From d26b17fd1966d3e0dd04de96260a6d9d730c754d Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Tue, 9 Feb 2021 16:11:07 +0000
Subject: [PATCH] added dynamut dir

---
 dynamut/dynamut.py      |  46 ++++++++++++++++++
 dynamut/dynamut_test.py | 101 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 147 insertions(+)
 create mode 100755 dynamut/dynamut.py
 create mode 100755 dynamut/dynamut_test.py

diff --git a/dynamut/dynamut.py b/dynamut/dynamut.py
new file mode 100755
index 0000000..fca749b
--- /dev/null
+++ b/dynamut/dynamut.py
@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug 19 14:33:51 2020
+
+@author: tanu
+"""
+
+
+#%% load packages
+import os,sys
+import subprocess
+import argparse
+import requests
+import re
+import time
+from bs4 import BeautifulSoup
+import pandas as pd
+from pandas.api.types import is_string_dtype
+from pandas.api.types import is_numeric_dtype
+#%%============================================================================
+
+#1) define muts batch
+#take mcsm file
+#split into 'n' batches
+#write output file with suffix of batch number
+
+
+#********** done this par ****************
+#2) get results for a batch url
+# read  file
+# store batch url
+#extract  number
+#build single url
+#build single results urls
+#get results and store them in df
+#update df 
+#dim of df = no. of muts in batch
+
+#3) format results
+# store unit measurements separtely
+# omit unit measurements from cols
+# create extra columns '_outcome' suffix by splitting numerical output
+# create separate col for  mcsm as it doesn't have output text
+      
+#%%============================================================================
diff --git a/dynamut/dynamut_test.py b/dynamut/dynamut_test.py
new file mode 100755
index 0000000..3e8ed34
--- /dev/null
+++ b/dynamut/dynamut_test.py
@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug 19 14:33:51 2020
+
+@author: tanu
+"""
+
+
+#%% load packages
+import os,sys
+import subprocess
+import argparse
+import requests
+import re
+import time
+from bs4 import BeautifulSoup
+import pandas as pd
+from pandas.api.types import is_string_dtype
+from pandas.api.types import is_numeric_dtype
+#%%============================================================================
+
+batch_result_url = 'http://biosig.unimelb.edu.au/dynamut/results_prediction/15955901077'
+
+mut = 'S104R'
+single_result_url = 'http://biosig.unimelb.edu.au/dynamut/single_results/15955901077' + '/' + mut
+
+
+
+#%%============================================================================
+param_dict = {}
+
+result_response = requests.get(single_result_url)
+if result_response.status_code == 200:
+        print('Fetching results')
+        # extract results using the html parser          
+        soup = BeautifulSoup(result_response.text, features = 'html.parser')
+        #web_result_raw = soup.find(id = 'predictions').get_text()
+        ddg_dynamut = soup.find(id = 'ddg_dynamut').get_text()
+        ddg_encom = soup.find(id = 'ddg_encom').get_text()
+        ddg_mcsm = soup.find(id = 'ddg_mcsm').get_text()
+        ddg_sdm = soup.find(id = 'ddg_sdm').get_text()
+        ddg_duet = soup.find(id = 'ddg_duet').get_text()
+        dds_encom = soup.find(id = 'dds_encom').get_text()
+        
+        param_dict = {"mutationinformation" : mut
+            , "ddg_dynamut" : ddg_dynamut
+            , "ddg_encom"   : ddg_encom
+            , "ddg_mcsm"    : ddg_mcsm
+            , "ddg_sdm"     : ddg_sdm
+            , "ddg_duet"    : ddg_duet
+            , "dds_encom"   : dds_encom
+            
+            }
+        results_df = pd.DataFrame.from_dict(param_dict, orient = "index").T  
+
+#%% for loop
+#%%
+host_dynamut = 'http://biosig.unimelb.edu.au/dynamut'
+batch_url_number = re.search(r'([0-9]+)$', batch_result_url).group(0) 
+single_url = host_dynamut + '/single_results/' + batch_url_number
+     
+muts = ["S104R", "G24R"]
+
+# initilialise empty df
+dynamut_results_df = pd.DataFrame()
+
+for i, mut in enumerate(muts):
+    #param_dict = {}
+    print('Running mutation', i, ':', mut)
+    snp = mut
+    single_result_url = single_url + '/' + snp
+    print('Getting results from:',  single_result_url)
+    
+    result_response = requests.get(single_result_url)
+    if result_response.status_code == 200:
+            print('Fetching results')
+            # extract results using the html parser          
+            soup = BeautifulSoup(result_response.text, features = 'html.parser')
+            #web_result_raw = soup.find(id = 'predictions').get_text()
+            ddg_dynamut = soup.find(id = 'ddg_dynamut').get_text()
+            ddg_encom = soup.find(id = 'ddg_encom').get_text()
+            ddg_mcsm = soup.find(id = 'ddg_mcsm').get_text()
+            ddg_sdm = soup.find(id = 'ddg_sdm').get_text()
+            ddg_duet = soup.find(id = 'ddg_duet').get_text()
+            dds_encom = soup.find(id = 'dds_encom').get_text()
+            
+            param_dict = {"mutationinformation" : snp
+                , "ddg_dynamut" : ddg_dynamut
+                , "ddg_encom"   : ddg_encom
+                , "ddg_mcsm"    : ddg_mcsm
+                , "ddg_sdm"     : ddg_sdm
+                , "ddg_duet"    : ddg_duet
+                , "dds_encom"   : dds_encom 
+                }
+            results_df = pd.DataFrame.from_dict(param_dict, orient = "index").T
+            print(results_df)
+            dynamut_results_df = dynamut_results_df.append(results_df)
+            print(dynamut_results_df)
+            
+