params.ctcf_reader_orientOnly.keep_only_with_orient_data()
OrientBlocksCTCFpg = OrientBlocksPredictorGenerator(params.ctcf_reader_orientOnly,
params.window_size)
ConvergentPairPG = ConvergentPairPredictorGenerator(params.ctcf_reader, binsize=params.window_size)
#Read other chip-seq data
logging.info('create chipPG')
chipPG = []
filenames_df = pd.read_csv(input_folder + "peaks/filenames.csv")
# assert len(os.listdir(input_folder + 'peaks/')) - 1 == len(filenames_df['name'])
# print(len(os.listdir(input_folder + 'peaks/')))
# print(len(filenames_df['name']))
# proteins=set(["RAD21", "SMC3", "POLR2A", "H3K27ac", "H3K27me3", "DNase-seq", "H3K9me3", "H3K4me1", "H3K4me2", "H3K4me3", "YY1"])
for index, row in filenames_df.iterrows():
# if row["name"] in proteins:
params.chip_reader = ChiPSeqReader(input_folder + 'peaks/' + row["filename"] + '.gz', name=row['name'])
params.chip_reader.read_file()
chipPG.append(SmallChipSeqPredictorGenerator(params.chip_reader,params.window_size,N_closest=4))
# assert len(chipPG)==len(proteins)
# #
# #Read methylation data
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
params.ctcf_reader_orientOnly, params.window_size)
ConvergentPairPG = ConvergentPairPredictorGenerator(
params.ctcf_reader, binsize=params.window_size)
#Read other chip-seq data
logging.info('create chipPG')
chipPG = []
filenames_df = pd.read_csv(input_folder + "H1/Chip-seq/filenames.csv")
# assert len(os.listdir(input_folder + 'peaks/')) - 1 == len(filenames_df['name'])
# print(len(os.listdir(input_folder + 'peaks/')))
# print(len(filenames_df['name']))
# proteins=set(["RAD21", "SMC3", "POLR2A", "H3K27ac", "H3K27me3", "DNase-seq", "H3K9me3", "H3K4me1", "H3K4me2", "H3K4me3", "YY1"])
for index, row in filenames_df.iterrows():
# if row["name"] in proteins:
params.chip_reader = ChiPSeqReader(input_folder + 'H1/Chip-seq/' +
row["filename"],
name=row['name'])
params.chip_reader.read_file()
chipPG.append(
SmallChipSeqPredictorGenerator(params.chip_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"},