bug fix for -t in remove and select, support degenerate nucleotides

nextgenusfs · Aug 1, 2017 · 7f0af85 · 7f0af85
1 parent b8d2581
commit 7f0af85
Show file tree

Hide file tree

Showing 12 changed files with 202 additions and 166 deletions.
diff --git a/Dockerfile-base b/Dockerfile-base
@@ -24,7 +24,9 @@ RUN wget https://github.com/torognes/vsearch/archive/v2.4.3.tar.gz && \
     make install && \
     cd ..
 
-RUN git clone git://github.com/nextgenusfs/amptk.git && \
+RUN wget https://github.com/nextgenusfs/amptk/archive/0.10.2.tar.gz && \
+    tar xzf 0.10.2.tar.gz && \
+    mv amptk-0.10.2 amptk && \
     cd amptk && \
     make && \
     cd ..

diff --git a/amptk.py b/amptk.py
@@ -59,7 +59,7 @@ def download(url, name):
         sys.stdout.write(status)
     f.close()
 
-version = '0.10.1'
+version = '0.10.2'
 
 default_help = """
 Usage:       amptk <command> <arguments>
@@ -762,6 +762,7 @@ def download(url, name):
              -m, --mapping_file  QIIME-like mapping file
              -t, --taxonomy      Taxonomy calculated elsewhere. 2 Column file.
              --method            Taxonomy method. Default: hybrid [utax, sintax, usearch, hybrid, rdp, blast]
+             --add2db            Add FASTA files to DB on the fly.
              --fasta_db          Alternative database of fasta sequenes to use for global alignment.
              --utax_db           UTAX formatted database. Default: ITS2.udb [See configured DB's below]
              --utax_cutoff       UTAX confidence value threshold. Default: 0.8 [0 to 0.9]

diff --git a/bin/amptk-fastq2sra.py b/bin/amptk-fastq2sra.py
@@ -41,13 +41,6 @@ class col:
 parser.add_argument('-a','--append', help='Append a name to all sample names for a run, i.e. --append run1 would yield Sample_run1')
 args=parser.parse_args()
 
-def FindBarcode(Seq, BarcodeDict):
-    for BarcodeLabel in BarcodeDict.keys():
-        Barcode = BarcodeDict[BarcodeLabel]
-        if Seq.startswith(Barcode):
-            return Barcode, BarcodeLabel
-    return "", ""
-
 log_name = args.out + '.amptk-sra.log'
 if os.path.isfile(log_name):
     os.remove(log_name)
@@ -238,12 +231,12 @@ def FindBarcode(Seq, BarcodeDict):
             #look for forward primer
             if args.require_primer != 'off': #means we only want ones with forward primer and or reverse, but don't remove them             
                 #now search for forward primer
-                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch)
+                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 if foralign["editDistance"] < 0:
                     continue
                 if args.require_primer == 'both': 
                     #now search for reverse primer
-                    revalign = edlib.align(ReverseCompRev, seq, mode="HW", task="locations", k=args.primer_mismatch)
+                    revalign = edlib.align(ReverseCompRev, seq, mode="HW", task="locations", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                     if revalign["editDistance"] < 0:  #reverse primer was not found
                         continue         
             #check size

diff --git a/bin/amptk-process_illumina_folder.py b/bin/amptk-process_illumina_folder.py
@@ -63,7 +63,7 @@ def processRead(input):
             for title, seq, qual in FastqGeneralIterator(open(input)):
                 Total += 1
                 #first thing is look for forward primer, if found trim it off
-                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch)
+                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 #if require primer is on make finding primer in amplicon required if amplicon is larger than read length
                 #if less than read length, can't enforce primer because could have been trimmed via staggered trim in fastq_mergepairs
                 if args.primer == 'on' and len(seq) > ReadLen:
@@ -83,7 +83,7 @@ def processRead(input):
                         Seq = seq
                         Qual = qual
                 #now look for reverse primer
-                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch)
+                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 if revalign["editDistance"] >= 0:
                     RevPrimerFound += 1
                     RevCutPos = revalign["locations"][0][0]

diff --git a/bin/amptk-process_illumina_raw.py b/bin/amptk-process_illumina_raw.py
@@ -68,7 +68,7 @@ def processRead(input):
                     NoBC += 1
                     continue
                 #first thing is look for forward primer, if found trim it off
-                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch)
+                foralign = edlib.align(FwdPrimer, seq, mode="HW", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 #if require primer is on make finding primer in amplicon required if amplicon is larger than read length
                 #if less than read length, can't enforce primer because could have been trimmed via staggered trim in fastq_mergepairs
                 if args.primer == 'on' and len(seq) > ReadLen:
@@ -88,7 +88,7 @@ def processRead(input):
                         Seq = seq
                         Qual = qual
                 #now look for reverse primer
-                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch)
+                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 if revalign["editDistance"] >= 0:
                     RevPrimerFound += 1
                     RevCutPos = revalign["locations"][0][0]

diff --git a/bin/amptk-process_ion.py b/bin/amptk-process_ion.py
@@ -76,13 +76,13 @@ def processRead(input):
                 Seq = seq[BarcodeLength:]
                 Qual = qual[BarcodeLength:]
                 #now search for forward primer
-                foralign = edlib.align(FwdPrimer, Seq, mode="HW", k=args.primer_mismatch)
+                foralign = edlib.align(FwdPrimer, Seq, mode="HW", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 if foralign["editDistance"] < 0:
                     NoPrimer += 1
                     continue
                 ForTrim = foralign["locations"][0][1]+1   
                 #now search for reverse primer
-                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch)
+                revalign = edlib.align(RevPrimer, Seq, mode="HW", task="locations", k=args.primer_mismatch, additionalEqualities=amptklib.degenNuc)
                 if revalign["editDistance"] >= 0:  #reverse primer was found
                     RevPrimerFound += 1 
                     #location to trim sequences
@@ -169,7 +169,7 @@ def processRead(input):
 #check if mapping file passed, use this if present, otherwise use command line arguments
 if args.mapping_file:
     if not os.path.isfile(args.mapping_file):
-        amptklib.error("Mapping file is not valid: %s" % args.mapping_file)
+        amptklib.log.error("Mapping file is not valid: %s" % args.mapping_file)
         sys.exit(1)
     mapdata = amptklib.parseMappingFile(args.mapping_file, barcode_file)
     #forward primer in first item in tuple, reverse in second