class PubChemData(EntityBase):
__tablename__ = 'pubchem_data'
pubchem_id = Column(String(20), primary_key=True)
names = Column(ARRAY(TEXT))
mass = Column(Float)
#weight = Column(Float)
monoisotopic_mass = Column(Float)
logp = Column(Float)
# structure info -
smiles = Column(ARRAY(TEXT))
inchi = Column(TEXT)
inchikey = Column(String(27))
formula = Column(String(256))
chebi_id = Column(String(20), ForeignKey('chebi_data.chebi_id'))
kegg_id = Column(String(20), ForeignKey('kegg_data.kegg_id'))
hmdb_id = Column(String(20), ForeignKey('hmdb_data.hmdb_id'))
chemspider_id = Column(String(20))
ref_etc = Column(JSON_GEN())
def __init__(self, **kwargs):
pass
class KeggData(EntityBase):
__tablename__ = 'kegg_data'
# Primary Ids
kegg_id = Column(String(20), primary_key=True)
# Reference Ids
chebi_id = Column(
String(20)) #ForeignKey('chebi_data.chebi_id', ondelete='SET NULL'))
lipidmaps_id = Column(String(
20)) #ForeignKey('lipidmaps_data.lipidmaps_id', ondelete='SET NULL'))
pubchem_id = Column(String(
20)) #ForeignKey('pubchem_data.pubchem_id', ondelete='SET NULL'))
cas_id = Column(String(20))
ref_etc = Column(JSON_GEN()) # Extra ref Refs
pdb_id = Column(String(24))
# Shared metadata
names = Column(ARRAY(Text))
monoisotopic_mass = Column(Float)
mass = Column(Float)
# Structure
formula = Column(String(256))
# Other Fun Facts
comments = Column(Text)
def __init__(self, **kwargs):
self.kegg_id = kwargs.get('kegg_id')
self.names = kwargs.get('names')
self.monoisotopic_mass = kwargs.get('monoisotopic_mass')
self.mass = kwargs.get('mass')
self.comments = kwargs.get('comments')
self.formula = kwargs.get('formula')
self.cas_id = kwargs.get('cas_id')
self.kegg_id = kwargs.get('kegg_id')
self.chebi_id = kwargs.get('chebi_id')
self.lipidmaps_id = kwargs.get('lipidmaps_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.ref_etc = kwargs.get('ref_etc')
if isinstance(self.monoisotopic_mass, str):
if not self.monoisotopic_mass:
self.monoisotopic_mass = None
else:
self.monoisotopic_mass = float(self.monoisotopic_mass)
if isinstance(self.mass, str):
if not self.mass:
self.mass = None
else:
self.mass = float(self.mass)
class KeggData(EntityBase):
__tablename__ = 'kegg_data'
kegg_id = Column(String(20), primary_key=True)
names = Column(ARRAY(TEXT))
exact_mass = Column(Float)
mol_weight = Column(Float)
comments = Column(TEXT)
# structure info -
formula = Column(String(256))
# RefIds - from database_accession.tsv
#cas_id = Column(String(20))
chebi_id = Column(String(20), ForeignKey('chebi_data.chebi_id'))
lipidmaps_id = Column(String(20),
ForeignKey('lipidmaps_data.lipidmaps_id'))
pubchem_id = Column(String(20), ForeignKey('pubchem_data.pubchem_id'))
ref_etc = Column(JSON_GEN())
def __init__(self, **kwargs):
self.kegg_id = kwargs.get('kegg_id')
self.names = kwargs.get('names')
self.exact_mass = kwargs.get('exact_mass')
self.mol_weight = kwargs.get('mol_weight')
self.comments = kwargs.get('comments')
self.formula = kwargs.get('formula')
self.cas_id = kwargs.get('cas_id')
self.kegg_id = kwargs.get('kegg_id')
self.chebi_id = kwargs.get('chebi_id')
self.lipidmaps_id = kwargs.get('lipidmaps_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.ref_etc = kwargs.get('ref_etc')
if isinstance(self.mol_weight, str):
if not self.mol_weight:
self.mol_weight = None
else:
self.mol_weight = float(self.mol_weight)
if isinstance(self.exact_mass, str):
if not self.exact_mass:
self.exact_mass = None
else:
self.exact_mass = float(self.exact_mass)
class CHEBIData(EntityBase):
__tablename__ = 'chebi_data'
# Metadata - from compounds.tsv
chebi_id = Column(String(20), primary_key=True)
chebi_id_alt = Column(ARRAY(String(20)))
#chebi_name = Column(TEXT)
names = Column(ARRAY(TEXT))
description = Column(TEXT)
quality = Column(Integer)
# Fun facts - from chemical_data.tsv
charge = Column(Float)
mass = Column(Float)
monoisotopic_mass = Column(Float)
# structure info -
smiles = Column(TEXT)
inchi = Column(TEXT)
inchikey = Column(String(27))
formula = Column(String(256))
# from comments.tsv
comments = Column(TEXT)
# RefIds - from database_accession.tsv
#cas_id = Column(String(20))
kegg_id = Column(String(20), ForeignKey('kegg_data.kegg_id'))
hmdb_id = Column(String(20), ForeignKey('hmdb_data.hmdb_id'))
lipidmaps_id = Column(String(20),
ForeignKey('lipidmaps_data.lipidmaps_id'))
pubchem_id = Column(String(20), ForeignKey('pubchem_data.pubchem_id'))
ref_etc = Column(JSON_GEN())
def __init__(self, **kwargs):
self.chebi_id = kwargs.get('chebi_id')
self.chebi_id_alt = kwargs.get('chebi_id_alt')
self.chebi_name = kwargs.get('chebi_name')
self.names = kwargs.get('names')
self.description = kwargs.get('description')
self.quality = kwargs.get('quality')
self.charge = kwargs.get('charge')
self.mass = kwargs.get('mass')
self.monoisotopic_mass = kwargs.get('monoisotopic_mass')
self.smiles = kwargs.get('smiles')
self.inchi = kwargs.get('inchi')
self.inchikey = kwargs.get('inchikey')
self.formula = kwargs.get('formula')
self.comments = kwargs.get('comments')
#self.cas_id = kwargs.get('cas_id')
self.kegg_id = kwargs.get('kegg_id')
self.hmdb_id = kwargs.get('hmdb_id')
self.lipidmaps_id = kwargs.get('lipidmaps_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.ref_etc = kwargs.get('ref_etc')
if isinstance(self.monoisotopic_mass, str):
if not self.monoisotopic_mass:
self.monoisotopic_mass = None
else:
self.monoisotopic_mass = float(self.monoisotopic_mass)
if isinstance(self.mass, str):
if not self.mass:
self.mass = None
else:
self.mass = float(self.mass)
if isinstance(self.charge, str):
if not self.charge:
self.charge = None
else:
self.charge = float(self.charge)
if isinstance(self.quality, str):
if not self.quality:
self.quality = None
else:
self.quality = int(self.quality)
class ChEBIData(EntityBase):
__tablename__ = 'chebi_data'
# Primary Ids
chebi_id = Column(String(20), primary_key=True)
# Reference Ids
# from database_accession.tsv # todo: add Foreign Keys!
kegg_id = Column(
String(24)) #ForeignKey('kegg_data.kegg_id', ondelete='SET NULL'))
hmdb_id = Column(
String(24)) #ForeignKey('hmdb_data.hmdb_id', ondelete='SET NULL'))
lipidmaps_id = Column(String(
32)) #ForeignKey('lipidmaps_data.lipidmaps_id', ondelete='SET NULL'))
pubchem_id = Column(String(
24)) #ForeignKey('pubchem_data.pubchem_id', ondelete='SET NULL'))
cas_id = Column(String(24))
ref_etc = Column(JSON_GEN()) # Extra ref Refs
chemspider_id = Column(String(24))
metlin_id = Column(String(24))
pubchem_sub_id = Column(String(24))
wiki_id = Column(String(256))
drugbank_id = Column(String(24))
pdb_id = Column(String(24))
#pubmed_id = Column(String(24))
uniprot_id = Column(String(24))
# Shared metadata
names = Column(ARRAY(Text))
description = Column(Text)
charge = Column(Float) # from chemical_data.tsv
mass = Column(Float)
monoisotopic_mass = Column(Float)
# Structure
smiles = Column(Text)
inchi = Column(Text)
inchikey = Column(Text)
formula = Column(Text)
# Other Fun Facts
quality = Column(Integer) # from compounds.tsv
comments = Column(Text) # from comments.tsv
def __init__(self, **kwargs):
self.chebi_id = kwargs.get('chebi_id')
self.kegg_id = kwargs.get('kegg_id')
self.hmdb_id = kwargs.get('hmdb_id')
self.lipidmaps_id = kwargs.get('lipidmaps_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.cas_id = kwargs.get('cas_id')
self.ref_etc = kwargs.get('ref_etc')
self.chemspider_id = kwargs.get('chemspider_id')
self.metlin_id = kwargs.get('metlin_id')
self.pubchem_sub_id = kwargs.get('pubchem_sub_id')
self.wiki_id = kwargs.get('wiki_id')
self.drugbank_id = kwargs.get('drugbank_id')
self.pdb_id = kwargs.get('pdb_id')
#self.pubmed_id = kwargs.get('pubmed_id')
self.uniprot_id = kwargs.get('uniprot_id')
self.names = kwargs.get('names')
self.description = kwargs.get('description')
self.charge = kwargs.get('charge')
self.mass = kwargs.get('mass')
self.monoisotopic_mass = kwargs.get('monoisotopic_mass')
self.smiles = kwargs.get('smiles')
self.inchi = kwargs.get('inchi')
self.inchikey = kwargs.get('inchikey')
self.formula = kwargs.get('formula')
self.quality = kwargs.get('quality')
self.comments = kwargs.get('comments')
if isinstance(self.monoisotopic_mass, str):
if not self.monoisotopic_mass:
self.monoisotopic_mass = None
else:
self.monoisotopic_mass = float(self.monoisotopic_mass)
if isinstance(self.mass, str):
if not self.mass:
self.mass = None
else:
self.mass = float(self.mass)
if isinstance(self.charge, str):
if not self.charge:
self.charge = None
else:
self.charge = float(self.charge)
if isinstance(self.quality, str):
if not self.quality:
self.quality = None
else:
self.quality = int(self.quality)
class LipidMapsData(EntityBase):
__tablename__ = 'lipidmaps_data'
# Primary Ids
lipidmaps_id = Column(String(20), primary_key=True)
# Reference Ids
kegg_id = Column(
String(20)) # ForeignKey('kegg_data.kegg_id', ondelete='SET NULL'))
hmdb_id = Column(
String(20)) # ForeignKey('hmdb_data.hmdb_id', ondelete='SET NULL'))
chebi_id = Column(
String(20)) # ForeignKey('chebi_data.chebi_id', ondelete='SET NULL'))
pubchem_id = Column(String(
20)) # ForeignKey('pubchem_data.pubchem_id', ondelete='SET NULL'))
lipidbank_id = Column(String(20))
cas_id = Column(String(20))
ref_etc = Column(JSON_GEN()) # Extra ref Refs
chemspider_id = Column(String(24))
metlin_id = Column(String(24))
pubchem_sub_id = Column(String(24))
wiki_id = Column(String(256))
drugbank_id = Column(String(24))
pdb_id = Column(String(24))
pubmed_id = Column(String(24))
# Shared metadata
names = Column(ARRAY(Text))
mass = Column(Float)
# Structure
smiles = Column(Text)
inchi = Column(Text)
inchikey = Column(Text)
formula = Column(Text)
# Other Fun Facts
category = Column(String(32))
main_class = Column(String(64))
sub_class = Column(String(128))
lvl4_class = Column(String(128))
def __init__(self, **kwargs):
self.lipidmaps_id = kwargs.get('lipidmaps_id')
self.kegg_id = kwargs.get('kegg_id')
self.hmdb_id = kwargs.get('hmdb_id')
self.chebi_id = kwargs.get('chebi_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.lipidbank_id = kwargs.get('lipidbank_id')
self.cas_id = kwargs.get('cas_id')
self.ref_etc = kwargs.get('ref_etc')
self.chemspider_id = kwargs.get('chemspider_id')
self.metlin_id = kwargs.get('metlin_id')
self.pubchem_sub_id = kwargs.get('pubchem_sub_id')
self.wiki_id = kwargs.get('wiki_id')
self.drugbank_id = kwargs.get('drugbank_id')
self.pdb_id = kwargs.get('pdb_id')
self.pubmed_id = kwargs.get('pubmed_id')
self.names = kwargs.get('names')
self.mass = kwargs.get('mass')
self.smiles = kwargs.get('smiles')
self.inchi = kwargs.get('inchi')
self.inchikey = kwargs.get('inchikey')
self.formula = kwargs.get('formula')
self.category = kwargs.get('category')
self.main_class = kwargs.get('main_class')
self.sub_class = kwargs.get('sub_class')
self.lvl4_class = kwargs.get('lvl4_class')
if isinstance(self.mass, str):
if not self.mass:
self.mass = None
else:
self.mass = float(self.mass)
class UserMixin(FlaskUserMixin):
# login
uid = Column(GUID(), primary_key=True)
username = Column(String(32))
# profile
admin = Column(Boolean(), default=False)
face = Column(JSON_GEN())
points = Column(SmallInteger)
last_active = Column(TIMESTAMP,
server_default=func.now(),
onupdate=func.current_timestamp())
# oauth
access_token = Column(String(255), unique=True, nullable=False)
refresh_token = Column(String(255), index=True)
issued_at = Column(Integer, nullable=False, default=lambda: int(time()))
expires_in = Column(Integer, nullable=False, default=0)
def get_id(self):
return str(self.uid) if self.uid else None
@property
def expires_at(self):
if self.issued_at is None or self.expires_in is None:
# bugfix for records that have no expiry
return 0
return self.issued_at + self.expires_in
@property
def is_active(self):
return True
@property
def is_authenticated(self):
return self.uid is not None
@property
def is_anonymous(self):
return False
def get_user_id(self):
# used for oauth2
return self.uid
def __hash__(self):
return hash(self.uid)
def __repr__(self):
return "{}({}..)".format(self.username, str(self.uid)[0:4])
def update_token(self, th):
self.access_token = th.access_token
self.issued_at = th.issued_at
self.expires_in = th.expires_in
if hasattr(th, 'refresh_token'):
self.refresh_token = th.refresh_token
def update_user(self, user):
if self.access_token != user.access_token and user.access_token is not None:
self.update_token(user)
if hasattr(user, 'refresh_token'):
self.refresh_token = user.refresh_token
if user.username != self.username and user.username is not None:
self.username = user.username
if user.points != self.points and user.points is not None:
self.points = user.points
if user.face != self.face and user.face is not None:
self.face = user.face
if user.admin != self.admin and user.admin is not None:
self.admin = user.admin
if user.last_active != self.last_active and user.last_active is not None:
self.last_active = user.last_active
class PubChemData(EntityBase):
__tablename__ = 'pubchem_data'
# Primary Ids
pubchem_id = Column(String(20), primary_key=True)
#pubchem_sub_id = Column(String(24)) #ForeignKey('pubchem_substrate_data.pubchem_id', ondelete='SET NULL'))
# Reference Ids
chebi_id = Column(
String(24)) #ForeignKey('chebi_data.chebi_id', ondelete='SET NULL'))
kegg_id = Column(
String(24)) #ForeignKey('kegg_data.kegg_id', ondelete='SET NULL'))
hmdb_id = Column(
String(24)) #ForeignKey('hmdb_data.hmdb_id', ondelete='SET NULL'))
cas_id = Column(String(24))
ref_etc = Column(JSON_GEN()) # Extra ref Refs
chemspider_id = Column(String(24))
#metlin_id = Column(String(24))
#wiki_id = Column(String(24))
#drugbank_id = Column(String(24))
#pdb_id = Column(String(24))
#pubmed_id = Column(String(24))
# Shared metadata
names = Column(ARRAY(Text))
mass = Column(Float)
monoisotopic_mass = Column(Float)
# Structure
smiles = Column(ARRAY(Text))
inchi = Column(Text)
inchikey = Column(String(27))
formula = Column(String(256))
# Other Fun Facts
logp = Column(Float)
def __init__(self, **kwargs):
self.pubchem_id = kwargs.get('pubchem_id')
self.pubchem_sub_id = kwargs.get('pubchem_sub_id')
self.chebi_id = kwargs.get('chebi_id')
self.kegg_id = kwargs.get('kegg_id')
self.hmdb_id = kwargs.get('hmdb_id')
self.cas_id = kwargs.get('cas_id')
self.ref_etc = kwargs.get('ref_etc')
self.chemspider_id = kwargs.get('chemspider_id')
self.metlin_id = kwargs.get('metlin_id')
self.wiki_id = kwargs.get('wiki_id')
self.drugbank_id = kwargs.get('drugbank_id')
self.pdb_id = kwargs.get('pdb_id')
self.pubmed_id = kwargs.get('pubmed_id')
self.names = kwargs.get('names')
self.mass = kwargs.get('mass')
self.weight = kwargs.get('weight')
self.monoisotopic_mass = kwargs.get('monoisotopic_mass')
self.smiles = kwargs.get('smiles')
self.inchi = kwargs.get('inchi')
self.inchikey = kwargs.get('inchikey')
self.formula = kwargs.get('formula')
self.logp = kwargs.get('logp')
print("TODO: pubchem handle synonyms and description")
class HMDBData(EntityBase):
__tablename__ = 'hmdb_data'
# Primary Ids
hmdb_id = Column(String(20), primary_key=True)
# Reference Ids
kegg_id = Column(
String(24)) #ForeignKey('kegg_data.kegg_id', ondelete='SET NULL'))
pubchem_id = Column(String(
24)) #ForeignKey('pubchem_data.pubchem_id'), ondelete='SET NULL')
chebi_id = Column(
String(24)) #ForeignKey('chebi_data.chebi_id'), ondelete='SET NULL')
cas_id = Column(String(24))
ref_etc = Column(JSON_GEN()) # Extra ref Refs
chemspider_id = Column(String(24))
metlin_id = Column(String(24))
pubchem_sub_id = Column(String(24))
wiki_id = Column(String(256))
drugbank_id = Column(String(24))
pdb_id = Column(String(24))
pubmed_id = Column(String(24))
# Shared metadata
names = Column(ARRAY(Text))
description = Column(Text)
avg_mol_weight = Column(Float)
monoisotopic_mol_weight = Column(Float)
# Structure
formula = Column(Text)
smiles = Column(Text)
inchi = Column(Text)
inchikey = Column(Text)
# Other Fun Facts
state = Column(String(32))
# biofluid_locations = Column(ARRAY(String(64)))
# tissue_locations = Column(ARRAY(String(64)))
#
# # Complex data
# taxonomy = Column(JSON_GEN)
# ontology = Column(JSON_GEN)
# proteins = Column(JSON_GEN)
# diseases = Column(JSON_GEN)
# synthesis_reference = Column(TEXT)
def __init__(self, **kwargs):
self.hmdb_id = kwargs.get('hmdb_id')
self.hmdb_id_alt = kwargs.get('hmdb_id_alt')
self.kegg_id = kwargs.get('kegg_id')
self.pubchem_id = kwargs.get('pubchem_id')
self.chebi_id = kwargs.get('chebi_id')
self.cas_id = kwargs.get('cas_id')
self.ref_etc = kwargs.get('ref_etc')
self.chemspider_id = kwargs.get('chemspider_id')
self.metlin_id = kwargs.get('metlin_id')
self.pubchem_sub_id = kwargs.get('pubchem_sub_id')
self.wiki_id = kwargs.get('wiki_id')
self.drugbank_id = kwargs.get('drugbank_id')
self.pdb_id = kwargs.get('pdb_id')
self.pubmed_id = kwargs.get('pubmed_id')
self.names = kwargs.get('names')
self.description = kwargs.get('description')
self.avg_mol_weight = kwargs.get('avg_mol_weight')
self.monoisotopic_mol_weight = kwargs.get('monoisotopic_mol_weight')
self.formula = kwargs.get('formula')
self.smiles = kwargs.get('smiles')
self.inchi = kwargs.get('inchi')
self.inchikey = kwargs.get('inchikey')
self.state = kwargs.get('state')
if isinstance(self.avg_mol_weight, str):
if not self.avg_mol_weight:
self.avg_mol_weight = None
else:
self.avg_mol_weight = str(self.avg_mol_weight)
if isinstance(self.monoisotopic_mol_weight, str):
if not self.monoisotopic_mol_weight:
self.monoisotopic_mol_weight = None
else:
self.monoisotopic_mol_weight = str(
self.monoisotopic_mol_weight)