def __init__(self, cleaned_data):
self.cleaned_data = cleaned_data
self.translations = None
self.degen_translations = None
self.clean_translations()
self.errors = []
self.seq_objs = []
self.minimum_number_of_genes = cleaned_data["number_genes"]
self.aminoacids = cleaned_data["aminoacids"]
try:
self.codon_positions = clean_positions(cleaned_data["positions"])
except exceptions.InadequateCodonPositions as e:
self.codon_positions = None
self.errors = [e]
self.file_format = cleaned_data["file_format"]
self.partition_by_positions = cleaned_data["partition_by_positions"]
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.gene_codes_and_lengths = None
self.taxon_names = cleaned_data["taxon_names"]
self.voucher_codes_metadata = dict()
self.gene_codes_metadata = self.get_gene_codes_metadata()
self.warnings = []
self.outgroup = cleaned_data["outgroup"]
self.dataset_file = None
self.aa_dataset_file = None
self.charset_block = None
self.dataset_str = self.create_dataset()
def __init__(self, cleaned_data):
self.cleaned_data = self.populate_cleaned_data_form(cleaned_data)
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.fasta_datasets = self.get_fasta_datasets()
self.genes_type = self.get_genes_type()
self.stats = self.get_stats_from_datasets()
def __init__(self, cleaned_data):
# skip sequences with accession numbers and building GenBank Fasta file
self.sequences_skipped = []
self.cleaned_data = cleaned_data
self.translations = None
self.degen_translations = None
self.clean_translations()
self.errors = []
self.seq_objs = []
self.minimum_number_of_genes = cleaned_data['number_genes']
self.aminoacids = cleaned_data['aminoacids']
try:
self.codon_positions = clean_positions(cleaned_data['positions'])
except exceptions.InadequateCodonPositions as e:
self.codon_positions = None
self.errors = [e]
self.file_format = cleaned_data['file_format']
self.partition_by_positions = cleaned_data['partition_by_positions']
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.gene_codes_and_lengths = None
self.taxon_names = cleaned_data['taxon_names']
self.voucher_codes_metadata = dict()
self.gene_codes_metadata = self.get_gene_codes_metadata()
self.warnings = []
self.outgroup = cleaned_data['outgroup']
self.dataset_file = None
self.aa_dataset_file = None
self.charset_block = None
self.dataset_str = self.create_dataset()
def test_get_voucher_codes_order(self):
"""Voucher codes should not be sorted. Same order as input from author
should be kept."""
self.cleaned_data["voucher_codes"] = "CP100-10\r\nCP100-11\r\nCP100-12\r\nCP100-13\r\nCP100-11"
expected = ("CP100-10", "CP100-11", "CP100-12", "CP100-13")
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, result)
def __init__(self, cleaned_data):
# skip sequences with accession numbers and building GenBank Fasta file
self.sequences_skipped = []
self.cleaned_data = cleaned_data
self.translations = None
self.degen_translations = None
self.clean_translations()
self.errors = []
self.seq_objs = []
self.minimum_number_of_genes = cleaned_data['number_genes']
self.aminoacids = cleaned_data['aminoacids']
try:
self.codon_positions = clean_positions(cleaned_data['positions'])
except exceptions.InadequateCodonPositions as e:
self.codon_positions = None
self.errors = [e]
self.file_format = cleaned_data['file_format']
self.partition_by_positions = cleaned_data['partition_by_positions']
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.gene_codes_and_lengths = None
self.taxon_names = cleaned_data['taxon_names']
self.voucher_codes_metadata = dict()
self.gene_codes_metadata = self.get_gene_codes_metadata()
self.warnings = []
self.outgroup = cleaned_data['outgroup']
self.dataset_file = None
self.aa_dataset_file = None
self.charset_block = None
self.dataset_str = self.create_dataset()
def __init__(self, cleaned_data):
self.cleaned_data = self.populate_cleaned_data_form(cleaned_data)
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.fasta_datasets = self.get_fasta_datasets()
self.genes_type = self.get_genes_type()
self.stats = self.get_stats_from_datasets()
def test_get_voucher_codes_order(self):
"""Voucher codes should not be sorted. Same order as input from author
should be kept."""
self.cleaned_data['voucher_codes'] = 'CP100-10\r\nCP100-11\r\nCP100-12\r\nCP100-13\r\nCP100-11'
expected = ('CP100-10', 'CP100-11', 'CP100-12', 'CP100-13')
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, result)
def test_get_voucher_codes_order(self):
"""Voucher codes should not be sorted. Same order as input from author
should be kept."""
self.cleaned_data[
'voucher_codes'] = 'CP100-10\r\nCP100-11\r\nCP100-12\r\nCP100-13\r\nCP100-11'
expected = ('CP100-10', 'CP100-11', 'CP100-12', 'CP100-13')
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, result)
def __init__(self, cleaned_data):
self.cleaned_data = cleaned_data
self.gene_info_to_display = self.get_gene_info_to_display()
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.voucher_info_values = self.get_voucher_info_values()
self.voucher_info = self.get_voucher_info()
self.sequences_info = self.get_sequence_info()
self.warnings = []
def __init__(self, cleaned_data):
self.cleaned_data = cleaned_data
self.gene_info_to_display = self.get_gene_info_to_display()
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.voucher_info_values = self.get_voucher_info_values()
self.voucher_info = self.get_voucher_info()
self.sequences_info = self.get_sequence_info()
self.warnings = []
def create_dataset(self):
if not self.codon_positions:
return ''
error_msg = None
if self.degen_translations is not None and self.codon_positions != [
'ALL'
]:
error_msg = 'Cannot degenerate codons if you have not selected all codon positions'
self.errors.append(error_msg)
elif self.degen_translations is not None and self.partition_by_positions != 'by gene':
error_msg = 'Cannot degenerate codons if they go to different partitions'
self.errors.append(error_msg)
if error_msg:
return ''
self.voucher_codes = get_voucher_codes(self.cleaned_data)
self.gene_codes = get_gene_codes(self.cleaned_data)
self.create_seq_objs()
if self.file_format in [
'NEXUS', 'GenBankFASTA', 'FASTA', 'MEGA', 'TNT', 'PHYLIP'
]:
try:
dataset = Dataset(
self.seq_objs,
format=self.file_format,
partitioning=self.partition_by_positions,
codon_positions=self.codon_positions[0],
aminoacids=self.aminoacids,
degenerate=self.degen_translations,
outgroup=self.outgroup,
)
except (MissingParameterError, ValueError,
TranslationErrorMixedGappedSeq) as e:
self.errors.append(e)
dataset = None
except NexusError as e:
self.errors.append(e.__str__())
dataset = None
if not dataset:
return ""
self.warnings += dataset.warnings
dataset_handler = DatasetHandler(dataset.dataset_str,
self.file_format)
self.dataset_file = dataset_handler.dataset_file
if self.file_format == 'PHYLIP':
self.charset_block = dataset.extra_dataset_str
return dataset.dataset_str
def __init__(self, cleaned_data):
print(">>>>>>_init", cleaned_data)
self.errors = []
self.seq_objs = dict()
self.codon_positions = cleaned_data['positions']
self.partition_by_positions = cleaned_data['partition_by_positions']
self.cleaned_data = cleaned_data
self.voucher_codes = get_voucher_codes(cleaned_data)
self.gene_codes = get_gene_codes(cleaned_data)
self.reading_frames = self.get_reading_frames()
self.taxon_names = cleaned_data['taxon_names']
self.dataset_str = self.create_dataset()
def create_dataset(self):
if not self.codon_positions:
return ""
if self.degen_translations is not None and self.codon_positions != ["ALL"]:
msg = "Cannot degenerate codons if you have not selected all codon positions"
self.errors.append(msg)
return ""
elif self.degen_translations is not None and self.partition_by_positions != "by gene":
msg = "Cannot degenerate codons if they go to different partitions"
self.errors.append(msg)
return ""
self.voucher_codes = get_voucher_codes(self.cleaned_data)
self.gene_codes = get_gene_codes(self.cleaned_data)
self.create_seq_objs()
if self.file_format in ["NEXUS", "GenBankFASTA", "FASTA", "MEGA", "TNT", "PHYLIP"]:
try:
dataset = Dataset(
self.seq_objs,
format=self.file_format,
partitioning=self.partition_by_positions,
codon_positions=self.codon_positions[0],
aminoacids=self.aminoacids,
degenerate=self.degen_translations,
outgroup=self.outgroup,
)
except MissingParameterError as e:
self.errors.append(e)
return ""
except ValueError as e:
self.errors.append(e)
return ""
except TranslationErrorMixedGappedSeq as e:
self.errors.append(e)
return ""
except NexusError as e:
self.errors.append(e.__str__())
return ""
self.warnings += dataset.warnings
dataset_handler = DatasetHandler(dataset.dataset_str, self.file_format)
self.dataset_file = dataset_handler.dataset_file
if self.file_format == "PHYLIP":
self.charset_block = dataset.extra_dataset_str
return dataset.dataset_str
def create_dataset(self):
if not self.codon_positions:
return ''
error_msg = None
if self.degen_translations is not None and self.codon_positions != ['ALL']:
error_msg = 'Cannot degenerate codons if you have not selected all codon positions'
self.errors.append(error_msg)
elif self.degen_translations is not None and self.partition_by_positions != 'by gene':
error_msg = 'Cannot degenerate codons if they go to different partitions'
self.errors.append(error_msg)
if error_msg:
return ''
self.voucher_codes = get_voucher_codes(self.cleaned_data)
self.gene_codes = get_gene_codes(self.cleaned_data)
self.create_seq_objs()
if self.file_format in ['NEXUS', 'GenBankFASTA', 'FASTA', 'MEGA', 'TNT', 'PHYLIP']:
try:
dataset = Dataset(
self.seq_objs,
format=self.file_format,
partitioning=self.partition_by_positions,
codon_positions=self.codon_positions[0],
aminoacids=self.aminoacids,
degenerate=self.degen_translations,
outgroup=self.outgroup,
)
except (MissingParameterError, ValueError, TranslationErrorMixedGappedSeq) as e:
self.errors.append(e)
dataset = None
except NexusError as e:
self.errors.append(e.__str__())
dataset = None
if not dataset:
return ""
self.warnings += dataset.warnings
dataset_handler = DatasetHandler(dataset.dataset_str, self.file_format)
self.dataset_file = dataset_handler.dataset_file
if self.file_format == 'PHYLIP':
self.charset_block = dataset.extra_dataset_str
return dataset.dataset_str
def results(request):
version, stats = get_version_stats()
if request.method == 'POST':
form = GenBankFastaForm(request.POST)
if form.is_valid():
cleaned_data = form.cleaned_data
voucher_codes = get_voucher_codes(cleaned_data)
gene_codes = get_gene_codes(cleaned_data)
res = utils.Results(voucher_codes, gene_codes)
res.get_datasets()
items_with_accession = res.items_with_accession
fasta = res.fasta
protein = res.protein
fasta_file = re.search('(fasta_[a-z0-9]+\.fasta)', res.fasta_file).groups()[0]
protein_file = re.search('(prot_[a-z0-9]+\.fasta)', res.protein_file).groups()[0]
return render(request, 'genbank_fasta/results.html',
{
'items_with_accession': items_with_accession,
'fasta': fasta,
'fasta_file': fasta_file,
'protein': protein,
'protein_file': protein_file,
'version': version,
'stats': stats,
},
)
else:
return render(request, 'genbank_fasta/index.html',
{
'form': form,
'version': version,
'stats': stats,
},
)
return HttpResponseRedirect('/genbank_fasta/')
def create_dataset(self):
self.voucher_codes = get_voucher_codes(self.cleaned_data)
self.gene_codes = get_gene_codes(self.cleaned_data)
self.create_seq_objs()
return self.from_seq_objs_to_fasta()
def test_get_voucher_codes(self):
expected = 3
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, len(result))
def test_get_voucher_codes_dropped(self):
self.cleaned_data["voucher_codes"] = "CP100-10\r\n--CP100-11\r\nCP100-12"
expected = 2
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, len(result))
def test_get_voucher_codes(self):
expected = 3
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, len(result))
def test_get_voucher_codes_dropped(self):
self.cleaned_data[
'voucher_codes'] = 'CP100-10\r\n--CP100-11\r\nCP100-12'
expected = 2
result = get_voucher_codes(self.cleaned_data)
self.assertEqual(expected, len(result))
