def install(self, pkg, require=None, update=True, reinstall=False):
"""install a package automatically scanning CRAN and biocLite repos
if require is not set and update is True, when a newest version of a package
is available, it is installed
"""
from easydev import to_list
pkgs = to_list(pkg)
for pkg in pkgs:
self._install(pkg, require=require, update=update, reinstall=reinstall)
def install(self, pkg, require=None, update=True, reinstall=False):
"""install a package automatically scanning CRAN and biocLite repos
if require is not set and update is True, when a newest version of a package
is available, it is installed
"""
from easydev import to_list
pkgs = to_list(pkg)
for pkg in pkgs:
self._install(pkg, require=require, update=update, reinstall=reinstall)
def keep_tissue_in(self, tissues):
"""Drop tissues not in the list
:param list tissues: a list of tissues to keep. If you have only
one tissue, can be provided as a string. Since rows are removed
some features (columns) may now be empty (all zeros). If so, those
columns are dropped (except for the special columns (e.g, MSI).
"""
tissues = easydev.to_list(tissues)
mask = self.df[self.colnames.tissue].isin(tissues)
self.df = self.df[mask]
self._cleanup()
def keep_tissue_in(self, tissues):
"""Drop tissues not in the list
:param list tissues: a list of tissues to keep. If you have only
one tissue, can be provided as a string. Since rows are removed
some features (columns) may now be empty (all zeros). If so, those
columns are dropped (except for the special columns (e.g, MSI).
"""
tissues = easydev.to_list(tissues)
mask = self.df[self.colnames.tissue].isin(tissues)
self.df = self.df[mask]
self._cleanup()
def get_interactions(self, query="", frmt='json', fields=[]):
"""Interactions of proteins
:param str query: a valid uniprot identifier (e.g. P00533). It can also
be a list of uniprot identifiers, or a string with
comma-separated identifiers.
:param str fields: additional fields to be added to the output
(e.g., sources, references)
:param str frmt: format of the output (json or tabular)
Example::
res_one = o.get_interactions('P00533')
res_many = o.get_interactions('P00533,O15117,Q96FE5')
res_many = o.get_interactions(['P00533','O15117','Q96FE5'])
res_one = o.get_interactions('P00533', fields='sources')
res_one = o.get_interactions('P00533', fields=['source'])
res_one = o.get_interactions('P00533', fields=['source', 'references'])
You may also keep query to an empty string, but the entire DB will then
be downloaded. This may take time and the :attr:`timeout` may need to be
increased manually.
If frmt is set to TSV, the output is a TSV table with a header. If set
to json, a dictionary is returned.
"""
# make sure there is no spaces
if isinstance(query, list):
query = ",".join(query)
else:
try: # if input is a string
query = query.replace(' ', '')
except:
pass
assert frmt in ['json', 'tsv'], "frmt must be set to json or tsv"
params = {}
params['format'] = frmt
from easydev import to_list
fields = to_list(fields)
if len(fields):
params['fields'] = fields
#TODO handle multiple fields
res = self.http_get(self.url + "interactions/%s" % query,
frmt=frmt,
params=params)
return res
def get_interactions(self, query="", frmt='json', fields=[]):
"""Interactions of proteins
:param str query: a valid uniprot identifier (e.g. P00533). It can also
be a list of uniprot identifiers, or a string with
comma-separated identifiers.
:param str fields: additional fields to be added to the output
(e.g., sources, references)
:param str frmt: format of the output (json or tabular)
Example::
res_one = o.get_interactions('P00533')
res_many = o.get_interactions('P00533,O15117,Q96FE5')
res_many = o.get_interactions(['P00533','O15117','Q96FE5'])
res_one = o.get_interactions('P00533', fields='sources')
res_one = o.get_interactions('P00533', fields=['source'])
res_one = o.get_interactions('P00533', fields=['source', 'references'])
You may also keep query to an empty string, but the entire DB will then
be downloaded. This may take time and the :attr:`timeout` may need to be
increased manually.
If frmt is set to TSV, the output is a TSV table with a header. If set
to json, a dictionary is returned.
"""
# make sure there is no spaces
if isinstance(query, list):
query=",".join(query)
else:
try: # if input is a string
query = query.replace(' ', '')
except:
pass
assert frmt in ['json', 'tsv'] ,"frmt must be set to json or tsv"
params = {}
params['format'] = frmt
from easydev import to_list
fields = to_list(fields)
if len(fields):
params['fields'] = fields
#TODO handle multiple fields
res = self.http_get(self.url + "interactions/%s" % query,
frmt=frmt, params=params)
return res
def drop_drugs(self, drugs):
"""drop a drug or a list of drugs"""
drugs = easydev.to_list(drugs)
tokeep = [x for x in self.drugIds if x not in drugs]
self.drugIds = tokeep
def drop_cosmic(self, cosmics):
"""drop a drug or a list of cosmic ids"""
cosmics = easydev.to_list(cosmics)
tokeep = [x for x in self.cosmicIds if x not in cosmics]
self.cosmicIds = tokeep
def drop_drugs(self, drugs):
"""drop a drug or a list of drugs"""
drugs = easydev.to_list(drugs)
tokeep = [x for x in self.drugIds if x not in drugs]
self.drugIds = tokeep
def drop_cosmic(self, cosmics):
"""drop a drug or a list of cosmic ids"""
cosmics = easydev.to_list(cosmics)
tokeep = [x for x in self.cosmicIds if x not in cosmics]
self.cosmicIds = tokeep
def optimise(self, NAFac=1, pmutation=0.5, selpress=1.2, popsize=50,
reltol=0.1, elitism=5, maxtime=60, sizefactor=0.0001,
time_index_1=1, maxgens=500, maxstallgens=100, ga_verbose=True):
"""Perform the optimisation and save results
* Results are stored in :attr:`results`
* Models with the tolerance are stored in :attr:`results.models`
Parameters are those of a Genetic Algorithm used to perform
the analysis.
If you run again, it uses the previous best bitstirng.
Set self.session.best_bitstring = None to start from the
full network.
"""
self.logging.info("Running the optimisation. Can take a very long"
"time. To see the progression, set verboseR "
"attribute to True")
# update config GA section with user parameters
self._update_config('GA', self.optimise.actual_kwargs)
# keep track of the GA parameters, which may have been update above
gad = self.config.GA.as_dict()
bs = self.session.get('best_bitstring')
if bs is not None:
bs = "c(" + ",".join([str(x) for x in list(bs)]) + ")"
else:
bs = 'NULL'
# do we want to pre process the data ?
script_template = """
library(CellNOptR)
pknmodel = readSIF("%(pkn)s")
cnolist = CNOlist("%(midas)s")
model = preprocessing(cnolist, pknmodel, compression=%(compression)s,
expansion=%(expansion)s, cutNONC=%(cutnonc)s,
maxInputsPerGate=%(maxInputsPerGate)s)
res = gaBinaryT1(cnolist, model, popSize=%(popsize)s, maxGens=%(maxgens)s,
maxTime=%(maxtime)s, elitism=%(elitism)s, pMutation=%(pmutation)s,
NAFac=%(NAFac)s, selPress=%(selpress)s, relTol=%(reltol)s, sizeFac=%(sizefactor)s,
stallGenMax=%(maxstallgens)s, initBstring=%(bs)s)
sim_results = cutAndPlot(cnolist, model, list(res$bString),
plotParams=list(maxrow = 80, cex=0.5),
plotPDF=F)
sim_results2 = NULL
# output are not the same... as in T1
signals = colnames(cnolist@signals$`0`)
colnames(sim_results$mse) = signals
for (i in seq_along(sim_results$simResults[[1]])){
colnames(sim_results$simResults[[1]][[i]]) = signals
}
# to be retrieved inside Python code
best_bitstring = res$bString
best_score = res$bScore
all_scores = res$stringsTolScores
all_bitstrings = res$stringsTol
reactions = model$reacID
results = as.data.frame(res$results)
stimuli = as.data.frame(cnolist@stimuli)
inhibitors = as.data.frame(cnolist@inhibitors)
species = colnames(cnolist@signals[[1]])
optim1 = T
"""
params = {
'pkn': self.pknmodel.filename,
'midas': self.data.filename,
'compression': bool2R(self._compression),
'expansion': bool2R(self._expansion),
'cutnonc': bool2R(self._cutnonc),
'maxInputsPerGate': self._max_inputs_per_gate,
'bs':bs
}
params.update(gad)
script = script_template % params
self.session.run(script)
self.reactions_r = self.session.reactions
# need to change type of some columns, which are all string
results = self.session.results
results.columns = [x.strip() for x in results.columns]
columns_int = ['Generation', 'Stall_Generation']
columns_float = ['Best_score', 'Avg_Score_Gen', 'Best_score_Gen', 'Iter_time']
results[columns_int] = results[columns_int].astype(int)
results[columns_float] = results[columns_float].astype(float)
# cnograph created automatically from the reactions
try:
N = len(self.session.best_bitstring)
all_bs = self.session.all_bitstrings
df = pd.DataFrame(all_bs, columns=self.reactions_r)
models = BooleanModels(df)
# flatten to handle exhaustive
import numpy as np
models.scores = np.array(list(pylab.flatten(self.session.all_scores)))
try:
models.cnograph.midas = self.data.copy()
except Exception as err:
# does not work with ExtLiverPCB
# CNOError: 'The cues IFNg was found in the MIDAS file but is not present in the model. Change your model or MIDAS file.'
print("something wrong in the copying of the midas into cnograph(models)")
print(err.message)
except:
N = len(self.session.best_bitstring)
all_bs = self.session.all_bitstrings
if N == len(self.reactions_r) and len(self.session.all_bitstrings)>0:
df = pd.DataFrame([self.session.all_bitstrings],
columns=self.reactions_r)
models = BooleanModels(df)
models.scores = easydev.to_list(self.session.all_scores)
self._models = models
else:
df = pd.DataFrame(columns=self.reactions_r)
models = BooleanModels(df)
models.scores = easydev.to_list(self.session.all_scores)
self._models = models
models.cnograph.midas = self.data.copy()
results = {
'best_score': self.session.best_score,
'best_bitstring': self.session.best_bitstring,
'all_scores': self.session.all_scores,
'all_bitstrings': self.session.all_bitstrings,
'reactions': self._reac_cnor2cno(self.reactions_r),
'sim_results': self.session.sim_results, # contains mse and sim at t0,t1,
'results': results,
'models': models,
'stimuli': self.session.stimuli.copy(),
'inhibitors': self.session.inhibitors.copy(),
'species': self.session.species,
}
results['pkn'] = self.pknmodel
results['midas'] = self.data
self.results.results = results
self.results.models = models
self._called.append('optimise')