class GeneLocus(core.PolymerLocus):
""" Knowledge of a gene
Attributes:
symbol (:obj:`str`): symbol
Related attributes:
proteins (:obj:`list` of :obj:`ProteinSpeciesType`): protein
"""
symbol = obj_tables.StringAttribute()
start = obj_tables.IntegerAttribute()
end = obj_tables.IntegerAttribute()
is_essential = obj_tables.BooleanAttribute()
proteins = obj_tables.OneToOneAttribute(ProteinSpeciesType,
related_name='gene')
homologs = obj_tables.LongStringAttribute()
evidence = obj_tables.OneToManyAttribute(core.Evidence,
related_name='genes')
cog = obj_tables.sci.onto.OntoTermAttribute(
kbOnt, terms=kbOnt['WC:COG'].subclasses(), none=True)
class Meta(obj_tables.Model.Meta):
verbose_name = 'Gene'
verbose_name_plural = 'Genes'
attribute_order = ('id', 'name', 'synonyms', 'symbol', 'polymer',
'start', 'end', 'cog', 'homologs', 'is_essential',
'proteins', 'evidence', 'identifiers', 'references',
'comments')
class Company(obj_tables.Model):
name = obj_tables.StringAttribute(primary=True, unique=True, verbose_name='Name')
url = obj_tables.UrlAttribute(verbose_name='URL')
address = obj_tables.OneToOneAttribute('Address', related_name='company', verbose_name='Address')
class Meta(obj_tables.Model.Meta):
table_format = obj_tables.TableFormat.column
attribute_order = (
'name',
'url',
'address',
)
verbose_name = 'Company'
verbose_name_plural = 'Companies'
class Gene(obj_tables.Model):
id = obj_tables.StringAttribute(primary=True,
unique=True,
verbose_name='Id')
symbol = obj_tables.StringAttribute(verbose_name='Symbol')
location = obj_tables.OneToOneAttribute('Location',
related_name='genes',
verbose_name='Location')
class Meta(obj_tables.Model.Meta):
table_format = obj_tables.TableFormat.row
attribute_order = (
'id',
'symbol',
'location',
)
verbose_name = 'Gene'
verbose_name_plural = 'Genes'
class Transcript(obj_tables.Model):
id = obj_tables.StringAttribute(primary=True,
unique=True,
verbose_name='Id')
gene = obj_tables.ManyToOneAttribute('Gene',
related_name='transcripts',
verbose_name='Gene')
location = obj_tables.OneToOneAttribute('Location',
related_name='transcripts',
verbose_name='Location')
class Meta(obj_tables.Model.Meta):
table_format = obj_tables.TableFormat.row
attribute_order = (
'id',
'gene',
'location',
)
verbose_name = 'Transcript'
verbose_name_plural = 'Transcripts'
class Person(obj_tables.Model):
name = obj_tables.StringAttribute(primary=True, unique=True, verbose_name='Name')
type = obj_tables.EnumAttribute(['family', 'friend', 'business'], verbose_name='Type')
company = obj_tables.ManyToOneAttribute('Company', related_name='employees', verbose_name='Company')
email_address = obj_tables.EmailAttribute(verbose_name='Email address')
phone_number = obj_tables.StringAttribute(verbose_name='Phone number')
address = obj_tables.OneToOneAttribute('Address', related_name='person', verbose_name='Address')
class Meta(obj_tables.Model.Meta):
table_format = obj_tables.TableFormat.row
attribute_order = (
'name',
'type',
'company',
'email_address',
'phone_number',
'address',
)
verbose_name = 'Person'
verbose_name_plural = 'People'
class ProteinSpeciesType(core.PolymerSpeciesType):
""" Knowledge of a protein monomer
Attributes:
uniprot (:obj:`str`): uniprot id
transcript (:obj:`TranscriptSpeciesType`): transcript
coding_regions (:obj:`list` of :obj:`LocusAttribute`): CDS coordinates
Related attributes:
transcription_factor_regulation (:obj:`list` of `TranscriptionFactorRegulation`): transcription factor regulation
ptm_sites (:obj:list` of `PtmSite`): protein modification sites
"""
uniprot = obj_tables.StringAttribute()
transcript = obj_tables.OneToOneAttribute(TranscriptSpeciesType,
related_name='protein')
coding_regions = LocusAttribute(related_name='proteins')
class Meta(obj_tables.Model.Meta):
verbose_name = 'Protein'
verbose_name_plural = 'Proteins'
attribute_order = ('id', 'name', 'uniprot', 'transcript',
'coding_regions', 'identifiers', 'references',
'comments')
def get_seq(self, table=1, cds=True):
""" Get the 5' to 3' sequence
Args:
table (:obj:`int`, optional): NCBI identifier for translation table
(default = standard table)
cds (:obj:`bool`, optional): True indicates the sequence is a complete CDS
Returns:
:obj:`Bio.Seq.Seq`: sequence
"""
ordered_cds = sorted(self.coding_regions, key=lambda x: x.start)
dna_seq = self.transcript.gene.polymer.get_subseq(
start=ordered_cds[0].start, end=ordered_cds[-1].end)
adjusted_cds = [(i.start - ordered_cds[0].start, i.end - ordered_cds[0].start + 1) \
for i in ordered_cds]
spliced_dna_seq = Bio.Seq.Seq('', alphabet=Bio.Alphabet.DNAAlphabet())
for i in adjusted_cds:
spliced_dna_seq += dna_seq[i[0]:i[1]]
if self.transcript.gene.strand == core.PolymerStrand.negative:
spliced_dna_seq = spliced_dna_seq.reverse_complement()
return spliced_dna_seq.transcribe().translate(table=table, cds=cds)
def get_seq_and_start_codon(self, table=1, cds=True):
""" Get the 5' to 3' amino acid sequence and the start codon
Args:
table (:obj:`int`, optional): NCBI identifier for translation table
(default = standard table)
cds (:obj:`bool`, optional): True indicates the sequence is a complete CDS
Returns:
:obj:`Bio.Seq.Seq`: coding RNA sequence that will be translated
:obj:`Bio.Seq.Seq`: amino acid sequence
:obj:`Bio.Seq.Seq`: start codon
"""
ordered_cds = sorted(self.coding_regions, key=lambda x: x.start)
dna_seq = self.transcript.gene.polymer.get_subseq(
start=ordered_cds[0].start, end=ordered_cds[-1].end)
adjusted_cds = [(i.start - ordered_cds[0].start, i.end - ordered_cds[0].start + 1) \
for i in ordered_cds]
spliced_dna_seq = Bio.Seq.Seq('', alphabet=Bio.Alphabet.DNAAlphabet())
for i in adjusted_cds:
spliced_dna_seq += dna_seq[i[0]:i[1]]
if self.transcript.gene.strand == core.PolymerStrand.negative:
spliced_dna_seq = spliced_dna_seq.reverse_complement()
coding_rna_seq = spliced_dna_seq.transcribe()
protein_seq = coding_rna_seq.translate(table=table, cds=cds)
start_codon_index = 0
for aa_seq in protein_seq:
if aa_seq == '*':
start_codon_index += 3
else:
break
start_codon = coding_rna_seq[start_codon_index:start_codon_index + 3]
return coding_rna_seq, protein_seq, start_codon
def get_empirical_formula(self, table=1, cds=True, seq_input=None):
""" Get the empirical formula
Args:
table (:obj:`int`, optional): NCBI identifier for translation table
(default = standard table)
cds (:obj:`bool`, optional): True indicates the sequence is a complete CDS
seq_input (:obj:`Bio.Seq.Seq`, optional): if provided, the method will use it
instead of reading from fasta file to reduce IO operation
Returns:
:obj:`chem.EmpiricalFormula`: empirical formula
"""
if seq_input:
seq = seq_input
else:
seq = self.get_seq(table=table, cds=cds)
l = len(seq) - seq.count('*')
n_a = seq.count('A') # Ala: Alanine (C3 H7 N O2)
n_r = seq.count('R') # Arg: Arginine (C6 H14 N4 O2)
n_n = seq.count('N') # Asn: Asparagine (C4 H8 N2 O3)
n_d = seq.count('D') # Asp: Aspartic acid (C4 H7 N O4)
n_c = seq.count('C') # Cys: Cysteine (C3 H7 N O2 S)
n_q = seq.count('Q') # Gln: Glutamine (C5 H10 N2 O3)
n_e = seq.count('E') # Glu: Glutamic acid (C5 H9 N O4)
n_g = seq.count('G') # Gly: Glycine (C2 H5 N O2)
n_h = seq.count('H') # His: Histidine (C6 H9 N3 O2)
n_i = seq.count('I') # Ile: Isoleucine (C6 H13 N O2)
n_l = seq.count('L') # Leu: Leucine (C6 H13 N O2)
n_k = seq.count('K') # Lys: Lysine (C6 H14 N2 O2)
n_m = seq.count('M') # Met: Methionine (C5 H11 N O2 S)
n_f = seq.count('F') # Phe: Phenylalanine (C9 H11 N O2)
n_p = seq.count('P') # Pro: Proline (C5 H9 N O2)
n_s = seq.count('S') # Ser: Serine (C3 H7 N O3)
n_t = seq.count('T') # Thr: Threonine (C4 H9 N O3)
n_w = seq.count('W') # Trp: Tryptophan (C11 H12 N2 O2)
n_y = seq.count('Y') # Tyr: Tyrosine (C9 H11 N O3)
n_v = seq.count('V') # Val: Valine (C5 H11 N O2)
n_u = seq.count('U') # Selcys: Selenocysteine (C3 H7 N O2 Se)
formula = chem.EmpiricalFormula()
formula.C = 3 * n_a + 6 * n_r + 4 * n_n + 4 * n_d + 3 * n_c + \
5 * n_q + 5 * n_e + 2 * n_g + 6 * n_h + 6 * n_i + \
6 * n_l + 6 * n_k + 5 * n_m + 9 * n_f + 5 * n_p + \
3 * n_s + 4 * n_t + 11 * n_w + 9 * n_y + 5 * n_v + \
3 * n_u
formula.H = 7 * n_a + 14 * n_r + 8 * n_n + 7 * n_d + 7 * n_c + \
10 * n_q + 9 * n_e + 5 * n_g + 9 * n_h + 13 * n_i + \
13 * n_l + 14 * n_k + 11 * n_m + 11 * n_f + 9 * n_p + \
7 * n_s + 9 * n_t + 12 * n_w + 11 * n_y + 11 * n_v + \
7 * n_u - 2 * (l - 1)
formula.N = 1 * n_a + 4 * n_r + 2 * n_n + 1 * n_d + 1 * n_c + \
2 * n_q + 1 * n_e + 1 * n_g + 3 * n_h + 1 * n_i + \
1 * n_l + 2 * n_k + 1 * n_m + 1 * n_f + 1 * n_p + \
1 * n_s + 1 * n_t + 2 * n_w + 1 * n_y + 1 * n_v + \
1 * n_u
formula.O = 2 * n_a + 2 * n_r + 3 * n_n + 4 * n_d + 2 * n_c + \
3 * n_q + 4 * n_e + 2 * n_g + 2 * n_h + 2 * n_i + \
2 * n_l + 2 * n_k + 2 * n_m + 2 * n_f + 2 * n_p + \
3 * n_s + 3 * n_t + 2 * n_w + 3 * n_y + 2 * n_v + \
2 * n_u - (l - 1)
formula.S = n_c + n_m
formula.Se = n_u
return formula
def get_charge(self, table=1, cds=True, seq_input=None):
""" Get the charge at physiological pH
Args:
table (:obj:`int`, optional): NCBI identifier for translation table
(default = standard table)
cds (:obj:`bool`, optional): True indicates the sequence is a complete CDS
seq_input (:obj:`Bio.Seq.Seq`, optional): if provided, the method will use it
instead of reading from fasta file to reduce IO operation
Returns:
:obj:`int`: charge
"""
if seq_input:
seq = seq_input
else:
seq = self.get_seq(table=table, cds=cds)
n_r = seq.count('R')
n_h = seq.count('H')
n_k = seq.count('K')
n_d = seq.count('D')
n_e = seq.count('E')
return (n_r + n_h + n_k) - (n_d + n_e)
def get_mol_wt(self, table=1, cds=True, seq_input=None):
""" Get the molecular weight
Args:
table (:obj:`int`, optional): NCBI identifier for translation table
(default = standard table)
cds (:obj:`bool`, optional): True indicates the sequence is a complete CDS
seq_input (:obj:`Bio.Seq.Seq`, optional): if provided, the method will use it
instead of reading from fasta file to reduce IO operation
Returns:
:obj:`float`: molecular weight
"""
if seq_input:
return self.get_empirical_formula(
table=table, cds=cds,
seq_input=seq_input).get_molecular_weight()
else:
return self.get_empirical_formula(table=table,
cds=cds).get_molecular_weight()