def bioGRID_homo_HPC_combine():
dataset_len = int(
len([
*bg.parse_bioGRID(
filename=
'./data/BioGRID/BIOGRID-ORGANISM-Homo_sapiens-3.5.187.tab2.txt',
wFile_GGI='./data/parsed/BioGRID_homo_GGI.pkl',
wFile_PPI='./data/parsed/BioGRID_homo_PPI.pkl',
root="../")
][1].index) * 0.5)
dataset = "bioGRID"
datasetName = "bioGRID_homo"
for folder in os.listdir("./resultData/h**o/"):
if dataset in folder:
for trial in range(6, 10):
print("folder: {}, trial: {}".format(folder, trial))
filenames = os.listdir("./resultData/h**o/" + folder)
ppiFiles = [i for i in filenames if "PPI" in i]
curTrialFiles = [
i for i in ppiFiles if i.split("_")[-3] == str(trial)
]
topPPIs, topScores = [], []
for i in curTrialFiles:
with open("./resultData/h**o/{}/{}".format(folder, i),
"r") as f:
topPPIs += json.loads(f.read())
with open(
"./resultData/h**o/{}/{}".format(
folder, "_".join(i.split("_")[:-1]) +
"_score.json"), "r") as f:
topScores += json.loads(f.read())
# sort
topPPIs, topScores = hr.sort_key_val(
topPPIs, topScores)
topPPIs = topPPIs[0:dataset_len]
topScores = topScores[0:dataset_len]
with open(
"./resultData/h**o/{}/{}_{}_trimmedPPIs.json".
format(folder, curTrialFiles[0].split("_")[0],
datasetName), "a+") as f:
f.write(json.dumps(topPPIs) + "\n")
with open(
"./resultData/h**o/{}/{}_{}_trimmedScores.json".
format(folder, curTrialFiles[0].split("_")[0],
datasetName), "a+") as f:
f.write(json.dumps(topScores) + "\n")
def append_precRecMap_multiCore(fNames,
predPPI,
samplePPI,
datasetClass,
coreNo,
isGGI=False,
logging=False):
if isGGI: i = 0
else: i = 1
fullPPISet = {
'bioGRID': [
list(ppi)
for ppi in np.asarray([*bg.parse_bioGRID(
root='../')][i][['nodeA', 'nodeB']])
],
'STRING': [
list(ppi)
for ppi in np.asarray([*string.parse_STRING(
root='../')][i][['nodeA', 'nodeB']])
],
'MINT': [
list(ppi) for ppi in np.asarray([*MINT.parse_MINT(
root='../')][i][['nodeA', 'nodeB']])
],
'IntAct_spoke': [
list(ppi) for ppi in np.asarray([
*IntAct.parse_IntAct(root='../', spokeModel=True)
][i][['nodeA', 'nodeB']])
]
}
fullPrecRecMap = {}
if not os.path.exists("./resultData/PRCurveMap.json"):
with open("./resultData/PRCurveMap.json", "w") as f:
f.write(json.dumps(fullPrecRecMap))
precRecMap = ppiLPred.precRecMap_multiCore(
fNames, predPPI, samplePPI, [fullPPISet[i] for i in datasetClass],
coreNo, logging)
with open('./resultData/PRCurveMap.json', 'r') as f:
fullPrecRecMap = json.loads(f.read())
fullPrecRecMap.update(precRecMap)
with open('./resultData/PRCurveMap.json', 'w') as f:
f.write(json.dumps(fullPrecRecMap))
def trim_ppi_result(fNames, datasetClass):
# get only the top PPI & scores equal to the size of its original dataset
trimNum = {
'bioGRID':
int(len([*bg.parse_bioGRID(root='../')][1].index) * 0.5),
'STRING':
int(len([*string.parse_STRING(root='../')][1].index) * 0.5),
'MINT':
int(len([*MINT.parse_MINT(root='../')][1].index) * 0.5),
'IntAct_spoke':
int(
len([*IntAct.parse_IntAct(root='../', spokeModel=True)
][1].index) * 0.5)
}
if not os.path.exists('./resultData/trimmed_predPPIs.json'):
with open('./resultData/trimmed_predPPIs.json', 'w') as f:
pass
with open('./resultData/trimmed_predScores.json', 'w') as f:
pass
for i in range(len(fNames)):
predPPI, predScore = [], []
with open("./resultData/{}_PPI.json".format(fNames[i]), 'r') as f:
for line in f.readlines():
predPPI.append(
json.loads(line)[0:trimNum[datasetClass[i]]])
with open("./resultData/{}_score.json".format(fNames[i]),
'r') as f:
for line in f.readlines():
predScore.append(
json.loads(line)[0:trimNum[datasetClass[i]]])
predPPIs, predScores = {fNames[i]: predPPI}, {fNames[i]: predScore}
with open('./resultData/trimmed_predPPIs.json', 'a+') as f:
f.write(json.dumps(predPPIs) + "\n")
with open('./resultData/trimmed_predScores.json', 'a+') as f:
f.write(json.dumps(predScores) + "\n")
def trim_multiple_ppi_result(fNames, datasetClass, trialSize):
trimNum = {
'bioGRID':
int(len([*bg.parse_bioGRID(root='../')][1].index) * 0.5),
'STRING':
int(len([*string.parse_STRING(root='../')][1].index) * 0.5),
'MINT':
int(len([*MINT.parse_MINT(root='../')][1].index) * 0.5),
'IntAct_spoke':
int(
len([*IntAct.parse_IntAct(root='../', spokeModel=True)
][1].index) * 0.5)
}
if not os.path.exists('./resultData/trimmed_predPPIs.json'):
with open('./resultData/trimmed_predPPIs.json', 'w') as f:
pass
with open('./resultData/trimmed_predScores.json', 'w') as f:
pass
for i in range(len(fNames)):
predPPI, predScore = [], []
for j in range(trialSize):
with open("./resultData/{}_{}_PPI.json".format(fNames[i], j),
'r') as f:
predPPI.append(
json.loads(f.read())[0:trimNum[datasetClass[i]]])
with open("./resultData/{}_{}_score.json".format(fNames[i], j),
'r') as f:
predScore.append(
json.loads(f.read())[0:trimNum[datasetClass[i]]])
predPPIs, predScores = {fNames[i]: predPPI}, {fNames[i]: predScore}
with open('./resultData/trimmed_predPPIs.json', 'a+') as f:
f.write(json.dumps(predPPIs) + "\n")
with open('./resultData/trimmed_predScores.json', 'a+') as f:
f.write(json.dumps(predScores) + "\n")
def bioGRID_homo_tenTrial_to_csvData():
bioGRID_GGI_df, bioGRID_PPI_df = bg.parse_bioGRID(
filename=
'./data/BioGRID/BIOGRID-ORGANISM-Homo_sapiens-3.5.187.tab2.txt',
wFile_GGI='./data/parsed/BioGRID_homo_GGI.pkl',
wFile_PPI='./data/parsed/BioGRID_homo_PPI.pkl',
root="../")
dataset_len = int(int(len(bioGRID_PPI_df.index) * 0.5) * 0.1)
geneToEntry = helper.uniprot_map()
predPPIs = {}
with open('./resultData/h**o/trimmed_predPPIs_homo.json', 'r') as f:
for line in f.readlines():
predPPIs.update(json.loads(line))
baseTags = [
'commonNeighbor', 'xyContrib_dualCN_uvJoin', 'CRA', 'Sim',
'CH2_L3', 'L3uvJoin'
]
for dataset in ["bioGRID_homo"]:
tags = [
"{}_tenTrial_{}".format(baseTag, dataset)
for baseTag in baseTags
]
for i in range(len(tags)):
tag = tags[i]
PPIsList = [[[geneToEntry[g[0]], geneToEntry[g[1]]]
for g in j[:dataset_len]
if g[0] in geneToEntry and g[1] in geneToEntry]
for j in predPPIs[tag]]
for j in range(len(PPIsList)):
with open('./GoSemSimPrepData/{}_{}.csv'.format(tag, j),
'w') as f:
f.write(
"\n".join(['nodeA\tnodeB'] +
["\t".join(ppi)
for ppi in PPIsList[j]]) + "\n")
# For ExactL3, generate as such.
# we defined the simple penalization index as xyContrib in ppiLPred.helperFunc, and jaccard coefficient as dualCN
# so, we pass this as arguments via our custom scoreArgs parameter
# the scoreArg is arranged as a list, ['normFunc'=?, 'uvSpec'=?, 'xySpec'=?, 'uvContrib'=?, 'xyContrib'=?, 'dualCN'=?, 'uvJoin'=?]
# for our case, it would be ['null', 'null', 'null', 'null', 'basic', 'basic', 'basic']
ExactL3_PPIs, ExactL3_Scores = ppiLPred._PPILinkPred(
nodePairs,
PPIr,
scoringMethod="interStr",
scoreArgs=['null', 'null', 'null', 'null', 'basic', 'basic', 'basic'])
ExactL3_sortedPPIs, ExactL3_sortedScores = helper.sort_key_val(
ExactL3_PPIs, ExactL3_Scores)
print(ExactL3_sortedPPIs)
print(ExactL3_sortedScores)
print("")
# example for accessing the database
# available dataset: bioGRID, STRING, MINT, IntAct, HuRI
import bioGRID as bg
bg_GI, bg_PPI = bg.parse_bioGRID(root="./src")
print(bg_PPI.head())
print(bg_GI.head())
# for other datasets:
# import STRING, MINT, IntAct
# STRING.parse_STRING(root="./src")
# MINT.parse_MINT(root="./src")
# IntAct.parse_IntAct(spokeModel=True, root="./src")
# HuRI.parse_HuRI(root="./src")
# by default they all returns Yeast dataset, please see the notebook and other provided data generating script to return the Human dataset, or just ask me
def trim_multiple_ppi_result(fNames, datasetClass, trialSize):
bioGRID_homo = int(
len([
*bg.parse_bioGRID(
filename=
'./data/BioGRID/BIOGRID-ORGANISM-Homo_sapiens-3.5.187.tab2.txt',
wFile_GGI='./data/parsed/BioGRID_homo_GGI.pkl',
wFile_PPI='./data/parsed/BioGRID_homo_PPI.pkl',
root="../")
][1].index) * 0.5)
STRING_homo = int(
len([
*string.parse_STRING(
ppiFile='./data/STRING/9606.protein.links.v11.0.txt',
typeFile='./data/STRING/9606.protein.actions.v11.0.txt',
uniProtMap=
'./data/UniProt/uniprot-taxonomy_9606_STRING.tab',
root='../',
wFile_GGI='./data/parsed/STRING_homo_GGI.pkl',
wFile_PPI='./data/parsed/STRING_homo_PPI.pkl')
][1].index) * 0.5)
MINT_homo = int(
len([
*MINT.parse_MINT(
ppiFile='./data/MINT/species human',
uniProtMap="./data/UniProt/uniprot-taxonomy_9606.tab",
wFile_GGI='./data/parsed/MINT_homo_GGI.pkl',
wFile_PPI='./data/parsed/MINT_homo_PPI.pkl',
root="../")
][1].index) * 0.5)
trimNum = {
'HuRI': int(len(HuRI.parse_HuRI(root='../').index) * 0.5),
"bioGRID_homo": bioGRID_homo,
"STRING_homo": STRING_homo,
"MINT_homo": MINT_homo
}
if not os.path.exists('./resultData/h**o/trimmed_predPPIs.json'):
with open('./resultData/h**o/trimmed_predPPIs.json', 'w') as f:
pass
with open('./resultData/h**o/trimmed_predScores.json', 'w') as f:
pass
for i in range(len(fNames)):
predPPI, predScore = [], []
for j in range(trialSize):
with open(
"./resultData/h**o/{}_{}_PPI.json".format(
fNames[i], j), 'r') as f:
predPPI.append(
json.loads(f.read())[0:trimNum[datasetClass[i]]])
with open(
"./resultData/h**o/{}_{}_score.json".format(
fNames[i], j), 'r') as f:
predScore.append(
json.loads(f.read())[0:trimNum[datasetClass[i]]])
predPPIs, predScores = {fNames[i]: predPPI}, {fNames[i]: predScore}
with open('./resultData/h**o/trimmed_predPPIs.json', 'a+') as f:
f.write(json.dumps(predPPIs) + "\n")
with open('./resultData/h**o/trimmed_predScores.json', 'a+') as f:
f.write(json.dumps(predScores) + "\n")
def append_precRecMap_multiCore(fNames,
predPPI,
samplePPI,
datasetClass,
coreNo,
isGGI=False,
logging=False):
if isGGI: i = 0
else: i = 1
bioGRID_homo = [
list(ppi) for ppi in np.asarray([
*bg.parse_bioGRID(
filename=
'./data/BioGRID/BIOGRID-ORGANISM-Homo_sapiens-3.5.187.tab2.txt',
wFile_GGI='./data/parsed/BioGRID_homo_GGI.pkl',
wFile_PPI='./data/parsed/BioGRID_homo_PPI.pkl',
root="../")
][i][['nodeA', 'nodeB']])
]
STRING_homo = [
list(ppi) for ppi in np.asarray([
*string.parse_STRING(
ppiFile='./data/STRING/9606.protein.links.v11.0.txt',
typeFile='./data/STRING/9606.protein.actions.v11.0.txt',
uniProtMap=
'./data/UniProt/uniprot-taxonomy_9606_STRING.tab',
root='../',
wFile_GGI='./data/parsed/STRING_homo_GGI.pkl',
wFile_PPI='./data/parsed/STRING_homo_PPI.pkl')
][i][['nodeA', 'nodeB']])
]
MINT_homo = [
list(ppi) for ppi in np.asarray([
*MINT.parse_MINT(
ppiFile='./data/MINT/species human',
uniProtMap="./data/UniProt/uniprot-taxonomy_9606.tab",
wFile_GGI='./data/parsed/MINT_homo_GGI.pkl',
wFile_PPI='./data/parsed/MINT_homo_PPI.pkl',
root="../")
][i][['nodeA', 'nodeB']])
]
fullPPISet = {
'HuRI': [
list(ppi) for ppi in np.asarray(
HuRI.parse_HuRI(root='../')[['nodeA', 'nodeB']])
],
'bioGRID_homo':
bioGRID_homo,
'STRING_homo':
STRING_homo,
'MINT_homo':
MINT_homo
}
fullPrecRecMap = {}
if not os.path.exists("./resultData/PRCurveMap_homo.json"):
with open("./resultData/PRCurveMap_homo.json", "w") as f:
f.write(json.dumps(fullPrecRecMap))
precRecMap = ppiLPred.precRecMap_multiCore(
fNames, predPPI, samplePPI, [fullPPISet[i] for i in datasetClass],
coreNo, logging)
with open('./resultData/PRCurveMap_homo.json', 'r') as f:
fullPrecRecMap = json.loads(f.read())
fullPrecRecMap.update(precRecMap)
with open('./resultData/PRCurveMap_homo.json', 'w') as f:
f.write(json.dumps(fullPrecRecMap))