tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

updating get_results_def.py

Browse source
This commit is contained in:
Tanushree Tunstall 2021-02-12 11:38:21 +00:00
parent c146ea0f43
commit db1c950c39
2 changed files with 47 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

54
dynamut/get_results_def.py
View file

@ -17,13 +17,8 @@ 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
#%%============================================================================ #%%============================================================================
homedir = os.path.expanduser('~')
#print(homedir)
host = 'http://biosig.unimelb.edu.au'
# Needed if things try to block the 'requests' user agent
#headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"}
#%% #%%
def get_results(url_file): def get_results(url_file, host_url, outdir, outfile_suffix):
# initilialise empty df # initilialise empty df
dynamut_results_out_df = pd.DataFrame() dynamut_results_out_df = pd.DataFrame()
with open(url_file, 'r') as f: with open(url_file, 'r') as f:
@ -38,7 +33,7 @@ def get_results(url_file):
#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'}):
print ("Found the URL:", a['href']) print ("Found the URL:", a['href'])
single_result_url = host + a['href'] single_result_url = host_url + a['href']
snp = re.search(r'([A-Z]+[0-9]+[A-Z]+$)', single_result_url).group(0) snp = re.search(r'([A-Z]+[0-9]+[A-Z]+$)', single_result_url).group(0)
print(snp) print(snp)
print('\nGetting results from:', single_result_url) print('\nGetting results from:', single_result_url)
@ -68,24 +63,47 @@ def get_results(url_file):
print('Result DF:', results_df, 'for URL:', line) print('Result DF:', results_df, 'for URL:', line)
#dynamut_results_df = dynamut_results_df.append(results_df)#!1 too many!:-) #dynamut_results_df = dynamut_results_df.append(results_df)#!1 too many!:-)
dynamut_results_out_df = dynamut_results_out_df.append(results_df) dynamut_results_out_df = dynamut_results_out_df.append(results_df)
#print(dynamut_results_out_df)
#print(dynamut_results_out_df) #============================
# Writing results file: csv
#============================
dynamut_results_dir = outdir + '/dynamut_results'
if not os.path.exists(dynamut_results_dir):
print('\nCreating dir: dynamut_results within:', outdir )
os.makedirs(dynamut_results_dir)
print('\nWriting dynamut results df') print('\nWriting dynamut results df')
print('\nResults File:' print('\nResults File:'
, '\nNo. of rows:', dynamut_results_out_df.shape[0] , '\nNo. of rows:', dynamut_results_out_df.shape[0]
, '\nNo. of cols:', dynamut_results_out_df.shape[1]) , '\nNo. of cols:', dynamut_results_out_df.shape[1])
print(dynamut_results_out_df) print(dynamut_results_out_df)
dynamut_results_out_df.to_csv('/tmp/test_dynamut.csv', index = False) #dynamut_results_out_df.to_csv('/tmp/test_dynamut.csv', index = False)
# build out filename
out_filename = dynamut_results_dir + '/dynamut_output_' + outfile_suffix + '.csv'
dynamut_results_out_df.to_csv(out_filename, index = False)
#%% EXAMPLE RUN
# globals
#homedir = os.path.expanduser('~')
#my_host = 'http://biosig.unimelb.edu.au'
#my_outdir = homedir + '/git/LSHTM_analysis/dynamut'
#%% #=============================================
# example 1: multiple urls in a single file # example 1: multiple urls in a single file
my_url_file_multiple = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_multiple.txt' #=============================================
print(my_url_file_multiple) #my_url_file_multiple = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_multiple.txt'
get_results(my_url_file_multiple) #print(my_url_file_multiple)
#get_results(url_file = my_url_file_multiple
# , host_url = my_host
# , outdir = my_outdir
# , outfile_suffix='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' #=============================================
print(my_url_file_multiple) #my_url_file_single = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_single.txt'
get_results(my_url_file_single) #print(my_url_file_multiple)
#get_results(my_url_file_single
# , host_url = my_host
# , outdir = my_outdir
# , outfile_suffix = 'single')
#%% #%%

17
dynamut/submit_def.py
View file

@ -31,7 +31,7 @@ def request_calculation(pdb_file
#, out_url_file #, out_url_file
): ):
""" """
Makes a POST request for a ligand affinity prediction. Makes a POST request for dynamut predictions.
@param pdb_file: valid path to pdb structure @param pdb_file: valid path to pdb structure
@type string @type string
@ -100,12 +100,17 @@ indir = datadir + '/' + drug + '/input'
outdir = datadir + '/' + drug + '/output' outdir = datadir + '/' + drug + '/output'
#outdir = homedir + '/git/LSHTM_analysis/dynamut' # for example #outdir = homedir + '/git/LSHTM_analysis/dynamut' # for example
my_pdb_file = homedir + '/git/Data/streptomycin/input/gid_complex.pdb'
my_mutation_list = homedir + '/git/Data/streptomycin/output/snp_batches/50/snp_batch_00.txt'
my_chain = 'A' my_chain = 'A'
my_batch = 1 my_pdb_file = homedir + '/git/Data/streptomycin/input/gid_complex.pdb'
#my_outfile = dynamut_temp_dir + '/dynamut_result_url_batch_' + str(batch_no) + '.txt'
# batch 1: 00.txt
#my_mutation_list = homedir + '/git/Data/streptomycin/output/snp_batches/50/snp_batch_00.txt'
#my_batch = 1
# batch 2: 01.txt
my_mutation_list = outdir + '/snp_batches/50/snp_batch_01.txt'
my_batch = 2
# %% call this function # %% call this function
request_calculation (pdb_file = my_pdb_file request_calculation (pdb_file = my_pdb_file
, mutation_list = my_mutation_list , mutation_list = my_mutation_list