From 50cf6ca3acec186ea55a13a3f42b6a21fcd1f7e5 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Fri, 6 Aug 2021 19:09:29 +0100
Subject: [PATCH] ran submit and get_results for one last batch for mcsm_na and
 did some bash formatting to get proper filenames, etc.

---
 mcsm/mcsm.py                       | 30 +++++++++++++++++++++++++++++-
 mcsm_na/get_results_mcsm_na.py     |  2 +-
 mcsm_na/run_get_results_mcsm_na.py |  5 +++--
 mcsm_na/run_submit_mcsm_na.py      |  8 +++++---
 4 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/mcsm/mcsm.py b/mcsm/mcsm.py
index 1adf57c..817089c 100644
--- a/mcsm/mcsm.py
+++ b/mcsm/mcsm.py
@@ -359,7 +359,19 @@ def format_mcsm_output(mcsm_outputcsv):
     print('Raw duet scores:\n', mcsm_data['duet_stability_change']
             , '\n---------------------------------------------------------------'
             , '\nScaled duet scores:\n', mcsm_data['duet_scaled'])
-
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+# additional check added
+    c2 = mcsm_data[mcsm_data['duet_scaled']>=0].count()
+    DUET_pos2 = c2.get(key = 'duet_scaled')
+    
+    if DUET_pos == DUET_pos2:
+        print('\nPASS: DUET values scaled correctly')
+    else:
+        print('\nFAIL: DUET values scaled numbers MISmatch'
+              , '\nExpected number:', DUET_pos
+              , '\nGot:', DUET_pos2
+              , '\n======================================================')
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
 #%%=====================================================================
     #############
     # scale affinity values
@@ -375,6 +387,22 @@ def format_mcsm_output(mcsm_outputcsv):
     print('Raw affinity scores:\n', mcsm_data['ligand_affinity_change']
             , '\n---------------------------------------------------------------'
             , '\nScaled affinity scores:\n', mcsm_data['affinity_scaled'])
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+# additional check added
+    c_lig = mcsm_data[mcsm_data['ligand_affinity_change']>=0].count()
+    Lig_pos = c_lig.get(key = 'ligand_affinity_change')
+
+    c_lig2 = mcsm_data[mcsm_data['affinity_scaled']>=0].count()     
+    Lig_pos2 = c_lig2.get(key = 'affinity_scaled')
+    
+    if Lig_pos == Lig_pos2:
+        print('\nPASS: Ligand affintiy values scaled correctly')
+    else:
+        print('\nFAIL: Ligand affinity values scaled numbers MISmatch'
+              , '\nExpected number:', Lig_pos
+              , '\nGot:', Lig_pos2
+              , '\n======================================================')
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
             
 #%%=====================================================================
     #############
diff --git a/mcsm_na/get_results_mcsm_na.py b/mcsm_na/get_results_mcsm_na.py
index 75a7721..ac87ac9 100644
--- a/mcsm_na/get_results_mcsm_na.py
+++ b/mcsm_na/get_results_mcsm_na.py
@@ -40,7 +40,7 @@ def get_results(url_file, host_url, output_dir, outfile_suffix):
             txt_url = f"{host_url}/mcsm_na/static/results/" + prediction_number + '.txt'
             print('CHECK txt url:', txt_url)
             
-            out_filename = mcsm_na_results_dir + '/' + outfile_suffix + '_output_' + prediction_number + '.txt'
+            out_filename = mcsm_na_results_dir + '/' + outfile_suffix + '_output_' + prediction_number + '.txt.gz'
             response_txt = requests.get(txt_url, stream = True)
             if response_txt.status_code == 200:
                 print('\nDownloading .txt:', txt_url
diff --git a/mcsm_na/run_get_results_mcsm_na.py b/mcsm_na/run_get_results_mcsm_na.py
index 0a0b83c..3d619c7 100755
--- a/mcsm_na/run_get_results_mcsm_na.py
+++ b/mcsm_na/run_get_results_mcsm_na.py
@@ -23,8 +23,9 @@ outdir = datadir + '/' + drug + '/output'
 
 #==============================================================================
 # batch 26: 25.txt, RETRIEVED: 16 Feb:
-my_url_file =  outdir + '/mcsm_na_temp/mcsm_na_result_url_gid_b26.txt'
-my_suffix = 'gid_b26'
+# batch 27: 26.txt, RETRIEVED: 6 Aug:
+my_url_file =  outdir + '/mcsm_na_temp/mcsm_na_result_url_gid_b27.txt'
+my_suffix = 'gid_b27'
 
 #==============================================================================
 
diff --git a/mcsm_na/run_submit_mcsm_na.py b/mcsm_na/run_submit_mcsm_na.py
index 249aba5..474ca5c 100755
--- a/mcsm_na/run_submit_mcsm_na.py
+++ b/mcsm_na/run_submit_mcsm_na.py
@@ -28,8 +28,10 @@ my_pdb_file = indir + '/gid_complex.pdb'
 
 #=============================================================================
 # batch 26: 25.txt # RAN: 16 Feb:
-my_mutation_list = outdir + '/snp_batches/20/snp_batch_25.txt'
-my_suffix = 'gid_b26'
+# batch 27: 26.txt # RAN: 6 Aug:
+# off by one
+my_mutation_list = outdir + '/snp_batches/20/snp_batch_26.txt'
+my_suffix = 'gid_b27'
 #==============================================================================
 
 #==========================
@@ -43,4 +45,4 @@ submit_mcsm_na(host_url = my_host
                , prediction_url = my_prediction_url
                , output_dir = outdir
                , outfile_suffix = my_suffix) 
-#%%#####################################################################               
\ No newline at end of file
+#%%#####################################################################