class RegulatoryElementLocus(core.PolymerLocus):
""" Knowledge of a regulatory element of a gene
Attributes:
type (:obj:`RegulatoryElementType`): type of regulatory element
activity (:obj:`ActivityLevel`): cell-type specific activity level
bound_start (:obj:`int`): start coordinate of binding
bound_end (:obj:`int`): end coordinate of binding
motif_features (:obj:`list` of :obj:`ProteinSpeciesType`): proteins that bind to the site
Related attributes:
regulatory_modules (:obj:`list` of :obj:`RegulatoryModule`): regulatory_modules
"""
type = obj_model.EnumAttribute(RegulatoryElementType)
activity = obj_model.EnumAttribute(ActivityLevel)
bound_start = obj_model.PositiveIntegerAttribute()
bound_end = obj_model.PositiveIntegerAttribute()
motif_features = obj_model.ManyToManyAttribute(
'ProteinSpeciesType', related_name='regulatory_elements')
class Meta(obj_model.Model.Meta):
attribute_order = ('id', 'polymer', 'name', 'type', 'activity',
'start', 'end', 'bound_start', 'bound_end',
'motif_features', 'comments', 'references',
'database_references')
class RegulatoryModule(obj_model.Model):
""" Knowledge about regulatory modules
Attributes:
gene (:obj:`GeneLocus`): gene
regulatory_elements (:obj:`list` of :obj:`RegulatoryElementLocus`): regulatory elements
comments (:obj:`str`): comments
references (:obj:`list` of :obj:`Reference`): references
database_references (:obj:`list` of :obj:`DatabaseReference`): database references
"""
gene = obj_model.OneToOneAttribute(GeneLocus,
related_name='regulatory_modules')
regulatory_elements = obj_model.ManyToManyAttribute(
RegulatoryElementLocus, related_name='regulatory_modules')
comments = obj_model.LongStringAttribute()
references = obj_model.ManyToManyAttribute(
core.Reference, related_name='regulatory_modules')
database_references = core.DatabaseReferenceAttribute(
related_name='regulatory_modules')
class Meta(obj_model.Model.Meta):
attribute_order = ('gene', 'regulatory_elements', 'comments',
'references', 'database_references')
class TranscriptionUnitLocus(core.PolymerLocus):
""" Knowledge about an open reading frame
Attributes:
promoter (:obj:`PromoterLocus`): promoter controlling the TU
genes (:obj:`list` of :obj:`GeneLocus`): genes
"""
promoter = obj_model.ManyToOneAttribute('PromoterLocus',
related_name='transcription_units')
genes = obj_model.ManyToManyAttribute('GeneLocus',
related_name='transcription_units')
class Meta(obj_model.Model.Meta):
attribute_order = ('id', 'polymer', 'name', 'strand', 'promoter',
'start', 'end', 'genes', 'comments', 'references',
'database_references')
def get_3_prime(self):
""" Get the 3' coordinate
Returns:
:obj:`int`: 3' coordinate
"""
if self.strand == core.PolymerStrand.positive:
return self.end
else:
return self.start
def get_5_prime(self):
""" Get the 5' coordinate
Returns:
:obj:`int`: 5' coordinate
"""
if self.strand == core.PolymerStrand.positive:
return self.start
else:
return self.end
class RnaSpeciesType(core.PolymerSpeciesType):
""" Knowledge of an RNA species
Attributes:
transcription_units (:obj:`list` of :obj:`TranscriptionUnitLocus`): transcription units
type (:obj:`RnaType`): type
Related attributes:
proteins (:obj:`list` of :obj:`ProteinSpeciesType`): protein(s)
"""
transcription_units = obj_model.ManyToManyAttribute(
'TranscriptionUnitLocus', related_name='rna')
type = obj_model.EnumAttribute(core.RnaType)
class Meta(obj_model.Model.Meta):
attribute_order = ('id', 'name', 'type', 'transcription_units',
'circular', 'double_stranded', 'half_life',
'comments', 'references', 'database_references')
def get_seq(self):
""" Get the sequence
Returns:
:obj:`Bio.Seq.Seq`: sequence
"""
tu_start = self.transcription_units[0].start
tu_end = self.transcription_units[0].end
dna_seq = self.transcription_units[0].polymer.get_subseq(
start=tu_start, end=tu_end)
return dna_seq.transcribe()
def get_empirical_formula(self):
""" Get the empirical formula for an RNA transcript with
* 5' monophosphate
* Deprotonated phosphate oxygens
:math:`N_A * AMP + N_C * CMP + N_G * GMP + N_U * UMP - (L-1) * OH`
Returns:
:obj:`chem.EmpiricalFormula`: empirical formula
"""
seq = self.get_seq()
n_a = seq.count('A')
n_c = seq.count('C')
n_g = seq.count('G')
n_u = seq.count('U')
l = len(seq)
formula = chem.EmpiricalFormula()
formula.C = 10 * n_a + 9 * n_c + 10 * n_g + 9 * n_u
formula.H = 12 * n_a + 12 * n_c + 12 * n_g + 11 * n_u - (l - 1)
formula.N = 5 * n_a + 3 * n_c + 5 * n_g + 2 * n_u
formula.O = 7 * n_a + 8 * n_c + 8 * n_g + 9 * n_u - (l - 1)
formula.P = n_a + n_c + n_g + n_u
return formula
def get_charge(self):
""" Get the charge for a transcript with
* 5' monophosphate
* Deprotonated phosphate oxygens
:math:`-L - 1`
Returns:
:obj:`int`: charge
"""
return -self.get_len() - 1
def get_mol_wt(self):
""" Get the molecular weight for a transcript with
* 5' monophosphate
* Deprotonated phosphate oxygens
Returns:
:obj:`float`: molecular weight (Da)
"""
return self.get_empirical_formula().get_molecular_weight()
class TranscriptSpeciesType(core.PolymerSpeciesType):
""" Knowledge of a transcript (spliced RNA) species
Attributes:
rna (:obj:`RnaSpeciesType`): transcribed RNA species before splicing
exons (:obj:`list` of :obj:`ExonLocus`): exons
Related attributes:
protein (:obj:`ProteinSpeciesType`): protein
"""
rna = obj_model.ManyToOneAttribute(PreRnaSpeciesType,
related_name='transcripts')
exons = obj_model.ManyToManyAttribute(ExonLocus,
related_name='transcripts')
class Meta(obj_model.Model.Meta):
attribute_order = ('id', 'name', 'rna', 'exons', 'half_life',
'comments', 'references', 'database_references')
def get_seq(self):
""" Get the 5' to 3' sequence
Returns:
:obj:`Bio.Seq.Seq`: sequence
"""
dna_seq = ''
for exon in self.exons:
dna_seq += self.rna.gene.polymer.get_subseq(start=exon.start,
end=exon.end)
if self.rna.gene.strand == core.PolymerStrand.negative:
dna_seq = dna_seq.reverse_complement()
return dna_seq.transcribe()
def get_empirical_formula(self):
""" Get the empirical formula for a transcript (spliced RNA) species with
* 5' monophosphate
* Deprotonated phosphate oxygens
:math:`N_A * AMP + N_C * CMP + N_G * GMP + N_U * UMP - (L-1) * OH`
Returns:
:obj:`chem.EmpiricalFormula`: empirical formula
"""
seq = self.get_seq()
n_a = seq.count('A')
n_c = seq.count('C')
n_g = seq.count('G')
n_u = seq.count('U')
l = len(seq)
formula = chem.EmpiricalFormula()
formula.C = 10 * n_a + 9 * n_c + 10 * n_g + 9 * n_u
formula.H = 12 * n_a + 12 * n_c + 12 * n_g + 11 * n_u - (l - 1)
formula.N = 5 * n_a + 3 * n_c + 5 * n_g + 2 * n_u
formula.O = 7 * n_a + 8 * n_c + 8 * n_g + 9 * n_u - (l - 1)
formula.P = n_a + n_c + n_g + n_u
return formula
def get_charge(self):
""" Get the charge for a transcript (spliced RNA) species with
* 5' monophosphate
* Deprotonated phosphate oxygens
:math:`-L - 1`
Returns:
:obj:`int`: charge
"""
return -self.get_len() - 1
def get_mol_wt(self):
""" Get the molecular weight for a transcript (spliced RNA) species with
* 5' monophosphate
* Deprotonated phosphate oxygens
Returns:
:obj:`float`: molecular weight (Da)
"""
return self.get_empirical_formula().get_molecular_weight()