def add_drugability_props_to_genome(self,
name,
description,
target,
_type,
options=None,
user="******"):
"""
ptype: SeqColDruggabilityParamTypes
"""
if not self.has_druggability_param(name):
dp = SeqColDruggabilityParam(name=name,
description=description,
target=target,
type=_type,
uploader=user)
if options:
dp.options = options
self.druggabilityParams.append(dp)
def _add_drugability_props_to_genome(self, genome):
for name, description, target, _type, options, dgo, do, dv in BioCyc.protein_pathway_search_params + BioCyc.pathways_search_params:
if not genome.has_druggability_param(name):
dp = SeqColDruggabilityParam(name=name, description=description, target=target,
type=_type, uploader=self.user)
if options:
dp.options = options
dp.defaultGroupOperation = dgo
dp.defaultOperation = do
dp.defaultValue = dv
genome.druggabilityParams.append(dp)
def update_genome_props(self):
if self.user == "demo":
user2 = ""
else:
user2 = self.user + "."
search_params = [("resistance", "Associated with resistance",
"variant-db", SeqColDruggabilityParamTypes.value,
["true", "false"], "true", "equal", "avg")]
search_params = search_params + [
(x.lower(), "Associated with " + x + " resistance", "variant-db",
SeqColDruggabilityParamTypes.value, ["true", "false"
], "true", "equal", "avg")
for x in Saureus.drugs
]
SeqCollection.objects(name=self.organism).update(
__raw__={
"$pull": {
"druggabilityParams": {
"target": "variant-db",
"uploader": self.user
}
}
})
collection = SeqCollection.objects(name=self.organism).get()
for name, description, target, _type, options, defaultValue, defaultOperation, defaultGroupOperation in search_params:
Protein.objects(organism=self.organism).update(
__raw__={"$set": {
"search." + user2 + name: False
}})
if not collection.has_druggability_param(name):
dp = SeqColDruggabilityParam(name=name,
description=description,
target=target,
type=_type,
uploader=self.user)
dp.options = options
dp.defaultValue = defaultValue
dp.defaultOperation = defaultOperation
dp.defaultGroupOperation = defaultGroupOperation
collection.druggabilityParams.append(dp)
collection.save()
def annotate_variants(organism_name, strain_name, database, parse_change):
"""
parse_change: function that transforms dbvar.qualifiers["change"] into aa_ref, aa_alt
"""
collection = SeqCollection.objects(name=organism_name).get()
prop = strain_name + "_" + database
Protein.objects(organism=organism_name).update(
__raw__={"$set": {
"search." + prop: False
}})
if not collection.has_druggability_param(prop):
dp = SeqColDruggabilityParam(name=prop,
description="Variant in strain " +
strain_name + " is reported in " +
database,
target="variant-strain",
type=SeqColDruggabilityParamTypes.value,
uploader="demo")
dp.options = ["true", "false"]
dp.defaultValue = "true"
dp.defaultOperation = "equal"
dp.defaultGroupOperation = "avg"
collection.druggabilityParams.append(dp)
prop = strain_name + "_" + database + "_pos"
Protein.objects(organism=organism_name).update(
__raw__={"$set": {
"search." + prop: False
}})
if not collection.has_druggability_param(prop):
dp = SeqColDruggabilityParam(
name=prop,
description="The position of the variant the strain " +
strain_name + " is reported in " + database,
target="variant-strain",
type=SeqColDruggabilityParamTypes.value,
uploader="demo")
dp.options = ["true", "false"]
dp.defaultValue = "true"
dp.defaultOperation = "equal"
dp.defaultGroupOperation = "avg"
collection.druggabilityParams.append(dp)
collection.save()
for p in Protein.objects(__raw__={
"organism": organism_name,
"features.qualifiers.strain": strain_name
}).no_cache():
dbvars = [f for f in p.features if f.type == database]
dirty = False
if dbvars:
strainvars = [
f for f in p.features if (f.type == "strain_variant") and (
f._data["qualifiers"]["strain"] == strain_name)
]
for dbvar in dbvars:
dirty = True
for strainvar in strainvars:
strainvar._data["qualifiers"]["ref_pos"] = False
if dbvar.location.start == strainvar.location.start:
p.search[strain_name + "_" + database + "_pos"] = True
strainvar._data["qualifiers"]["ref_pos"] = dbvar._id
try:
dref, dalt = parse_change(
dbvar._data["qualifiers"]["change"])
sref, salt = strainvar._data["qualifiers"][
"change"].strip().split("/")
sref = sref.strip()
salt = salt.strip()
if (dref == sref) and (dalt == salt):
p.search[strain_name + "_" + database] = True
strainvar._data["qualifiers"][
"ref"] = dbvar._id
except Exception as ex:
_log.warn(ex)
if (("frameshift"
in dbvar._data["qualifiers"]["change"].lower())
and
("frameshift" in strainvar._data["qualifiers"]
["change"].lower())):
p.search[strain_name + "_" + database] = True
if dirty:
p.save()
def load_metadata(self, organism_name, datafile, uploader=demo):
import pandas as pd
from tqdm import tqdm
seqCollection = list(SeqCollection.objects(name=organism_name))
seqCollection = seqCollection[0]
errors = []
upload = DataUpload(uploader=uploader, errors=errors)
df = pd.read_table(datafile, comment="#", index_col=False)
headerProperties = [
c for c in df.columns if c != BioMongoDB.GENE_FIELD_IMPORT
]
prots = Protein.objects(organism=organism_name)
for hp in headerProperties:
prots.update(
__raw__={
"$pull": {
"properties": {
"property": hp,
"_type": uploader
}
},
"$unset": {
"search." + hp: ""
}
})
upload.properties = headerProperties
numericFields = []
for k, v in dict(df.dtypes).items():
if v not in [np.float64, np.int64]:
df[k] = df[k].astype('category')
else:
numericFields.append(k)
assert BioMongoDB.GENE_FIELD_IMPORT in df.columns
for linenum, fields in tqdm(df.iterrows()):
gene = fields[BioMongoDB.GENE_FIELD_IMPORT]
if not gene:
text = str(linenum) + " gene field is empty"
errors.append(text)
continue
count = Protein.objects(organism=organism_name,
alias=gene).count()
if not count:
text = str(
linenum
) + " " + gene + " does not exists in " + organism_name
print(text)
errors.append(text)
continue
prots = Protein.objects(organism=organism_name, alias=gene)
for propertyName in headerProperties:
prop = {"_type": uploader, "value": fields[propertyName]}
prop["property"] = propertyName
prots.update(
__raw__={
"$push": {
"properties": prop
},
"$set": {
"search." + propertyName: fields[propertyName]
}
})
for p in headerProperties:
dpType = "number" if p in numericFields else "value"
options = [] if p in numericFields else list(set(df[p]))
currentDp = seqCollection.druggabilityParam(p, uploader)
if currentDp:
currentDp = currentDp[0]
currentDp.options = options
currentDp.type = dpType
else:
dp = SeqColDruggabilityParam(type=dpType,
name=p,
options=options,
uploader=uploader,
target="protein")
seqCollection.druggabilityParams.append(dp)
seqCollection.uploads.append(upload)
seqCollection.save()
def load_in_sndg(self, organism="H37Rv"):
from SNDG.BioMongo.Model.Protein import Protein
from SNDG.BioMongo.Model.Feature import Feature, Location
from SNDG.BioMongo.Model.SeqCollection import SeqCollection
from SNDG.BioMongo.Model.SeqColDruggabilityParam import SeqColDruggabilityParamTypes, SeqColDruggabilityParam
from bson.objectid import ObjectId
search_params = [("resistance", "Associated with resistance", "variant-db",
SeqColDruggabilityParamTypes.value, ["true", "false"], "true", "equal", "avg")
]
search_params = search_params + [
(x, "Associated with " + x + " resistance", "variant-db",
SeqColDruggabilityParamTypes.value, ["true", "false"], "true", "equal", "avg")
for x in TBDream.drugs
]
Protein.objects(organism=organism).update(__raw__={"$pull": {"features": {"type": "tbdream"}}})
collection = SeqCollection.objects(name=organism).get()
for name, description, target, _type, options, defaultValue, defaultOperation, defaultGroupOperation in search_params:
Protein.objects(organism=organism).update(__raw__={"$set": {"search." + name: False}})
if not collection.has_druggability_param(name):
dp = SeqColDruggabilityParam(name=name, description=description, target=target,
type=_type, uploader="demo")
dp.options = options
dp.defaultValue = defaultValue
dp.defaultOperation = defaultOperation
dp.defaultGroupOperation = defaultGroupOperation
collection.druggabilityParams.append(dp)
collection.save()
for rv, rows in self._df.groupby("rv"):
prot = list(Protein.objects(organism=organism, gene__iexact=rv))
if prot:
prot = prot[0]
for _, r in rows.iterrows():
mut = None
if r.change:
change = str(r.change[0]) + "/" + str(r.change[1])
mut = SeqUtils.seq1(r.change[1])
else:
change = r.AminoAcid
if math.isnan(r.codon):
try:
pos = int(r.AminoAcid)
except:
_log.warn("couldnt find the variant position")
continue
else:
pos = int(r.codon)
try:
res, t = r.RTotalIsolates.strip().split("/")
r_div_total_coef = int(res) * 1.0 / int(t)
r_div_total = r.RTotalIsolates.strip()
except:
r_div_total = None
r_div_total_coef = None
quals = {
"drug": r.Drug,
"change": change,
"gene": r.GeneID,
"pattern": r.ResistancePattern,
"additional": r.AdditionalMutations,
"r_div_total": r_div_total,
"r_div_total_coef": r_div_total_coef,
"mic": r.MIC}
if mut:
quals["mut"] = mut
fvariant = Feature(_id=ObjectId(), location=Location(start=pos, end=pos), type="tbdream",
identifier="TBDream id " + r.ID,
qualifiers=quals)
prot.features.append(fvariant)
prot.search.resistance = True
prot.search[r.Drug] = True
prot.save()