File: QCumber-2

package info (click to toggle)
qcumber 2.3.0-2
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye, sid
  • size: 2,276 kB
  • sloc: python: 3,097; sh: 153; makefile: 18
file content (721 lines) | stat: -rwxr-xr-x 30,685 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
#!/usr/bin/env python3
__author__ = 'LieuV'
__version__ = "2.1.1"

import argparse
import re
import getpass
import warnings
import os
import json
import sys
from itertools import groupby
from collections import OrderedDict
import subprocess
from pandas import read_csv
import snakemake
import datetime
import yaml
import input_utils
# Set paths

ADAPTER_PATH = ""   # Adapter path from trimmomatic.
                    # Should be set during installation

KRAKEN_DB = subprocess.check_output("echo $KRAKEN_DB_PATH",
                                    shell=True).decode("utf-8").strip()
if len(KRAKEN_DB) == 0:
    KRAKEN_DB = " "  # insert space such that snakemake can handle empty value

# Pattern for Illumina readnames
base_pattern = (
    r"(?P<setname>.*)_(?P<lane>L\d{3})_(?P<read>(R1|R2))_(?P<nfiles>\d{3}).*")

# --------------------------------------< Functions >----------------------------------------------------------


def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.RawDescriptionHelpFormatter, description="""\
    --------------------------------------------------------------------

                             < QCumber >
              < Quality control and read trimming of NGS data >
           https://gitlab.com/RKIBioinformaticsPipelines/QCumber/

    --------------------------------------------------------------------""",
        epilog=("Example usage: QCumber-2 --input fastq_folder"
                " --reference reference.fasta"))

    # ------------------------------------------------< INPUT >---------------------------------------------------------#

    group_input = parser.add_argument_group("Input")
    group_input.add_argument(
        '--input', '-i', dest='input',
        help=("input sample folder. Illumina filenames should end with"
              "_<lane>_<R1|R2>_number, e.g. Sample_12_345_R1_001.fastq,"
              " to find the right paired set."),
        required=False, nargs="+")
    group_input.add_argument(
        '--read1', '-1', dest='r1', help="Read 1 file", required=False)
    group_input.add_argument(
        '--read2', '-2', dest='r2', help="Read 2 file", required=False)
    group_input.add_argument(
        '--technology', '-T', dest='technology', choices=["Illumina",
                                                          "IonTorrent",
                                                          "PacBio"],
        required=False,
        help=("If not set, automatically determine technology and "
              "search for fastq and bam files. "
              "Set technology to IonTorrent if all files are bam-files,"
              " else set technology to Illumina."))
    group_input.add_argument(
        '--adapter', '-a', dest='adapter',
        choices=['TruSeq2-PE', 'TruSeq2-SE', 'TruSeq3-PE',
                 'TruSeq3-SE', 'TruSeq3-PE-2', 'NexteraPE-PE'],
        help="Adapter name for trimming. Default: all")

    mapping_exclusion = group_input.add_mutually_exclusive_group()
    mapping_exclusion.add_argument(
        '--reference', '-r', dest='reference', required=False,
        help=("Map reads against reference."
              + " Reference needs to be in fasta-format."))
    mapping_exclusion.add_argument(
        '--index', '-I', dest='index', required=False,
        help="Bowtie2 index if available.")

    group_input.add_argument(
        '--kraken_db', '-d', dest='kraken_db',
        help=("Custom Kraken database. Default value is taken from"
              " environment variable KRAKEN_DB_PATH. "
              "Default: %(default)s."),
        required=False, default=KRAKEN_DB)

    group_input.add_argument(
        '--kraken_classified_out', dest='kraken_classified_out',
        help=("Kraken (un)classified-out option."
              " If set, both the --classified-out"
              " and --unclassified-out option are set. "
              "Default: %(default)s."),
        required=False, default=False, action='store_true')

    group_optional = parser.add_argument_group("Optional steps")
    group_optional.add_argument(
        '--sav', '-w', dest='sav', required=False,
        help=("Illumina folder for SAV. Requires RunInfo.xml, RunParameter.xml"
              "and Interop folder."))
    group_optional.add_argument(
        '--trimBetter', choices=["assembly", "mapping", "default"],
        help=("Optimize trimming parameter using 'Per sequence base content'"
              + " from fastqc. Not recommended for amplicons."))
    group_optional.add_argument('--nokraken', '-K', action="store_true")
    group_optional.add_argument('--notrimming', '-Q', action="store_true")

    group_params = parser.add_argument_group("Parameter settings")
    group_params.add_argument(
        '--illuminaclip', '-L', dest='illuminaclip', default="2:30:10",
        help=('Illuminaclip option: '
              '<leading quality>:<trailing quality>:<sliding window>.'
              'Default: %(default)s'))
    group_params.add_argument(
        '--only_trim_adapters', '-A', action='store_true',
        help='If this option is selected, only adapters will be clipped')
    group_params.add_argument(
        '--minlen', '-m', default=50, dest='minlen',
        help=('Minlen parameter for Trimmomatic. Drops read short than minlen.'
              ' Default: %(default)s'),
        type=int)
    group_params.add_argument(
        '--trimOption', '-O', dest="trimOption",
        help=('Additional Trimmomatic input.'
              ' Default (if trimBetter is not set): SLIDINGWINDOW:4:20'),
        type=str)
    group_params.add_argument(
        '--trimBetter_threshold', '-b', dest='trimBetter_threshold',
        help=("Set -trimBetter to use this option.Default setting"
              " for Illumina: 0.15 and for IonTorrent: 0.25."),
        required=False, type=float)
    group_output = parser.add_argument_group("Output")
    group_output.add_argument('--output', '-o', dest='output', default="")
    group_output.add_argument(
        '--rename', '-R', dest="rename", required=False,
        help="TSV File with two columns: <old sample name> <new sample name>")
    group_output.add_argument(
        '--save_mapping', '-S', action="store_true", default=False)

    parser.add_argument('--threads', '-t', dest='threads', default=4, type=int,
                        help="Number of threads. Default:  %(default)s")

    parser.add_argument(
        '--config', '-c', dest='config',
        help=("Configfile to run pipeline. "
              "Additional parameters in the commandline "
              "will override arguments in configfile."
              "If not given and config/config.txt exists in"
              "the directory of the QCumber-2 executable,"
              "that file will be loaded by default."))
    parser.add_argument('--version', '-v',
                        action='version', version='%(prog)s v' + __version__)

    arguments, unknown_args = parser.parse_known_args()
    arguments = vars(arguments)
    if len(sys.argv) == 1:
        parser.print_help()
        sys.exit(1)

    configfile = arguments["config"]
    default_configfile = os.path.join(
            os.path.dirname(os.path.realpath(__file__)),
            "config",
            "config.txt")
    if not arguments["config"] and os.path.isfile(default_configfile):
        configfile = default_configfile

    if configfile:
        config_args = yaml.load(open(configfile, "r"))
        keep_args = dict()
        for arg in config_args.keys():
            print(arg)
            if (arguments[arg] is None) or arguments[arg] == " ":
                arguments[arg] = config_args[arg]

    arguments["output"] = os.path.abspath(arguments["output"])
    if arguments["only_trim_adapters"]:
        arguments["trimBetter"] = None
    if not os.path.isdir(arguments["output"]):
        os.mkdir(arguments["output"])
    if arguments["reference"]:
        arguments["reference"] = os.path.abspath(arguments["reference"])
    if arguments["sav"]:
        arguments["sav"] = os.path.abspath(arguments["sav"])
    if arguments["rename"]:
        arguments["rename"] = os.path.abspath(arguments["rename"])

    parameter = yaml.load(
        open(os.path.join(
                os.path.dirname(os.path.realpath(__file__)),
                "config",
                "parameter.txt"),
             "r"))
    check_input_validity(arguments)
    # Load adaptive filetypes
    qcumber_path = os.path.dirname(os.path.realpath(__file__))
    sample_file_name = os.path.join(arguments["output"], "samples.yaml")
    with open(os.path.join(qcumber_path,
                           'filenames.yaml'),
              'r') as filetype_h:
        filename_types = yaml.load(filetype_h)
    all_files = []
    for file_or_dir in arguments["input"]:
        if os.path.isdir(file_or_dir):
            for root, dirs, files in os.walk(file_or_dir):
                for file in files:
                    if os.path.getsize(os.path.join(root, file)) != 0:
                        all_files.append(os.path.join(root, file))
        elif os.path.isfile(file_or_dir):
            if os.path.getsize(file_or_dir):
                all_files.append(file_or_dir)
    # Get Parsed Samples fomr input utils module
    formats_found,  discarded = input_utils.parse_sample_info(
            all_files, filename_types, ['pacbio', 'illumina_fastq'])
    try:
        illumina_data = formats_found['illumina_fastq']
        # print(repr(format_known.mfrs).replace('>,', '>,\n'))
    except KeyError:
            exit('No samples found or none met criteria!!\n'
                 'These files were discarded:\n'
                 '%s' % '\n'.join(discarded))
    try:
        pacbio_data = formats_found['pacbio']
        print('looking for pacbio data...')
        pac_samples = pacbio_data.get_samples()
        with open(sample_file_name.replace('.yaml',
                                           '_pacbio.yaml'),
                  'w') as sample_file:
            yaml.dump(pac_samples, sample_file, default_flow_style=False)
        print('looking for illumina data...')
    except KeyError:
        pass
    sample_dict = illumina_data.flatten_naive()
    # flatten naive just drops read info from sampel name
    # if it is paired end data.
    len_known = len(sample_dict)
    if False:
        try:
            salvaged_dict = illumina_data.leftovers.process_leftovers(
                rename=True,
                rename_start_index=len_known+1)
            sample_dict.update(salvaged_dict)
        except input_utils.AmbigiousPairedReadsError as err:
            eprint('Failed parsing files with unrecognized'
                   ' naming convention\n',
                   'Reason:\n', err)
    # Write samples to working directory
    with open(sample_file_name, 'w') as sample_file:
        yaml.dump(sample_dict, sample_file, default_flow_style=False)

    type, samples, joined_samples, name_dict, join_reads = (
        get_input(arguments, parameter))
    get_defaults(arguments, parameter)

    force_run_list = []
    os.makedirs(arguments["output"], exist_ok=True)
    config_file_path = os.path.join(arguments["output"], "config.yaml")
    #if os.path.isfile(config_file_path):
    #    pass
    #else:
    with open(config_file_path, 'w') as config_fh:
        yaml.dump(arguments, config_fh,
                  default_flow_style=False)

    # additional infos
    general_information = OrderedDict()
    general_information["User"] = getpass.getuser()
    general_information["QCumber"] = __version__
    general_information["QCumber_path"] = os.path.dirname(
                                            os.path.realpath(__file__))
    general_information["Execution time"] = datetime.datetime.now().ctime()

    system_info = os.uname()
    general_information["Operating system"] = OrderedDict()
    general_information["Operating system"]["System"] = system_info.sysname
    general_information["Operating system"]["Server"] = system_info.nodename
    general_information["Operating system"]["Operating version"] = (
        system_info.version)
    general_information["Operating system"]["Release"] = system_info.release
    general_information["Operating system"]["Machine"] = system_info.machine
    general_information["Tool versions"] = OrderedDict()
    general_information["Tool versions"]["Python"] = re.sub("\n",
                                                            "", sys.version)
    general_information["Tool versions"]["Snakemake"] = snakemake.__version__
    general_information["Tool versions"]["FastQC"] = (
        get_version("fastqc --version"))

    if not arguments["notrimming"]:
        general_information["Tool versions"]["Trimmomatic"] = (
            get_version("trimmomatic -version", "trimmomatic"))
        if arguments["technology"] == "Illumina" and not arguments["adapter"]:
            general_information["adapter"] = (
                os.path.join(os.path.dirname(os.path.realpath(__file__)),
                             "config", "adapters.fa"))
        elif arguments["technology"] == "Illumina" and arguments["adapter"]:
            general_information["adapter"] = os.path.join(ADAPTER_PATH,
                                                          (arguments["adapter"]
                                                           + ".fa"))
    if arguments["reference"] or arguments["index"]:
        general_information["Tool versions"]["Bowtie2"] = (
            get_version("bowtie2 --version"))
    if not arguments["nokraken"]:
        general_information["Tool versions"]["Kraken"] = (
            get_version("kraken --version"))
    general_information["Sample information"] = OrderedDict()
    general_information["Sample information"]["type"] = type
    general_information["Sample information"]["samples"] = samples
    general_information["Sample information"]["join_reads"] = join_reads
    general_information["Sample information"]["join_lanes"] = joined_samples

    general_information["Sample information"]["rename"] = name_dict
    os.makedirs(os.path.join(arguments["output"],
                             "QCResults", "_data"), exist_ok=True)

    general_information_file = os.path.join(arguments["output"],
                                            "QCResults", "_data",
                                            "general_information.json")
    json.dump(general_information, open(general_information_file, "w"))

    # Fixed:
    # if QCumber is run repeatedly, the rule bowtie_mapping
    # will not be executed.
    # hence it is necessary to force to run the rule everytime
    #  if (arguments["save_mapping"]):
    #      force_run = "--forcerun bowtie_mapping"
    #  else:
    force_run = "--forcerun"
    cmd_string = (
        "snakemake "
        "--configfile {workdir}/config.yaml "
        "--snakefile {snakefile} {additional_commands} "
        "--directory {workdir} "
        "--cores {cores} {targets} {force_run} "
        ).format(
            additional_commands=" ".join(unknown_args),
            snakefile=os.path.join(os.path.dirname(os.path.realpath(__file__)),
                                   "Snakefile"),
            workdir=arguments["output"],
            configfile=general_information_file,
            cores=arguments["threads"],
            targets='',  # "QCResults/batch_report.html",
            force_run=force_run)
    print(cmd_string)
    process = subprocess.Popen(
        ("snakemake "
         "--configfile {workdir}/config.yaml "
         "--snakefile {snakefile} {additional_commands} "
         "--directory {workdir} "
         "--cores {cores} {targets} {force_run} "
         ' -R $(snakemake --list-params-changes '
         #  '--list-input-changes --list-code-changes '
            '--configfile {workdir}/config.yaml '
            '--snakefile {snakefile} {additional_commands} '
            '--directory {workdir} '
            '--cores {cores} {targets} {force_run})'
         ).format(
            additional_commands=" ".join(unknown_args),
            snakefile=os.path.join(os.path.dirname(os.path.realpath(__file__)),
                                   "Snakefile"),
            workdir=arguments["output"],
            configfile=general_information_file,
            cores=arguments["threads"],
            targets='',  # "QCResults/batch_report.html",
            force_run=force_run),
        shell=True)
    process.wait()
    exit(process.returncode)


def get_basename(abs_name):
    return os.path.basename(os.path.splitext(
        os.path.splitext(os.path.basename(abs_name))[0])[0])


def getFilenameWithoutExtension(string, getBase=False):
    if getBase:
        string = os.path.basename(string)
    string = os.path.splitext(string)[0]
    i = 0
    while os.path.splitext(string)[-1] in [
            ".gz", ".gzip", ".zip", ".bz", ".fasta", ".fastq", ".bam"]:
        string = os.path.splitext(string)[0]
    return string


def get_setname(filename, base=True, grouping=True):
    """ Get Setname

    Args:
        filename (obj::`str`): filename;

    Kwargs:
        base (bool): transform filename to basename (default = True)
        grouping (bool): if not grouping, only return basename of file
            (default = True)
    Returns:
    """
    if not grouping:
        return get_basename(filename)
    try:
        if base:
            filename = get_basename(filename)
        sep = iter([";", "\t"])
        if arguments["rename"]:
            rename_dict = read_csv(arguments["rename"],
                                   index_col=0, header=None)

            while (rename_dict.columns.__len__() == 0
                   or sep.__length_hint__() != 0):
                rename_dict = read_csv(arguments["rename"], index_col=0,
                                       header=None, sep=next(sep))
            if rename_dict.columns.__len__() == 0:
                warnings.warn(
                    ("Problems reading rename-file %s. "
                     "Valid delimiters are"
                     " ';', ',' or '\\t'.") % arguments["rename"],
                    UserWarning, stacklevel=2)

            new_name = [(x, rename_dict.ix[x][1]) for x
                        in rename_dict.index
                        if filename.startswith(x)]
            if len(new_name) != 1:
                warnings.warn(
                    ("Could not find unique renames."
                     " Found %s for %s") % (new_name, filename),
                    UserWarning, stacklevel=2)
                filename = getFilenameWithoutExtension(filename, True)
            else:
                filename = filename.replace(new_name[0][0], new_name[0][1])
    except:
        # print("Couldnt rename sample files.")
        pass
    try:
        paired_reads_pattern = base_pattern
        setname_pattern = re.search(paired_reads_pattern,
                                    os.path.basename(filename))
        if setname_pattern:
            return setname_pattern.group("setname")
        else:
            return filename
    except:
        print("Problems getting samplenames: %s" % filename)
        return filename


def get_defaults(arguments, parameter):
    if arguments["only_trim_adapters"]:
        return
    if arguments["trimBetter"] == "assembly":
        # if arguments["forAssembly"]:
        if not arguments["trimBetter_threshold"]:
            arguments["trimBetter_threshold"] = (
                parameter["forAssembly." + arguments['technology']]
                         ['trimBetter_threshold'])
        if not arguments["trimOption"]:
            arguments["trimOption"] = (
                    parameter["forAssembly." + arguments['technology']]
                             ["trimOption"])

    elif arguments["trimBetter"] == "mapping":
        # elif arguments["forMapping"]:
        if not arguments["trimBetter_threshold"]:
            arguments["trimBetter_threshold"] = (
                parameter["forMapping." + arguments['technology']]
                         ["trimBetter_threshold"])
        if not arguments["trimOption"]:
            arguments["trimOption"] = (
                parameter["forMapping." + arguments['technology']]
                         ["trimOption"])
    elif arguments["trimBetter"] == "default":
        arguments["trimBetter_threshold"] = (parameter["Trimmomatic"]
                                                      ["trimBetter_threshold"])

    if not arguments["trimOption"]:
        arguments["trimOption"] = parameter["Trimmomatic"]["trimOption"]

    if arguments["trimBetter_threshold"]:
        arguments["trimBetter_threshold"] = (parameter["Trimmomatic"]
                                                      ["trimBetter_threshold"])


def get_version(cmd, jar=None):
    try:
        return re.match(r"(?P<version>.*)\n",
                        subprocess.check_output(
                            cmd, shell=True, stderr=subprocess.PIPE
                        ).decode("utf-8")).group("version")
    except:
        try:
            try:
                return subprocess.check_output(
                        cmd, shell=True,
                        stderr=subprocess.PIPE
                    ).decode("utf-8")
            except:
                from debpackageinfo import get_upstream_version
                return get_upstream_version(jar)
        except:
            return "NaN"


def get_input(arguments, parameter):
    """
    Get Read Input

    Checks wether input reads are from Ion Torrent or Illumina, by checking
    file extensions of bam and/or fastq. Detects presence of read pair in input
    and returns type of reads used (single end / paired end reads)

    Args:
        None

    Returns:
        (obj::`str`): type - PE or SE  (Paired Ends / Single Ends)
        (obj::`collections.OrderedDict`): sample_dict
        (obj::`collections.OrderedDict`): join_lanes
        (obj::`dict`): name_dict
        (obj::`dict`): join_reads
    """
    bam_ext = [x.strip(" ") for x in parameter["Fileextension"]["bam"]]
    fastq_ext = [x.strip(" ") for x in parameter["Fileextension"]["fastq"]]

    sample_dict = OrderedDict()
    all_files = []
    name_dict = {}
    join_reads = {}
    type = "PE"
    join_lanes = OrderedDict()

    if arguments["r1"]:
        assert os.path.getsize(arguments["r1"]) != 0, (
               "File %s is empty." % arguments["r1"])

        if any([arguments["r1"].endswith(ext) for ext in bam_ext]):
            arguments["technology"] = "IonTorrent"
        else:
            arguments["technology"] = "Illumina"
        if arguments["r2"]:
            assert os.path.getsize(arguments["r2"]) != 0, (
                   "File %s is empty." % arguments["r2"])

            sample_dict[get_setname(arguments["r1"])] = (
                [os.path.abspath(arguments["r1"]),
                 os.path.abspath(arguments["r2"])])
            name_dict[get_basename(arguments["r1"])] = (
                get_setname(arguments["r1"]) + "_R1")
            name_dict[get_basename(arguments["r2"])] = (
                get_setname(arguments["r2"]) + "_R2")
        else:
            type = "SE"
            sample_dict[get_setname(arguments["r1"])] = (
                [os.path.abspath(arguments["r1"])])
            name_dict[get_basename(arguments["r1"])] = (
                get_setname(arguments["r1"]))
    else:
        if os.path.isdir(arguments["input"][0]):
            for root, dirs, files in os.walk(arguments["input"][0]):
                for file in files:
                    if any([file.endswith(ext)
                            for ext in fastq_ext + bam_ext]):
                        if os.path.getsize(os.path.join(root, file)) != 0:
                            all_files.append(os.path.join(root, file))
                        else:
                            warnings.warn("Skip empty file %s" % file,
                                          stacklevel=2)
        else:
            all_files = arguments["input"]
            assert all_files, (
                   ("Check input again. "
                    "No files found for pattern %s ") % arguments["input"])

        if len([x for x
                in all_files
                if any([ext in x for ext in bam_ext])
                ]
               ) == len(all_files):
            arguments["technology"] = "IonTorrent"
        else:
            arguments["technology"] = "Illumina"

        if (len(all_files) == 0):
            sys.exit(str(arguments["input"])
                     + " does not contain fastq or bam files.")

        # find read pairs
        all_files = sorted(list(all_files))

        if all([re.search(base_pattern, x) for x in all_files]):
            for setname, files in groupby(all_files,
                                          key=lambda x: re.search(
                                              base_pattern,
                                              x
                                          ).group("setname")):
                read_pairs = dict()
                setname = get_setname(setname)
                for lane, lane_file in groupby(list(files),
                                               key=lambda x: re.search(
                                                                 base_pattern,
                                                                 x
                                                             ).group("lane")):
                    read_pairs[lane] = []
                    for readgroup, readfiles in groupby(
                            list(lane_file),
                            key=lambda x: re.search(base_pattern, x
                                                    ).group("read")):
                        readfiles = list(readfiles)
                        if len(readfiles) != 0:
                            if len(readfiles) > 1:
                                concat_reads = (
                                        "QCResults/tmp/join_reads/"
                                        + "_".join(
                                            re.search(base_pattern,
                                                      os.path.basename(
                                                          readfiles[0])
                                                      ).groups()[:-2])
                                        + "_000.fastq.gz")
                                join_reads[concat_reads] = [os.path.abspath(x)
                                                            for x in readfiles]
                                readfiles = concat_reads

                            else:
                                readfiles = os.path.abspath(readfiles[0])
                            read_pairs[lane].append(readfiles)
                # Multiple lanes
                if len(read_pairs) > 1:
                    join_lanes[setname] = []
                for key in sorted(read_pairs.keys()):
                    samplename = setname + "_" + key
                    sample_dict[samplename] = read_pairs[key]
                    if len(read_pairs[key]) == 2:  # type == "PE":
                        name_dict[get_basename(read_pairs[key][0])] = (
                            get_setname(samplename) + "_R1")
                        name_dict[get_basename(read_pairs[key][1])] = (
                            get_setname(samplename) + "_R2")
                    else:
                        type = "SE"
                        name_dict[get_basename(read_pairs[key][0])] = (
                            get_setname(samplename, grouping=False))
                    if len(read_pairs) > 1:
                        join_lanes[setname].append(samplename)
        else:  # treat each file as sample
            print("Treat files as single end")
            sample_dict = OrderedDict(
                    [[get_setname(x, grouping=False), [os.path.abspath(x)]]
                     for x in all_files])
            name_dict = dict(
                    [get_basename(x), get_setname(x, grouping=False)]
                    for x in all_files)
            type = "SE"

    return type, sample_dict, join_lanes, name_dict, join_reads


def check_input_validity(arguments):

    if arguments["reference"]:
        ref_file = arguments["reference"]
        seq_record = ""
        if not os.path.exists(arguments["reference"]):
            sys.exit("Reference does not exist.")
        try:
            if ref_file[-2:] == "gz":
                with subprocess.Popen(["gzip", "-cd", ref_file],
                                      stdout=subprocess.PIPE) as gz_proc:
                    seq_record = gz_proc.stdout.readline().decode()
                    gz_proc.terminate()
            else:
                with open(arguments["reference"], "r") as ref_fh:
                    seq_record = ref_fh.readline()
            assert seq_record.startswith(">"), ("Error: Reference"
                                                "file is not valid.")
        except AssertionError as e:
            sys.exit(e)
        except FileNotFoundError:
            sys.exit("Error: Reference file not found")

    #
    # Check validity of Kraken DB
    if not arguments["nokraken"]:
        if not os.path.exists(arguments["kraken_db"]):
            sys.exit("ERROR: %s does not exist.i"
                     " Enter a valid database"
                     " for kraken" % arguments["kraken_db"])
        else:
            if "database.kdb" not in os.listdir(arguments["kraken_db"]):
                sys.exit("ERROR: database "
                         + arguments["kraken_db"]
                         + " does not contain necessary file database.kdb")
    #
    # Check input
    if arguments["input"]:
        if not all([os.path.exists(x[0]) for x in arguments["input"]]):
            sys.exit(str(arguments["input"]) + " does not exist.")
    else:
        if not arguments["r1"]:
            sys.exit("Pleaser enter an input file (--input or -1/-2)")
        if not os.path.isfile(arguments["r1"]):
            sys.exit(arguments["r1"]
                     + " does not exist. Input file required."
                     + " Use option -input or -1 / -2.")

        if arguments["r2"]:
            if not os.path.isfile(arguments["r2"]):
                sys.exit(arguments["r2"] + " does not exist.")

    if arguments["trimBetter_threshold"] and not arguments["trimBetter"]:
        sys.exit("--trimBetter must be set to use --trimbetter_threshold."
                 " Add --trimBetter to your command "
                 "or remove --trimbetter_threshold.")

# --------------------------------------< main >-------------------------------


if __name__ == "__main__":
    main()