Update GenomicIntervalReader using tools to use NiceReaderWrapper.

Bad lines are silently ignored.

lib/galaxy/datatypes/converters/interval_to_bed_converter.py

@@ -14,7 +14,7 @@ def __main__():
     strandCol = int(sys.argv.pop(1))-1
     out = open(output_name,'w')
     count = 0
-    for region in bx.intervals.io.GenomicIntervalReader( open(input_name, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(input_name, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
         out.write(region.chrom+"\t"+str(region.start)+"\t"+str(region.end)+"\tregion_"+str(count)+"\t"+"0\t"+region.strand+"\n")
         count += 1
     out.close()

tools/encode/random_intervals_no_bits.py

@@ -104,12 +104,12 @@ def main():
     
     #set up bounding regions to hold random intervals
     bounds = []
-    for bound in bx.intervals.io.GenomicIntervalReader( open( region_fname, 'r' ), chrom_col=0, start_col=1, end_col=2, fix_strand=True): bounds.append(bound)
+    for bound in bx.intervals.io.NiceReaderWrapper( open( region_fname, 'r' ), chrom_col=0, start_col=1, end_col=2, fix_strand=True): bounds.append(bound)
     
     #set up length and number of regions to mimic
     regions = [ [] for i in range(len(bounds)) ]
     
-    for region in bx.intervals.io.GenomicIntervalReader( open(intervals_fname, 'r' ), chrom_col=interval_chr, start_col=interval_start, end_col=interval_end, strand_col=interval_strand, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(intervals_fname, 'r' ), chrom_col=interval_chr, start_col=interval_start, end_col=interval_end, strand_col=interval_strand, fix_strand=True, return_header=False):
         #loop through bounds, find first proper bounds then add
         #if an interval crosses bounds, it will be added to the first bound
         for i in range(len(bounds)):
@@ -127,7 +127,7 @@ def main():
     #read mask file
     mask = []
     if use_mask != "no_mask":
-        for region in bx.intervals.io.GenomicIntervalReader( open(mask_fname, 'r' ), chrom_col=mask_chr, start_col=mask_start, end_col=mask_end, fix_strand=True): mask.append(region)
+        for region in bx.intervals.io.NiceReaderWrapper( open(mask_fname, 'r' ), chrom_col=mask_chr, start_col=mask_start, end_col=mask_end, fix_strand=True): mask.append(region)
     
     out_file = open (out_fname, "w") or die ("Can not open output file")
     

tools/extract/interval2maf.py

@@ -151,7 +151,7 @@ def __main__():
     # Iterate over input ranges 
     num_blocks=0
     num_lines = 0
-    for region in bx.intervals.io.GenomicIntervalReader( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
         try:
             num_lines += 1
             src = "%s.%s" % (dbkey,region.chrom)

tools/extract/interval2maf_pairwise.py

@@ -149,7 +149,7 @@ def __main__():
     # Iterate over input ranges 
     num_blocks=0
     num_lines = 0
-    for region in bx.intervals.io.GenomicIntervalReader( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
         try:
             num_lines += 1
             src = "%s.%s" % (dbkey,region.chrom)

tools/extract/interval_maf_to_merged_fasta.py

@@ -146,7 +146,7 @@ def __main__():
         sys.exit()
 
     #Step through interval file
-    for region in bx.intervals.io.GenomicIntervalReader( open(interval_file, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, strand_col=strand_col, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(interval_file, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, strand_col=strand_col, fix_strand=True, return_header=False):
         target_sequences = {}
         alignment = Genomic_Region()
         for i in range(region.end-region.start): alignment.append(Genomic_Position(dbkey, target_dbkey))

tools/extract/interval_maf_to_merged_fasta_user.py

@@ -121,7 +121,7 @@ def __main__():
     
     
     #Step through interval file
-    for region in bx.intervals.io.GenomicIntervalReader( open(interval_file, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, strand_col=strand_col, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(interval_file, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, strand_col=strand_col, fix_strand=True, return_header=False):
         target_sequences = {}
         alignment = Genomic_Region()
         for i in range(region.end-region.start): alignment.append(Genomic_Position(dbkey, target_dbkey))

tools/extract/user_interval2maf.py

@@ -111,7 +111,7 @@ def __main__():
     # Iterate over input ranges 
     num_blocks=0
     num_lines = 0
-    for region in bx.intervals.io.GenomicIntervalReader( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(interval_file, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False):
         try:
             num_lines += 1
             src = "%s.%s" % (dbkey,region.chrom)

tools/filters/maf/maf_stats.py

@@ -89,7 +89,7 @@ def __main__():
     
     num_region = 0
     #loop through interval file
-    for region in bx.intervals.io.GenomicIntervalReader( open(input_interval_filename, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, fix_strand=True, return_header=False):
+    for region in bx.intervals.io.NiceReaderWrapper( open(input_interval_filename, 'r' ), chrom_col=chr_col, start_col=start_col, end_col=end_col, fix_strand=True, return_header=False):
         sequences = {dbkey: [ False for i in range( region.end - region.start)]}
         
         src = dbkey + "." + region.chrom