def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = "test_data"
infile1 = "%s/INPUT_fasta_for_aln.fa" % test_folder
# tests in (testname, [test_description,] arg_and_infile_string) format
test_runs = [
('aln__basic-1-error',
'-e 1 -m 3 -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q -W' %
infile1),
('aln__collapsed-input',
'-e 1 -m 3 -c -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q -W' %
infile1),
('aln__show-multiple-0-fasta',
'-e 1 -m 0 -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q -W' %
infile1),
('aln__dont-split',
'-e 1 -m 3 -s -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q -W' %
infile1),
('aln__no-split_multiple-0',
'-e 1 -m 0 -s -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q -W' %
infile1),
]
# MAYBE-TODO add run-tests for more options/combinations?
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser, options, args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs,
define_option_parser(),
main,
test_folder,
argument_converter=argument_converter,
outfile_option='-o')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = 'test_data'
infile1 = test_folder + '/INPUT_raw-fastq_complex-5prime.fq'
infile2 = test_folder + '/INPUT_raw-fastq_simple-both-ends.fq'
# tests in (testname, test_description, arg_string, infiles) format
test_runs = [
('full-not-unique', "testing all 'bad' cases, 5' end only, without collapsing to unique", '-3 ""', [infile1]),
('full-unique', "testing all 'bad' cases, 5' end only, WITH collapsing to unique for all outfiles", '-3 "" -C', [infile1]),
('end-5prime', "simpler test, 5' end only (collapsing to unique)", '-3 "" -C', [infile2]),
('end-3prime', "simpler test, 3' end only (collapsing to unique)", '-5 "" -C', [infile2]),
('ends-both', "simpler test, 5' and 3' ends (collapsing to unique)", '-C', [infile2]),
# this test uses the standard 5' and 3' cassette seqs as two alternative 5' ones, so the 5' output is like ends-both 5'+3'
('ends-two-5prime', "simpler test, two 5' adapters (collapsing to unique)", '-5 %s,%s -3 "" -C'%(
CASSETTE_DEFAULT_5prime,CASSETTE_DEFAULT_3prime), [infile2]),
]
# MAYBE-TODO currently some of the tests are weird because fastx_collapser changes the order of the sequences for no good reason (see <IGNORE> lines in some of the files)
# convert tests into (testname, arg_and_infile_string) format, adding the options that are always used
test_runs = [('pre__'+testname, descr, test_args+' -Q '+' '.join(infiles))
for testname,descr,test_args,infiles in test_runs]
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser,options,args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs, define_option_parser(), main, test_folder,
argument_converter=argument_converter, outfile_option='-o',
append_to_outfilenames='')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
test_folder = "test_data"
infile = "test_data/INPUT_gene-data-1_all-cases.gff3"
tests = [("gff-ex__gene-data-analysis", "-E -n -1 %s"%infile)]
parser = define_option_parser()
argument_converter = lambda parser,options,args: (args[0], options, args[1])
return run_functional_tests(tests, parser, main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='.txt')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = "test_data"
sys.exit("NO TESTS DEFINED!")
# tests in (testname, [test_description,] arg_and_infile_string) format
test_runs = [ ]
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser,options,args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs, define_option_parser(), main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='.txt')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
test_folder = "test_data_v0"
aln_infile0 = "%s/INPUT_alignment0_old-format.sam"%test_folder
aln_infile1 = "%s/INPUT_alignment1_genomic-unique.sam"%test_folder
aln_infile2 = "%s/INPUT_alignment2_for-genes.sam"%test_folder
aln_infile3 = "%s/INPUT_alignment3_for-merging.sam"%test_folder
gff_genefile = "%s/INPUT_gene-data-1_all-cases.gff3"%test_folder
dataset_to_remove = "%s/INPUT_mutants_to_remove.txt"%test_folder
test_runs = [
('cassette-end-5prime', "-e 5prime -r forward -n3 -L", [aln_infile1]),
('cassette-end-3prime', "-e 3prime -r forward -n3 -L", [aln_infile1]),
('read-direction-reverse', "-r reverse -e 5prime -n3 -L", [aln_infile1]),
('unknown-as-match', "--treat_unknown_as_match -e 5prime -r forward -n3 -L", [aln_infile1]),
('dont-count-cassette', "-l -e 5prime -r forward -n3 -L", [aln_infile1]),
('ignore-cassette', "-c -e 5prime -r forward -n3 -L", [aln_infile1]),
('separate-cassette', "-C -e 5prime -r forward -n3 -L", [aln_infile1]),
('sorted-by-count', "-o read_count -e 5prime -r forward -n3 -L", [aln_infile1]),
('with-gene-info_merged', "-e 5prime -r forward -g %s -n0"%gff_genefile, [aln_infile2]),
('with-gene-info_unmerged', "-B -e 5prime -r forward -g %s -n0"%gff_genefile, [aln_infile2]),
('multiple-infiles', "-e 5prime -r forward -n0 -L", [aln_infile1,aln_infile2]),
('dont-merge-tandems', "-n0", [aln_infile3]),
('merge-adjacent-none', "-n0 -Q -Y0", [aln_infile3]),
('merge-adjacent1-r3', "-MQ -D1 -w3 -Y0 -n0", [aln_infile3]),
('merge-adjacent1-r1', "-MQ -D1 -w1 -Y0 -n0", [aln_infile3]),
('merge-adjacent2-r3', "-MQ -D2 -w3 -Y0 -n0", [aln_infile3]),
('remove-from-other-all', "-x %s -n0"%dataset_to_remove, [aln_infile2]),
('remove-from-other-min4', "-x %s -z4 -n0"%dataset_to_remove, [aln_infile2]),
('remove-from-other-perfect', "-x %s -p -z4 -n0"%dataset_to_remove, [aln_infile2]),
('remove-not-other-all', "-X %s -n0"%dataset_to_remove, [aln_infile2]),
('remove-not-other-min4', "-X %s -Z4 -n0"%dataset_to_remove, [aln_infile2]),
('remove-not-other-perfect', "-X %s -P -Z4 -n0"%dataset_to_remove, [aln_infile2]),
('old-infile-format', "-e 5prime -r forward -n3 -L", [aln_infile0]),
]
# TODO add run-test for removing data from multiple files?
# MAYBE-TODO add run-test for a metadata file with 5' and 3' read counts?
# MAYBE-TODO add run-tests for other mutant-merging options? But they all have pretty good unit-tests.
# MAYBE-TODO add run-test for --gene_annotation_file?
# MAYBE-TODO add run-test for --input_collapsed_to_unique? Or is that unit-tested already?
# convert tests into (testname, arg_and_infile_string) format, adding the options that are always used
test_names_and_args = [('count-aln__'+testname, test_args+' -q '+' '.join(infiles))
for testname,test_args,infiles in test_runs]
parser = define_option_parser()
argument_converter = lambda parser,options,args: (args[:-1], args[-1], options)
return run_functional_tests(test_names_and_args, parser, main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='.txt')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = "_test_inputs"
# tests in (testname, [test_description,] arg_and_infile_string) format
test_runs = [
("split-index", "-i CAGATC,ACCCGG -q %s/%s"%(test_folder, 'with_indexes.fq')),
("split-index", "-s -i CAGATC,ACCCGG -q %s/%s"%(test_folder, 'with_indexes_inseq.fq')),
# same test name because same reference outfiles
]
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser,options,args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs, define_option_parser(), main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
# tests in (testname, [test_description,] arg_and_infile_string) format
# running the last test without -q to see the command-line output formatting
test_runs = [
('strip__basic', 'basic cassette-stripping', '-C expected-cassette-end_CIB1-3p -b "-f" -q %s'%Testing.infile1),
('strip__mism', 'cassette-stripping +mism', '-C expected-cassette-end_CIB1-3p -b "-f" -q %s'%Testing.infile2),
('strip__indel', 'cassette-stripping +indel', '-C expected-cassette-end_CIB1-3p -b "-f" -e 100 %s'%Testing.infile3),
]
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser,options,args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs, define_option_parser(), main, Testing.test_folder,
argument_converter=argument_converter)
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
test_folder = "test_data"
# TODO replace those with pickled infiles? Since doing it this way uses the deprecated read_data_from_file method! Although that'll be harder to maintain... Hmmm.
dataset1 = "test_data/INPUT_mutants1_no-genes.txt"
dataset2 = "test_data/INPUT_mutants2_with-genes.txt"
tests = [("join-datasets__basic", "-o position %s %s -q"%(dataset1, dataset2)),
("join-datasets__with-names", "-D dataset1,dataset2 -o position %s %s -q"%(dataset1, dataset2)),
("join-datasets__other-order", "-D dataset2,dataset1 -o position %s %s -q"%(dataset2, dataset1)),
]
# MAYBE-TODO add run test for -A/-a option?
# MAYBE-TODO add run-tests for -X, -z, -Z?
parser = define_option_parser()
argument_converter = lambda parser,options,args: (args[:-1], args[-1], options)
return run_functional_tests(tests, parser, main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='.txt')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = "test_data"
infile1 = "%s/INPUT_fasta_for_aln.fa"%test_folder
# tests in (testname, [test_description,] arg_and_infile_string) format
test_runs = [
('aln__basic-1-error', '-e 1 -m 3 -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q'%infile1),
('aln__collapsed-input', '-e 1 -m 3 -c -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q'%infile1),
('aln__show-multiple-0-fasta', '-e 1 -m 0 -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q'%infile1),
('aln__dont-split', '-e 1 -m 3 -s -G Chlre4nm_chl-mit -C cassette-pMJ013b %s -q'%infile1),
]
# MAYBE-TODO add run-tests for more options/combinations?
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser,options,args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs, define_option_parser(), main, test_folder,
argument_converter=argument_converter, outfile_option='-o')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
test_folder = "test_data"
RISCC_infiles_1 = ('test_data/INPUT_RISCC1-alignment-cassette-side.sam', 'test_data/INPUT_RISCC1-alignment-genome-side.sam',
'test_data/INPUT_RISCC1-IBs.fq', 'test_data/INPUT_RISCC1-IB-clusters.py')
#aln_infile0 = "test_data/INPUT_alignment0_old-format.sam"
#aln_infile1 = "test_data/INPUT_alignment1_genomic-unique.sam"
#aln_infile2 = "test_data/INPUT_alignment2_for-genes.sam"
#gff_genefile = "test_data/INPUT_gene-data-1_all-cases.gff3"
#dataset_to_remove = "test_data/INPUT_mutants_to_remove.txt"
test_runs = [
('basic-3prime-outward_clust', "-e 3prime -d outward -c %s -g %s -b %s -B %s"%RISCC_infiles_1, []),
('basic-3prime-outward_no-clust', "-e 3prime -d outward -c %s -g %s -b %s"%RISCC_infiles_1[:-1], []),
#('cassette-end-5prime', "-e 5prime -r forward -n3 -L", [aln_infile1]),
#('cassette-end-3prime', "-e 3prime -r forward -n3 -L", [aln_infile1]),
#('read-direction-reverse', "-r reverse -e 5prime -n3 -L", [aln_infile1]),
#('sorted-by-count', "-o read_count -e 5prime -r forward -n3 -L", [aln_infile1]),
#('with-gene-info_merged', "-e 5prime -r forward -g %s -n0"%gff_genefile, [aln_infile2]),
#('remove-from-other-all', "-x %s -n0"%dataset_to_remove, [aln_infile2]),
#('remove-from-other-min4', "-x %s -z4 -n0"%dataset_to_remove, [aln_infile2]),
#('remove-from-other-perfect', "-x %s -p -z4 -n0"%dataset_to_remove, [aln_infile2]),
#('remove-not-other-all', "-X %s -n0"%dataset_to_remove, [aln_infile2]),
#('remove-not-other-min4', "-X %s -Z4 -n0"%dataset_to_remove, [aln_infile2]),
#('remove-not-other-perfect', "-X %s -P -Z4 -n0"%dataset_to_remove, [aln_infile2]),
]
# TODO remove the mutation-detection lines from aln_infile1 and from all the outfiles, since that's been simplified?
# TODO add run-test for removing data from multiple files?
# MAYBE-TODO add run-test for a metadata file with 5' and 3' read counts?
# MAYBE-TODO add run-tests for other mutant-merging options? But they all have pretty good unit-tests.
# MAYBE-TODO add run-test for --gene_annotation_file?
# MAYBE-TODO add run-test for --input_collapsed_to_unique? Or is that unit-tested already?
# convert tests into (testname, arg_and_infile_string) format, adding the options that are always used
test_names_and_args = [('count-aln__'+testname, test_args+' -q '+' '.join(infiles))
for testname,test_args,infiles in test_runs]
parser = define_option_parser()
argument_converter = lambda parser,options,args: (args[0], options)
return run_functional_tests(test_names_and_args, parser, main, test_folder,
argument_converter=argument_converter, append_to_outfilenames='.txt')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
from testing_utilities import run_functional_tests
test_folder = 'test_data'
infile1 = test_folder + '/INPUT_raw-fastq_complex-5prime.fq'
infile2 = test_folder + '/INPUT_raw-fastq_simple-both-ends.fq'
# tests in (testname, test_description, arg_string, infiles) format
test_runs = [
('full-not-unique',
"testing all 'bad' cases, 5' end only, without collapsing to unique",
'-3 ""', [infile1]),
('full-unique',
"testing all 'bad' cases, 5' end only, WITH collapsing to unique for all outfiles",
'-3 "" -C', [infile1]),
('end-5prime', "simpler test, 5' end only (collapsing to unique)",
'-3 "" -C', [infile2]),
('end-3prime', "simpler test, 3' end only (collapsing to unique)",
'-5 "" -C', [infile2]),
('ends-both', "simpler test, 5' and 3' ends (collapsing to unique)",
'-C', [infile2]),
# this test uses the standard 5' and 3' cassette seqs as two alternative 5' ones, so the 5' output is like ends-both 5'+3'
('ends-two-5prime',
"simpler test, two 5' adapters (collapsing to unique)",
'-5 %s,%s -3 "" -C' %
(CASSETTE_DEFAULT_5prime, CASSETTE_DEFAULT_3prime), [infile2]),
]
# MAYBE-TODO currently some of the tests are weird because fastx_collapser changes the order of the sequences for no good reason (see <IGNORE> lines in some of the files)
# convert tests into (testname, arg_and_infile_string) format, adding the options that are always used
test_runs = [('pre__' + testname, descr,
test_args + ' -Q ' + ' '.join(infiles))
for testname, descr, test_args, infiles in test_runs]
# argument_converter converts (parser,options,args) to the correct argument order for main
argument_converter = lambda parser, options, args: (args, options)
# use my custom function to run all the tests, auto-detect reference files, compare to output.
return run_functional_tests(test_runs,
define_option_parser(),
main,
test_folder,
argument_converter=argument_converter,
outfile_option='-o',
append_to_outfilenames='')
def do_test_run():
""" Test run: run script on test infile, compare output to reference file."""
test_folder = "test_data_v0"
aln_infile0 = "%s/INPUT_alignment0_old-format.sam" % test_folder
aln_infile1 = "%s/INPUT_alignment1_genomic-unique.sam" % test_folder
aln_infile2 = "%s/INPUT_alignment2_for-genes.sam" % test_folder
aln_infile3 = "%s/INPUT_alignment3_for-merging.sam" % test_folder
gff_genefile = "%s/INPUT_gene-data-1_all-cases.gff3" % test_folder
dataset_to_remove = "%s/INPUT_mutants_to_remove.txt" % test_folder
test_runs = [
('cassette-end-5prime', "-e 5prime -r forward -n3 -L", [aln_infile1]),
('cassette-end-3prime', "-e 3prime -r forward -n3 -L", [aln_infile1]),
('read-direction-reverse', "-r reverse -e 5prime -n3 -L",
[aln_infile1]),
('unknown-as-match',
"--treat_unknown_as_match -e 5prime -r forward -n3 -L", [aln_infile1
]),
('dont-count-cassette', "-l -e 5prime -r forward -n3 -L",
[aln_infile1]),
('ignore-cassette', "-c -e 5prime -r forward -n3 -L", [aln_infile1]),
('separate-cassette', "-C -e 5prime -r forward -n3 -L", [aln_infile1]),
('sorted-by-count', "-o read_count -e 5prime -r forward -n3 -L",
[aln_infile1]),
('with-gene-info_merged',
"-e 5prime -r forward -g %s -n0" % gff_genefile, [aln_infile2]),
('with-gene-info_unmerged',
"-B -e 5prime -r forward -g %s -n0" % gff_genefile, [aln_infile2]),
('multiple-infiles', "-e 5prime -r forward -n0 -L",
[aln_infile1, aln_infile2]),
('dont-merge-tandems', "-n0", [aln_infile3]),
('merge-adjacent-none', "-n0 -Q -Y0", [aln_infile3]),
('merge-adjacent1-r3', "-MQ -D1 -w3 -Y0 -n0", [aln_infile3]),
('merge-adjacent1-r1', "-MQ -D1 -w1 -Y0 -n0", [aln_infile3]),
('merge-adjacent2-r3', "-MQ -D2 -w3 -Y0 -n0", [aln_infile3]),
('remove-from-other-all', "-x %s -n0" % dataset_to_remove,
[aln_infile2]),
('remove-from-other-min4', "-x %s -z4 -n0" % dataset_to_remove,
[aln_infile2]),
('remove-from-other-perfect', "-x %s -p -z4 -n0" % dataset_to_remove,
[aln_infile2]),
('remove-not-other-all', "-X %s -n0" % dataset_to_remove,
[aln_infile2]),
('remove-not-other-min4', "-X %s -Z4 -n0" % dataset_to_remove,
[aln_infile2]),
('remove-not-other-perfect', "-X %s -P -Z4 -n0" % dataset_to_remove,
[aln_infile2]),
('old-infile-format', "-e 5prime -r forward -n3 -L", [aln_infile0]),
]
# TODO add run-test for removing data from multiple files?
# MAYBE-TODO add run-test for a metadata file with 5' and 3' read counts?
# MAYBE-TODO add run-tests for other mutant-merging options? But they all have pretty good unit-tests.
# MAYBE-TODO add run-test for --gene_annotation_file?
# MAYBE-TODO add run-test for --input_collapsed_to_unique? Or is that unit-tested already?
# convert tests into (testname, arg_and_infile_string) format, adding the options that are always used
test_names_and_args = [('count-aln__' + testname,
test_args + ' -q ' + ' '.join(infiles))
for testname, test_args, infiles in test_runs]
parser = define_option_parser()
argument_converter = lambda parser, options, args: (args[:-1], args[-1],
options)
return run_functional_tests(test_names_and_args,
parser,
main,
test_folder,
argument_converter=argument_converter,
append_to_outfilenames='.txt')