logging.info('create metPG')
metPG = []
filemanes_df = pd.read_csv(input_folder + "methylation/filenames.csv")
# assert len(os.listdir(input_folder + 'peaks/')) - 1 == len(filenames_df['name'])
for index, row in filemanes_df.iterrows():
#print(row["name"])
params.met_reader = ChiPSeqReader(input_folder + 'methylation/'+ row["filename"], name=row['name'])
params.met_reader.read_file(renamer={"0":"chr","1":"start","2":"end","4":"sigVal"})
metPG.append(SmallChipSeqPredictorGenerator(params.met_reader,params.window_size,N_closest=4))
#Read cage data
cagePG = []
filemanes_df = pd.read_csv(input_folder + "cage/filenames.csv")
# assert len(os.listdir(input_folder + 'cage/')) - 1 == len(filemanes_df['name'])
for index, row in filemanes_df.iterrows():
#print(row["name"])
params.cage_reader = ChiPSeqReader(input_folder+"cage/GSM849365_hg19_wgEncodeRikenCageK562CellPapClusters.bed.gz", name=row['name'])# + "cage/" + row["filename"], name=row['name'])
params.cage_reader.read_file(renamer={"0":"chr","1":"start","2":"end","4":"sigVal"})
cagePG.append(SmallChipSeqPredictorGenerator(params.cage_reader,params.window_size,N_closest=4))
#Read RNA-Seq data
params.RNAseqReader = RNAseqReader(fname=input_folder + "RNA-seq/rna-seqPolyA.tsvpre.txt",
name="RNA")
params.RNAseqReader.read_file(rename={ "Gene name": "gene",
"Gene start (bp)": "start",
"Gene end (bp)": "end",
"Chromosome/scaffold name": "chr",
"FPKM": "sigVal"},
sep="\t")
RNAseqPG = SmallChipSeqPredictorGenerator(params.RNAseqReader,
window_size=params.window_size,
N_closest=3)
# #Read TSS data
# metPG = []
# filemanes_df = pd.read_csv(input_folder + "methylation/filenames.csv")
# assert len(os.listdir(input_folder + 'peaks/')) - 1 == len(filenames_df['name'])
# for index, row in filemanes_df.iterrows():
# #print(row["name"])
# params.met_reader = ChiPSeqReader(input_folder + 'methylation/'+ row["filename"], name=row['name'])
# params.met_reader.read_file(renamer={"0":"chr","1":"start","2":"end","4":"sigVal"})
# metPG.append(SmallChipSeqPredictorGenerator(params.met_reader,params.window_size,N_closest=4))
#Read cage data
cagePG = []
filemanes_df = pd.read_csv(input_folder + "cage/filenames.csv")
# assert len(os.listdir(input_folder + 'cage/')) - 1 == len(filemanes_df['name'])
for index, row in filemanes_df.iterrows():
#print(row["name"])
params.cage_reader = ChiPSeqReader(input_folder + "cage/" +
row["filename"],
name=row['name'])
params.cage_reader.read_file(renamer={
"0": "chr",
"1": "start",
"2": "end",
"4": "sigVal"
})
cagePG.append(
SmallChipSeqPredictorGenerator(params.cage_reader,
params.window_size,
N_closest=4))
#Read RNA-Seq data
params.RNAseqReader = RNAseqReader(fname=input_folder +
"RNA-seq/rna-seqPolyA.tsvpre.txt",
name="RNA")