||
|
|
||||||
|
|
||||||
|
target_path = dynamut_results_dir + '/' + outfile_suffix + '_results_' + prediction_number + '.tar.gz'
|
||||||
|
response_tgz = requests.get(tgz_url, stream = True)
|
||||||
|
if response_tgz.status_code == 200:
|
||||||
|
with open(target_path, 'wb') as f:
|
||||||
|
f.write(response_tgz.raw.read())
|
||||||
|
|
|
@ -17,6 +17,7 @@ import pandas as pd
|
||||||
from pandas.api.types import is_string_dtype
|
from pandas.api.types import is_string_dtype
|
||||||
from pandas.api.types import is_numeric_dtype
|
from pandas.api.types import is_numeric_dtype
|
||||||
#%%#####################################################################
|
#%%#####################################################################
|
||||||
|
|
||||||
def get_results(url_file, host_url, output_dir, outfile_suffix):
|
def get_results(url_file, host_url, output_dir, outfile_suffix):
|
||||||
# initilialise empty df
|
# initilialise empty df
|
||||||
dynamut_results_out_df = pd.DataFrame()
|
dynamut_results_out_df = pd.DataFrame()
|
||||||
|
@ -27,7 +28,7 @@ def get_results(url_file, host_url, output_dir, outfile_suffix):
|
||||||
#batch_response = requests.get(line, headers=headers)
|
#batch_response = requests.get(line, headers=headers)
|
||||||
batch_response = requests.get(line)
|
batch_response = requests.get(line)
|
||||||
batch_soup = BeautifulSoup(batch_response.text, features = 'html.parser')
|
batch_soup = BeautifulSoup(batch_response.text, features = 'html.parser')
|
||||||
|
|
||||||
# initilialise empty df
|
# initilialise empty df
|
||||||
#dynamut_results_df = pd.DataFrame()
|
#dynamut_results_df = pd.DataFrame()
|
||||||
for a in batch_soup.find_all('a', href=True, attrs = {'class':'btn btn-default btn-sm'}):
|
for a in batch_soup.find_all('a', href=True, attrs = {'class':'btn btn-default btn-sm'}):
|
||||||
|
@ -80,4 +81,17 @@ def get_results(url_file, host_url, output_dir, outfile_suffix):
|
||||||
# build out filename
|
# build out filename
|
||||||
out_filename = dynamut_results_dir + '/dynamut_output_' + outfile_suffix + '.csv'
|
out_filename = dynamut_results_dir + '/dynamut_output_' + outfile_suffix + '.csv'
|
||||||
dynamut_results_out_df.to_csv(out_filename, index = False)
|
dynamut_results_out_df.to_csv(out_filename, index = False)
|
||||||
|
|
||||||
|
# Download .tar.gz file
|
||||||
|
prediction_number = re.search(r'([0-9]+$)', line).group(0)
|
||||||
|
tgz_url = f"{host_url}/dynamut/results_file/results_" + prediction_number + '.tar.gz'
|
||||||
|
tgz_filename = dynamut_results_dir + '/' + outfile_suffix + '_results_' + prediction_number + '.tar.gz'
|
||||||
|
response_tgz = requests.get(tgz_url, stream = True)
|
||||||
|
if response_tgz.status_code == 200:
|
||||||
|
print('\nDownloading tar.gz file:', tgz_url
|
||||||
|
, '\nSaving file as:', tgz_filename)
|
||||||
|
with open(tgz_filename, 'wb') as f:
|
||||||
|
f.write(response_tgz.raw.read())
|
||||||
|
|
||||||
#%%#####################################################################
|
#%%#####################################################################
|
||||||
|
|
||||||
|
|
|
@ -35,4 +35,5 @@ get_results(url_file = my_url_file
|
||||||
, host_url = my_host
|
, host_url = my_host
|
||||||
, output_dir = outdir
|
, output_dir = outdir
|
||||||
, outfile_suffix = my_suffix)
|
, outfile_suffix = my_suffix)
|
||||||
|
|
||||||
########################################################################
|
########################################################################
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue