def make_spreadsheet_for_ena_download(self):
sheet = Spreadsheet()
sheet.supplier, sheet.organisation, sheet.contact, sheet.technology, sheet.name, sheet.accession, sheet.size, \
sheet.limit = ('Supplier', 'Org', 'Contact', 'Illumina', 'AStudyName1', None, 1.90, '01/01/2025')
sheet.reads = [RawRead(forward_read='PAIR1', reverse_read='T', sample_name='SAMPLE1',
taxon_id='1280', library_name='LIB1', sample_accession=None),
RawRead(forward_read='Pair2.fastq.gz', reverse_read='F', sample_name='SAMPLE2',
taxon_id='1280', library_name='LIB2', sample_accession=None)]
return sheet
def test_study_name_with_invalid_char_should_fail_validation(self):
self.assertEqual(
33,
len(
validate_study_name(
Spreadsheet.new_instance(
"!\"£$%^&*()+={}[]:@~;'#?/>.<,|\\`¬\t"))))
def test_supplier_name_with_invalid_char_should_fail_validation(self):
self.assertEqual(
33,
len(
validate_no_abnormal_characters_in_supplier_name(
Spreadsheet.new_instance(
"name",
supplier="!\"£$%^&*()+={}[]:@~;'#?/>.<,|\\`¬\t"))))
def test_invalid_name_for_external_data_part_of_internal_study(self):
self.assertEqual(
[
"Data part of internal sequencing study should have the suffix '_external' in the name: "
"ValidName12345__"
],
validate_external_data_part_of_internal_sequencing_study_name(
Spreadsheet.new_instance("ValidName12345__", [])))
def test_sample_name_with_valid_char_should_pass_validation(self):
self.assertEqual([],
validate_sample_names(
Spreadsheet.new_instance("ValidName12345__", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name="SAMPLE_1",
taxon_id="1280",
library_name='LIB1')
])))
def test_copy_files_single_strand(self, copyfile_patch):
under_test = Preparation.new_instance(Spreadsheet.new_instance("MyStudy", [
RawRead(forward_read='PAIR1_1.fastq.gz', reverse_read='PAIR1_2.fastq.gz', sample_name='SAMPLE1',
taxon_id='1280', library_name='LIB1', sample_accession=None),
RawRead(forward_read='SINGLE.fastq.gz', reverse_read=None, sample_name='SAMPLE2',
taxon_id='1280', library_name='LIB2', sample_accession=None)]), 'destination', 0, 0)
under_test.copy_files('source')
self.assertEquals(copyfile_patch.call_args_list,
[call('source/PAIR1_1.fastq.gz', 'destination/0/PAIR1_1.fastq.gz'),
call('source/PAIR1_2.fastq.gz', 'destination/0/PAIR1_2.fastq.gz'),
call('source/SINGLE.fastq.gz', 'destination/0/SINGLE.fastq.gz')])
def test_pair_naming_convention_is_valid_for_single_read(self):
self.assertEqual([],
validate_pair_naming_convention(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_single_read_is_compressed(self):
self.assertEqual([],
validate_files_are_compressed(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1.fastq.gz',
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_no_hyphen_in_filename(self):
self.assertEqual([],
validate_no_hyphen_in_filename(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_valid_taxon_id(self):
self.assertEqual([],
validate_taxon_ids(
Spreadsheet.new_instance("ValidName12345__", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_mandatory_fields_for_reads_are_populated_single_read(self):
self.assertEqual([],
validate_mandatory_read_fields(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='READ.fastq.gz',
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_forward_read_not_populated(self):
with self.assertRaises(Exception):
validate_mandatory_read_fields(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read=None,
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
]))
def test_none_is_not_valid(self):
self.assertEqual(
["Double-ended is incorrectly formatted, must be T or F"],
check_double_ended_column_is_T_or_F(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def setUp(self):
self.tempdir = TempDirectory()
self.tempdir.write('1/Accession1.fastq.gz', b'the text')
self.tempdir.write('2/Accession1_1.fastq.gz', b'the text')
self.tempdir.write('2/Accession1_2.fastq.gz',b'the text')
self.tempdir_path = self.tempdir.path
print('temp',self.tempdir_path)
self.under_test1 = Preparation.new_instance(Spreadsheet.new_instance("MyStudy", [
RawRead(forward_read='Accession1', reverse_read='T', sample_name='SAMPLE1',
taxon_id='1280', library_name='LIB1', sample_accession=None),
RawRead(forward_read='Accession2', reverse_read='T', sample_name='SAMPLE2',
taxon_id='1280', library_name='LIB2', sample_accession=None)]), self.tempdir_path, 0, 0)
self.under_test2 = Preparation.new_instance(Spreadsheet.new_instance("MyStudy", [
RawRead(forward_read='Accession1', reverse_read='T', sample_name='SAMPLE1',
taxon_id='1280', library_name='LIB1', sample_accession=None),
RawRead(forward_read='Accession2', reverse_read='T', sample_name='SAMPLE2',
taxon_id='1280', library_name='LIB2', sample_accession=None)]), self.tempdir_path, 1, 0)
self.under_test3 = Preparation.new_instance(Spreadsheet.new_instance("MyStudy", [
RawRead(forward_read='Accession1', reverse_read='T', sample_name='SAMPLE1',
taxon_id='1280', library_name='LIB1', sample_accession=None),
RawRead(forward_read='Accession2', reverse_read='T', sample_name='SAMPLE2',
taxon_id='1280', library_name='LIB2', sample_accession=None)]), self.tempdir_path, 2, 0)
def test_library_name_not_populated(self):
self.assertEqual([
"Missing library name for RawRead(forward_read='READ.fastq.gz', reverse_read=None, "
"sample_name='SAMPLE1', sample_accession=None, taxon_id='1280', library_name=None)"
],
validate_mandatory_read_fields(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='READ.fastq.gz',
reverse_read=None,
sample_name='SAMPLE1',
taxon_id="1280",
library_name=None)
])))
def test_sample_name_with_invalid_char_should_fail_validation(self):
self.assertEqual(
34,
len(
validate_sample_names(
Spreadsheet.new_instance("ValidName12345__", [
RawRead(
sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name="!\"£$%^&*()+={}[]:@~;'#?/>.<,|\\`¬\t ",
taxon_id="1280",
library_name='LIB1')
]))))
def test_path_in_filename_is_invalid(self):
self.assertEqual(
[
"Path present in filename: /some/path/PAIR1_1.fastq.gz",
"Path present in filename: /some/path/PAIR1_2.fastq.gz",
],
validate_no_path_in_filename(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='/some/path/PAIR1_1.fastq.gz',
reverse_read='/some/path/PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_invalid_pair_naming_convention(self):
self.assertEqual([
"Inconsistent naming convention of forward and reverse reads for RawRead("
"forward_read='PAIR1xxx_1.fastq.gz', reverse_read='PAIR1_2.fastq.gz', "
"sample_name='SAMPLE1', sample_accession=None, taxon_id='1280', library_name='LIB1')"
],
validate_pair_naming_convention(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1xxx_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_T_or_F_is_valid(self):
self.assertEqual([],
check_double_ended_column_is_T_or_F(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='T',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='F',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_uniqueness_of_files_sample_and_library_ENA_download(self):
self.assertEqual([],
validate_uniqueness_of_reads(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1',
reverse_read='T',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR2',
reverse_read='F',
sample_name='SAMPLE2',
taxon_id="1280",
library_name='LIB2')
])))
def test_forward_read_not_unique(self):
self.assertEqual(["Forward read is not unique: PAIR1_1.fastq.gz"],
validate_uniqueness_of_reads(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR1_2.fastq.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1'),
RawRead(sample_accession=None,
forward_read='PAIR1_1.fastq.gz',
reverse_read='PAIR2_2.fastq.gz',
sample_name='SAMPLE2',
taxon_id="1280",
library_name='LIB2')
])))
def test_header_initialization_no_accession(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir,
'test_upload_no_pair_no_lib_no_accession.xls'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1_1.fastq.gz', None, 'SAMPLE1', 'LIB1', None),
self._raw_read('PAIR2_1.fastq.gz', None, 'SAMPLE2', 'LIB2', None)
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession=None,
limit='30/09/2020')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_reads_are_not_fastq(self):
self.assertEqual([
"Forward read file is not correctly formatted for RawRead(forward_read='PAIR1_1.gz', "
"reverse_read='PAIR1_2.gz', sample_name='SAMPLE1', sample_accession=None, "
"taxon_id='1280', library_name='LIB1')",
"Reverse read file is not correctly formatted for RawRead(forward_read='PAIR1_1.gz', "
"reverse_read='PAIR1_2.gz', sample_name='SAMPLE1', sample_accession=None, "
"taxon_id='1280', library_name='LIB1')"
],
validate_files_are_compressed(
Spreadsheet.new_instance("1234567890123456", [
RawRead(sample_accession=None,
forward_read='PAIR1_1.gz',
reverse_read='PAIR1_2.gz',
sample_name='SAMPLE1',
taxon_id="1280",
library_name='LIB1')
])))
def test_no_filename_only_run_accession(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_run_accession.xls'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1', 'T', 'SAMPLE1', 'LIB1', 'ACCESSION1'),
self._raw_read('PAIR2', 'T', 'SAMPLE2', 'LIB2', 'ACCESSION2'),
self._raw_read('PAIR3', 'F', 'SAMPLE3', 'LIB3', 'ACCESSION3')
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession='accession',
limit='30/09/2020')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_sample_and_library_names_as_integers(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_sample_name_as_int.xls'))
expected = Spreadsheet.new_instance("AStudyName1", [
self._raw_read('ERR0000001_1.fastq.gz', 'ERR0000001_2.fastq.gz',
'101260', '1000000001', 'ERR0000001', '485'),
self._raw_read('ERR0000002_1.fastq.gz', 'ERR0000002_2.fastq.gz',
'101264', '2000000002', 'ERR0000002', '485')
],
contact="Me",
organisation="Org",
supplier='Supplier',
technology='Illumina',
size=1.90,
accession=None,
limit='01/01/2025')
actual = loader.load_xls()
self.assertSpreadsheet(expected, actual)
def test_cells_read_xlsx(self):
loader = SpreadsheetLoader(
os.path.join(self.data_dir, 'test_upload.xlsx'))
expected = Spreadsheet.new_instance("MyStudy", [
self._raw_read('PAIR1_1.fastq.gz', 'PAIR1_2.fastq.gz', 'SAMPLE1',
'LIB1', 'ACCESSION1'),
self._raw_read('PAIR2_1.fastq.gz', 'PAIR2_2.fastq.gz', 'SAMPLE2',
'LIB2', 'ACCESSION2')
],
contact="Some Name",
organisation="ENA",
supplier='ENA',
technology='Illumina',
size=123456.0,
accession='accession',
limit='30/09/2020')
actual = loader.load_xlsx()
self.assertSpreadsheet(expected, actual)
def load_xlsx(self):
result = Spreadsheet()
data_row = 0
header_row = 0
for i in range(10):
if self._sheet.cell(row=i + 1, column=1).value == 'Study Name':
result.name = self._sheet.cell(row=i + 1, column=2).value
if self._sheet.cell(row=i + 1, column=1).value == 'Supplier Name':
result.supplier = self._sheet.cell(row=i + 1, column=2).value
if self._sheet.cell(row=i + 1, column=1).value == 'Supplier Organisation':
result.organisation = self._sheet.cell(row=i + 1, column=2).value
if self._sheet.cell(row=i + 1, column=1).value == 'Sanger Contact Name':
result.contact = self._sheet.cell(row=i + 1, column=2).value
if self._sheet.cell(row=i + 1, column=1).value == 'Sequencing Technology':
result.technology = self._sheet.cell(row=i + 1, column=2).value
if self._sheet.cell(row=i + 1, column=1).value == 'Study Accession number':
result.accession = self.__extract_text_value_xlsx(i + 1, 2)
if self._sheet.cell(row=i + 1, column=1).value == 'Total size of files in GBytes':
result.size = float(self._sheet.cell(row=i + 1, column=2).value)
if self._sheet.cell(row=i + 1, column=1).value == 'Data to be kept until':
result.limit = self._sheet.cell(row=i + 1, column=2).value.strftime('%d/%m/%Y')
if self._sheet.cell(row=i + 1, column=1).value == 'Filename' or self._sheet.cell(row=i + 1, column=1).value == 'Run Accession':
data_row = i + 2
header_row = i + 1
break
filename_column = None
run_accession_column = None
for i in range(self._sheet.max_column):
if self._sheet.cell(row=header_row, column=i + 1).value == 'Filename':
filename_column = i +1
if self._sheet.cell(row=header_row, column=i + 1).value == 'Run Accession':
run_accession_column = i +1
if filename_column is not None:
if self._sheet.cell(row=header_row, column=i + 1).value == 'Mate File':
mate_filename_column = i + 1
if run_accession_column is not None:
if self._sheet.cell(row=header_row, column=i + 1).value == 'Double-ended Reads':
double_ended_reads_column = i + 1
if self._sheet.cell(row=header_row, column=i + 1).value == 'Sample Name':
sample_name_column = i + 1
if self._sheet.cell(row=header_row, column=i + 1).value == 'Sample Accession number':
sample_accession_column = i + 1
if self._sheet.cell(row=header_row, column=i + 1).value == 'Taxon ID':
taxon_id_column = i + 1
if self._sheet.cell(row=header_row, column=i + 1).value == 'Library Name':
library_name_column = i + 1
reads = []
for i in range(data_row, self._sheet.max_row+1):
sample_name = self.__extract_float_value_xlsx(i, sample_name_column)
library_name = self.__extract_float_value_xlsx(i, library_name_column)
if library_name is None:
library_name = sample_name
if filename_column is not None:
reads.append(RawRead(
self.__extract_text_value_xlsx(i, filename_column),
self.__extract_text_value_xlsx(i, mate_filename_column),
sample_name,
self.__extract_text_value_xlsx(i, sample_accession_column),
self.__extract_float_value_xlsx(i, taxon_id_column),
library_name))
if run_accession_column is not None:
reads.append(RawRead(
(self.__extract_text_value_xlsx(i, run_accession_column)),
self.__extract_text_value_xlsx(i, double_ended_reads_column),
sample_name,
self.__extract_text_value_xlsx(i, sample_accession_column),
self.__extract_float_value_xlsx(i, taxon_id_column),
library_name))
result.reads = reads
return result
def load_xls(self):
result = Spreadsheet()
data_row = 0
header_row = 0
for i in range(self._sheet.nrows):
if self._sheet.cell_value(i, 0) == 'Study Name':
result.name = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Supplier Name':
result.supplier = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Supplier Organisation':
result.organisation = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Sanger Contact Name':
result.contact = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Sequencing Technology':
result.technology = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Study Accession number':
result.accession = self.__extract_text_value_xls(i, 1)
if self._sheet.cell_value(i, 0) == 'Total size of files in GBytes':
result.size = self._sheet.cell_value(i, 1)
if self._sheet.cell_value(i, 0) == 'Data to be kept until':
year, month, day, hour, minute, second = xlrd.xldate_as_tuple(self._sheet.cell_value(i, 1),
self._workbook.datemode)
result.limit = "%02d/%02d/%04d" % (day, month, year)
if self._sheet.cell_value(i, 0) == 'Filename' or self._sheet.cell_value(i, 0) == 'Run Accession':
data_row = i + 1
header_row = i
break
filename_column = None
run_accession_column = None
for i in range(self._sheet.ncols):
if self._sheet.cell_value(header_row, i) == 'Filename':
filename_column = i
if self._sheet.cell_value(header_row, i) == 'Run Accession':
run_accession_column = i
if filename_column is not None:
if self._sheet.cell_value(header_row, i) == 'Mate File':
mate_filename_column = i
if run_accession_column is not None:
if self._sheet.cell_value(header_row, i) == 'Double-ended Reads':
double_ended_reads_column = i
if self._sheet.cell_value(header_row, i) == 'Sample Name':
sample_name_column = i
if self._sheet.cell_value(header_row, i) == 'Sample Accession number':
sample_accession_column = i
if self._sheet.cell_value(header_row, i) == 'Taxon ID':
taxon_id_column = i
if self._sheet.cell_value(header_row, i) == 'Library Name':
library_name_column = i
reads = []
for i in range(data_row, self._sheet.nrows):
sample_name = self.__extract_float_value_xls(i, sample_name_column)
library_name = self.__extract_float_value_xls(i, library_name_column)
if library_name is None:
library_name = sample_name
if filename_column is not None:
reads.append(RawRead(
self.__extract_text_value_xls(i, filename_column),
self.__extract_text_value_xls(i, mate_filename_column),
sample_name,
self.__extract_text_value_xls(i, sample_accession_column),
self.__extract_float_value_xls(i, taxon_id_column),
library_name))
if run_accession_column is not None:
reads.append(RawRead(
(self.__extract_text_value_xls(i, run_accession_column)),
self.__extract_text_value_xls(i, double_ended_reads_column),
sample_name,
self.__extract_text_value_xls(i, sample_accession_column),
self.__extract_float_value_xls(i, taxon_id_column),
library_name))
result.reads = reads
return result
def test_supplier_name_with_valid_char_should_pass_validation(self):
self.assertEqual([],
validate_no_abnormal_characters_in_supplier_name(
Spreadsheet.new_instance(
"name", supplier="This should work")))
def test_valid_name_for_external_data_part_of_internal_study(self):
self.assertEqual(
[],
validate_external_data_part_of_internal_sequencing_study_name(
Spreadsheet.new_instance("345_external", [])))
