PKG-INFO

 Metadata-Version: 2.1
 Name: HTSeq
-Version: 0.10.0
+Version: 0.11.2
 Summary: A framework to process and analyze data from high-throughput sequencing (HTS) assays
 Home-page: https://github.com/simon-anders/htseq
 Author: Simon Anders

README.rst

@@ -29,13 +29,15 @@ and are transferring the binaries onto another machine with a compatible
 environment (architechture, shared libraries). If you are not sure,
 chances are you need them.
 
-Both ``Linux`` and ``OSX`` are supported and binaries are provided for virtually
-all ``Linux`` versions and for some ``OSX`` versions (the latter only for ``Python 2.7``
-and ``Python 3.6``). A source package which should not require ``Cython`` nor ``SWIG``
-is provided for all other cases. ``Windows`` is not officially supported as we don't
-have access to a Continuous Integration ``Windows`` machine that supports ``pysam``.
-However, if you have built ``HTSeq`` for ``Windows``, please open an issue and we'll
-try and include it in the release.
+Both **Linux** and **OSX** are supported and binaries are provided for virtually
+all Linux versions and for some OSX versions (the latter only for Python 2.7
+and 3.6). A source package which should not require ``Cython`` nor ``SWIG``
+is provided for all other cases.
+
+**Windows is not officially supported** as we don't have access to a Continuous
+Integration Windows machine that supports ``pysam``. However, if you have built
+``HTSeq`` for Windows, please open an issue and we'll try and include it in the
+release.
 
 Installation
 ~~~~~~~~~~~~
@@ -57,6 +59,20 @@ To install directly from PyPI:
 
    </div>
 
+To install a specific version (e.g. version 0.11.0):
+
+.. raw:: html
+
+   <div class="highlight highlight-source-shell">
+
+::
+
+    pip install 'HTSeq==0.11.0'
+
+.. raw:: html
+
+   </div>
+
 If this fails, please install all dependencies first:
 
 .. raw:: html

VERSION

-0.10.0
+0.11.2

debian/changelog

+htseq (0.11.2-1) unstable; urgency=medium
+
+  * New upstream version
+  * debhelper 12
+  * Standards-Version: 4.3.0
+  * Secure URI in copyright format
+  * Drop ancient X-Python-Version field
+
+ -- Andreas Tille <tille@debian.org>  Fri, 11 Jan 2019 23:31:53 +0100
+
 htseq (0.10.0-1) unstable; urgency=medium
 
   * New upstream version

debian/compat

-11
+12

debian/control

@@ -5,7 +5,7 @@ Uploaders: Diane Trout <diane@ghic.org>,
 Section: python
 Testsuite: autopkgtest-pkg-python
 Priority: optional
-Build-Depends: debhelper (>= 11~),
+Build-Depends: debhelper (>= 12~),
                python-debian,
                python-setuptools,
                python-all-dev,
@@ -21,12 +21,10 @@ Build-Depends: debhelper (>= 11~),
                swig,
                cython,
                cython3
-Standards-Version: 4.1.4
+Standards-Version: 4.3.0
 Vcs-Browser: https://salsa.debian.org/med-team/htseq
 Vcs-Git: https://salsa.debian.org/med-team/htseq.git
 Homepage: http://www-huber.embl.de/users/anders/HTSeq/doc/overview.html
-X-Python-Version: >= 2.7
-X-Python3-Version: >= 3.4
 
 Package: python-htseq
 Architecture: any

debian/copyright

-Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: HTSeq
 Upstream-Contact: Simon Anders
 Source: https://pypi.python.org/pypi/HTSeq/

python2/HTSeq/_version.py

-__version__ = "0.10.0"
\ No newline at end of file
+__version__ = "0.11.2"
\ No newline at end of file

python2/HTSeq/scripts/count.py

@@ -41,12 +41,13 @@ def count_reads_in_features(sam_filenames, gff_filename,
             r = (r,)
         for read in r:
             if read is not None:
-                samoutfile.write(read.original_sam_line.rstrip() +
-                                 "\tXF:Z:" + assignment + "\n")
+                read.optional_fields.append(('XF', assignment))
+                samoutfile.write(read.get_sam_line() + "\n")
 
-    if samouts != "":
+    if samouts != []:
         if len(samouts) != len(sam_filenames):
-            raise ValueError('Select the same number of SAM input and output files')
+            raise ValueError(
+                    'Select the same number of SAM input and output files')
         # Try to open samout files early in case any of them has issues
         for samout in samouts:
             with open(samout, 'w'):
@@ -73,10 +74,12 @@ def count_reads_in_features(sam_filenames, gff_filename,
                 try:
                     feature_id = f.attr[id_attribute]
                 except KeyError:
-                    raise ValueError("Feature %s does not contain a '%s' attribute" %
+                    raise ValueError(
+                            "Feature %s does not contain a '%s' attribute" %
                             (f.name, id_attribute))
                 if stranded != "no" and f.iv.strand == ".":
-                    raise ValueError("Feature %s at %s does not have strand information but you are "
+                    raise ValueError(
+                            "Feature %s at %s does not have strand information but you are "
                             "running htseq-count in stranded mode. Use '--stranded=no'." %
                             (f.name, f.iv))
                 features[f.iv] += feature_id
@@ -116,22 +119,28 @@ def count_reads_in_features(sam_filenames, gff_filename,
     lowqual_all = []
     nonunique_all = []
     for isam, (sam_filename) in enumerate(sam_filenames):
-        if samouts != '':
+        if samouts != []:
             samoutfile = open(samouts[isam], 'w')
         else:
             samoutfile = None
 
         try:
-            if sam_filename != "-":
-                read_seq_file = SAM_or_BAM_Reader(sam_filename)
-                read_seq = read_seq_file
-                first_read = next(iter(read_seq))
-            else:
+            if sam_filename == "-":
                 read_seq_file = SAM_or_BAM_Reader(sys.stdin)
+            else:
+                read_seq_file = SAM_or_BAM_Reader(sam_filename)
             read_seq_iter = iter(read_seq_file)
+            # Catch empty BAM files
+            try:
                 first_read = next(read_seq_iter)
-                read_seq = itertools.chain([first_read], read_seq_iter)
                 pe_mode = first_read.paired_end
+            except:
+                first_read = None
+                pe_mode = False
+            if first_read is not None:
+                read_seq = itertools.chain([first_read], read_seq_iter)
+            else:
+                read_seq = []
         except:
             sys.stderr.write(
                 "Error occured when reading beginning of SAM/BAM file.\n")
@@ -175,7 +184,10 @@ def count_reads_in_features(sam_filenames, gff_filename,
                     try:
                         if r.optional_field("NH") > 1:
                             nonunique += 1
-                            write_to_samout(r, "__alignment_not_unique", samoutfile)
+                            write_to_samout(
+                                    r,
+                                    "__alignment_not_unique",
+                                    samoutfile)
                             if multimapped_mode == 'none':
                                 continue
                     except KeyError:
@@ -325,7 +337,8 @@ def count_reads_in_features(sam_filenames, gff_filename,
     print('\t'.join(["__alignment_not_unique"] + pad + [str(c) for c in nonunique_all]))
 
 
-def my_showwarning(message, category, filename, lineno=None, file=None, line=None):
+def my_showwarning(message, category, filename, lineno=None, file=None,
+                   line=None):
     sys.stderr.write("Warning: %s\n" % message)
 
 
@@ -396,9 +409,11 @@ def main():
             "suitable for Ensembl GTF files: gene_id)")
 
     pa.add_argument(
-            "--additional-attr", type=str, nargs='+',
-            default=(), help="Additional feature attributes (default: none, " +
-            "suitable for Ensembl GTF files: gene_name)")
+            "--additional-attr", type=str,
+            action='append',
+            default=[], help="Additional feature attributes (default: none, " +
+            "suitable for Ensembl GTF files: gene_name). Use multiple times " +
+            "for each different attribute")
 
     pa.add_argument(
             "-m", "--mode", dest="mode",
@@ -414,19 +429,20 @@ def main():
 
     pa.add_argument(
             "--secondary-alignments", dest="secondary_alignments", type=str,
-            choices=("score", "ignore"), default="score",
+            choices=("score", "ignore"), default="ignore",
             help="Whether to score secondary alignments (0x100 flag)")
 
     pa.add_argument(
             "--supplementary-alignments", dest="supplementary_alignments", type=str,
-            choices=("score", "ignore"), default="score",
+            choices=("score", "ignore"), default="ignore",
             help="Whether to score supplementary alignments (0x800 flag)")
 
     pa.add_argument(
-            "-o", "--samout", type=str, dest="samouts", nargs='+',
-            default="", help="write out all SAM alignment records into an output " +
-            "SAM file called SAMOUT, annotating each line with its feature assignment " +
-            "(as an optional field with tag 'XF')")
+            "-o", "--samout", type=str, dest="samouts",
+            action='append',
+            default=[], help="write out all SAM alignment records into " +
+            "SAM files (one per input file needed), annotating each line " +
+            "with its feature assignment (as an optional field with tag 'XF')")
 
     pa.add_argument(
             "-q", "--quiet", action="store_true", dest="quiet",

python2/HTSeq/scripts/qa.py

@@ -5,11 +5,14 @@
 # (c) Simon Anders, European Molecular Biology Laboratory, 2010
 # released under GNU General Public License
 
-import sys, time, os.path, optparse
+import sys
+import os.path
+import optparse
 from itertools import *
 import numpy
 import HTSeq
 
+
 def main():
 
     try:
@@ -26,10 +29,10 @@ def main():
     except ImportError:
         from matplotlib.pyplot import normalize as Normalize
 
-
     # **** Parse command line ****
 
-    optParser = optparse.OptionParser( usage = "%prog [options] read_file",
+    optParser = optparse.OptionParser(
+        usage="%prog [options] read_file",
         description=
         "This script take a file with high-throughput sequencing reads " +
         "(supported formats: SAM, Solexa _export.txt, FASTQ, Solexa " +
@@ -41,20 +44,26 @@ def main():
         "Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology " +
         " Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General " +
         " Public License v3. Part of the 'HTSeq' framework, version %s." % HTSeq.__version__)
-    optParser.add_option( "-t", "--type", type="choice", dest="type",
+    optParser.add_option(
+        "-t", "--type", type="choice", dest="type",
         choices=("sam", "bam", "solexa-export", "fastq", "solexa-fastq"),
         default="sam", help="type of read_file (one of: sam [default], bam, " +
         "solexa-export, fastq, solexa-fastq)")
-    optParser.add_option( "-o", "--outfile", type="string", dest="outfile",
+    optParser.add_option(
+        "-o", "--outfile", type="string", dest="outfile",
         help="output filename (default is <read_file>.pdf)")
-    optParser.add_option( "-r", "--readlength", type="int", dest="readlen",
+    optParser.add_option(
+        "-r", "--readlength", type="int", dest="readlen",
         help="the maximum read length (when not specified, the script guesses from the file")
-    optParser.add_option( "-g", "--gamma", type="float", dest="gamma",
+    optParser.add_option(
+        "-g", "--gamma", type="float", dest="gamma",
         default = 0.3,
         help="the gamma factor for the contrast adjustment of the quality score plot")
-    optParser.add_option( "-n", "--nosplit", action="store_true", dest="nosplit",
+    optParser.add_option(
+        "-n", "--nosplit", action="store_true", dest="nosplit",
         help="do not split reads in unaligned and aligned ones")
-    optParser.add_option( "-m", "--maxqual", type="int", dest="maxqual", default=41,
+    optParser.add_option(
+        "-m", "--maxqual", type="int", dest="maxqual", default=41,
         help="the maximum quality score that appears in the data (default: 41)")
 
     if len(sys.argv) == 1:
@@ -64,7 +73,9 @@ def main():
     (opts, args) = optParser.parse_args()
 
     if len(args) != 1:
-        sys.stderr.write( sys.argv[0] + ": Error: Please provide one argument (the read_file).\n" )
+        sys.stderr.write(
+            sys.argv[0] +
+            ": Error: Please provide one argument (the read_file).\n")
         sys.stderr.write("  Call with '-h' to get usage information.\n")
         sys.exit(1)
 
@@ -95,7 +106,6 @@ def main():
     else:
         outfilename = opts.outfile
 
-
     # **** Get read length ****
 
     if opts.readlen is not None:
@@ -113,7 +123,6 @@ def main():
     max_qual = opts.maxqual
     gamma = opts.gamma
 
-
     # **** Initialize count arrays ****
 
     base_arr_U = numpy.zeros((readlen, 5), numpy.int)
@@ -122,7 +131,6 @@ def main():
         base_arr_A = numpy.zeros((readlen, 5), numpy.int)
         qual_arr_A = numpy.zeros((readlen, max_qual+1), numpy.int)
 
-
     # **** Main counting loop ****
 
     i = 0
@@ -147,7 +155,6 @@ def main():
         raise
     print i, "reads processed"
 
-
     # **** Normalize result ****
 
     def norm_by_pos(arr):
@@ -162,7 +169,6 @@ def main():
         arr_n[arr == 0] = 0
         return arr_n
 
-
     base_arr_U_n = norm_by_pos(base_arr_U)
     qual_arr_U_n = norm_by_start(qual_arr_U)
     nreads_U = base_arr_U[0, :].sum()
@@ -171,7 +177,6 @@ def main():
         qual_arr_A_n = norm_by_start(qual_arr_A)
         nreads_A = base_arr_A[0, :].sum()
 
-
     # **** Make plot ****
 
     def plot_bases(arr):
@@ -197,12 +202,12 @@ def main():
         pyplot.subplot(221)
         plot_bases(base_arr_U_n)
         pyplot.ylabel("proportion of base")
-        pyplot.title( "non-aligned reads\n%.0f%% (%.3f million)" %
+        pyplot.title("non-aligned reads\n%.0f%% (%.4f million)" %
                      (100. * nreads_U / (nreads_U+nreads_A), nreads_U / 1e6))
 
         pyplot.subplot(222)
         plot_bases(base_arr_A_n)
-        pyplot.title( "aligned reads\n%.0f%% (%.3f million)" %
+        pyplot.title("aligned reads\n%.0f%% (%.4f million)" %
                      (100. * nreads_A / (nreads_U+nreads_A), nreads_A / 1e6))
 
         pyplot.subplot(223)
@@ -232,8 +237,8 @@ def main():
         pyplot.xlabel("position in read")
         pyplot.ylabel("base-call quality score")
 
-
     pyplot.savefig(outfilename)
 
+
 if __name__ == "__main__":
     main()

python2/src/HTSeq/_HTSeq.pxd

@@ -20,7 +20,7 @@ cdef class Sequence( object ):
    cdef public bytes seq
    cdef public str name
    cdef public str descr
-   cpdef Sequence get_reverse_complement( self )      
+   cpdef Sequence get_reverse_complement(self, bint rename=?)      
    cpdef object add_bases_to_count_array(Sequence self, numpy.ndarray count_array_)
    cpdef Sequence trim_left_end(Sequence self, Sequence pattern, float mismatch_prop=?)   
    cpdef Sequence trim_right_end(Sequence self, Sequence pattern, float mismatch_prop=?)   

python2/src/HTSeq/_HTSeq.pyx

@@ -651,10 +651,15 @@ cdef class Sequence(object):
         self.name = name
         self.descr = None
 
-    cpdef Sequence get_reverse_complement(self):
+    cpdef Sequence get_reverse_complement(self, bint rename=True):
+        if rename:
             return Sequence(
                 reverse_complement(self.seq),
                 "revcomp_of_" + self.name)
+        else:
+            return Sequence(
+                reverse_complement(self.seq),
+                self.name)
 
     def __str__(self):
         return self.seq
@@ -903,13 +908,20 @@ cdef class SequenceWithQualities(Sequence):
         self.write_to_fastq_file(sio, convert_to_phred)
         return sio.getvalue()
 
-    cpdef SequenceWithQualities get_reverse_complement(self):
+    cpdef SequenceWithQualities get_reverse_complement(self, bint rename=True):
         cdef SequenceWithQualities res
+        if rename:
             res = SequenceWithQualities(
                 reverse_complement(self.seq),
                 "revcomp_of_" + self.name,
                 self._qualstr[::-1],
                 self._qualscale)
+        else:
+            res = SequenceWithQualities(
+                reverse_complement(self.seq),
+                self.name,
+                self._qualstr[::-1],
+                self._qualscale)
         if self._qualarr is not None:
             res._qualarr = self._qualarr[::-1]
         return res

python3/HTSeq/_version.py

-__version__ = "0.10.0"
\ No newline at end of file
+__version__ = "0.11.2"
\ No newline at end of file

python3/HTSeq/scripts/count.py

@@ -41,10 +41,10 @@ def count_reads_in_features(sam_filenames, gff_filename,
             r = (r,)
         for read in r:
             if read is not None:
-                samoutfile.write(read.original_sam_line.rstrip() +
-                                 "\tXF:Z:" + assignment + "\n")
+                read.optional_fields.append(('XF', assignment))
+                samoutfile.write(read.get_sam_line() + "\n")
 
-    if samouts != "":
+    if samouts != []:
         if len(samouts) != len(sam_filenames):
             raise ValueError('Select the same number of SAM input and output files')
         # Try to open samout files early in case any of them has issues
@@ -116,22 +116,28 @@ def count_reads_in_features(sam_filenames, gff_filename,
     lowqual_all = []
     nonunique_all = []
     for isam, (sam_filename) in enumerate(sam_filenames):
-        if samouts != '':
+        if samouts != []:
             samoutfile = open(samouts[isam], 'w')
         else:
             samoutfile = None
 
         try:
-            if sam_filename != "-":
-                read_seq_file = SAM_or_BAM_Reader(sam_filename)
-                read_seq = read_seq_file
-                first_read = next(iter(read_seq))
-            else:
+            if sam_filename == "-":
                 read_seq_file = SAM_or_BAM_Reader(sys.stdin)
+            else:
+                read_seq_file = SAM_or_BAM_Reader(sam_filename)
             read_seq_iter = iter(read_seq_file)
+            # Catch empty BAM files
+            try:
                 first_read = next(read_seq_iter)
-                read_seq = itertools.chain([first_read], read_seq_iter)
                 pe_mode = first_read.paired_end
+            except:
+                first_read = None
+                pe_mode = False
+            if first_read is not None:
+                read_seq = itertools.chain([first_read], read_seq_iter)
+            else:
+                read_seq = []
         except:
             sys.stderr.write(
                 "Error occured when reading beginning of SAM/BAM file.\n")
@@ -139,12 +145,20 @@ def count_reads_in_features(sam_filenames, gff_filename,
 
         try:
             if pe_mode:
+                if ((supplementary_alignment_mode == 'ignore') and
+                   (secondary_alignment_mode == 'ignore')):
+                    primary_only = True
+                else:
+                    primary_only = False
                 if order == "name":
-                    read_seq = HTSeq.pair_SAM_alignments(read_seq)
+                    read_seq = HTSeq.pair_SAM_alignments(
+                            read_seq,
+                            primary_only=primary_only)
                 elif order == "pos":
                     read_seq = HTSeq.pair_SAM_alignments_with_buffer(
                             read_seq,
-                            max_buffer_size=max_buffer_size)
+                            max_buffer_size=max_buffer_size,
+                            primary_only=primary_only)
                 else:
                     raise ValueError("Illegal order specified.")
             empty = 0
@@ -396,9 +410,11 @@ def main():
             "suitable for Ensembl GTF files: gene_id)")
 
     pa.add_argument(
-            "--additional-attr", type=str, nargs='+',
-            default=(), help="Additional feature attributes (default: none, " +
-            "suitable for Ensembl GTF files: gene_name)")
+            "--additional-attr", type=str,
+            action='append',
+            default=[], help="Additional feature attributes (default: none, " +
+            "suitable for Ensembl GTF files: gene_name). Use multiple times " +
+            "for each different attribute")
 
     pa.add_argument(
             "-m", "--mode", dest="mode",
@@ -414,19 +430,20 @@ def main():
 
     pa.add_argument(
             "--secondary-alignments", dest="secondary_alignments", type=str,
-            choices=("score", "ignore"), default="score",
+            choices=("score", "ignore"), default="ignore",
             help="Whether to score secondary alignments (0x100 flag)")
 
     pa.add_argument(
             "--supplementary-alignments", dest="supplementary_alignments", type=str,
-            choices=("score", "ignore"), default="score",
+            choices=("score", "ignore"), default="ignore",
             help="Whether to score supplementary alignments (0x800 flag)")
 
     pa.add_argument(
-            "-o", "--samout", type=str, dest="samouts", nargs='+',
-            default="", help="write out all SAM alignment records into an output " +
-            "SAM file called SAMOUT, annotating each line with its feature assignment " +
-            "(as an optional field with tag 'XF')")
+            "-o", "--samout", type=str, dest="samouts",
+            action='append',
+            default=[], help="write out all SAM alignment records into " +
+            "SAM files (one per input file needed), annotating each line " +
+            "with its feature assignment (as an optional field with tag 'XF')")
 
     pa.add_argument(
             "-q", "--quiet", action="store_true", dest="quiet",

python3/HTSeq/scripts/qa.py

@@ -5,11 +5,14 @@
 # (c) Simon Anders, European Molecular Biology Laboratory, 2010
 # released under GNU General Public License
 
-import sys, time, os.path, optparse
+import sys
+import os.path
+import optparse
 from itertools import *
 import numpy
 import HTSeq
 
+
 def main():
 
     try:
@@ -26,10 +29,10 @@ def main():
     except ImportError:
         from matplotlib.pyplot import normalize as Normalize
 
-
     # **** Parse command line ****
 
-    optParser = optparse.OptionParser( usage = "%prog [options] read_file",
+    optParser = optparse.OptionParser(
+        usage="%prog [options] read_file",
         description=
         "This script take a file with high-throughput sequencing reads " +
         "(supported formats: SAM, Solexa _export.txt, FASTQ, Solexa " +
@@ -41,20 +44,26 @@ def main():
         "Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology " +
         " Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General " +
         " Public License v3. Part of the 'HTSeq' framework, version %s." % HTSeq.__version__)
-    optParser.add_option( "-t", "--type", type="choice", dest="type",
+    optParser.add_option(
+        "-t", "--type", type="choice", dest="type",
         choices=("sam", "bam", "solexa-export", "fastq", "solexa-fastq"),
         default="sam", help="type of read_file (one of: sam [default], bam, " +
         "solexa-export, fastq, solexa-fastq)")
-    optParser.add_option( "-o", "--outfile", type="string", dest="outfile",
+    optParser.add_option(
+        "-o", "--outfile", type="string", dest="outfile",
         help="output filename (default is <read_file>.pdf)")
-    optParser.add_option( "-r", "--readlength", type="int", dest="readlen",
+    optParser.add_option(
+        "-r", "--readlength", type="int", dest="readlen",
         help="the maximum read length (when not specified, the script guesses from the file")
-    optParser.add_option( "-g", "--gamma", type="float", dest="gamma",
+    optParser.add_option(
+        "-g", "--gamma", type="float", dest="gamma",
         default=0.3,
         help="the gamma factor for the contrast adjustment of the quality score plot")
-    optParser.add_option( "-n", "--nosplit", action="store_true", dest="nosplit",
+    optParser.add_option(
+        "-n", "--nosplit", action="store_true", dest="nosplit",
         help="do not split reads in unaligned and aligned ones")
-    optParser.add_option( "-m", "--maxqual", type="int", dest="maxqual", default=41,
+    optParser.add_option(
+        "-m", "--maxqual", type="int", dest="maxqual", default=41,
         help="the maximum quality score that appears in the data (default: 41)")
 
     if len(sys.argv) == 1:
@@ -64,7 +73,8 @@ def main():
     (opts, args) = optParser.parse_args()
 
     if len(args) != 1:
-        sys.stderr.write( sys.argv[0] + ": Error: Please provide one argument (the read_file).\n" )
+        sys.stderr.write(
+            sys.argv[0] + ": Error: Please provide one argument (the read_file).\n")
         sys.stderr.write("  Call with '-h' to get usage information.\n")
         sys.exit(1)
 
@@ -95,7 +105,6 @@ def main():
     else:
         outfilename = opts.outfile
 
-
     # **** Get read length ****
 
     if opts.readlen is not None:
@@ -113,7 +122,6 @@ def main():
     max_qual = opts.maxqual
     gamma = opts.gamma
 
-
     # **** Initialize count arrays ****
 
     base_arr_U = numpy.zeros((readlen, 5), numpy.int)
@@ -122,7 +130,6 @@ def main():
         base_arr_A = numpy.zeros((readlen, 5), numpy.int)
         qual_arr_A = numpy.zeros((readlen, max_qual+1), numpy.int)
 
-
     # **** Main counting loop ****
 
     i = 0
@@ -147,7 +154,6 @@ def main():
         raise
     print(i, "reads processed")
 
-
     # **** Normalize result ****
 
     def norm_by_pos(arr):
@@ -162,7 +168,6 @@ def main():
         arr_n[arr == 0] = 0
         return arr_n
 
-
     base_arr_U_n = norm_by_pos(base_arr_U)
     qual_arr_U_n = norm_by_start(qual_arr_U)
     nreads_U = base_arr_U[0, :].sum()
@@ -171,7 +176,6 @@ def main():
         qual_arr_A_n = norm_by_start(qual_arr_A)
         nreads_A = base_arr_A[0, :].sum()
 
-
     # **** Make plot ****
 
     def plot_bases(arr):
@@ -197,12 +201,12 @@ def main():
         pyplot.subplot(221)
         plot_bases(base_arr_U_n)
         pyplot.ylabel("proportion of base")
-        pyplot.title( "non-aligned reads\n%.0f%% (%.3f million)" %
+        pyplot.title("non-aligned reads\n%.0f%% (%.4f million)" %
                      (100. * nreads_U / (nreads_U+nreads_A), nreads_U / 1e6))
 
         pyplot.subplot(222)
         plot_bases(base_arr_A_n)
-        pyplot.title( "aligned reads\n%.0f%% (%.3f million)" %
+        pyplot.title("aligned reads\n%.0f%% (%.4f million)" %
                      (100. * nreads_A / (nreads_U+nreads_A), nreads_A / 1e6))
 
         pyplot.subplot(223)
@@ -232,8 +236,8 @@ def main():
         pyplot.xlabel("position in read")
         pyplot.ylabel("base-call quality score")
 
-
     pyplot.savefig(outfilename)
 
+
 if __name__ == "__main__":
     main()

python3/src/HTSeq/_HTSeq.pxd

@@ -20,7 +20,7 @@ cdef class Sequence( object ):
    cdef public bytes seq
    cdef public str name
    cdef public str descr
-   cpdef Sequence get_reverse_complement( self )      
+   cpdef Sequence get_reverse_complement(self, bint rename=?)
    cpdef object add_bases_to_count_array(Sequence self, numpy.ndarray count_array_)
    cpdef Sequence trim_left_end(Sequence self, Sequence pattern, float mismatch_prop=?)   
    cpdef Sequence trim_right_end(Sequence self, Sequence pattern, float mismatch_prop=?)   

python3/src/HTSeq/_HTSeq.pyx

@@ -645,10 +645,15 @@ cdef class Sequence(object):
         self.name = name
         self.descr = None
 
-    cpdef Sequence get_reverse_complement(self):
+    cpdef Sequence get_reverse_complement(self, bint rename=True):
+        if rename:
             return Sequence(
                 reverse_complement(self.seq),
                 "revcomp_of_" + self.name)
+        else:
+            return Sequence(
+                reverse_complement(self.seq),
+                self.name)
 
     def __str__(self):
         return self.seq.decode()
@@ -898,13 +903,20 @@ cdef class SequenceWithQualities(Sequence):
         self.write_to_fastq_file(sio, convert_to_phred)
         return sio.getvalue()
 
-    cpdef SequenceWithQualities get_reverse_complement(self):
+    cpdef SequenceWithQualities get_reverse_complement(self, bint rename=True):
         cdef SequenceWithQualities res
+        if rename:
             res = SequenceWithQualities(
                 reverse_complement(self.seq),
                 "revcomp_of_" + self.name,
                 self._qualstr[::-1],
                 self._qualscale)
+        else:
+            res = SequenceWithQualities(
+                reverse_complement(self.seq),
+                self.name,
+                self._qualstr[::-1],
+                self._qualscale)
         if self._qualarr is not None:
             res._qualarr = self._qualarr[::-1]
         return res