def task_search_for_orphan_enzymes():
activity_enzyme_names = list(
set(Activity.objects().distinct('enzyme_name')))
for name in activity_enzyme_names:
if len(Sequence.objects(enzyme_name=name)) == 0:
enzyme_type = Activity.objects(enzyme_name=name)[0].enzyme_type
new_seq = Sequence(enzyme_name=name, enzyme_type=enzyme_type)
new_seq.save()
print(
f"found orphan enzyme, added sequence entry for {name} - {enzyme_type}"
)
def add_new_enzymes():
enzyme_type = request.form['enzyme_type']
existing_name = request.form['existing_name']
new_name = request.form['new_name']
user = user_datastore.get_user(current_user.id)
paper = Paper.objects(id=request.form['paper_id'])[0]
if enzyme_type == '' or enzyme_type is None:
result = {
'status': 'danger',
'msg': 'Must select an enzyme type',
'issues': []
}
elif existing_name == new_name and new_name == "":
result = {
'status': 'danger',
'msg': 'Must select an enzyme or enter a new name',
'issues': []
}
elif existing_name != "" and new_name != "":
result = {
'status': 'danger',
'msg': 'Choose either an existing enzyme or enter a new name',
'issues': ["(One must be blank)"]
}
elif existing_name != "":
seq = Sequence.objects(enzyme_name=existing_name)[0]
seq.papers.append(paper)
seq.save()
result = {
'status': 'success',
'msg': 'Sequence added to paper',
'issues': []
}
elif new_name != "":
seq = Sequence(enzyme_name=new_name,
enzyme_type=enzyme_type,
added_by=user,
owner=user,
papers=[paper])
seq.save()
if user not in paper.edits_by:
paper.edits_by.append(user)
papers_functions.tag_paper_with_enzyme_types(paper)
result = {
'status': 'success',
'msg': 'Sequence added to paper',
'issues': []
}
else:
result = {
'status': 'danger',
'msg': 'Error creating new enzyme',
'issues': []
}
return jsonify(result=result)
def df_to_db(spec_df):
#added_by_dict = make_added_by_user_dict()
print('Saving biocatdb_2 excel to mongodb..')
for i, row in spec_df.iterrows():
html_doi = str(row['html_doi'])
doi = str(row['html_doi'])
added_by_string = str(row['added_by'])
list_html_to_remove = [
'https://doi.org/', 'http://doi.org/', 'http://dx.doi.org/'
]
for to_remove in list_html_to_remove:
if to_remove in doi:
doi = html_doi.replace(to_remove, '')
if len(Paper.objects(doi=doi)) == 0:
paper = Paper(short_citation=str(row['short_citation']),
html=html_doi,
doi=doi)
paper = paper.save()
print(f"{row['short_citation']} added")
else:
paper = Paper.objects(doi=doi)[0]
if row['enzyme_type'] is not None and row['enzyme_type'] != '' and type(
row['enzyme_type']) == str:
if len(EnzymeType.objects(enzyme_type=row['enzyme_type'])) == 0:
enz_type = EnzymeType(enzyme_type=row['enzyme_type'],
description='')
enz_type.save()
if row['enzyme_name'] is not None and row['enzyme_name'] != '' and type(
row['enzyme_name']) == str:
if len(Sequence.objects(enzyme_name=row['enzyme_name'])) == 0:
seq = Sequence(enzyme_name=check_is_nan(row['enzyme_name']),
enzyme_type=check_is_nan(row['enzyme_type']),
papers=[paper])
seq.save()
else:
seq = Sequence.objects(enzyme_name=row['enzyme_name'])[0]
if paper not in seq.papers:
seq.papers.append(paper)
seq = seq.save()
if row['binary'] == 1:
binary = True
else:
binary = False
if row['auto_generated'] == 1:
auto_gen = True
else:
auto_gen = False
activity = Activity(
enzyme_type=check_is_nan(row['enzyme_type']),
enzyme_name=check_is_nan(row['enzyme_name']),
reaction=check_is_nan(row['reaction']),
short_citation=check_is_nan(row['short_citation']),
html_doi=check_is_nan(row['html_doi']),
added_by_string=added_by_string,
paper=paper,
cascade_num=check_is_nan(row['cascade_num']),
substrate_1_smiles=get_smile(row['substrate_1_smiles']),
substrate_2_smiles=get_smile(row['substrate_2_smiles']),
product_1_smiles=get_smile(row['product_1_smiles']),
temperature=check_is_nan(row['temperature']),
ph=check_is_nan(row['ph']),
solvent=check_is_nan(row['solvent']),
other_conditions=check_is_nan(row['other_conditions']),
notes=check_is_nan(row['notes']),
reaction_vol=check_is_nan(row['reaction_vol']),
formulation=check_is_nan(row['formulation']),
biocat_conc=check_is_nan(row['biocat_conc']),
kcat=check_is_float(row['kcat']),
km=check_is_float(row['km']),
mw=check_is_float(row['mw']),
substrate_1_conc=check_is_nan(row['substrate_1_conc']),
substrate_2_conc=check_is_nan(row['substrate_2_conc']),
specific_activity=check_is_float(row['specific_activity']),
conversion=check_is_float(row['conversion']),
conversion_time=check_is_float(row['conversion_time']),
categorical=check_is_nan(row['categorical']),
binary=binary,
selectivity=check_is_nan(row['selectivity']),
auto_generated=auto_gen)
activity.save()
print('..done')
def save_or_add_seqs(data_list, paper):
# Used by upload excel
user = user_datastore.get_user(current_user.id)
issues = []
enzyme_types = EnzymeType.objects().distinct('enzyme_type')
for seq_dict in data_list:
if 'sequence_unavailable' in seq_dict:
if seq_dict['sequence_unavailable'] == '':
seq_dict['sequence_unavailable'] = 'False'
if 'structure' in seq_dict:
if seq_dict['structure'] == '':
seq_dict['structure'] = 'False'
if 'sequence' in seq_dict:
seq_dict['sequence'] = seq_dict['sequence'].replace('\n', '')
seq_dict['sequence'] = seq_dict['sequence'].replace(' ', '')
if seq_dict.get('enzyme_name', '') == '':
issues.append(f"Sequence must have a name")
else:
if len(Sequence.objects(enzyme_name=seq_dict['enzyme_name'])) == 0:
if seq_dict.get('enzyme_type', '') not in enzyme_types:
print(
f"Enzyme type {seq_dict.get('enzyme_type', '')} does not exist"
)
issues.append(
f"Enzyme type {seq_dict.get('enzyme_type', '')} does not exist"
)
elif sequence_check(seq_dict.get('sequence', '')) == False:
print(
f"Amino acid sequence for {seq_dict['enzyme_name']} uses incorrect amino acid characters"
)
issues.append(
f"Amino acid sequence for {seq_dict['enzyme_name']} uses incorrect amino acid characters"
)
else:
print('Creating new sequence..')
seq = Sequence(enzyme_name=seq_dict['enzyme_name'],
enzyme_type=seq_dict['enzyme_type'],
other_names=seq_dict.get('other_names',
'').split(', '),
sequence=seq_dict.get('sequence', ''),
n_tag=seq_dict.get('n_tag', ''),
c_tag=seq_dict.get('c_tag', ''),
sequence_unavailable=strtobool(
seq_dict.get('sequence_unavailable',
'False')),
accession=seq_dict.get('accession', ''),
other_identifiers=seq_dict.get(
'other_names', '').split(', '),
pdb=seq_dict.get('pdb', ''),
mutant_of=seq_dict.get('mutant_of', ''),
notes=seq_dict.get('notes', ''),
papers=[paper],
owner=user)
seq.save()
else:
seq = Sequence.objects(enzyme_name=seq_dict['enzyme_name'])[0]
if paper not in seq.papers:
seq.papers.append(paper)
if seq.owner == user or seq.owner is None:
seq.owner = user
other_names = seq_dict.get('other_names', '').split(', ')
seq.other_names.extend(other_names)
if (seq.sequence is None or seq.sequence == ''):
seq.sequence = seq_dict.get('sequence', '')
if strtobool(seq_dict.get('sequence_unavailable',
'False')) == True:
seq.sequence_unavailable = True
if (seq.accession is None or seq.accession == ''):
seq.accession = seq_dict.get('accession', '')
if seq_dict.get('pdb', '') != '':
seq.pdb = seq_dict.get('pdb', '')
if (seq.mutant_of is None or seq.mutant_of == ''):
seq.mutant_of = seq_dict.get('mutant_of', '')
if (seq.notes is None or seq.notes == ''):
seq.notes = seq_dict.get('notes', '')
else:
print(
'Sequence already exists but owned by another user - added to paper, but no data updated'
)
issues.append(
'Sequence already exists but owned by another user - added to paper, but no data updated'
)
seq.save()
return issues