def from_TriTrypDB(name, gff, fasta, tax, tmp_dir=None):
genome = {x.id: x for x in sp(fasta)}
from BCBio import GFF
import re
annotation = list(GFF.parse(gff, base_dict=genome))
contig = annotation[0]
seqCol = BioDocFactory.create_genome(name, contig, tax, Tax)
seqCol.save()
if not tmp_dir:
tmp_dir = "/tmp/" + name + "/"
mkdir(tmp_dir)
gene_ids = {}
with tqdm(annotation) as pbar:
for contig in pbar:
pbar.set_description(contig.id)
if len(contig.seq) > 15000000:
contig.seq = ""
contigDoc, gene_ids2 = BioDocFactory.create_contig(
contig,
seqCol,
type_map={
"rRNA": "rRNA",
"ncRNA": "ncRNA",
NCBI.f_mRNA: "gene",
"exon": "exon",
"gene": "gene",
NCBI.f_CDS: NCBI.f_CDS,
"rRNA": "rRNA",
"tRNA": "tRNA",
"tmRNA": "tmRNA",
"snoRNA": "snoRNA",
"three_prime_UTR": "three_prime_UTR",
"five_prime_UTR": "five_prime_UTR"
})
gene_ids.update(gene_ids2)
contigDoc.save()
prots = []
with tqdm(tritryp_protein_iter(annotation)) as pbar:
for (protein, cds_f) in pbar:
protDoc = Protein(seq=str(protein.seq), name=protein.id)
if "description" in cds_f.qualifiers:
protein_description = cds_f.qualifiers['description'][0]
elif "Note" in cds_f.qualifiers:
protein_description = cds_f.qualifiers['Note'][0]
elif "product" in cds_f.qualifiers:
protein_description = cds_f.qualifiers['product'][0]
else:
protein_description = ""
protDoc.description = protein_description
gos = []
if "Ontology_term" in cds_f.qualifiers:
gos = [
x.lower() for x in cds_f.qualifiers["Ontology_term"]
if "GO:" in x and (
x not in ["GO:0008150", "GO:0003674", "GO:0005575"])
]
note = cds_f.qualifiers["Note"][0].split(
" ")[0] if "Note" in cds_f.qualifiers else ""
ecs = ["ec:" + note] if re.match(
'^[0-9]+\.[0-9\-]+\.[0-9\-]+\.[0-9\-]$', note) else []
ontologies = list(set(ecs + gos))
protDoc.gene = [protein.id]
protDoc.ontologies = ontologies
protDoc.alias = [protein.id]
if len(protDoc.seq) > 30000:
raise Exception("No existen proteinas tan largas...")
protDoc.gene_id = gene_ids[protein.id]
protDoc.organism = name
protDoc.auth = str(BioMongoDB.demo_id)
protDoc.seq_collection_id = seqCol
prots.append(protDoc)
if pbar.n and ((pbar.n % 1000) == 0):
Protein.objects.insert(prots)
prots = []
if prots:
Protein.objects.insert(prots)
_common_annotations(name, tmp_dir)
def create_protein(cls, seqrecord, feature, exons=[]):
alias = cls.alias(feature)
locus_tag = feature.qualifiers["locus_tag"][0]
protein_name = locus_tag
seq = str(seqrecord.seq)
# if "translation" in feature.qualifiers:
# seq = feature.qualifiers["translation"][0]
# else:
# if exons:
# seq = str(reduce(Seq.__add__, [exon.extract(seqrecord.seq) for exon in exons]).translate())
# else:
# seq = str(feature.extract(Seq(str(seqrecord.seq))).translate())
if "gene_symbol_source" in feature.qualifiers:
try:
int(feature.qualifiers["gene_symbol_source"][0])
protein_name = ""
except:
protein_name = feature.qualifiers['gene_symbol'][0]
# elif "product" in mrna_feature.qualifiers:
# protein_name = mrna_feature.qualifiers['product'][0]
p = Protein(seq=seq, name=protein_name)
if "description" in feature.qualifiers:
protein_description = feature.qualifiers['description'][0]
elif "Note" in feature.qualifiers:
protein_description = feature.qualifiers['Note'][0]
elif "product" in feature.qualifiers:
protein_description = feature.qualifiers['product'][0]
else:
protein_description = ""
bp = BioProperty(
_type="annotation",
description="homolog proteins and sources used for the annotation")
if "protein_id" in feature.qualifiers:
bp.ncbi_protein_id = feature.qualifiers["protein_id"][0]
if "db_xref" in feature.qualifiers:
bp.ncbi_db_xref = feature.qualifiers["db_xref"][0]
if "Dbxref" in feature.qualifiers:
bp.ncbi_db_xref = feature.qualifiers["Dbxref"][0]
if "top_cog_hit" in feature.qualifiers:
bp.cog = feature.qualifiers["top_cog_hit"][0]
if "gene_symbol_source" in feature.qualifiers:
bp.source = feature.qualifiers["gene_symbol_source"][0]
if "gene_product_name_source" in feature.qualifiers:
bp.source = feature.qualifiers["gene_product_name_source"][0]
ecs = []
if "EC" in feature.qualifiers:
ecs = ecs + [
x.lower() if x.lower().startswith("ec") else "ec:" + x.lower()
for x in feature.qualifiers["EC"] if "." in x
]
if "EC_number" in feature.qualifiers:
ecs = ecs + [
x.lower() if x.lower().startswith("ec") else "ec:" + x.lower()
for x in feature.qualifiers["EC_number"] if "." in x
]
if "Dbxref" in feature.qualifiers:
ecs = ecs + [
x.lower() if x.lower().startswith("ec") else "ec:" + x.lower()
for x in feature.qualifiers["Dbxref"] if "." in x
]
gos = []
if "db_xref" in feature.qualifiers:
gos = gos + [
x.lower()
for x in feature.qualifiers["db_xref"] if "GO:" in x and
(x not in ["GO:0008150", "GO:0003674", "GO:0005575"])
]
if "GO" in feature.qualifiers:
gos = gos + [
x.lower() for x in feature.qualifiers["GO"] if "GO:" in x and
(x not in ["GO:0008150", "GO:0003674", "GO:0005575"])
]
if "Ontology_term" in feature.qualifiers:
gos = [
x.lower() for x in feature.qualifiers["Ontology_term"]
if "GO:" in x and (
x not in ["GO:0008150", "GO:0003674", "GO:0005575"])
]
ontologies = list(set(ecs + gos))
p.gene = list([locus_tag, protein_name
]) if locus_tag != protein_name else [locus_tag]
p.name = protein_name
p.description = protein_description
p.ontologies = ontologies
p.properties = [bp]
p.alias = alias
return p