Merge branch 'master' of github.com:BiobankLab/FA_TOOL

Conflicts: README.md modified: README.md modified: bin/cmdfatool.py modified: fatool/sequence.py
BiobankLab · 65dca7247265393d2874e2745430d5e1e9978158 · blazejmarciniak committed Jun 27, 2016 · Jun 27, 2016 · 65dca72
2 parents f455fa2 + a7a6333
commit 65dca7247265393d2874e2745430d5e1e9978158
Unified Split

Showing with 115 additions and 17 deletions.

+11 −11 README.md

+80 −0 bin/cmdfatool.py

+24 −6 fatool/sequence.py
diff --git a/README.md b/README.md
@@ -66,7 +66,7 @@ optional arguments:
   --operator OPERATOR           user who have fired script it will be noted in log
   
   
-    extractNames:
+    extractNames
   
 usage: cmdfatool.py extractNames [-h] -f FAFILE [-o OUTPUT] [--report REPORT]
                                  [--operator OPERATOR]
@@ -79,7 +79,7 @@ optional arguments:
   --operator OPERATOR           user who have fired script it will be noted in log
  
  
-    extractContigs:
+    extractContigs
  
 usage: cmdfatool.py extractContigs [-h] -f FAFILE --list LIST -o OUTPUT
                                    [--report REPORT] [--operator OPERATOR]
@@ -126,7 +126,7 @@ optional arguments:
   --operator OPERATOR   user who have fired script it will be noted in log
   
   
-  split
+    split
 
 usage: cmdfatool.py split [-h] -f FAFILE -d OUTPUTDIR [--report REPORT]
                           [--operator OPERATOR]
@@ -139,7 +139,7 @@ optional arguments:
   --operator OPERATOR   user who have fired script it will be noted in log
   
   
-  reverse
+    reverse
   
 usage: cmdfatool.py reverse [-h] -f FAFILE -o OUTPUT [--report REPORT]
                             [--operator OPERATOR]
@@ -152,7 +152,7 @@ optional arguments:
   --operator OPERATOR   user who have fired script it will be noted in log  
   
   
-  validate
+    validate
   
 usage: cmdfatool.py validate [-h] -f FAFILE -t TYPE [--details]
 
@@ -164,7 +164,7 @@ optional arguments:
   --details             set if you want to see detaild validation info
   
   
-  stats
+    stats
   
 usage: cmdfatool.py stats [-h] -f FAFILE [--report REPORT]
                           [--operator [OPERATOR [OPERATOR ...]]]
@@ -175,7 +175,7 @@ optional arguments:
   --report REPORT             log file if not supplied stdout
   --operator [OPERATOR [OPERATOR ...]]  user who have fired script it will be noted in log
 
-  findPrimer:
+    findPrimer
 
 usage: cmdfatool.py findPrimer [-h] -f FAFILE --start START --stop STOP --mode
                                {FF,FR} [--minlen MINLEN] [--maxlen MAXLEN]
@@ -186,9 +186,9 @@ optional arguments:
   -h, --help            show this help message and exit
   -f FAFILE, --fafile FAFILE  
                         file to show statistics usualy *.fa
-  --start START         strat codon 5'
-  --stop STOP           stop codon 3'
-  --mode {FF,FR}        FF (start forward, stop forward) or FR (start 5' stop 3')
+  --start START         first sequence to be found
+  --stop STOP           last sequence to be found
+  --mode {FF,FR}        FF (start - forward orientated, stop - forward orientated) or FR (start - forward orientated, stop - reverse orientated)
   --minlen MINLEN       minimum length (detfault 50bp)
   --maxlen MAXLEN       max length (detfault 1000bp)
   --mml MML             mismatch level number of allowed missmatches in primers (detfault 0)
@@ -209,4 +209,4 @@ optional arguments:
   -m MARKER, --marker MARKER  marker that indicates start of cut
   -l LENGTH, --length LENGTH  length of cut
   --keepMarker KEEPMARKER     weather to keep marker or not default 1 (Yes)
-  -o OUTPUT, --output OUTPUT  output file default: output.fa
+  -o OUTPUT, --output OUTPUT  output file default: output.fa
diff --git a/bin/cmdfatool.py b/bin/cmdfatool.py
@@ -125,6 +125,15 @@ def main():
     sub_lnam.add_argument('--operator', help='user who have fired script it will be noted in report', nargs='*', type=str)
     sub_lnam.set_defaults(func=cut_name_pattern)
     
+    sub_trn_d2p = subparsers.add_parser('translateDNA2Proteins', help='display translation to proteins')
+    sub_trn_d2p.add_argument('-f', '--fafile', help='file to show statistics usualy *.fa', type=argparse.FileType('r'), required=True)
+    sub_trn_d2p.add_argument('-o', '--output', help='output file default: output.fa', type=argparse.FileType('w'), default='output.fa')
+    sub_trn_d2p.add_argument('--startCodons', help='list of start codons separated by space bar', nargs='*', type=str)
+    sub_trn_d2p.add_argument('--stopCodons', help='list of stop codons separated by space bar', nargs='*', type=str)
+    sub_trn_d2p.add_argument('--nss', help='No Start Stop', action='store_true')
+    sub_trn_d2p.add_argument('--report', help='report results into file if not supplied stdout', type=argparse.FileType('w'))
+    sub_trn_d2p.add_argument('--operator', help='user who have fired script it will be noted in report', nargs='*', type=str)
+    sub_trn_d2p.set_defaults(func=translate_dna_to_protein)
     '''
     sub_fap  = subparsers.add_parser('findPrimer', help='show statistics of fa file')
     sub_fap.add_argument('-f', '--fafile', help='file to show statistics usualy *.fa', type=argparse.FileType('r'), required=True)
@@ -421,6 +430,77 @@ def cut_name_pattern(args):
         r.leave_name_after_marker(args.marker, args.length, args.keepMarker)
     fa.write(args.output)
     
+def translate_dna_to_protein(args):
+    rep = str(make_log_header('translate2protein', args.operator))
+    fa = Fa.load_from_file(args.fafile)
+    r_dict = {}
+    otp = ''
+    if args.nss:
+        for r in fa.contigs:
+            r_dict = r.translate2protein({})
+            otp += '\n=============================\n'+r.name+'\n=============================\n'
+            otp += '\nFORWARD\n'
+            i = 0
+            for f in r_dict['fwd']:
+                otp += 'FRAME:\t'+str(i+1)+'\n'
+                otp += 'BEFORE:\t '+f[0]
+                otp += 'TRANSLATION:\n '+f[1]
+                otp += 'AFTER:\t '+f[2]
+                otp += '\n------------------------------------------------\n'
+                i+=1
+            otp += '\nREVERS\n'
+            otp += '\n------------------------------------------------\n'
+            i = 0
+            for f in r_dict['rev']:
+                otp += 'FRAME:\t'+str(i+1)+'\n'
+                otp += 'BEFORE:\t '+f[0]
+                otp += 'TRANSLATION:\n '+f[1]
+                otp += 'AFTER:\t '+f[2]
+                otp += '\n------------------------------------------------\n'
+                i+=1
+        rep += otp
+                
+    else:
+        tdict = {
+            'GCA':'A','GCC':'A','GCG':'A','GCT':'A', 'TGC':'C','TGT':'C', 'GAC':'D', 'GAT':'D', 'GAA':'E', 'GAG':'E',
+            'TTC':'F', 'TTT':'F', 'GGA':'G', 'GGC':'G', 'GGG':'G', 'GGT':'G', 'CAC':'H', 'CAT':'H', 'ATA':'I', 'ATC':'I', 'ATT':'I',
+            'AAA':'K', 'AAG':'K', 'TTA':'L', 'TTG':'L', 'CTA':'L', 'CTC':'L', 'CTG':'L', 'CTT':'L', 'ATG':'M', 'AAC':'N', 'AAT':'N',
+            'CCA':'P', 'CCC':'P', 'CCG':'P', 'CCT':'P', 'CAA':'Q', 'CAG':'Q', 'AGA':'R', 'AGG':'R', 'CGA':'R', 'CGC':'R', 'CGG':'R', 
+            'CGT':'R', 'AGC':'S', 'AGT':'S', 'TCA':'S', 'TCC':'S', 'TCG':'S', 'TCT':'S', 'ACA':'T', 'ACC':'T', 'ACG':'T', 'ACT':'T',
+            'GTA':'V', 'GTC':'V', 'GTG':'V', 'GTT':'V', 'TGG':'W', 'TAC':'Y', 'TAT':'Y', 'TAG': '*', 'TGA':'*', 'TAA':'*'
+        }
+        for r in fa.contigs:
+        
+            r_dict = r.translate2protein_in_range(args.startCodons, args.stopCodons, tdict)
+            otp += '\n=============================\n'+r.name+'\n=============================\n'
+            otp += 'FORWARD\n'
+            i = 0
+            
+            for f in r_dict['fwd']:
+                otp += 'FRAME:\t'+str(i+1)+'\n'
+                for k in f:
+                    otp += '\n'+k[0]+' start: '+str(k[1])
+                    otp += '\n------------------------------------------------\n'
+                otp += '\n=================================================\n'
+            otp += 'REVERS\n'
+            i = 0
+            for f in r_dict['rev']:
+                otp += 'FRAME:\t'+str(i+1)+'\n'
+                for k in f:
+                    otp += '\n'+k[0]+' start: '+str(k[1])
+                    otp += '\n------------------------------------------------\n'
+                otp += '\n=================================================\n'
+        rep += otp
+    
+    fa.write(args.output)
+    rep += '\n\n------------------------------------------------------'
+    rep += '\nFinished:\t'+str(datetime.datetime.now())
+    if args.report:
+        with args.report as log_file:
+            log_file.write(rep)
+    else:
+        print rep
+    
 def cut_name(args):
     pass
 
diff --git a/fatool/sequence.py b/fatool/sequence.py
@@ -286,13 +286,12 @@ def translate2protein_in_range_generic(seq, start, stop, tdict):
         # creating pattern to find stop codons
         for r in stop:
             p_stop +=  r+'|'
-        p_stop = '('+p.rstrip('|')+')'
+        p_stop = '('+p_stop.rstrip('|')+')'
         
-        # match for start contigs
         m = re.finditer(p, seq)
         
         # there will be stored latest string position for each frame
-        frame_iterator[0,0,0]
+        frame_iterator = [0,0,0]
         
         stop_pos = len(seq) # where to stop searching if no stopcodon found
         
@@ -303,9 +302,10 @@ def translate2protein_in_range_generic(seq, start, stop, tdict):
                 # set i for start position of current start contig
                 i = r.start()
                 ret = ''
-                while i+3 <= stop:
+                while i+3 <= stop_pos:
                     ret += Sequence.translate(seq[i:i+3], tdict)
                     if re.match(p_stop, seq[i:i+3]):
+                        #print 'exiting on: '+seq[i:i+3]
                         i = i+3
                         break
                     else:
@@ -321,18 +321,36 @@ def translate2protein_in_range_generic(seq, start, stop, tdict):
                     
         return [frame1, frame2, frame3]
         
+    def translate2protein_in_range(self, start, stop, tdict):
+        tdict = {
+            'GCA':'A','GCC':'A','GCG':'A','GCT':'A', 'TGC':'C','TGT':'C', 'GAC':'D', 'GAT':'D', 'GAA':'E', 'GAG':'E',
+            'TTC':'F', 'TTT':'F', 'GGA':'G', 'GGC':'G', 'GGG':'G', 'GGT':'G', 'CAC':'H', 'CAT':'H', 'ATA':'I', 'ATC':'I', 'ATT':'I',
+            'AAA':'K', 'AAG':'K', 'TTA':'L', 'TTG':'L', 'CTA':'L', 'CTC':'L', 'CTG':'L', 'CTT':'L', 'ATG':'M', 'AAC':'N', 'AAT':'N',
+            'CCA':'P', 'CCC':'P', 'CCG':'P', 'CCT':'P', 'CAA':'Q', 'CAG':'Q', 'AGA':'R', 'AGG':'R', 'CGA':'R', 'CGC':'R', 'CGG':'R', 
+            'CGT':'R', 'AGC':'S', 'AGT':'S', 'TCA':'S', 'TCC':'S', 'TCG':'S', 'TCT':'S', 'ACA':'T', 'ACC':'T', 'ACG':'T', 'ACT':'T',
+            'GTA':'V', 'GTC':'V', 'GTG':'V', 'GTT':'V', 'TGG':'W', 'TAC':'Y', 'TAT':'Y', 'TAG': '*', 'TGA':'*', 'TAA':'*'
+        }
+        
+        f = Sequence.translate2protein_in_range_generic(self.seq, start, stop, tdict)
+        r = Sequence.translate2protein_in_range_generic(self.reverse().seq, start, stop, tdict)
+        
+        return {'fwd':f, 'rev':r}
+        
+        
     @staticmethod
     def translate2protein_generic(seq, tdict):
         # +5 to secure all frames
         f1 = ''
         f2 = ''
         f3 = ''
+        i = 0
         while i+5 < len(seq):
             f1 += Sequence.translate(seq[i:i+3], tdict)
             f2 += Sequence.translate(seq[i+1:i+4], tdict)
             f3 += Sequence.translate(seq[i+2:i+5], tdict)
+            i = i + 3
             
-        return [('',f1,seq[-2:]),(seq[0:1],f2,seq[-1:]),(seq[0:2],f2,)]
+        return [('',f1,seq[-2:]),(seq[0:1],f2,seq[-1:]),(seq[0:2],f2,'')]
     
     def translate2protein(self, tdict):
         tdict = {
@@ -348,7 +366,7 @@ def translate2protein(self, tdict):
         return {'fwd':f, 'rev':r}
     
     @staticmethod
-    def translate(contig, tdict):
+    def translate(codon, tdict):
         if codon in tdict:
             return tdict[codon]
         else: