added the ability to read the reverse as the second column in the inp…

…ut file as well as extending the previous try and except conditions

prince/match_score.py

@@ -8,7 +8,7 @@ def check_file_exists(itr8tr):
     first=next(itr8tr)
     return(chain([first],itr8tr))
 
-def compute_match_score(genome, templates, templateKmers, kmerLength):
+def compute_match_score(genome, genome_reverse, templates, templateKmers, kmerLength):
     try:
         reads1 = check_file_exists(SeqIO.parse(genome + "1.fq", "fastq"))
         reads2 = check_file_exists(SeqIO.parse(genome + "2.fq", "fastq"))
@@ -33,10 +33,32 @@ def compute_match_score(genome, templates, templateKmers, kmerLength):
                             reads2 = check_file_exists(SeqIO.parse(handle, "fastq"))
                     except:
                         try:
-                            reads1 = check_file_exists(SeqIO.parse(genome, "fastq"))
-                            reads2 = iter(())
+                            with gzip.open(genome + "_1.fq.gz", "rt") as handle:
+                                reads1 = check_file_exists(SeqIO.parse(handle, "fastq"))
+
+                            with gzip.open(genome + "_2.fq.gz", "rt") as handle:
+                                reads2 = check_file_exists(SeqIO.parse(handle, "fastq"))
                         except:
-                            raise IOError("Can not open target file %s." % genome)
+                            try:
+                                if genome_reverse == "":
+                                    reads1 = check_file_exists(SeqIO.parse(genome, "fastq"))
+                                    reads2 = iter(())
+                                else:
+                                    reads1 = check_file_exists(SeqIO.parse(genome, "fastq"))
+                                    reads2 = check_file_exists(SeqIO.parse(genome_reverse, "fastq"))
+                            except:
+                                try:
+                                    if genome_reverse == "":
+                                        with gzip.open(genome, "rt") as handle:
+                                            reads1 = check_file_exists(SeqIO.parse(handle, "fastq"))
+                                        reads2 = iter(())
+                                    else:
+                                        with gzip.open(genome, "rt") as handle:
+                                            reads1 = check_file_exists(SeqIO.parse(handle, "fastq"))
+                                        with gzip.open(genome_reverse, "rt") as handle:
+                                            reads2 = check_file_exists(SeqIO.parse(handle, "fastq"))
+                                except:
+                                    raise IOError("Can not open target file %s." % genome)
 
     #Run reads through Coarse Filtering to drastically reduce computation for Fine Filtering
     nucleotides_seen,recruitedReads = coarse_filtering(chain(reads1,reads2), kmerLength, templateKmers)

prince/query_sample.py

@@ -8,10 +8,15 @@ def test_target(opts, templates,templateNames, templateKmers):
         query = file.readline().strip("\n")
         while query:
             start_time = time.time()
-            targetFileName = query.split("/")[-1] #CHANGE
+            #add split on tab to deal with second column scenarios
+            targetFileName = query.split("\t")[0].split("/")[-1] #CHANGE
             print("\nQuerying %s" % targetFileName)
-
-            targetMatchScore = compute_match_score(query, templates, templateKmers, opts.k)
+            query1 = query.split("\t")[0]
+            try:
+                query2 = query.split("\t")[1]
+            except:
+                query2 = ""
+            targetMatchScore = compute_match_score(query1, query2, templates, templateKmers, opts.k)
 
             data = get_data(opts.boost_output)
             equations = get_equations(data)