15112023 update

draskot · Nov 15, 2023 · 3debe31 · 3debe31
1 parent 84e80dc
commit 3debe31
Show file tree

Hide file tree

Showing 12 changed files with 149 additions and 115 deletions.
diff --git a/VelikaVini b/VelikaVini
@@ -88,6 +88,8 @@ then
 else
     sh $vini_dir/download_Cosmic_data
 
+
+
     rm -f $WORKDIR/*err $WORKDIR/*out    
     if  [ $cosmic == y ]
     then
@@ -197,8 +199,11 @@ do
     let i++
 done < $vini_dir/ligands/ligands_list
 
+rm -f $WORKDIR/SLEM_values
+rm -f $WORKDIR/${CANCER_PATHWAY}_results/*
 for (( therapy_level=1; therapy_level<$((max_therapy_level+1)); therapy_level++ ))
 do
+    sed -i '/\btherapy_level\b/d' $vini_dir/globals
     echo "export therapy_level=${therapy_level}" >> $vini_dir/globals
     sh $vini_dir/malavini
 done

diff --git a/Vini b/Vini
@@ -14,11 +14,13 @@ else
     > Vini.crashlog
     > restartfile
     > globals
-    SEVEN=7 ; TWO=2 ; TRUE=1 ; FALSE=0 ; ONES=1 ; NULL=0
+    NULL=0 ; ONES=1 ; TWO=2 ; THREE=3 ; SEVEN=7
+    TRUE=1 ; FALSE=0
     echo "export TRUE=$TRUE"   >> $vini_dir/globals
     echo "export FALSE=$FALSE" >> $vini_dir/globals
     echo "export ONES=$ONES"   >> $vini_dir/globals
     echo "export TWO=$TWO"     >> $vini_dir/globals
+    echo "export THREE=$THREE" >> $vini_dir/globals
     echo "export SEVEN=$SEVEN" >> $vini_dir/globals
     echo "export NULL=$NULL"   >> $vini_dir/globals
     echo "export state=init"   >> $vini_dir/globals
@@ -265,6 +267,8 @@ then
     touch -a -m -t 200001010101 $WORKDIR/COSMIC_token #reset time creation to 01-01-2000
     sh $vini_dir/renew_COSMIC_token #update COSMIC token if older than 24 hours
     kit="n"
+    echo "export kit=$kit" >> $vini_dir/globals
+
 else
     echo "export cosmic=n" >> $vini_dir/globals
     echo "export exp=noexp"   >> $vini_dir/globals

diff --git a/cosmicTools.py b/cosmicTools.py
@@ -7,7 +7,7 @@
 from time import sleep
 import random
 
-TOKEN_NUMBER = "525119157257208421313759694701535336"
+TOKEN_NUMBER = "850268004265384203146370457663115076"
 WORKING_DIR = os.path.join(os.path.realpath('.'), 'genes')
 
 def mapUniprotIDToCosmicID_fromList(UNIPROT_LIST):

diff --git a/create_SLEM_named_list b/create_SLEM_named_list
@@ -1,5 +1,9 @@
 source $vini_dir/globals
 
+SLEM_FILE=$WORKDIR/${CANCER_PATHWAY}_results/SLEM_values_${cell_line}_thl${therapy_level}_${exp}
+> ${SLEM_FILE}_named
+
+
 while read -r line
 do
     echo -n "."
@@ -17,39 +21,59 @@ do
 
     if [[ $therapy_level == 1 ]]
     then
-        drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #get drug name 
-        drug1=`echo $drug1 | awk -F',' '{print $1}'`       
-        printf "%s%s%s%s\n" "SLEM_" $drug1 " " $SLEM >> ${SLEM_FILE}_named 
+        dot_count=$(echo "$word" | tr -cd '.' | wc -c)
+        if  [ ${dot_count} == $NULL ]
+        then
+            drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #get drug name 
+            drug1=`echo $drug1 | awk -F',' '{print $1}'`       
+            printf "%s%s%s%s\n" "SLEM_" $drug1 " " $SLEM >> ${SLEM_FILE}_named 
+        fi
     else
         if  [[ $therapy_level == 2 ]]  
         then
-            drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #convert "i" to name 
-            drug1=`echo $drug1 | awk -F',' '{print $1}'`       
-            drug2=`head -"$j" $vini_dir/ligands/ligands_list | tail -1` #convert "j" to name 
-            drug2=`echo $drug2 | awk -F',' '{print $1}'`       
-            printf "%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 " " $SLEM >> ${SLEM_FILE}_named 
-        else
-            if   [[ $therapy_level == 3 ]] 
+            word=`echo $line | awk '{print $1}'`
+            dot_count=$(echo "$word" | tr -cd '.' | wc -c)
+            if  [ ${dot_count} == $ONES ]
             then
                 drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #convert "i" to name 
                 drug1=`echo $drug1 | awk -F',' '{print $1}'`       
                 drug2=`head -"$j" $vini_dir/ligands/ligands_list | tail -1` #convert "j" to name 
-                drug2=`echo $drug2 | awk -F',' '{print $1}'`
-                drug3=`head -"$k" $vini_dir/ligands/ligands_list | tail -1` #convert "k" to name 
-                drug3=`echo $drug3 | awk -F',' '{print $1}'`
-                printf "%s%s%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 "." $drug3 " " $SLEM >> ${SLEM_FILE}_named 
-            else
-                if  [[ $therapy_level == 4 ]]
+                drug2=`echo $drug2 | awk -F',' '{print $1}'`       
+                printf "%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 " " $SLEM >> ${SLEM_FILE}_named 
+                #echo "brakepoint! $dot_count" ; sleep 1000
+            fi
+        else
+            if   [[ $therapy_level == 3 ]] 
+            then
+                word=`echo $line | awk '{print $1}'`
+                dot_count=$(echo "$word" | tr -cd '.' | wc -c)
+                if  [ ${dot_count} == $TWO ]
                 then
-                    drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #convert "i" 
-                    drug1=`echo $drug1 | awk -F',' '{print $1}'`
+                    drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #convert "i" to name 
+                    drug1=`echo $drug1 | awk -F',' '{print $1}'`       
                     drug2=`head -"$j" $vini_dir/ligands/ligands_list | tail -1` #convert "j" to name 
                     drug2=`echo $drug2 | awk -F',' '{print $1}'`
                     drug3=`head -"$k" $vini_dir/ligands/ligands_list | tail -1` #convert "k" to name 
                     drug3=`echo $drug3 | awk -F',' '{print $1}'`
-                    drug4=`head -"$l" $vini_dir/ligands/ligands_list | tail -1` #convert "l" to name 
-                    drug4=`echo $drug4 | awk -F',' '{print $1}'`
-                    printf "%s%s%s%s%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 "." $drug3 "." $drug4 " " $SLEM >> ${SLEM_FILE}_named 
+                    printf "%s%s%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 "." $drug3 " " $SLEM >> ${SLEM_FILE}_named 
+                fi
+            else
+                if  [[ $therapy_level == 4 ]]
+                then
+                    word=`echo $line | awk '{print $1}'`
+                    dot_count=$(echo "$word" | tr -cd '.' | wc -c)
+                    if  [ ${dot_count} == $THREE ]
+                    then
+                        drug1=`head -"$i" $vini_dir/ligands/ligands_list | tail -1` #convert "i" 
+                        drug1=`echo $drug1 | awk -F',' '{print $1}'`
+                        drug2=`head -"$j" $vini_dir/ligands/ligands_list | tail -1` #convert "j" to name 
+                        drug2=`echo $drug2 | awk -F',' '{print $1}'`
+                        drug3=`head -"$k" $vini_dir/ligands/ligands_list | tail -1` #convert "k" to name 
+                        drug3=`echo $drug3 | awk -F',' '{print $1}'`
+                        drug4=`head -"$l" $vini_dir/ligands/ligands_list | tail -1` #convert "l" to name 
+                        drug4=`echo $drug4 | awk -F',' '{print $1}'`
+                        printf "%s%s%s%s%s%s%s%s%s%s\n" "SLEM_" $drug1 "." $drug2 "." $drug3 "." $drug4 " " $SLEM >> ${SLEM_FILE}_named 
+                    fi
                 fi
             fi
         fi

diff --git a/delete_SLEM_entries_with_equal_indices b/delete_SLEM_entries_with_equal_indices
@@ -2,7 +2,6 @@ source $vini_dir/globals
 
 
 SLEM_FILE=$WORKDIR/${CANCER_PATHWAY}_results/SLEM_values_${cell_line}_thl${therapy_level}_${exp}
-> ${SLEM_FILE}_named
 > ${SLEM_FILE}_reduced
 
 while read -r line

diff --git a/download_Cosmic_data b/download_Cosmic_data
@@ -1,5 +1,7 @@
 module purge
 
+source $vini_dir/globals
+
 echo -n "Activating miniconda3 environment..."
 source $INSTALL/miniconda3/bin/activate
 conda activate env310

diff --git a/genes/Uniprot_ID_list b/genes/Uniprot_ID_list
@@ -1,97 +1,97 @@
-P18848
-P01116
-O00716
+Q9NQB0
+Q04206
+P04637
+P31213
+Q9Y243
 P38936
+O14920
 P14616
-P09211
-P04626
-P08238
-Q9GZP0
-P04049
-P37275
-Q12778
-P16234
-Q02930
-P14780
+P01112
+P19838
+Q9UJU2
+P36402
+P07288
+O43278
+Q00987
+P01127
+O15393
+P27930
+P14625
+P00750
+Q07890
 P24864
+P37275
+Q92793
+P35222
+P21802
+Q68CJ9
 P55211
-P10275
-P31213
-O00459
-Q07890
-P11362
-Q02750
+P01308
 P11308
-P25963
-P14625
-Q9HCS4
-P35222
-Q92934
-Q9Y243
-O43278
-P46527
-Q09472
-Q07889
+P60484
+P01133
+Q8TEY5
+O15530
 P49841
-P00749
+P41161
+Q9GZP0
+O00329
+O96020
+P24941
 O43889
-P16220
-P31749
-P00533
-P01133
-P10398
-P09619
 Q92569
-P42338
-P31751
-Q01094
-O00329
-P07900
-P41161
-P07288
-P08069
-Q04206
-Q70SY1
-Q9NRA1
-Q9UJU2
-Q8TEY5
-Q92793
-P36402
-O14920
-P06400
-Q9NQB0
-P27361
+P18848
+Q02930
+O00459
+P09619
+P10398
 Q14209
-P10415
-P01308
+Q9HCS4
+P10275
+P08238
+P04626
 P15056
-P05019
-P01127
-O15393
-Q96BA8
-P36507
+Q92934
 P62993
+P11362
+P36507
+P10415
+P04049
+P24385
+P07900
+P08254
+P16234
+P09211
+Q96BA8
+P01116
 O15111
+Q12778
+Q09472
+P42338
+P27986
+P27361
+Q02750
+Q9Y6K9
+P25963
+O00716
+P31749
+P04085
+P16220
+P00749
+P14780
+P00533
+P01135
+Q01094
 Q99801
-Q00987
-P01112
-Q68CJ9
-P24941
-P08254
-P19838
-O15530
 P42345
+P31751
+Q9NRA1
+Q70SY1
+P46527
+P08069
+P42336
 P01111
-P60484
-P27930
-Q9Y6K9
-P01135
-P27986
 P28482
-P04637
-P42336
-P00750
-P24385
-P04085
-P21802
-O96020
+Q07889
+P05019
+P06400
diff --git a/get_gene_expression_parallel.py b/get_gene_expression_parallel.py
@@ -13,7 +13,7 @@
 t0 = time.time()
 # this token has to be manually obtained from https://cancer.sanger.ac.uk/cosmic/download
 
-TOKEN_NUMBER = "525119157257208421313759694701535336"
+TOKEN_NUMBER = "850268004265384203146370457663115076"
 WORKING_DIR = os.path.join(os.path.realpath('.'), 'genes', 'expressions')
 
 def mapUniprotIDtoCosmicID(UNIPROT_ID):

diff --git a/get_gene_mutation.py b/get_gene_mutation.py
@@ -15,7 +15,7 @@
 t0 = time.time()
 # this token has to be manually obtained from https://cancer.sanger.ac.uk/cosmic/download
 
-TOKEN_NUMBER = "525119157257208421313759694701535336"
+TOKEN_NUMBER = "850268004265384203146370457663115076"
 WORKING_DIR_MUTATIONS = os.path.join(os.path.realpath('.'), 'genes', 'mutations')
 WORKING_DIR_SEQUENCES = os.path.join(os.path.realpath('.'), 'genes', 'sequences')
 

diff --git a/get_gene_mutation_cell_line.py b/get_gene_mutation_cell_line.py
@@ -10,7 +10,7 @@
 t0 = time.time()
 # this token has to be manually obtained from https://cancer.sanger.ac.uk/cosmic/download
 
-TOKEN_NUMBER = "525119157257208421313759694701535336"
+TOKEN_NUMBER = "850268004265384203146370457663115076"
 WORKING_DIR_MUTATIONS = os.path.join(os.path.realpath('.'), 'genes', 'mutations')
 WORKING_DIR_SEQUENCES = os.path.join(os.path.realpath('.'), 'genes', 'sequences')
 

diff --git a/predict_mutated_genes b/predict_mutated_genes
@@ -1,7 +1,7 @@
 #Using https://web.expasy.org/translate/ tool for nucleotide to aminoacids sequence translation
 
-#partition=`cat  active_partition`      #Define AlphaFold parameters
-cpus=`cat ${partition}_cores`
+
+cpus=`cat ${active_partition}_cores`
 outdir=$vini_dir/genes/pdb_files
 
 SEQDIR=$vini_dir/genes/sequences/
-Original file line number
+Diff line change
@@ -1,97 +1,97 @@
-    P18848
-    P01116
-    O00716
+    Q9NQB0
+    Q04206
+    P04637
+    P31213
+    Q9Y243
     P38936
+    O14920
     P14616
-    P09211
-    P04626
-    P08238
-    Q9GZP0
-    P04049
-    P37275
-    Q12778
-    P16234
-    Q02930
-    P14780
+    P01112
+    P19838
+    Q9UJU2
+    P36402
+    P07288
+    O43278
+    Q00987
+    P01127
+    O15393
+    P27930
+    P14625
+    P00750
+    Q07890
     P24864
+    P37275
+    Q92793
+    P35222
+    P21802
+    Q68CJ9
     P55211
-    P10275
-    P31213
-    O00459
-    Q07890
-    P11362
-    Q02750
+    P01308
     P11308
-    P25963
-    P14625
-    Q9HCS4
-    P35222
-    Q92934
-    Q9Y243
-    O43278
-    P46527
-    Q09472
-    Q07889
+    P60484
+    P01133
+    Q8TEY5
+    O15530
     P49841
-    P00749
+    P41161
+    Q9GZP0
+    O00329
+    O96020
+    P24941
     O43889
-    P16220
-    P31749
-    P00533
-    P01133
-    P10398
-    P09619
     Q92569
-    P42338
-    P31751
-    Q01094
-    O00329
-    P07900
-    P41161
-    P07288
-    P08069
-    Q04206
-    Q70SY1
-    Q9NRA1
-    Q9UJU2
-    Q8TEY5
-    Q92793
-    P36402
-    O14920
-    P06400
-    Q9NQB0
-    P27361
+    P18848
+    Q02930
+    O00459
+    P09619
+    P10398
     Q14209
-    P10415
-    P01308
+    Q9HCS4
+    P10275
+    P08238
+    P04626
     P15056
-    P05019
-    P01127
-    O15393
-    Q96BA8
-    P36507
+    Q92934
     P62993
+    P11362
+    P36507
+    P10415
+    P04049
+    P24385
+    P07900
+    P08254
+    P16234
+    P09211
+    Q96BA8
+    P01116
     O15111
+    Q12778
+    Q09472
+    P42338
+    P27986
+    P27361
+    Q02750
+    Q9Y6K9
+    P25963
+    O00716
+    P31749
+    P04085
+    P16220
+    P00749
+    P14780
+    P00533
+    P01135
+    Q01094
     Q99801
-    Q00987
-    P01112
-    Q68CJ9
-    P24941
-    P08254
-    P19838
-    O15530
     P42345
+    P31751
+    Q9NRA1
+    Q70SY1
+    P46527
+    P08069
+    P42336
     P01111
-    P60484
-    P27930
-    Q9Y6K9
-    P01135
-    P27986
     P28482
-    P04637
-    P42336
-    P00750
-    P24385
-    P04085
-    P21802
-    O96020
+    Q07889
+    P05019
+    P06400