def modevalworker(setting, scores, baseline):
if baseline:
baselines = pd.read_csv("../results/modeval_knownmodules/baseline.tsv",
index_col=[0, 1, 2])
modules = Modules(
json.load(open("../" + setting["output_folder"] + "modules.json")))
runinfo = json.load(open("../" + setting["output_folder"] +
"runinfo.json"))
dataset = json.load(open("../" + setting["dataset_location"]))
settingscores = []
for regnet_name in dataset["knownmodules"].keys():
for knownmodules_name in dataset["knownmodules"][regnet_name].keys():
# baselinesoi = {
# baseline_name:baseline.ix[(dataset["baselinename"], regnet_name, knownmodules_name)].to_dict()
# for baseline_name, baseline in baselines.items()
# }
if baseline:
baselineoi = {
baseline_name: baseline.loc[(baseline_name, regnet_name,
knownmodules_name)].to_dict()
for baseline_name, baseline in baselines.groupby(
level="baseline_name")
}
else:
baselineoi = None
knownmodules_location = dataset["knownmodules"][regnet_name][
knownmodules_name]
knownmodules = Modules(
json.load(open("../" + knownmodules_location)))
settingscores_goldstandard = modevalscorer(modules, knownmodules,
baselineoi)
settingscores_goldstandard["settingid"] = setting["settingid"]
settingscores_goldstandard["knownmodules_name"] = knownmodules_name
settingscores_goldstandard["regnet_name"] = regnet_name
settingscores_goldstandard[
"goldstandard"] = regnet_name + "#" + knownmodules_name
settingscores_goldstandard["runningtime"] = runinfo["runningtime"]
settingscores.append(settingscores_goldstandard)
scores[setting["settingid"]] = settingscores
def modevalworker(setting, scores):
baseline_names = ["permuted", "sticky", "scalefree"]
baselines = {
baseline_name:
pd.read_table("../results/modeval_knownmodules/baselines_" +
baseline_name + ".tsv",
index_col=[0, 1, 2])
for baseline_name in baseline_names
}
modules = Modules(
json.load(open("../" + setting["output_folder"] + "modules.json")))
runinfo = json.load(open("../" + setting["output_folder"] +
"runinfo.json"))
dataset = json.load(open("../" + setting["dataset_location"]))
settingscores = []
for regnet_name in dataset["knownmodules"].keys():
for knownmodules_name in dataset["knownmodules"][regnet_name].keys():
baselinesoi = {
baseline_name:
baseline.ix[(dataset["baselinename"], regnet_name,
knownmodules_name)].to_dict()
for baseline_name, baseline in baselines.items()
}
knownmodules_location = dataset["knownmodules"][regnet_name][
knownmodules_name]
knownmodules = Modules(
json.load(open("../" + knownmodules_location)))
settingscores_goldstandard = modevalscorer(modules, knownmodules,
baselinesoi)
settingscores_goldstandard["settingid"] = setting["settingid"]
settingscores_goldstandard["knownmodules_name"] = knownmodules_name
settingscores_goldstandard["regnet_name"] = regnet_name
settingscores_goldstandard[
"goldstandard"] = regnet_name + "#" + knownmodules_name
settingscores_goldstandard["runningtime"] = runinfo["runningtime"]
settingscores.append(settingscores_goldstandard)
scores[setting["settingid"]] = settingscores
def blockcluster(E, ngenes=10, nconditions=10, **kwargs):
importr("blockcluster")
print(ngenes, nconditions)
rresults = ro.r["coclusterContinuous"](ro.r["as.matrix"](standardize(E)), nbcocluster=ro.IntVector([nconditions,ngenes]))
modules = Modules(convert_labels2modules(rresults.slots["colclass"], E.columns))
moduleconditions = convert_labels2modules(rresults.slots["rowclass"], E.index)
return(modules)
def modeval_coverage_worker(setting, scores, verbose=False):
dataset = json.load(open("../" + setting["dataset_location"]))
baseline_names = ["permuted", "sticky", "scalefree"]
baselines = {
baseline_name: pd.read_table("../results/modeval_coverage/baselines_" +
baseline_name + ".tsv",
index_col=[0, 1])
for baseline_name in baseline_names
}
baselines = {
baseline_name: baseline.ix[dataset["baselinename"]]
for baseline_name, baseline in baselines.items()
}
runinfo = json.load(open("../" + setting["output_folder"] +
"runinfo.json"))
modules = Modules(
json.load(open("../" + setting["output_folder"] + "modules.json")))
if verbose: print("▶ " + str(setting["settingid"]))
subscores = []
for bound_name, bound_location in dataset["binding"].items():
if bound_location.endswith(".pkl"):
bound = pd.read_pickle("../" + bound_location)
else:
bound = pd.read_table("../" + bound_location,
index_col=0,
header=[0, 1])
subscores.append(modbindevalscorer(modules, bound))
# calculate the average over different regulatory circuit cutoffs
settingscores = pd.DataFrame(subscores).mean().to_dict()
for baseline_name, baseline in baselines.items():
settingscores["aucodds_" + baseline_name] = settingscores[
"aucodds"] / baseline["aucodds"].mean()
settingscores["settingid"] = setting["settingid"]
settingscores["goldstandard"] = "regcircuit"
settingscores["runningtime"] = runinfo["runningtime"]
scores[setting["settingid"]] = [settingscores]
if verbose: print("◼ " + str(setting["settingid"]))
def modenrichevalworker(setting, scores):
dataset = json.load(open("../" + setting["dataset_location"]))
modules = Modules(
json.load(open("../" + setting["output_folder"] + "modules.json")))
settingscores = []
for gsets_name in dataset["gsets"].keys():
gsets_location = dataset["gsets"][gsets_name]
membership = pd.read_pickle("../" + gsets_location)
connectivity = pd.read_pickle("../" + gsets_location[:-4] +
"_connectivity.pkl")
settingscores_gsets = modenrichevalscorer(modules, membership,
connectivity)
settingscores.extend([{
"settingid": setting["settingid"],
"scorename": scorename + "#" + gsets_name,
"score": score
} for scorename, score in settingscores_gsets.items()])
scores[setting["settingid"]] = settingscores
def baseline_permuted(modules, **kwargs):
modules = Modules(modules)
modules = modules.shuffle()
return modules