diff --git a/ippisite/ippidb/admin.py b/ippisite/ippidb/admin.py
index 3b32cd020b9245306579d28bf9379a49357f6f86..bfa448254966b23ddfe8b14c7ad97bdcfe6b53b4 100644
--- a/ippisite/ippidb/admin.py
+++ b/ippisite/ippidb/admin.py
@@ -2,44 +2,56 @@ from django.contrib import admin
from .models import *
from django.apps import apps
+
@admin.register(Bibliography)
class BibliographyAdmin(admin.ModelAdmin):
- list_display = ('authors_list', 'title', 'journal_name', 'biblio_year', 'id_source')
+ list_display = ('authors_list', 'title',
+ 'journal_name', 'biblio_year', 'id_source')
+
@admin.register(Protein)
class ProteinAdmin(admin.ModelAdmin):
list_display = ('uniprot_id', 'recommended_name_long')
+
@admin.register(Taxonomy)
class TaxonomyAdmin(admin.ModelAdmin):
list_display = ('taxonomy_id', 'name')
+
@admin.register(Domain)
class DomainAdmin(admin.ModelAdmin):
list_display = ('pfam_acc', 'pfam_id', 'pfam_description', 'domain_family')
+
@admin.register(ProteinDomainBoundComplex)
class ProteinDomainBoundComplexAdmin(admin.ModelAdmin):
list_display = ('protein', 'domain', 'ppc_copy_nb', 'ppp_copy_nb_per_p')
- list_display_links = ('protein', 'domain', 'ppc_copy_nb', 'ppp_copy_nb_per_p')
+ list_display_links = (
+ 'protein', 'domain', 'ppc_copy_nb', 'ppp_copy_nb_per_p')
+
@admin.register(ProteinDomainPartnerComplex)
class ProteinDomainPartnerComplexAdmin(admin.ModelAdmin):
list_display = ('protein', 'domain', 'ppc_copy_nb')
list_display_links = ('protein', 'domain', 'ppc_copy_nb')
+
@admin.register(Symmetry)
class Symmetry(admin.ModelAdmin):
list_display = ('code', 'description')
+
@admin.register(MDDRCompoundImport)
class MDDRCompoundImport(admin.ModelAdmin):
list_display = ('mddr_name', 'dvpmt_phase', 'canonical_smile')
+
@admin.register(Compound)
class Compound(admin.ModelAdmin):
list_display = ('iupac_name', 'common_name', 'canonical_smile')
+
@admin.register(TestActivityDescription)
class TextActivityDescription(admin.ModelAdmin):
list_display = ('test_name', 'test_type', 'test_modulation_type')
@@ -57,5 +69,3 @@ admin.site.site_title = admin.site.site_header
admin.site.index_header = 'iPPI-DB administration'
admin.site.index_title = admin.site.index_header
-
-
diff --git a/ippisite/ippidb/forms.py b/ippisite/ippidb/forms.py
index 35e35581ff2815478e57e133ee20f36a18b6b60b..168c54a42c30ce9551c0090b11614469f6f929bd 100644
--- a/ippisite/ippidb/forms.py
+++ b/ippisite/ippidb/forms.py
@@ -1,4 +1,4 @@
-from django.forms import ModelForm,modelformset_factory,formset_factory
+from django.forms import ModelForm, modelformset_factory, formset_factory
from django import forms
from django.db import models
from django.core.exceptions import ValidationError
@@ -7,84 +7,102 @@ from django.core.validators import RegexValidator
from .models import Bibliography, Protein, ProteinDomainComplex, Ppi, PpiComplex
from .ws import pdb_entry_exists
+
class IdForm(ModelForm):
+
class Meta:
model = Bibliography
- fields = ['source','id_source']
+ fields = ['source', 'id_source']
widgets = {
- 'source' : forms.RadioSelect,
+ 'source': forms.RadioSelect,
'id_source': forms.TextInput(attrs={'placeholder': 'ID'}),
}
+
class BibliographyForm(ModelForm):
+
class Meta:
model = Bibliography
exclude = ['authors_list', 'biblio_year']
widgets = {
- 'source': forms.TextInput(attrs={'readonly':'readonly','class':'readonly'}),
- 'id_source': forms.TextInput(attrs={'readonly':'readonly', 'class':'readonly'}),
- 'title': forms.TextInput(attrs={'readonly':'readonly', 'class':'readonly'}),
- 'journal_name': forms.TextInput(attrs={'readonly':'readonly', 'class':'readonly'}),
+ 'source': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'id_source': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'title': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'journal_name': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
}
+
def validate_pdb_exists(value):
if not(pdb_entry_exists(value)):
- raise ValidationError('PDB entry not found: %(value)s', params={'value': value}, code='invalid')
+ raise ValidationError(
+ 'PDB entry not found: %(value)s', params={'value': value}, code='invalid')
+
class PDBForm(forms.Form):
- pdb_id = forms.CharField(label="PDB ID",max_length=4, widget=forms.TextInput(attrs={'placeholder': 'e.g 4HHB', 'required':'required'}), required=True, validators=[
- RegexValidator('^[0-9][a-zA-Z0-9]{3}$', message='PDB ID must be 1 numeric + 3 alphanumeric characters'),
+ pdb_id = forms.CharField(label="PDB ID", max_length=4, widget=forms.TextInput(attrs={'placeholder': 'e.g 4HHB', 'required': 'required'}), required=True, validators=[
+ RegexValidator(
+ '^[0-9][a-zA-Z0-9]{3}$', message='PDB ID must be 1 numeric + 3 alphanumeric characters'),
validate_pdb_exists
- ])
+ ])
PDBFormSet = formset_factory(PDBForm)
-formset=PDBFormSet()
+formset = PDBFormSet()
+
class ProteinForm(ModelForm):
- class Meta:
- model = Protein
- exclude = ['recommended_name_long', 'short_name']
- widgets = {
- 'uniprot_id' : forms.TextInput(attrs={'readonly':'readonly','class':'readonly'}),
- 'gene_name' : forms.TextInput(attrs={'readonly':'readonly','class':'readonly'}),
- 'entry_name' : forms.TextInput(attrs={'readonly':'readonly','class':'readonly'}),
- 'organism': forms.TextInput(attrs={'readonly':'readonly','class':'readonly'}),
+
+ class Meta:
+ model = Protein
+ exclude = ['recommended_name_long', 'short_name']
+ widgets = {
+ 'uniprot_id': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'gene_name': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'entry_name': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
+ 'organism': forms.TextInput(attrs={'readonly': 'readonly', 'class': 'readonly'}),
}
-ProteinFormSet = modelformset_factory(Protein, exclude=('recommended_name_long', 'short_name'), extra=0)
+ProteinFormSet = modelformset_factory(
+ Protein, exclude=('recommended_name_long', 'short_name'), extra=0)
TYPE_CHOICES = (
- ('Hetero2merAB','Inhib_Hetero 2-mer AB'),
- ('Homo2merA2','Inhib_Homo 2-mer A2'),
- ('custom', 'Inhib_Custom your own'),
- ('Hetero2merAB','Stab_Hetero 2-mer AB'),
- ('Homo2merA2','Stab_Homo 2-mer A2'),
- ('HomoLike2mer','Stab_Homo-Like 2-mer A2'),
- ('Homo3merA3','Stab_Homo 3-mer A3'),
- ('Homo3merA2','Stab_Homo 3-mer A3 inhibited A2-dimer'),
- ('Homo4merA4','Stab_Homo 4-mer A4'),
- ('RingHomo3mer','Stab_Ring-Like 3-mer A3'),
- ('RingHomo5mer','Stab_Ring-Like 5-mer A5'),
- ('custom', 'Stab_Custom your own'),
- )
+ ('Hetero2merAB', 'Inhib_Hetero 2-mer AB'),
+ ('Homo2merA2', 'Inhib_Homo 2-mer A2'),
+ ('custom', 'Inhib_Custom your own'),
+ ('Hetero2merAB', 'Stab_Hetero 2-mer AB'),
+ ('Homo2merA2', 'Stab_Homo 2-mer A2'),
+ ('HomoLike2mer', 'Stab_Homo-Like 2-mer A2'),
+ ('Homo3merA3', 'Stab_Homo 3-mer A3'),
+ ('Homo3merA2', 'Stab_Homo 3-mer A3 inhibited A2-dimer'),
+ ('Homo4merA4', 'Stab_Homo 4-mer A4'),
+ ('RingHomo3mer', 'Stab_Ring-Like 3-mer A3'),
+ ('RingHomo5mer', 'Stab_Ring-Like 5-mer A5'),
+ ('custom', 'Stab_Custom your own'),
+)
+
class ProteinDomainComplexTypeForm(forms.Form):
complexType = forms.ChoiceField(
widget=forms.RadioSelect,
choices=TYPE_CHOICES,
- )
+ )
+
class ProteinDomainComplexForm(ModelForm):
- class Meta:
- model = ProteinDomainComplex
- fields = ['protein', 'domain', 'ppc_copy_nb']
+
+ class Meta:
+ model = ProteinDomainComplex
+ fields = ['protein', 'domain', 'ppc_copy_nb']
+
class PpiForm(ModelForm):
- class Meta:
- model = Ppi
- fields = ['pdb_id', 'symmetry']
+
+ class Meta:
+ model = Ppi
+ fields = ['pdb_id', 'symmetry']
+
class PpiComplexForm(ModelForm):
- class Meta:
- model = PpiComplex
- fields = ['complex', 'cc_nb']
+
+ class Meta:
+ model = PpiComplex
+ fields = ['complex', 'cc_nb']
diff --git a/ippisite/ippidb/gx.py b/ippisite/ippidb/gx.py
index 999004b40da1e46bc72936289d7868cab616e6d9..e74a84da2adaba230ab1e07674cf13ea346ccda5 100644
--- a/ippisite/ippidb/gx.py
+++ b/ippisite/ippidb/gx.py
@@ -2,14 +2,17 @@ from bioblend.galaxy import GalaxyInstance
from bioblend.galaxy.tools.inputs import inputs
workflow_id = 'dad6103ff71ca4fe'
-galaxy_url = 'https://galaxy-dev.web.pasteur.fr'
+galaxy_url = 'https://galaxy-dev.web.pasteur.fr'
api_key = '21c2ce387688b1a785040762f7c9c331'
+
def run_workflow_and_get_results(input_file):
gi = GalaxyInstance(galaxy_url, key=api_key)
gi.verify = False
history_id = gi.histories.create_history("ippidb_history")['id']
- dataset_id = gi.tools.upload_file(input_file, history_id)['outputs'][0]['id']
- inputs = {'0':{'id':dataset_id, 'src': 'hda' }}
- workflow_run = gi.workflows.invoke_workflow(workflow_id, inputs=inputs, history_id=history_id)
- print(workflow_run)
+ dataset_id = gi.tools.upload_file(
+ input_file, history_id)['outputs'][0]['id']
+ inputs = {'0': {'id': dataset_id, 'src': 'hda'}}
+ workflow_run = gi.workflows.invoke_workflow(
+ workflow_id, inputs=inputs, history_id=history_id)
+ print(workflow_run)
diff --git a/ippisite/ippidb/management/commands/import_v1_data.py b/ippisite/ippidb/management/commands/import_v1_data.py
index 41c0a5b771eb30f32cd79eef46de39a74b9e26d6..533a9d6dd8140c86081619cbd63de8571b93b3c8 100644
--- a/ippisite/ippidb/management/commands/import_v1_data.py
+++ b/ippisite/ippidb/management/commands/import_v1_data.py
@@ -9,6 +9,7 @@ from ippidb.models import Bibliography, Protein, Taxonomy, MolecularFunction, \
Domain, ProteinDomainBoundComplex, ProteinDomainPartnerComplex, Symmetry, Ppi, PpiComplex, Disease, \
Compound, MDDRCompoundImport, MDDRActivityClass, TestActivityDescription, CellLine
+
class MyConverter(mysql.connector.conversion.MySQLConverter):
def row_to_python(self, row, fields):
@@ -21,6 +22,7 @@ class MyConverter(mysql.connector.conversion.MySQLConverter):
return[to_unicode(col) for col in row]
+
class Command(BaseCommand):
help = "Import data from the local v1 database"
@@ -90,37 +92,43 @@ class Command(BaseCommand):
help='Stop on fail',
)
-
def handle(self, *args, **options):
- conn = mysql.connector.connect(converter_class=MyConverter, host="localhost", user="root", password="ippidb", database="ippidb")
+ conn = mysql.connector.connect(
+ converter_class=MyConverter, host="localhost", user="root", password="ippidb", database="ippidb")
cursor = conn.cursor()
if options['bibliographies']:
cursor.execute("""SELECT * FROM biblio""")
rows = cursor.fetchall()
Bibliography.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed bibliography table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed bibliography table'))
for row in rows:
try:
b = Bibliography()
- if row[1]=='article':
+ if row[1] == 'article':
b.source = 'PM'
else:
b.source = 'PT'
b.id_source = row[2]
b.save(autofill=True)
except Exception as e:
- self.stdout.write(self.style.ERROR('Failed inserting {}'.format(row[2])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {}'.format(row[2])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {}'.format(row[2])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {}'.format(row[2])))
if options['proteins']:
cursor.execute("""SELECT * FROM protein""")
rows = cursor.fetchall()
Protein.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed protein table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed protein table'))
Taxonomy.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed taxonomy table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed taxonomy table'))
MolecularFunction.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed molecular function table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed molecular function table'))
for row in rows:
try:
p = Protein()
@@ -130,16 +138,20 @@ class Command(BaseCommand):
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[1], row[2]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[1], row[2]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
if options['domains']:
cursor.execute("""SELECT * FROM domain""")
rows = cursor.fetchall()
Domain.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed domain table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed domain table'))
for row in rows:
try:
p = Domain()
@@ -150,16 +162,20 @@ class Command(BaseCommand):
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[1], row[2]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[1], row[2]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
if options['symmetries']:
Symmetry.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed symmetries table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed symmetries table'))
rows = [
- ['AS', 'asymmetric'],
+ ['AS', 'asymmetric'],
['C2', 'C2 symmetry'],
['D2', 'D2 symmetry'],
['C3', 'C3 symmetry'],
@@ -179,15 +195,18 @@ class Command(BaseCommand):
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[0], row[1]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[0], row[1]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[0], row[1])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[0], row[1])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(row[0], row[1])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(row[0], row[1])))
if options['ppi']:
sql_request_string = '''
select distinct protein.NumUniprot, domain.PfamNumAccession, complexe.NbCopy, cmpdAction.IDComplexeBound, bindingSiteEvidence.CodePDB, 'part1', ppi.IDPPI, disease.Disease from bindingSite inner join ppi on (bindingSite.IDBindingSite=ppi.IDBindingSite1) inner join complexe on (ppi.IDComplexe1=complexe.IDComplexe) left outer join cmpdAction on (complexe.IDComplexe=cmpdAction.IDComplexeBound) inner join protein on (bindingSite.IDProtein=protein.IDProtein) inner join domain on (bindingSite.IDDomain=domain.IDDomain) inner join disease on (disease.IDPPI=ppi.IDPPI) left outer join bindingSiteEvidence on (ppi.IDPPI=bindingSiteEvidence.IDPPI)
-union
+union
select distinct protein.NumUniprot, domain.PfamNumAccession , complexe.NbCopy, cmpdAction.IDComplexeBound, null, 'part2', ppi.IDPPI, disease.Disease from bindingSite inner join ppi on (bindingSite.IDBindingSite=ppi.IDBindingSite2) inner join complexe on (ppi.IDComplexe2=complexe.IDComplexe) left outer join cmpdAction on (complexe.IDComplexe=cmpdAction.IDComplexeBound) inner join protein on (bindingSite.IDProtein=protein.IDProtein) inner join domain on (bindingSite.IDDomain=domain.IDDomain) inner join disease on (disease.IDPPI=ppi.IDPPI)'''
cursor.execute(sql_request_string)
rows = cursor.fetchall()
@@ -196,21 +215,23 @@ select distinct protein.NumUniprot, domain.PfamNumAccession , complexe.NbCopy,
Disease.objects.all().delete()
Ppi.objects.all().delete()
PpiComplex.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed protein domain complex, PPI, and disease tables'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed protein domain complex, PPI, and disease tables'))
ppi_ids_mapping = {}
for row in rows:
try:
# create or retrieve Ppi object
- if row[5]=='part1':
+ if row[5] == 'part1':
ppi = Ppi()
- disease, created = Disease.objects.get_or_create(name=row[7])
+ disease, created = Disease.objects.get_or_create(
+ name=row[7])
ppi.pdb_id = row[4]
ppi.pockets_nb = 1
ppi.symmetry = Symmetry.objects.get(code='AS')
ppi.save()
ppi.diseases.add(disease)
ppi.save()
- ppi_ids_mapping[row[6]]=ppi.id
+ ppi_ids_mapping[row[6]] = ppi.id
else:
ppi = Ppi.objects.get(id=ppi_ids_mapping[row[6]])
# create a complex
@@ -236,20 +257,25 @@ select distinct protein.NumUniprot, domain.PfamNumAccession , complexe.NbCopy,
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[0], row[1]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[0], row[1]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[0], row[1])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[0], row[1])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(row[0], row[1])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(row[0], row[1])))
cursor.execute("""SELECT * FROM testActivityDescription""")
rows = cursor.fetchall()
TestActivityDescription.objects.all().delete()
CellLine.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed test activity descriptions table and cell lines table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed test activity descriptions table and cell lines table'))
for row in rows:
try:
tad = TestActivityDescription()
- cursor.execute("""select IDSource from biblio where IDBiblio={}""".format(row[2]))
+ cursor.execute(
+ """select IDSource from biblio where IDBiblio={}""".format(row[2]))
biblio_row = cursor.fetchone()
biblio = Bibliography.objects.get(id_source=biblio_row[0])
tad.biblio = biblio
@@ -259,21 +285,26 @@ select distinct protein.NumUniprot, domain.PfamNumAccession , complexe.NbCopy,
tad.test_modulation_type = row[8][0]
tad.nb_active_compounds = row[9]
if row[16] is not None:
- tad.cell_line, created = CellLine.objects.get_or_create(name=row[16])
+ tad.cell_line, created = CellLine.objects.get_or_create(
+ name=row[16])
tad.save()
except Exception as e:
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[1], row[2]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[1], row[2]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {}'.format(row[2])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {}'.format(row[2])))
if options['mddr']:
MDDRCompoundImport.objects.all().delete()
MDDRActivityClass.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed MDDR Compound and Activity class tables'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed MDDR Compound and Activity class tables'))
for sdf_file in glob.glob('/home/hmenager/iPPIDB/mddr20151_2d.sdf/*.sdf'):
for item in readfile("sdf", sdf_file):
try:
@@ -284,86 +315,97 @@ select distinct protein.NumUniprot, domain.PfamNumAccession , complexe.NbCopy,
m.db_import_date = timezone.now()
m.save()
for activity_class_name in item.data['ACTIV_CLASS'].split(','):
- activity_class, created = MDDRActivityClass.objects.get_or_create(name=activity_class_name)
+ activity_class, created = MDDRActivityClass.objects.get_or_create(
+ name=activity_class_name)
m.activity_classes.add(activity_class)
m.save()
except Exception as e:
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {}'.format(str(item)))
+ raise CommandError(
+ 'Failed inserting {}'.format(str(item)))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {}'.format(str(item))))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {}'.format(str(item))))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(item.data['MOLNAME'], str(item))))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(item.data['MOLNAME'], str(item))))
if options['compound']:
cursor.execute("""SELECT * FROM compound""")
rows = cursor.fetchall()
Compound.objects.all().delete()
- self.stdout.write(self.style.SUCCESS('Successfully flushed compound table'))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully flushed compound table'))
for row in rows:
try:
compound = Compound()
compound.canonical_smile = row[1]
- compound.is_macrocycle = (row[4]=='Y')
+ compound.is_macrocycle = (row[4] == 'Y')
compound.aromatic_ratio = row[5]
compound.balaban_index = row[6]
- compound.fsp3 = row[7] #Csp3Ratio
- compound.gc_molar_refractivity=row[10] #GCMolarRefractivity
- compound.log_d = row[13] #LogD
- compound.a_log_p = row[14] #ALogP
- compound.mean_atom_vol_vdw = row[15] #MeanAtomVolVdW
- compound.molecular_weight = row[16] #MolecularWeight
- compound.nb_acceptor_h = row[17] #NbAcceptorH
- compound.nb_aliphatic_amines = row[18] #NbAliphaticsAmines
- compound.nb_aromatic_bonds = row[19] #NbAromaticBonds
- compound.nb_aromatic_ether = row[20] #NbAromaticsEther
- compound.nb_aromatic_sssr = row[21] #NbAromaticsSSSR
- compound.nb_atom = row[22] #NbAtom
- compound.nb_atom_non_h = row[23] #NbAtomNonH
- compound.nb_benzene_like_rings = row[24] #NbBenzLikeRings
- compound.nb_bonds = row[25] #NbBonds
- compound.nb_bonds_non_h = row[26] #NbBondsNonH
- compound.nb_br = row[27] #NbBr
- compound.nb_c = row[28] #NbC
- compound.nb_chiral_centers = row[29] #NbChiralCenters
- compound.nb_circuits = row[30] #NbCircuits
- compound.nb_cl = row[31] #NbCl
- compound.nb_csp2 = row[32] #NbCsp2
- compound.nb_csp3 = row[33] #NbCsp3
- compound.nb_donor_h = row[34] #NbDonorH
- compound.nb_double_bonds = row[35] #NbDoubleBonds
- compound.nb_f = row[36] #NbF
- compound.nb_i = row[37] #NbI
- compound.nb_multiple_bonds = row[38] #NbMultBonds
- compound.nb_n = row[39] #NbN
- compound.nb_o = row[40] #NbO
- compound.nb_rings = row[41] #NbRings
- compound.nb_rotatable_bonds = row[42] #NbRotatableBonds
- compound.randic_index = row[44] #RandicIndex
- compound.rdf070m = row[45] #RDF070m
- compound.rotatable_bond_fraction = row[46] #RotatableBondFraction
- compound.sum_atom_polar = row[47] #SumAtomPolar
- compound.sum_atom_vol_vdw = row[48] #SumAtomVolVdW
- compound.tpsa = row[51] #TPSA
- compound.ui = row[52] #Ui
- compound.wiener_index = row[54] #WienerIndex
- if row[55]!='N':
- compound.common_name = row[55] #CmpdNameSh
- compound.pubchem_id = row[56] #IdPubchem
- if row[57]!='N':
- compound.chemspider_id = row[57] #IdPubchem
+ compound.fsp3 = row[7] # Csp3Ratio
+ compound.gc_molar_refractivity = row[
+ 10] # GCMolarRefractivity
+ compound.log_d = row[13] # LogD
+ compound.a_log_p = row[14] # ALogP
+ compound.mean_atom_vol_vdw = row[15] # MeanAtomVolVdW
+ compound.molecular_weight = row[16] # MolecularWeight
+ compound.nb_acceptor_h = row[17] # NbAcceptorH
+ compound.nb_aliphatic_amines = row[
+ 18] # NbAliphaticsAmines
+ compound.nb_aromatic_bonds = row[19] # NbAromaticBonds
+ compound.nb_aromatic_ether = row[20] # NbAromaticsEther
+ compound.nb_aromatic_sssr = row[21] # NbAromaticsSSSR
+ compound.nb_atom = row[22] # NbAtom
+ compound.nb_atom_non_h = row[23] # NbAtomNonH
+ compound.nb_benzene_like_rings = row[24] # NbBenzLikeRings
+ compound.nb_bonds = row[25] # NbBonds
+ compound.nb_bonds_non_h = row[26] # NbBondsNonH
+ compound.nb_br = row[27] # NbBr
+ compound.nb_c = row[28] # NbC
+ compound.nb_chiral_centers = row[29] # NbChiralCenters
+ compound.nb_circuits = row[30] # NbCircuits
+ compound.nb_cl = row[31] # NbCl
+ compound.nb_csp2 = row[32] # NbCsp2
+ compound.nb_csp3 = row[33] # NbCsp3
+ compound.nb_donor_h = row[34] # NbDonorH
+ compound.nb_double_bonds = row[35] # NbDoubleBonds
+ compound.nb_f = row[36] # NbF
+ compound.nb_i = row[37] # NbI
+ compound.nb_multiple_bonds = row[38] # NbMultBonds
+ compound.nb_n = row[39] # NbN
+ compound.nb_o = row[40] # NbO
+ compound.nb_rings = row[41] # NbRings
+ compound.nb_rotatable_bonds = row[42] # NbRotatableBonds
+ compound.randic_index = row[44] # RandicIndex
+ compound.rdf070m = row[45] # RDF070m
+ compound.rotatable_bond_fraction = row[
+ 46] # RotatableBondFraction
+ compound.sum_atom_polar = row[47] # SumAtomPolar
+ compound.sum_atom_vol_vdw = row[48] # SumAtomVolVdW
+ compound.tpsa = row[51] # TPSA
+ compound.ui = row[52] # Ui
+ compound.wiener_index = row[54] # WienerIndex
+ if row[55] != 'N':
+ compound.common_name = row[55] # CmpdNameSh
+ compound.pubchem_id = row[56] # IdPubchem
+ if row[57] != 'N':
+ compound.chemspider_id = row[57] # IdPubchem
compound.chembl_id = row[58]
compound.iupac_name = row[59]
- #compound.mddr_compound = row[60]
- #FIXME lookup MDDR to get the right ID
+ # compound.mddr_compound = row[60]
+ # FIXME lookup MDDR to get the right ID
compound.save()
except Exception as e:
if options['stoponfail']:
import traceback
self.stderr.write(traceback.format_exc())
- raise CommandError('Failed inserting {} {}'.format(row[1], row[2]))
+ raise CommandError(
+ 'Failed inserting {} {}'.format(row[1], row[2]))
else:
- self.stdout.write(self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.ERROR('Failed inserting {} {}'.format(row[1], row[2])))
else:
- self.stdout.write(self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
+ self.stdout.write(
+ self.style.SUCCESS('Successfully inserted {} {}'.format(row[1], row[2])))
diff --git a/ippisite/ippidb/models.py b/ippisite/ippidb/models.py
index 4456cfa2ba1916a3542f799f48c12fd9cc9fde64..4daa47324126d647e9d2abc93a7b2d5b033e9f74 100644
--- a/ippisite/ippidb/models.py
+++ b/ippisite/ippidb/models.py
@@ -4,7 +4,9 @@ from django.db import models
from .ws import get_pubmed_info, get_epo_info, get_uniprot_info, get_taxonomy_info, get_go_info, get_pfam_info
+
class AutoFillableModel(models.Model):
+
"""
AutoFillableModel makes it possible to automatically fill model fields from
external sources in the autofill() method
@@ -24,6 +26,7 @@ class AutoFillableModel(models.Model):
class Bibliography(AutoFillableModel):
+
"""
Bibliography data table
"""
@@ -32,7 +35,8 @@ class Bibliography(AutoFillableModel):
('PT', 'Patent'),
('DO', 'DOI ID')
)
- source = models.CharField('Bibliographic type', max_length=2, choices=SOURCES, default='PM')
+ source = models.CharField(
+ 'Bibliographic type', max_length=2, choices=SOURCES, default='PM')
id_source = models.CharField('Bibliographic ID', max_length=25)
title = models.CharField('Title', max_length=300)
journal_name = models.CharField('Journal name', max_length=50, null=True)
@@ -43,7 +47,8 @@ class Bibliography(AutoFillableModel):
in_vitro = models.BooleanField('in vitro study', default=False)
in_vivo = models.BooleanField('in vivo study', default=False)
in_cellulo = models.BooleanField('in cellulo study', default=False)
- pharmacokinetic = models.BooleanField('pharmacokinetic study', default=False)
+ pharmacokinetic = models.BooleanField(
+ 'pharmacokinetic study', default=False)
xray = models.BooleanField('X-Ray data', default=False)
def autofill(self):
@@ -64,7 +69,8 @@ class Bibliography(AutoFillableModel):
class Taxonomy(AutoFillableModel):
- taxonomy_id = models.DecimalField('NCBI TaxID', unique=True, max_digits=9, decimal_places=0)
+ taxonomy_id = models.DecimalField(
+ 'NCBI TaxID', unique=True, max_digits=9, decimal_places=0)
name = models.CharField('Organism name', max_length=200)
def autofill(self):
@@ -77,8 +83,10 @@ class Taxonomy(AutoFillableModel):
class Meta:
verbose_name_plural = "taxonomies"
+
class MolecularFunction(AutoFillableModel):
- go_id = models.CharField('Gene Ontology ID', unique=True, max_length=10) # GO term id format: 'GO:0000000'
+ go_id = models.CharField('Gene Ontology ID', unique=True, max_length=10)
+ # GO term id format: 'GO:0000000'
description = models.CharField('description', max_length=500)
def autofill(self):
@@ -88,9 +96,11 @@ class MolecularFunction(AutoFillableModel):
def __str__(self):
return self.description
+
class Protein(AutoFillableModel):
uniprot_id = models.CharField('Uniprot ID', unique=True, max_length=10)
- recommended_name_long = models.CharField('Uniprot Recommended Name (long)', max_length=75)
+ recommended_name_long = models.CharField(
+ 'Uniprot Recommended Name (long)', max_length=75)
short_name = models.CharField('Short name', max_length=50)
gene_name = models.CharField('Gene name', unique=True, max_length=30)
entry_name = models.CharField('Entry name', max_length=30)
@@ -122,11 +132,14 @@ class Protein(AutoFillableModel):
def __str__(self):
return '{} ({})'.format(self.uniprot_id, self.recommended_name_long)
+
class Domain(AutoFillableModel):
- pfam_acc = models.CharField('Pfam Accession', max_length=10, unique=True)
- pfam_id = models.CharField('Pfam Family Identifier', max_length=20)
+ pfam_acc = models.CharField('Pfam Accession', max_length=10, unique=True)
+ pfam_id = models.CharField('Pfam Family Identifier', max_length=20)
pfam_description = models.CharField('Pfam Description', max_length=100)
- domain_family = models.CharField('Domain family', max_length=25) #TODO: what is this field? check database contents
+ domain_family = models.CharField('Domain family', max_length=25)
+ # TODO: what is this field? check database
+ # contents
def autofill(self):
info = get_pfam_info(self.pfam_acc)
@@ -136,26 +149,34 @@ class Domain(AutoFillableModel):
def __str__(self):
return '{} ({}-{})'.format(self.pfam_acc, self.pfam_id, self.pfam_description)
+
class ProteinDomainComplex(models.Model):
protein = models.ForeignKey('Protein')
domain = models.ForeignKey('Domain')
- ppc_copy_nb = models.IntegerField('Number of copies of the protein in the complex')
-
+ ppc_copy_nb = models.IntegerField(
+ 'Number of copies of the protein in the complex')
+
class Meta:
verbose_name_plural = "complexes"
def __str__(self):
return '{}-{}'.format(self.protein_id, self.domain_id)
+
class ProteinDomainBoundComplex(ProteinDomainComplex):
- ppp_copy_nb_per_p = models.IntegerField('Number of copies of the protein in the pocket')
+ ppp_copy_nb_per_p = models.IntegerField(
+ 'Number of copies of the protein in the pocket')
+
class Meta:
verbose_name_plural = "bound complexes"
-
+
+
class ProteinDomainPartnerComplex(ProteinDomainComplex):
+
class Meta:
verbose_name_plural = "partner complexes"
+
class Symmetry(models.Model):
code = models.CharField('Symmetry code', max_length=2)
description = models.CharField('Description', max_length=300)
@@ -168,14 +189,17 @@ class Symmetry(models.Model):
class Disease(models.Model):
- name = models.CharField('Disease', max_length=30, unique=True) # is there any database/nomenclature for diseases?
+ name = models.CharField('Disease', max_length=30, unique=True)
+ # is there any database/nomenclature for diseases?
def __str__(self):
return self.name
+
class Ppi(models.Model):
pdb_id = models.CharField('PDB ID', max_length=4, null=True)
- pockets_nb = models.IntegerField('Total number of pockets in the complex', default=1)
+ pockets_nb = models.IntegerField(
+ 'Total number of pockets in the complex', default=1)
symmetry = models.ForeignKey(Symmetry)
diseases = models.ManyToManyField(Disease)
@@ -192,14 +216,15 @@ class Ppi(models.Model):
"""
return bound ppi complexes belonging to this ppi
"""
- #this is the less efficient query ever seen, FIXME
+ # this is the less efficient query ever seen, FIXME
return PpiComplex.objects.filter(ppi=self, complex__in=ProteinDomainBoundComplex.objects.all())
class PpiComplex(models.Model):
ppi = models.ForeignKey(Ppi)
complex = models.ForeignKey(ProteinDomainComplex)
- cc_nb = models.IntegerField('Number of copies of the complex in the PPI', default=1)
+ cc_nb = models.IntegerField(
+ 'Number of copies of the complex in the PPI', default=1)
class Meta:
verbose_name_plural = "Ppi complexes"
@@ -209,60 +234,83 @@ class PpiComplex(models.Model):
class Compound(models.Model):
- canonical_smile = models.CharField('Canonical Smile', unique=True, max_length=500)
- is_macrocycle = models.BooleanField('Contains one or more macrocycles')
- aromatic_ratio = models.DecimalField('Aromatic ratio', max_digits=3, decimal_places=2)
- balaban_index = models.DecimalField('Balaban index', max_digits=3, decimal_places=2)
+ canonical_smile = models.CharField(
+ 'Canonical Smile', unique=True, max_length=500)
+ is_macrocycle = models.BooleanField('Contains one or more macrocycles')
+ aromatic_ratio = models.DecimalField(
+ 'Aromatic ratio', max_digits=3, decimal_places=2)
+ balaban_index = models.DecimalField(
+ 'Balaban index', max_digits=3, decimal_places=2)
fsp3 = models.DecimalField('Fsp3', max_digits=3, decimal_places=2)
- gc_molar_refractivity = models.DecimalField('GC Molar Refractivity', max_digits=5, decimal_places=2)
- log_d = models.DecimalField('LogD (Partition coefficient octanol-1/water, with pKa information)', max_digits=4, decimal_places=2)
- a_log_p = models.DecimalField('ALogP (Partition coefficient octanol-1/water)', max_digits=4, decimal_places=2)
- mean_atom_vol_vdw = models.DecimalField('Mean atom volume computed with VdW radii', max_digits=4, decimal_places=2)
- molecular_weight = models.DecimalField('Molecular weight', max_digits=6, decimal_places=2)
+ gc_molar_refractivity = models.DecimalField(
+ 'GC Molar Refractivity', max_digits=5, decimal_places=2)
+ log_d = models.DecimalField(
+ 'LogD (Partition coefficient octanol-1/water, with pKa information)', max_digits=4, decimal_places=2)
+ a_log_p = models.DecimalField(
+ 'ALogP (Partition coefficient octanol-1/water)', max_digits=4, decimal_places=2)
+ mean_atom_vol_vdw = models.DecimalField(
+ 'Mean atom volume computed with VdW radii', max_digits=4, decimal_places=2)
+ molecular_weight = models.DecimalField(
+ 'Molecular weight', max_digits=6, decimal_places=2)
nb_acceptor_h = models.IntegerField('Number of hydrogen bond acceptors')
nb_aliphatic_amines = models.IntegerField('Number of aliphatics amines')
nb_aromatic_bonds = models.IntegerField('Number of aromatic bonds')
nb_aromatic_ether = models.IntegerField('Number of aromatic ethers')
- nb_aromatic_sssr = models.IntegerField('Number of aromatic Smallest Set of System Rings (SSSR)')
- nb_atom = models.IntegerField('Number of atoms')
- nb_atom_non_h = models.IntegerField('Number of non hydrogen atoms')
+ nb_aromatic_sssr = models.IntegerField(
+ 'Number of aromatic Smallest Set of System Rings (SSSR)')
+ nb_atom = models.IntegerField('Number of atoms')
+ nb_atom_non_h = models.IntegerField('Number of non hydrogen atoms')
nb_benzene_like_rings = models.IntegerField('Number of benzene-like rings')
nb_bonds = models.IntegerField('Number of bonds')
- nb_bonds_non_h = models.IntegerField('Number of bonds not involving a hydrogen')
- nb_br = models.IntegerField('Number of Bromine atoms')
- nb_c = models.IntegerField('Number of Carbon atoms')
- nb_chiral_centers = models.IntegerField('Number of chiral centers')
- nb_circuits = models.IntegerField('Number of circuits')
- nb_cl = models.IntegerField('Number of Chlorine atoms')
- nb_csp2 = models.IntegerField('Number of sp2-hybridized carbon atoms')
- nb_csp3 = models.IntegerField('Number of sp3-hybridized carbon atoms')
- nb_donor_h = models.IntegerField('Number of hydrogen bond donors')
- nb_double_bonds = models.IntegerField('Number of double bonds')
- nb_f = models.IntegerField('Number of fluorine atoms')
- nb_i = models.IntegerField('Number of iodine atoms')
- nb_multiple_bonds = models.IntegerField('Number of multiple bonds')
+ nb_bonds_non_h = models.IntegerField(
+ 'Number of bonds not involving a hydrogen')
+ nb_br = models.IntegerField('Number of Bromine atoms')
+ nb_c = models.IntegerField('Number of Carbon atoms')
+ nb_chiral_centers = models.IntegerField('Number of chiral centers')
+ nb_circuits = models.IntegerField('Number of circuits')
+ nb_cl = models.IntegerField('Number of Chlorine atoms')
+ nb_csp2 = models.IntegerField('Number of sp2-hybridized carbon atoms')
+ nb_csp3 = models.IntegerField('Number of sp3-hybridized carbon atoms')
+ nb_donor_h = models.IntegerField('Number of hydrogen bond donors')
+ nb_double_bonds = models.IntegerField('Number of double bonds')
+ nb_f = models.IntegerField('Number of fluorine atoms')
+ nb_i = models.IntegerField('Number of iodine atoms')
+ nb_multiple_bonds = models.IntegerField('Number of multiple bonds')
nb_n = models.IntegerField('Number of nitrogen atoms')
- nb_o = models.IntegerField('Number of oxygen atoms')
- nb_rings = models.IntegerField('Number of rings')
- nb_rotatable_bonds = models.IntegerField('Number of rotatable bonds')
- randic_index = models.DecimalField('Randic index', max_digits=4, decimal_places=2)
- rdf070m = models.DecimalField('RDF070m, radial distribution function weighted by the atomic masses at 7Ã…', max_digits=5, decimal_places=2)
- rotatable_bond_fraction = models.DecimalField('Fraction of rotatable bonds', max_digits=3, decimal_places=2)
- sum_atom_polar = models.DecimalField('Sum of atomic polarizabilities', max_digits=5, decimal_places=2)
- sum_atom_vol_vdw = models.DecimalField('Sum of atom volumes computed with VdW radii', max_digits=6, decimal_places=2)
- tpsa = models.DecimalField('Topological Polar Surface Area (TPSA)', max_digits=5, decimal_places=2)
- ui = models.DecimalField('Unsaturation index', max_digits=4, decimal_places=2)
- wiener_index = models.IntegerField('Wiener index')
- common_name = models.CharField('Common name', unique=True, max_length=20, blank=True, null=True)
- pubchem_id = models.CharField('Pubchem ID', max_length=10, blank=True, null=True)
- chemspider_id = models.CharField('Chemspider ID', unique=True, max_length=10, blank=True, null=True)
- chembl_id = models.CharField('Chembl ID', max_length=30, blank=True, null=True)
- iupac_name = models.CharField('IUPAC name', max_length=255, blank=True, null=True)
- mddr_compound = models.ForeignKey('MDDRCompoundImport', blank=True, null=True)
+ nb_o = models.IntegerField('Number of oxygen atoms')
+ nb_rings = models.IntegerField('Number of rings')
+ nb_rotatable_bonds = models.IntegerField('Number of rotatable bonds')
+ randic_index = models.DecimalField(
+ 'Randic index', max_digits=4, decimal_places=2)
+ rdf070m = models.DecimalField(
+ 'RDF070m, radial distribution function weighted by the atomic masses at 7Ã…', max_digits=5, decimal_places=2)
+ rotatable_bond_fraction = models.DecimalField(
+ 'Fraction of rotatable bonds', max_digits=3, decimal_places=2)
+ sum_atom_polar = models.DecimalField(
+ 'Sum of atomic polarizabilities', max_digits=5, decimal_places=2)
+ sum_atom_vol_vdw = models.DecimalField(
+ 'Sum of atom volumes computed with VdW radii', max_digits=6, decimal_places=2)
+ tpsa = models.DecimalField(
+ 'Topological Polar Surface Area (TPSA)', max_digits=5, decimal_places=2)
+ ui = models.DecimalField(
+ 'Unsaturation index', max_digits=4, decimal_places=2)
+ wiener_index = models.IntegerField('Wiener index')
+ common_name = models.CharField(
+ 'Common name', unique=True, max_length=20, blank=True, null=True)
+ pubchem_id = models.CharField(
+ 'Pubchem ID', max_length=10, blank=True, null=True)
+ chemspider_id = models.CharField(
+ 'Chemspider ID', unique=True, max_length=10, blank=True, null=True)
+ chembl_id = models.CharField(
+ 'Chembl ID', max_length=30, blank=True, null=True)
+ iupac_name = models.CharField(
+ 'IUPAC name', max_length=255, blank=True, null=True)
+ mddr_compound = models.ForeignKey(
+ 'MDDRCompoundImport', blank=True, null=True)
class MDDRActivityClass(models.Model):
- name = models.CharField('Activity Class', max_length=100, unique=True)
+ name = models.CharField('Activity Class', max_length=100, unique=True)
class Meta:
verbose_name_plural = "MDDR activity classes"
@@ -270,58 +318,67 @@ class MDDRActivityClass(models.Model):
def __str__(self):
return self.name
+
class MDDRCompoundImport(models.Model):
MDDR_DEVELOPMENT_PHASES = (
- ('Biological Testing',''),
- ('Preclinical',''),
- ('Phase III',''),
- ('Phase II',''),
- ('Phase I/II',''),
- ('Phase I',''),
- ('Launched',''),
- ('Pre-Registered',''),
- ('Not Applicable',''),
- ('Discontinued',''),
- ('Clinical',''),
- ('Withdrawn',''),
- ('Registered',''),
- ('Not Determined',''),
- ('Phase II/III',''),
- ('IND Filed',''),
+ ('Biological Testing', ''),
+ ('Preclinical', ''),
+ ('Phase III', ''),
+ ('Phase II', ''),
+ ('Phase I/II', ''),
+ ('Phase I', ''),
+ ('Launched', ''),
+ ('Pre-Registered', ''),
+ ('Not Applicable', ''),
+ ('Discontinued', ''),
+ ('Clinical', ''),
+ ('Withdrawn', ''),
+ ('Registered', ''),
+ ('Not Determined', ''),
+ ('Phase II/III', ''),
+ ('IND Filed', ''),
)
- mddr_name = models.CharField('MDDR name', max_length=40)
- dvpmt_phase = models.CharField('Development phase', max_length=20, choices=MDDR_DEVELOPMENT_PHASES)
- canonical_smile = models.CharField('Canonical Smile', max_length=500, blank=True, null=True)
- #TODO index this table on canonical_smile
- db_import_date = models.DateTimeField('MDDR release year/month')
+ mddr_name = models.CharField('MDDR name', max_length=40)
+ dvpmt_phase = models.CharField(
+ 'Development phase', max_length=20, choices=MDDR_DEVELOPMENT_PHASES)
+ canonical_smile = models.CharField(
+ 'Canonical Smile', max_length=500, blank=True, null=True)
+ # TODO index this table on canonical_smile
+ db_import_date = models.DateTimeField('MDDR release year/month')
activity_classes = models.ManyToManyField(MDDRActivityClass)
class Meta:
# over multiple releases of the MDDR database, the same compound can evolve in its development phase
- # the same compound can have different names and development phases in the same MDDR release
+ # the same compound can have different names and development phases in
+ # the same MDDR release
unique_together = (('mddr_name', 'dvpmt_phase', 'canonical_smile'),)
verbose_name_plural = "MDDR compound imports"
def __str__(self):
return "{}, {}".format(self.mddr_name, self.dvpmt_phase)
+
class MDDRSimilarity(models.Model):
- canonical_smile_ippidb = models.CharField('Canonical Smile for IPPIDB compound', max_length=500, unique=True, blank=True, null=True)
- canonical_smile_mddr = models.CharField('Canonical Smile for MDDR Compound', max_length=500, unique=True, blank=True, null=True)
- tanimoto = models.DecimalField('Tanimoto', max_digits=6, decimal_places=5)
+ canonical_smile_ippidb = models.CharField(
+ 'Canonical Smile for IPPIDB compound', max_length=500, unique=True, blank=True, null=True)
+ canonical_smile_mddr = models.CharField(
+ 'Canonical Smile for MDDR Compound', max_length=500, unique=True, blank=True, null=True)
+ tanimoto = models.DecimalField('Tanimoto', max_digits=6, decimal_places=5)
class Meta:
unique_together = (('canonical_smile_ippidb', 'canonical_smile_mddr'),)
verbose_name_plural = "MDDR similarities"
+
class CellLine(models.Model):
name = models.CharField('Name', max_length=50, unique=True)
def __str__(self):
return self.name
+
class TestActivityDescription(models.Model):
TEST_TYPES = (
('BIOCH', 'Biochemical assay'),
@@ -333,11 +390,13 @@ class TestActivityDescription(models.Model):
('S', 'Stabilization')
)
biblio = models.ForeignKey(Bibliography)
- ppi = models.ForeignKey(Ppi, blank=True, null=True)
- test_name = models.CharField('Test name', max_length=100)
+ ppi = models.ForeignKey(Ppi, blank=True, null=True)
+ test_name = models.CharField('Test name', max_length=100)
test_type = models.CharField('Test type', max_length=5, choices=TEST_TYPES)
- test_modulation_type = models.CharField('Test modulation type', max_length=1, choices=TEST_MODULATION_TYPES)
- nb_active_compounds = models.IntegerField('Total number of active compounds')
+ test_modulation_type = models.CharField(
+ 'Test modulation type', max_length=1, choices=TEST_MODULATION_TYPES)
+ nb_active_compounds = models.IntegerField(
+ 'Total number of active compounds')
cell_line = models.ForeignKey(CellLine, blank=True, null=True)
def get_complexes(self):
@@ -345,11 +404,12 @@ class TestActivityDescription(models.Model):
get the complexes tested for this PPI
depends on the modulation type
"""
- if self.test_modulation_type=='I':
+ if self.test_modulation_type == 'I':
return self.ppi.get_ppi_complexes()
else:
return self.ppi.get_ppi_bound_complexes()
+
class CompoundActivityResult(models.Model):
MODULATION_TYPES = (
('B', 'Binding'),
@@ -357,34 +417,42 @@ class CompoundActivityResult(models.Model):
('S', 'Stabilization')
)
ACTIVITY_TYPES = (
- ('pIC50','pIC50 (half maximal inhibitory concentration, -log10)'),
- ('pEC50','pEC50 (half maximal effective concentration, -log10)'),
- ('pKd','pKd (dissociation constant, -log10)'),
- ('pKi','pKi (inhibition constant, -log10)'),
+ ('pIC50', 'pIC50 (half maximal inhibitory concentration, -log10)'),
+ ('pEC50', 'pEC50 (half maximal effective concentration, -log10)'),
+ ('pKd', 'pKd (dissociation constant, -log10)'),
+ ('pKi', 'pKi (inhibition constant, -log10)'),
)
- compound = models.ForeignKey(Compound)
- test_activity_description = models.ForeignKey(TestActivityDescription)
- activity_type = models.CharField('Activity type', max_length=5, choices=ACTIVITY_TYPES)
- activity = models.DecimalField('Activity', max_digits=12, decimal_places=10)
- modulation_type = models.CharField('Modulation type', max_length=1, choices=MODULATION_TYPES)
+ compound = models.ForeignKey(Compound)
+ test_activity_description = models.ForeignKey(TestActivityDescription)
+ activity_type = models.CharField(
+ 'Activity type', max_length=5, choices=ACTIVITY_TYPES)
+ activity = models.DecimalField(
+ 'Activity', max_digits=12, decimal_places=10)
+ modulation_type = models.CharField(
+ 'Modulation type', max_length=1, choices=MODULATION_TYPES)
class Meta:
- unique_together = (('compound', 'test_activity_description', 'activity_type'),)
+ unique_together = (
+ ('compound', 'test_activity_description', 'activity_type'),)
+
class TestCytotoxDescription(models.Model):
- biblio = models.ForeignKey(Bibliography)
- test_name = models.CharField('Cytotoxicity test name', max_length=100)
+ biblio = models.ForeignKey(Bibliography)
+ test_name = models.CharField('Cytotoxicity test name', max_length=100)
cell_line = models.ForeignKey(CellLine)
- compound_concentration = models.DecimalField('Compound concentration in μM', max_digits=7, decimal_places=3, blank=True, null=True)
+ compound_concentration = models.DecimalField(
+ 'Compound concentration in μM', max_digits=7, decimal_places=3, blank=True, null=True)
+
class CompoundCytotoxicityResult(models.Model):
- compound = models.ForeignKey(Compound)
+ compound = models.ForeignKey(Compound)
test_cytotoxicity_description = models.ForeignKey(TestCytotoxDescription)
toxicity = models.BooleanField('Toxicity', default=False)
class Meta:
unique_together = (('compound', 'test_cytotoxicity_description'),)
+
class TestPKDescription(models.Model):
ADMINISTRATION_MODES = (
('IV', ''),
@@ -392,24 +460,33 @@ class TestPKDescription(models.Model):
('IP', ''),
('SL', 'SL')
)
- biblio = models.ForeignKey(Bibliography)
- test_name = models.CharField('Pharmacokinetic test name', max_length=100)
+ biblio = models.ForeignKey(Bibliography)
+ test_name = models.CharField('Pharmacokinetic test name', max_length=100)
organism = models.ForeignKey(Taxonomy)
- administration_mode = models.CharField('Administration mode', max_length=2, choices=ADMINISTRATION_MODES,blank=True, null=True)
- dose = models.DecimalField('Dose in mg/kg', max_digits=7, decimal_places=4, blank=True, null=True)
- dose_interval = models.IntegerField('Dose interval, in hours', blank=True, null=True)
+ administration_mode = models.CharField(
+ 'Administration mode', max_length=2, choices=ADMINISTRATION_MODES, blank=True, null=True)
+ dose = models.DecimalField(
+ 'Dose in mg/kg', max_digits=7, decimal_places=4, blank=True, null=True)
+ dose_interval = models.IntegerField(
+ 'Dose interval, in hours', blank=True, null=True)
+
class CompoundPKResult(models.Model):
- compound = models.ForeignKey(Compound)
+ compound = models.ForeignKey(Compound)
test_pk_description = models.ForeignKey(TestPKDescription)
tolerated = models.NullBooleanField('Tolerated', null=True)
- auc = models.IntegerField('Area under curve (ng.mL-1.hr)', blank=True, null=True)
- clearance = models.DecimalField('Clearance (mL/hr)', max_digits=7, decimal_places=3, blank=True, null=True)
- cmax = models.DecimalField('Maximal concentration (ng/mL)', max_digits=7, decimal_places=3, blank=True, null=True)
- oral_bioavailability = models.IntegerField('Oral Bioavailability (%F)', blank=True, null=True)
- t_demi = models.IntegerField('t½', blank=True, null=True)
- t_max = models.IntegerField('tmax', blank=True, null=True)
- voldistribution = models.DecimalField('Volume distribution (Vd)', max_digits=5, decimal_places=2, blank=True, null=True)
+ auc = models.IntegerField(
+ 'Area under curve (ng.mL-1.hr)', blank=True, null=True)
+ clearance = models.DecimalField(
+ 'Clearance (mL/hr)', max_digits=7, decimal_places=3, blank=True, null=True)
+ cmax = models.DecimalField(
+ 'Maximal concentration (ng/mL)', max_digits=7, decimal_places=3, blank=True, null=True)
+ oral_bioavailability = models.IntegerField(
+ 'Oral Bioavailability (%F)', blank=True, null=True)
+ t_demi = models.IntegerField('t½', blank=True, null=True)
+ t_max = models.IntegerField('tmax', blank=True, null=True)
+ voldistribution = models.DecimalField(
+ 'Volume distribution (Vd)', max_digits=5, decimal_places=2, blank=True, null=True)
class Meta:
unique_together = (('compound', 'test_pk_description'),)
@@ -420,11 +497,13 @@ class CompoundAction(models.Model):
('O', 'Orthosteric'),
('A', 'Allosteric')
)
- compound = models.ForeignKey(Compound)
- activation_mode = models.CharField('Activation mode', max_length=1, choices=ACTIVATION_MODES)
+ compound = models.ForeignKey(Compound)
+ activation_mode = models.CharField(
+ 'Activation mode', max_length=1, choices=ACTIVATION_MODES)
ppi = models.ForeignKey(Ppi)
pdb_id = models.CharField('PDB ID', max_length=4)
- nb_copy_compounds = models.IntegerField('Number of copies for the compound')
+ nb_copy_compounds = models.IntegerField(
+ 'Number of copies for the compound')
class Meta:
unique_together = (('ppi', 'compound', 'activation_mode', 'pdb_id'),)
@@ -436,10 +515,12 @@ class CompoundAction(models.Model):
"""
return self.ppi.get_ppi_bound_complexes()
+
class RefCompoundBiblio(models.Model):
- compound = models.ForeignKey(Compound)
- bibliography = models.ForeignKey(Bibliography)
- compound_name = models.CharField('Compound name in the publication', max_length=50)
+ compound = models.ForeignKey(Compound)
+ bibliography = models.ForeignKey(Bibliography)
+ compound_name = models.CharField(
+ 'Compound name in the publication', max_length=50)
class Meta:
unique_together = (('compound', 'bibliography'),)
diff --git a/ippisite/ippidb/urls.py b/ippisite/ippidb/urls.py
index 377643bea8062f91dab63debefe8169df3f69c85..3cfaacf9b49cf01e977c2512c7f71a14c894d5be 100644
--- a/ippisite/ippidb/urls.py
+++ b/ippisite/ippidb/urls.py
@@ -1,10 +1,10 @@
-from django.conf.urls import include,url
+from django.conf.urls import include, url
from . import views
-from ippidb.forms import IdForm, BibliographyForm,PDBForm,ProteinDomainComplexTypeForm,ProteinDomainComplexForm,PpiForm
-from ippidb.views import IppiWizard,FORMS
+from ippidb.forms import IdForm, BibliographyForm, PDBForm, ProteinDomainComplexTypeForm, ProteinDomainComplexForm, PpiForm
+from ippidb.views import IppiWizard, FORMS
ippidb_wizard = IppiWizard.as_view(FORMS,
- url_name='ippidb_step')
+ url_name='ippidb_step')
urlpatterns = [
@@ -12,14 +12,17 @@ urlpatterns = [
url(r'^about$', views.about, name='about'),
url(r'^about/general/$', views.general, name='general'),
url(r'^about/pharmacology/$', views.pharmacology, name='pharmacology'),
- url(r'^about/physicochemistry/$', views.physicochemistry, name='physicochemistry'),
- url(r'^about/drug-candidate/$', views.drugCandidate, name='drug-candidate'),
+ url(r'^about/physicochemistry/$',
+ views.physicochemistry, name='physicochemistry'),
+ url(r'^about/drug-candidate/$',
+ views.drugCandidate, name='drug-candidate'),
url(r'^query$', views.query, name='query'),
url(r'^query/pharma/$', views.pharma, name='pharma'),
url(r'^query/chemical/$', views.chemical, name='chemical'),
url(r'^tutorials$', views.tutorials, name='tutorials'),
- url(r'^admin-session$', views.adminSession, name='admin-session'),
- url(r'^admin-session/add/(?P<step>.+)/$', ippidb_wizard, name='ippidb_step'),
+ url(r'^admin-session$', views.adminSession, name='admin-session'),
+ url(r'^admin-session/add/(?P<step>.+)/$',
+ ippidb_wizard, name='ippidb_step'),
url(r'^admin-session/add/$', ippidb_wizard, name='ippidb'),
]
diff --git a/ippisite/ippidb/views.py b/ippisite/ippidb/views.py
index ddc731043ce42c509474af7d007d9facf6ff21c0..6994beb62beb3b90abc79aa5b93d344a138f8e0c 100644
--- a/ippisite/ippidb/views.py
+++ b/ippisite/ippidb/views.py
@@ -2,50 +2,62 @@ import ippidb
from django.shortcuts import render
from django.http import HttpResponseRedirect
-from formtools.wizard.views import SessionWizardView,NamedUrlSessionWizardView
+from formtools.wizard.views import SessionWizardView, NamedUrlSessionWizardView
from .forms import IdForm, BibliographyForm, PDBForm, ProteinForm, ProteinDomainComplexTypeForm, ProteinDomainComplexForm, PpiForm, ProteinFormSet, PDBFormSet
from .models import Protein, Bibliography
from .ws import get_pdb_uniprot_mapping
+
def index(request):
return render(request, 'index.html')
+
def about(request):
return render(request, 'about.html')
+
def general(request):
return render(request, 'general.html')
+
def pharmacology(request):
return render(request, 'pharmacology.html')
+
def physicochemistry(request):
return render(request, 'physicochemistry.html')
+
def drugCandidate(request):
return render(request, 'drug-candidate.html')
+
def query(request):
return render(request, 'query.html')
+
def pharma(request):
return render(request, 'pharma.html')
+
def chemical(request):
return render(request, 'chemical.html')
+
def tutorials(request):
return render(request, 'tutorials.html')
+
def adminSession(request):
return render(request, 'admin-session.html')
FORMS = [("IdForm", ippidb.forms.IdForm),
("BibliographyForm", ippidb.forms.BibliographyForm),
("PDBForm", ippidb.forms.PDBFormSet),
- ("ProteinForm",ippidb.forms.ProteinFormSet),
- ("ProteinDomainComplexTypeForm", ippidb.forms.ProteinDomainComplexTypeForm),
+ ("ProteinForm", ippidb.forms.ProteinFormSet),
+ ("ProteinDomainComplexTypeForm",
+ ippidb.forms.ProteinDomainComplexTypeForm),
("ProteinDomainComplexForm", ippidb.forms.ProteinDomainComplexForm),
("PpiForm", ippidb.forms.PpiForm)]
@@ -53,19 +65,21 @@ TEMPLATES = {"IdForm": "IdForm.html",
"BibliographyForm": "BibliographyForm.html",
"PDBForm": "PDBForm.html",
"ProteinForm": "ProteinForm.html",
- "ProteinDomainComplexTypeForm":"ProteinDomainComplexTypeForm.html",
+ "ProteinDomainComplexTypeForm": "ProteinDomainComplexTypeForm.html",
"ProteinDomainComplexForm": "ProteinDomainComplexForm.html",
"PpiForm": "PpiForm.html"}
+
class IppiWizard(NamedUrlSessionWizardView):
+
def get_template_names(self):
return [TEMPLATES[self.steps.current]]
def get_form_instance(self, step):
- if self.steps.current=='BibliographyForm':
+ if self.steps.current == 'BibliographyForm':
pk = self.storage.get_step_data('IdForm').get('pk')
return Bibliography.objects.get(pk=pk)
- if self.steps.current=='ProteinForm':
+ if self.steps.current == 'ProteinForm':
pks = self.storage.get_step_data('PDBForm').get('pks')
return Protein.objects.filter(id__in=pks)
@@ -76,12 +90,12 @@ class IppiWizard(NamedUrlSessionWizardView):
when appropriate
"""
data = super(IppiWizard, self).process_step(form).copy()
- if self.steps.current=='IdForm':
+ if self.steps.current == 'IdForm':
form.instance.autofill()
if self.steps.current in ['IdForm', 'Bibliography']:
form.instance.save()
data['pk'] = form.instance.id
- if self.steps.current=='PDBForm':
+ if self.steps.current == 'PDBForm':
pdb_ids = [form['pdb_id'] for form in form.cleaned_data]
uniprot_ids = []
protein_ids = []
@@ -103,4 +117,3 @@ class IppiWizard(NamedUrlSessionWizardView):
return render(self.request, '/admin-session/add.html', {
'form_data': [form.cleaned_data for form in form_list],
})
-
diff --git a/ippisite/ippidb/ws.py b/ippisite/ippidb/ws.py
index ad6fd40ee8fd118cc998ffa40465371673ad9faf..fa72b16dcb9373f28a123eb17169bcc5baba15c5 100644
--- a/ippisite/ippidb/ws.py
+++ b/ippisite/ippidb/ws.py
@@ -3,12 +3,15 @@ from bioservices.uniprot import UniProt
import xml.etree.ElementTree as ET
import requests
+
def get_pubmed_info(pmid):
eu = EUtils()
r = eu.EFetch('pubmed', pmid, retmode='dict', rettype='abstract')
- article = r['PubmedArticleSet']['PubmedArticle']['MedlineCitation']['Article']
+ article = r['PubmedArticleSet'][
+ 'PubmedArticle']['MedlineCitation']['Article']
title = article['ArticleTitle']
- authors_list = [a['LastName']+ ' ' + a['Initials'] for a in article['AuthorList']['Author']]
+ authors_list = [a['LastName'] + ' ' + a['Initials']
+ for a in article['AuthorList']['Author']]
authors = ', '.join(authors_list)
journal_name = article['Journal']['Title']
biblio_date = article['Journal']['JournalIssue']['PubDate']
@@ -16,60 +19,76 @@ def get_pubmed_info(pmid):
biblio_year = biblio_date['Year']
else:
biblio_year = biblio_date['MedlineDate'][0:3]
- return {'title':title,
- 'journal_name':journal_name,
- 'biblio_year':biblio_year,
+ return {'title': title,
+ 'journal_name': journal_name,
+ 'biblio_year': biblio_year,
'authors_list': authors}
+
def get_epo_info(patent_number):
- resp = requests.get('http://ops.epo.org/3.1/rest-services/published-data/publication/docdb/{}/biblio.json'.format(patent_number))
+ resp = requests.get(
+ 'http://ops.epo.org/3.1/rest-services/published-data/publication/docdb/{}/biblio.json'.format(patent_number))
data = resp.json()
- exchange_doc = data['ops:world-patent-data']['exchange-documents']['exchange-document']
+ exchange_doc = data['ops:world-patent-data'][
+ 'exchange-documents']['exchange-document']
if isinstance(exchange_doc, list):
exchange_doc = exchange_doc[0]
- title = [el['$'] for el in exchange_doc['bibliographic-data']['invention-title'] if el['@lang']=='en']
- authors = [i['inventor-name']['name']['$'] for i in exchange_doc['bibliographic-data']['parties']['inventors']['inventor'] if i['@data-format']=='original']
- biblio_year = [el['date']['$'][:4] for el in exchange_doc['bibliographic-data']['publication-reference']['document-id'] if el['@document-id-type']=='epodoc'][0]
+ title = [el['$']
+ for el in exchange_doc['bibliographic-data']['invention-title'] if el['@lang'] == 'en']
+ authors = [i['inventor-name']['name']['$']
+ for i in exchange_doc['bibliographic-data']['parties']['inventors']['inventor'] if i['@data-format'] == 'original']
+ biblio_year = [el['date']['$'][:4]
+ for el in exchange_doc['bibliographic-data']['publication-reference']['document-id'] if el['@document-id-type'] == 'epodoc'][0]
return {'title': title,
'journal_name': None,
'biblio_year': biblio_year,
'authors_list': authors}
+
def get_uniprot_info(uniprot_id):
uniprot_client = UniProt()
- ns = {'u':'http://uniprot.org/uniprot'}
+ ns = {'u': 'http://uniprot.org/uniprot'}
resp = uniprot_client.retrieve(uniprot_id)
- recommended_name = resp.root.findall('u:entry/u:protein/u:recommendedName/u:fullName', ns)[0].text
- organism = resp.root.findall('u:entry/u:organism/u:dbReference[@type="NCBI Taxonomy"]', ns)[0].attrib['id']
- gene = resp.root.findall('u:entry/u:gene/u:name[@type="primary"]', ns)[0].text
+ recommended_name = resp.root.findall(
+ 'u:entry/u:protein/u:recommendedName/u:fullName', ns)[0].text
+ organism = resp.root.findall(
+ 'u:entry/u:organism/u:dbReference[@type="NCBI Taxonomy"]', ns)[0].attrib['id']
+ gene = resp.root.findall(
+ 'u:entry/u:gene/u:name[@type="primary"]', ns)[0].text
entry_name = resp.root.findall('u:entry/u:name', ns)[0].text
go_els = resp.root.findall('u:entry/u:dbReference[@type="GO"]', ns)
molecular_functions = []
for go_el in go_els:
- term_property_value = go_el.findall('u:property[@type="term"]', ns)[0].attrib['value']
- if term_property_value[0:2]=='F:':
- molecular_functions.append('GO_'+go_el.attrib['id'][3:])
+ term_property_value = go_el.findall(
+ 'u:property[@type="term"]', ns)[0].attrib['value']
+ if term_property_value[0:2] == 'F:':
+ molecular_functions.append('GO_' + go_el.attrib['id'][3:])
return {'recommended_name': recommended_name,
'organism': int(organism),
'gene': gene,
'entry_name': entry_name,
'molecular_functions': molecular_functions
- }
+ }
+
def get_go_info(go_id):
- resp = requests.get('https://www.ebi.ac.uk/ols/api/ontologies/go/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F{}'.format(go_id))
+ resp = requests.get(
+ 'https://www.ebi.ac.uk/ols/api/ontologies/go/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F{}'.format(go_id))
data = resp.json()
label = data['label']
return {'label': label}
+
def get_taxonomy_info(taxonomy_id):
eu = EUtils()
r = eu.EFetch('taxonomy', taxonomy_id, retmode='dict')
scientific_name = r['TaxaSet']['Taxon']['ScientificName']
return {'scientific_name': scientific_name}
+
def get_pfam_info(pfam_acc):
- resp = requests.get('http://pfam.xfam.org/family/{}?output=xml'.format(pfam_acc))
+ resp = requests.get(
+ 'http://pfam.xfam.org/family/{}?output=xml'.format(pfam_acc))
root = ET.fromstring(resp.text)
ns = {'pfam': 'http://pfam.xfam.org/'}
entry = root.findall('pfam:entry', ns)[0]
@@ -79,14 +98,18 @@ def get_pfam_info(pfam_acc):
return {'id': pfam_id,
'description': description}
+
def get_pdb_uniprot_mapping(pdb_id):
- resp = requests.get('https://www.ebi.ac.uk/pdbe/api/mappings/uniprot/{}'.format(pdb_id.lower()))
+ resp = requests.get(
+ 'https://www.ebi.ac.uk/pdbe/api/mappings/uniprot/{}'.format(pdb_id.lower()))
uniprot_ids = list(resp.json()[pdb_id]['UniProt'].keys())
return uniprot_ids
+
def pdb_entry_exists(pdb_id):
""" test if a PDB entry exists using EBI web services """
- resp = requests.get('https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/{}'.format(pdb_id.lower()))
+ resp = requests.get(
+ 'https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/{}'.format(pdb_id.lower()))
# EBI sends back either a 404 or an empty json if the PDB does not exist
if not(resp.ok):
return False