def runPrismX(clusterCount: int):
#urllib.request.urlretrieve("https://mssm-seq-matrix.s3.amazonaws.com/mouse_matrix.h5", "mouse_matrix.h5")
start = time.time()
correlationFolder = "correlation_" + str(clusterCount) + "_folder_q"
predictionFolder = "prediction_" + str(clusterCount) + "_folder_q"
libs = px.list_libraries()
gmt_file = px.load_library(libs[110])
px.createCorrelationMatrices("mouse_matrix.h5",
correlationFolder,
clusterCount=clusterCount,
sampleCount=5000,
correlationSampleCount=5000,
verbose=True)
t1 = time.time() - start
print("T1: " + str(t1))
px.correlation_scores(gmt_file,
correlationFolder,
predictionFolder,
verbose=True)
t2 = time.time() - start
print("T2: " + str(t2))
model = px.trainModel(predictionFolder,
correlationFolder,
gmt_file,
training_size=300000,
test_train_split=0.1,
sample_positive=40000,
sample_negative=200000,
random_state=42,
verbose=True)
pickle.dump(model, open("gobp_model_" + str(clusterCount) + ".pkl", 'wb'))
t3 = time.time() - start
print("T3: " + str(t3))
import prismx as px
import pickle
from memory_profiler import memory_usage
import os
import time
import matplotlib.pyplot as plt
import pandas as pd
import feather
from prismx.utils import load_json, get_config, get_data_path, read_gmt
from prismx.loaddata import get_genes
from progress.bar import Bar
import numpy as np
px.print_libraries()
libs = px.list_libraries()
gmt_file = px.load_library(libs[28])
outname = libs[28]
correlationFolder = "correlation_100_folder"
predictionFolder = "prediction_100_folder"
outfolder = "prismxresult_100"
px.predict_gmt("gobp_model_100.pkl",
gmt_file,
correlationFolder,
predictionFolder,
outfolder,
outname,
step_size=1000,
verbose=True)
clusterCount = 50
correlationFolder = "correlation_" + str(clusterCount) + "_folder"
predictionFolder = "prediction_" + str(clusterCount) + "_folder"
outfolder = "prismxresult_" + str(clusterCount)
#px.createCorrelationMatrices("mouse_matrix.h5", correlationFolder, clusterCount=clusterCount, sampleCount=5000, correlationSampleCount=5000, verbose=True)
genesetlibs = [
"ChEA_2016", "KEA_2013", "GWAS_Catalog_2019", "huMAP",
"GO_Biological_Process_2018", "MGI_Mammalian_Phenotype_Level_4_2019"
]
genesetlibs.sort()
for lib in genesetlibs[0:2]:
gmt_file = px.load_library(lib)
px.correlation_scores(gmt_file,
correlationFolder,
predictionFolder,
verbose=True)
model = px.trainModel(predictionFolder,
correlationFolder,
gmt_file,
training_size=300000,
test_train_split=0.1,
sample_positive=40000,
sample_negative=200000,
random_state=42,
verbose=True)
pickle.dump(model, open(lib + "_model_" + str(clusterCount) + ".pkl",
'wb'))
import prismx as px
import pickle
from memory_profiler import memory_usage
import os
import time
import matplotlib.pyplot as plt
import pandas as pd
import feather
from prismx.utils import load_json, get_config, get_data_path, read_gmt
from prismx.loaddata import get_genes
from progress.bar import Bar
import numpy as np
px.print_libraries()
libs = px.list_libraries()
gmt_file = px.load_library(libs[28])
outname = libs[28]
correlationFolder = "correlation_100_folder"
predictionFolder = "prediction_100_folder"
outfolder = "prismxresult_100"
px.predict_gmt("gobp_model_100.pkl",
gmt_file,
correlationFolder,
predictionFolder,
outfolder,
outname,
step_size=1000,
verbose=True)
nx = "GO_Biological_Process_2018"
set_auc.loc[nx, :]
gene_auc.loc[nx, :]
p1 = pd.read_feather("prediction_folder_300_umap/prediction_0.f").set_index(
"index")
correlationFolder = "correlation_folder_300"
predictionFolder = "prediction_folder_300_umap"
outfolder = "prismxresult"
clustn = 300
libs = px.list_libraries()
gmt_file = px.load_library(libs[111], overwrite=True)
outname = libs[111]
#px.predict_gmt("gobp_model_"+str(clustn)+".pkl", gmt_file, correlationFolder, predictionFolder, outfolder, libs[111], step_size=200, intersect=True, verbose=True)
gop = pd.read_feather("prismxresult/GO_Biological_Process_2018.f")
gop = gop.set_index("index")
geneAUC, setAUC = px.benchmarkGMTfast(gmt_file,
correlationFolder,
predictionFolder,
outfolder + "/" + outname + ".f",
intersect=True,
verbose=True)
diff_gene = geneAUC.iloc[:, 1] - geneAUC.iloc[:, 0]
diff_set = setAUC.iloc[:, 1] - setAUC.iloc[:, 0]
import time
import shutil
#sys.path.append('C:/prismx/')
import prismx as px
libs = px.list_libraries()
clustn = 26
f = open("validationscore" + str(clustn) + ".txt", 'r')
libraries = [x.split("\t")[0] for x in f.readlines()]
newlibs = list(set(libs).difference(set(libraries)))
for i in range(0, len(newlibs)):
try:
print(newlibs[i])
gmt_file = px.load_library(newlibs[i])
print("loaded")
g1, g2, g3 = px.read_gmt(gmt_file)
# set output configuration
outname = newlibs[i]
correlationFolder = "correlation_" + str(clustn) + "_folder"
predictionFolder = "prediction_" + str(clustn)
outfolder = "prismxresult_" + str(clustn)
if len(g1) < 14000:
# calculate PrismX predictions with pretrained model
px.predict_gmt("gobp_model_" + str(clustn) + ".pkl",
gmt_file,
correlationFolder,
predictionFolder,
outfolder,
outname,
