added the capability to read reverse read via a second column in the …

…input as well as reverting output to a similar format as previous version

prince/match_score.py

@@ -13,7 +13,7 @@ def combine_records(record1,record2):
     else:
         return itertools.chain(record1,record2)
 
-def get_reads_records(filename):
+def get_reads_records(filename, filename_rev = "" ):
     '''
     Retrieves records for the reads.
     Inputs:
@@ -30,17 +30,33 @@ def get_reads_records(filename):
     gzip_handle2 = None
     # First, check whether filename is actually just a path
     columns = filename.split('.')
+    if filename_rev != "":
+        columns_rev = filename.split('.')
     if columns[-1] == 'gz':
         try:
             gzip_handle1 = gzip.open(filename,'rt')
             record1 = SeqIO.parse(gzip_handle1,'fastq')
         except:
             raise IOError("Cannot open target file %s." % filename)
+        #assuming if first file is gz, second file is gz too
+        if filename_rev != "":
+            try:
+                gzip_handle2 = gzip.open(filename_rev,'rt')
+                record2 = SeqIO.parse(gzip_handle2,'fastq')
+            except:
+                raise IOError("Cannot open target file %s." % filename_rev)
+
     elif columns[-1] == 'fastq' or columns[-1] == 'fq':
         try:
                 record1 = SeqIO.parse(filename,'fastq')
         except:
             raise IOError("Can not open target file %s." % filename)
+        #assuming if first file is fastq or fq, second file is the same too
+        if filename_rev != "":
+            try:
+                record2 = SeqIO.parse(filename_rev,'fastq')
+            except:
+                raise IOError("Cannot open target file %s." % filename_rev)        
     # Otherwise, check all possible file extensions
     else:
         delimiters = ['','_']
@@ -86,12 +102,12 @@ def get_reads_records(filename):
     return record1,record2,gzip_handle1,gzip_handle2
 
 
-def compute_match_score(filename, template_obj, kmerLength, primers):
+def compute_match_score(filename, filename_rev, template_obj, kmerLength, primers):
     '''
     Inputs:
     - (str) data_prefix: the prefix of the NGS dataset paths
     '''
-    record1, record2, gzip1, gzip2 = get_reads_records(filename) 
+    record1, record2, gzip1, gzip2 = get_reads_records(filename, filename_rev) 
     #Run reads through Coarse Filtering to drastically reduce computation for Fine Filtering
     reads = combine_records(record1,record2)
 

prince/query_sample.py

@@ -8,21 +8,26 @@ def test_target(opts, template_obj, primers):
         query = file.readline().strip("\n")
         while query:
             start_time = time.time()
-            targetFileName = query.split("/")[-1] #CHANGE
+            targetFileName = query.split("\t")[0].split("/")[-1] 
+            target_forward = query.split("\t")[0]
+            try:
+                target_reverse = query.split("\t")[1]
+            except:
+                target_reverse = ""
             print("\nQuerying %s" % targetFileName)
 
-            targetMatchScore = compute_match_score(query, template_obj, opts.k, primers)
+            targetMatchScore = compute_match_score(target_forward, target_reverse, template_obj, opts.k, primers)
 
             data = get_data(opts.boost_output)
             equations = get_equations(data)
             predictions = []
 
             # Write target predictions to text file
             with open(opts.target_output, "a+") as f:
-                if os.path.getsize(opts.target_output) == 0:
-                    f.write("Templates,")
-                    f.write(",".join(template_obj["Names"]))
-                    f.write("\n")
+                #if os.path.getsize(opts.target_output) == 0:
+                f.write("Templates,")
+                f.write(",".join(template_obj["Names"]))
+                f.write("\n")
                 f.write(targetFileName)
                 for t, ms in enumerate(targetMatchScore):
                     slope, intercept = equations[t]