예제 #1
0
def convert_Ti_to_FLX(sff_fp, output_fp, use_sfftools=False):
    """Converts Titanium SFF to FLX length reads."""
    if use_sfftools:
        check_sfffile()
        _check_call(['sfffile', '-flx', '-o', output_fp, sff_fp],
                    stdout=open(os.devnull, 'w'))
    else:
        header, reads = adjust_sff_cycles(parse_binary_sff(open(sff_fp), True),
                                          100)
        write_binary_sff(open(output_fp, 'w'), header, reads)
예제 #2
0
def convert_Ti_to_FLX(sff_fp, output_fp, use_sfftools=False):
    """Converts Titanium SFF to FLX length reads."""
    if use_sfftools:
        check_sfffile()
        _check_call(
            ['sfffile', '-flx', '-o', output_fp, sff_fp],
            stdout=open(os.devnull, 'w'))
    else:
        header, reads = adjust_sff_cycles(parse_binary_sff(open(sff_fp), True), 100)
        write_binary_sff(open(output_fp, 'w'), header, reads)
예제 #3
0
def make_per_library_sff(sff_fps, id_list_fp, debug=False):
    id_list_basepath, _ = os.path.splitext(id_list_fp)
    output_fp = id_list_basepath + '.sff'

    sff_datasets = [parse_binary_sff(open(fp), True) for fp in sff_fps]
    sff_data = combine_sff_data(*sff_datasets)
    ids = parse_id_list(open(id_list_fp))

    filtered_sff_data = filter_sff_reads(sff_data, ids_to_keep=ids)
    if debug:
        print 'Creating SFF file for %s' % id_list_fp
    write_binary_sff(open(output_fp, 'w'), *filtered_sff_data)
예제 #4
0
def make_per_library_sff(sff_fps, id_list_fp, debug=False):
    id_list_basepath, _ = os.path.splitext(id_list_fp)
    output_fp = id_list_basepath + '.sff'

    sff_datasets = [parse_binary_sff(open(fp), True) for fp in sff_fps]
    sff_data = combine_sff_data(*sff_datasets)
    ids = parse_id_list(open(id_list_fp))

    filtered_sff_data = filter_sff_reads(sff_data, ids_to_keep=ids)
    if debug:
        print 'Creating SFF file for %s' % id_list_fp
    write_binary_sff(open(output_fp, 'w'), *filtered_sff_data)
예제 #5
0
def set_sff_trimpoints(sff_dir, technical_lengths):
    """Set trimpoints to end of technical read for all SFF files in directory.
    """
    for lib_id, sff_fp in get_per_lib_sff_fps(sff_dir):
        try:
            readlength = technical_lengths[lib_id]
        except KeyError:
            continue
        sff_data = parse_binary_sff(open(sff_fp), True)
        clipped_header, clipped_reads = set_clip_qual_left(sff_data, readlength)

        _, temp_fp = tempfile.mkstemp(dir=sff_dir)
        with open(temp_fp, "w") as f:
            write_binary_sff(f, clipped_header, clipped_reads)

        shutil.move(temp_fp, sff_fp)
예제 #6
0
def set_sff_trimpoints(sff_dir, technical_lengths):
    """Set trimpoints to end of technical read for all SFF files in directory.
    """
    for lib_id, sff_fp in get_per_lib_sff_fps(sff_dir):
        try:
            readlength = technical_lengths[lib_id]
        except KeyError:
            continue
        sff_data = parse_binary_sff(open(sff_fp), True)
        clipped_header, clipped_reads = set_clip_qual_left(sff_data, readlength)
        
        _, temp_fp = tempfile.mkstemp(dir=sff_dir)
        with open(temp_fp, 'w') as f:
            write_binary_sff(f, clipped_header, clipped_reads)

        shutil.move(temp_fp, sff_fp)
예제 #7
0
    def test_write_binary_sff(self):
        read = READ_HEADER.copy()
        read.update(READ_DATA)

        header = COMMON_HEADER.copy()
        header['number_of_reads'] = 1

        write_binary_sff(self.output_file, header, [read])

        file_pos = self.output_file.tell()
        self.assertTrue(file_pos % 8 == 0)

        self.output_file.seek(0)
        observed_header, observed_reads = parse_binary_sff(
            self.output_file, native_flowgram_values=True)
        observed_reads = list(observed_reads)
        self.assertEqual(observed_header, header)
        self.assertEqual(observed_reads[0], read)
        self.assertEqual(len(observed_reads), 1)

        file_pos = self.output_file.tell()
        self.assertTrue(file_pos % 8 == 0)
예제 #8
0
    def test_write_binary_sff(self):
        read = READ_HEADER.copy()
        read.update(READ_DATA)

        header = COMMON_HEADER.copy()
        header['number_of_reads'] = 1

        write_binary_sff(self.output_file, header, [read])

        file_pos = self.output_file.tell()
        self.assertTrue(file_pos % 8 == 0)

        self.output_file.seek(0)
        observed_header, observed_reads = parse_binary_sff(
            self.output_file, native_flowgram_values=True)
        observed_reads = list(observed_reads)
        self.assertEqual(observed_header, header)
        self.assertEqual(observed_reads[0], read)
        self.assertEqual(len(observed_reads), 1)

        file_pos = self.output_file.tell()
        self.assertTrue(file_pos % 8 == 0)