def load_into_mongo(yaml_dict):
for rxn_name in yaml_dict:
enzymes = []
for enz in list(yaml_dict[rxn_name]['enzymes'].keys()):
enzymes.append(enz)
if len(EnzymeType.objects(enzyme_type=enz)) == 0:
new_type = EnzymeType(enzyme_type=enz,
description='')
new_type.save()
if len(Reaction.objects(name=rxn_name)) == 0:
reaction = Reaction(name=rxn_name,
smarts=yaml_dict[rxn_name]['smarts'],
enzyme_types=enzymes,
cofactors=yaml_dict[rxn_name]['enzymes'],
positive_tests=yaml_dict[rxn_name]['positive_tests'],
negative_tests=yaml_dict[rxn_name]['negative_tests'],
type=yaml_dict[rxn_name]['type'])
if 'experimental' in yaml_dict[rxn_name]:
reaction.experimental = bool(yaml_dict[rxn_name]['experimental'])
if 'two_step' in yaml_dict[rxn_name]:
reaction.two_step = bool(yaml_dict[rxn_name]['two_step'])
reaction.save()
def add_enzyme_type():
form = EnzymeTypeForm()
if form.validate_on_submit() == True:
if form.description.data == '':
form.description.data = None
if form.other_abbreviations.data == '':
other_abbreviations = None
else:
other_abbreviations = form.other_abbreviations.data.split(', ')
enz_type = EnzymeType(enzyme_type=form.enzyme_type.data,
full_name=form.full_name.data,
other_abbreviations=other_abbreviations,
description=form.description.data)
enz_type.save()
flash("Data added successfully", 'success')
return redirect(url_for('biocatdb.add_enzyme_type'))
return render_template('enzyme_type/add_enzyme_type.html', form=form)
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')
