convert to python3 style print

Author: wckdouglas

bin/split_bam.py

@@ -2,7 +2,7 @@
 
 import pysam
 import argparse
-from sequencing_tools.split_N_bam import parse_bam
+from sequencing_tools.split_bam_tools import split_N_bam
 
 def getopt():
     parser = argparse.ArgumentParser(description = 'Splitting paired-end bam into two bam files: '+\
@@ -23,7 +23,7 @@ def main():
     with pysam.Samfile(args.in_bam, 'rb') as inbam:
         with pysam.Samfile(split_bam,'wb',template = inbam) as out_split_bam, \
                 pysam.Samfile(other_bam, 'wb', template = inbam) as out_fragment_bam:
-            parse_bam(inbam, out_split_bam, out_fragment_bam)
+            split_N_bam(inbam, out_split_bam, out_fragment_bam)
     return 0
 
 

sequencing_tools/bam_cluster.pyx

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 
+from __future__ import print_function
 from matplotlib import use as mpl_use
 mpl_use('Agg')
 import numpy as np
@@ -80,7 +81,7 @@ def plot_bc_member(member_count, filename):
     p.set_xlabels('Member in barcode family')
     p.set_ylabels('Barcode count')
     p.savefig(figurename)
-    sys.stderr.write('Plotted: %s\n' %figurename)
+    print('Plotted: %s' %figurename, file = sys.stderr)
 
 
 def cluster_bam(tag, bool conserved, AlignmentFile in_bam, out_fastq):
@@ -123,7 +124,7 @@ def cluster_bam(tag, bool conserved, AlignmentFile in_bam, out_fastq):
                     # reinitialize group
                     read_group = readGroup(aln, tag)
             if iter_count % 5000000 == 0 and iter_count != 0:
-                sys.stderr.write('Parsed %i alignments\n' %iter_count)
+                print('Parsed %i alignments' %iter_count, file = sys.stderr)
 
     #spit out the rest in the stupid list
     read_group.cluster(conserved)

sequencing_tools/cluster_reads.pyx

@@ -1,9 +1,9 @@
-
+from __future__ import print_function
 import numpy as np
 from matplotlib import use as mpl_use
 mpl_use('Agg')  # Must be before importing matplotlib.pyplot or pylab
 import matplotlib.pyplot as plt
-from sys import stderr
+import sys
 import cjson
 import gzip
 import re
@@ -114,7 +114,7 @@ def plotBCdistribution(barcode_family_count, outputprefix):
     ax.spines['right'].set_visible(False)
     ax.spines['top'].set_visible(False)
     fig.savefig(figurename)
-    stderr.write('Plotted %s.\n' %figurename)
+    print('Plotted %s.' %figurename, file = sys.stderr)
     return 0
 
 def concensusPairs(table, float fraction_threshold):
@@ -140,7 +140,7 @@ def concensusPairs(table, float fraction_threshold):
 def dictToJson(barcode_dict, json_file):
     with open(json_file,'w') as f:
         [f.write(cjson.encode(items) + '\n') for items in barcode_dict.iteritems()]
-    stderr.write('written %s' %(json_file) + '\n')
+    print('written %s' %(json_file) + '\n', file = sys.stderr)
     return 0
 
 def errorFreeReads(int min_family_member_count, float fraction_threshold, str json_record):
@@ -165,16 +165,16 @@ def errorFreeReads(int min_family_member_count, float fraction_threshold, str js
     member_count = table.shape[0]
     if member_count >= min_family_member_count:
         sequence_left, quality_left, sequence_right, quality_right = concensusPairs(table, fraction_threshold)
-        left_record = '%s_%i_readCluster\n%s\n+\n%s\n' %(index, member_count, sequence_left, quality_left)
-        right_record = '%s_%i_readCluster\n%s\n+\n%s\n' %(index, member_count, sequence_right, quality_right)
+        left_record = '%s_%i_readCluster\n%s\n+\n%s' %(index, member_count, sequence_left, quality_left)
+        right_record = '%s_%i_readCluster\n%s\n+\n%s' %(index, member_count, sequence_right, quality_right)
         return left_record, right_record
     else:
         return 'No'
 
 def writeSeqToFiles(read1, read2, output_cluster_count, result):
     if result!='No':
-        read1.write('@cluster%i_%s' %(output_cluster_count, result[0]))
-        read2.write('@cluster%i_%s' %(output_cluster_count, result[1]))
+        print('@cluster%i_%s' %(output_cluster_count, result[0]), file = read1)
+        print('@cluster%i_%s' %(output_cluster_count, result[1]), file = read2)
         return 1
     else:
         return 0
@@ -199,7 +199,7 @@ def writingAndClusteringReads(outputprefix, min_family_member_count, json_file,
             output_cluster_count += write_func(output_cluster_count, result)
             counter += 1
             if counter % 1000000 == 0:
-                stderr.write('Processed %i read clusters.\n' %(counter))
+                print('Processed %i read clusters.' %(counter), file = sys.stderr)
     pool.close()
     pool.join()
     return output_cluster_count, read1File, read2File
@@ -317,7 +317,7 @@ def recordsToDict(str outputprefix, str inFastq1, str inFastq2, int idx_base, in
         for read_num, (read1,read2) in iterator:
             discarded_sequence_count += cluster_reads(read1, read2)
             if read_num % 10000000 == 0:
-                stderr.write('[%s] Parsed: %i sequence\n' %(programname,read_num))
+                print('[%s] Parsed: %i sequence' %(programname,read_num), file = sys.stderr)
 
     barcode_count = len(barcode_dict.keys())
     return barcode_dict, read_num, barcode_count, discarded_sequence_count

sequencing_tools/filter_multi.pyx

@@ -1,3 +1,4 @@
+from __future__ import print_function
 import pysam
 from cpython cimport bool
 import sys
@@ -177,8 +178,8 @@ def process_pair_bam(in_bam, out_bam, bam_in_bool, bam_out_bool):
 
     read_flag = 'rb' if bam_in_bool else 'r'
     write_flag = 'wb' if bam_out_bool else 'w'
-    sys.stderr.write('Start processing bam file: %s\n' %(in_bam))
-    sys.stderr.write('Writing to: %s\n' %(out_bam))
+    print('Start processing bam file: %s' %(in_bam), file = sys.stderr)
+    print('Writing to: %s' %(out_bam), file = sys.stderr)
     with pysam.Samfile(in_bam, read_flag) as in_sam:
         with pysam.Samfile(out_bam, write_flag, template = in_sam) as out_sam:
             for read_count, alignment in enumerate(in_sam):
@@ -205,7 +206,7 @@ def process_pair_bam(in_bam, out_bam, bam_in_bool, bam_out_bool):
             out_sam.write(read1_aln)
             out_sam.write(read2_aln)
             out_read_count += 1
-    sys.stderr.write('Writting %i read pairs\n' %(out_read_count))
+    print('Writting %i read pairs' %(out_read_count), file = sys.stderr)
     return 0
 
 def process_single_bam(in_bam, out_bam, bam_in_bool, bam_out_bool):
@@ -218,8 +219,8 @@ def process_single_bam(in_bam, out_bam, bam_in_bool, bam_out_bool):
 
     read_flag = 'rb' if bam_in_bool else 'r'
     write_flag = 'wb' if bam_out_bool else 'w'
-    sys.stderr.write('Start processing bam file: %s\n' %(in_bam))
-    sys.stderr.write('Writing to: %s\n' %(out_bam))
+    print('Start processing bam file: %s' %(in_bam), file = sys.stderr)
+    print('Writing to: %s' %(out_bam), file = sys.stderr)
     with pysam.Samfile(in_bam, read_flag) as in_sam:
         with pysam.Samfile(out_bam, write_flag, template = in_sam) as out_sam:
             for read_count, alignment in enumerate(in_sam):
@@ -244,5 +245,5 @@ def process_single_bam(in_bam, out_bam, bam_in_bool, bam_out_bool):
 
             out_sam.write(read_aln)
             out_read_count += 1
-    sys.stderr.write('Writting %i reads\n' %(out_read_count))
+    print('Writting %i reads' %(out_read_count), file = sys.stderr)
     return 0

sequencing_tools/fragment_pairs.pyx

@@ -140,7 +140,7 @@ def bam_to_bed(bam_file, out_file, int min_size, int max_size, tag, output_all):
                         print(line, file=out_file)
             except StopIteration:
                 break
-    sys.stderr.write('Witten %i pair fragments and %i multiple jump fragments\n' %(pair_count, single_count))
+    print('Witten %i pair fragments and %i multiple jump fragments' %(pair_count, single_count), file = sys.stderr)
     return 0
 
 

sequencing_tools/function_clip.pyx

@@ -1,10 +1,11 @@
+from __future__ import print_function
 from itertools import izip, imap, product
 from multiprocessing import Pool
 from functools import partial
 import numpy as np
 import gzip
 cimport numpy as np
-from sys import stderr
+import sys
 from cpython cimport bool
 import io
 import os
@@ -198,13 +199,13 @@ def run_pairs(outputprefix, inFastq1, inFastq2, idx_base,
             out, prefix, seq_record = clipping(read1, read2)
             out_count += out
             if out == 1:
-                file_dict[prefix].write(seq_record + '\n')
+                print(seq_record, file = file_dict[prefix])
             if count % 10000000 == 0 and count != 0:
-                stderr.write('[%s] Parsed %i records\n'%(programname, count))
+                print('[%s] Parsed %i records'%(programname, count), file = sys.stderr)
     [f.close() for f in file_dict.values()]
 
-    stderr.write('[%s] Parsed:           %i sequences\n' %(programname, count))
-    stderr.write('[%s] Output:           %i sequences\n' %(programname, out_count))
+    print('[%s] Parsed:           %i sequences' %(programname, count), file = sys.stderr)
+    print('[%s] Output:           %i sequences' %(programname, out_count), file = sys.stderr)
     return 0
 
 
@@ -240,10 +241,10 @@ def run_pairs_stdout(inFastq1, inFastq2, idx_base,
             out, prefix, seq_record = clipping(read1, read2)
             out_count += out
             if out == 1:
-                print seq_record
+                print(seq_record, file = sys.stdout)
             if count % 10000000 == 0 and count != 0:
-                stderr.write('[%s] Parsed %i records\n'%(programname, count))
+                print('[%s] Parsed %i records'%(programname, count), file = sys.stderr)
 
-    stderr.write('[%s] Parsed:           %i sequences\n' %(programname, count))
-    stderr.write('[%s] Output:           %i sequences\n' %(programname, out_count))
+    print('[%s] Parsed:           %i sequences' %(programname, count), file = sys.stderr)
+    print('[%s] Output:           %i sequences' %(programname, out_count), file = sys.stderr)
     return 0

sequencing_tools/pileup_errors.pyx

@@ -1,3 +1,4 @@
+from __future__ import print_function
 from itertools import izip
 from pysam.libcalignmentfile cimport AlignmentFile, AlignedSegment
 from cpython cimport bool

sequencing_tools/read_cluster.pyx

@@ -1,4 +1,4 @@
-from __future__ import division
+from __future__ import division, print_function
 import numpy as np
 import pysam
 from itertools import izip, imap

sequencing_tools/split_N_bam.pyx

@@ -1,9 +1,12 @@
+from __future__ import print_function
+import sys
 import re
 from pysam.libcalignmentfile cimport AlignmentFile, AlignedSegment
 from cpython cimport bool
 from functools import partial
 from itertools import izip
 from sequencing_tools.bam_tools import split_cigar
+from sequencing_tools.fragment_pairs import concordant_pairs, is_split_pair
 
 cdef int softClipSize(AlignedSegment aln):
     # compare softclip size, output maximum softclipped base on either side
@@ -68,10 +71,10 @@ cpdef int split_bam_pair(AlignmentFile bam, AlignmentFile uniquebam, AlignmentFi
                         multibam.write(read2)
                         multi_written += 1
             if pair_count % 5000000 == 0:
-                print 'Parsed %i alignment pairs' %pair_count
+                print('Parsed %i alignment pairs' %pair_count, file = sys.stderr)
         except StopIteration:
             break
-            print 'Written %i to uniq bam, %i to multi bam' %(uniq_written, multi_written)
+            print('Written %i to uniq bam, %i to multi bam' %(uniq_written, multi_written), file = sys.stderr)
     return 0
 
 cpdef int split_bam_single(AlignmentFile bam, AlignmentFile uniquebam, AlignmentFile multibam, aligner):
@@ -92,6 +95,33 @@ cpdef int split_bam_single(AlignmentFile bam, AlignmentFile uniquebam, Alignment
                 multibam.write(read)
                 multi_written += 1
         if count % 5000000 == 0:
-            print 'Parsed %i alignment pairs' %count
-    print 'Written %i to uniq bam, %i to multi bam' %(uniq_written, multi_written)
-    return 0
+            print('Parsed %i alignment pairs' %count, file = sys.stderr)
+    print('Written %i to uniq bam, %i to multi bam' %(uniq_written, multi_written), file = sys.stderr)
+    return 0
+
+cpdef int split_N_bam(AlignmentFile inbam,
+                    AlignmentFile out_split_bam,
+                    AlignmentFile out_fragment_bam):
+    cdef:
+        int split_out = 0
+        int out = 0
+        AlignedSegment read1, read2
+
+    while True:
+        try:
+            read1 = inbam.next()
+            read2 = inbam.next()
+            if concordant_pairs(read1, read2):
+                if is_split_pair(read1, read2):
+                    out_split_bam.write(read1)
+                    out_split_bam.write(read2)
+                    split_out += 2
+                else:
+                    out_fragment_bam.write(read1)
+                    out_fragment_bam.write(read2)
+                    out += 2
+        except StopIteration:
+            break
+    print('Written %i unsplit and %i split alignments' %(out, split_out), file = sys.stderr)
+    return 0
+