params.ctcf_reader_orientOnly.set_sites_orientation(
input_folder +
"CTCF/wgEncodeAwgTfbsHaibK562CtcfcPcr1xUniPk.narrowPeak-orient.bed"
)
params.ctcf_reader_orientOnly.keep_only_with_orient_data()
# set corresponding predictor generators and its options:
OrientBlocksCTCFpg = OrientBlocksPredictorGenerator(
params.ctcf_reader_orientOnly, params.window_size)
ConvergentPairPG = ConvergentPairPredictorGenerator(
params.ctcf_reader, binsize=params.window_size)
# Read RNA-Seq data
# RNA-seq_file format: this file should have fields "gene", "start", "end", "chr","FPKM"
# you can rename table fields below
params.RNAseqReader = RNAseqReader(fname=input_folder +
"RNA-seq/rna-seqPolyA.tsvpre.txt",
name="RNA")
# read RNA-seq data and rename table fields
params.RNAseqReader.read_file(rename={
"Gene name": "gene",
"Gene start (bp)": "start",
"Gene end (bp)": "end",
"Chromosome/scaffold name": "chr",
"FPKM": "sigVal"
},
sep="\t")
# set corresponding predictor generators and its options:
RNAseqPG = SmallChipSeqPredictorGenerator(
params.RNAseqReader, window_size=params.window_size, N_closest=3)
# write all predictor generators which you want to use:
# #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 + 'peaks/')) - 1 == len(filenames_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/GSE95111_genes.fpkm_table.txt.pre.txt",
name="RNA")
params.RNAseqReader.read_file(rename={
"Gene name": "gene",
"Gene start (bp)": "start",
"Gene end (bp)": "end",
"Chromosome/scaffold name": "chr",
"shCtrl-1_0": "sigVal"
},
sep="\t")
RNAseqPG = SmallChipSeqPredictorGenerator(
params.RNAseqReader, window_size=params.window_size, N_closest=3)
#Read E1 data
params.eig_reader = E1Reader()
params.eig_reader.read_files(
params.window_size,
N_closest=4)
ctcf_reader_orientOnly = ChiPSeqReader(CTCF_file, name="CTCF")
ctcf_reader_orientOnly.read_file()
ctcf_reader_orientOnly.set_sites_orientation(CTCF_orient_file)
ctcf_reader_orientOnly.keep_only_with_orient_data()
# set corresponding predictor generators and its options:
OrientBlocksCTCFpg = OrientBlocksPredictorGenerator(
ctcf_reader_orientOnly, params.window_size)
ConvergentPairPG = ConvergentPairPredictorGenerator(
params.ctcf_reader, binsize=params.window_size)
#Read RNA-Seq data
#RNA-seq_file format: this file should have fields "gene", "start", "end", "chr","FPKM"
#you can rename table fields below
params.RNAseqReader = RNAseqReader(RNA_seq_file, name="RNA")
#read RNA-seq data and rename table fields
params.RNAseqReader.read_file(rename={
"FPKM": "sigVal",
"Gene start (bp)": "start",
"Gene end (bp)": "end",
"Chromosome/scaffold name": "chr",
"Gene name": "gene"
},
sep="\t")
# set corresponding predictor generators and its options:
RNAseqPG = SmallChipSeqPredictorGenerator(params.RNAseqReader,
window_size=params.window_size,
N_closest=3)
params.pgs = [
OrientCtcfpg, NotOrientCTCFpg, OrientBlocksCTCFpg, RNAseqPG,
# # 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/GSM2533845_NPC_rep1.txtpre.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
# params.TssReader=TssReader(fname=input_folder + "TSS/NCBI_refSeq_hg19.bed", name="TSS")
# params.TssReader.read_file()
# TSSPG=Distance_to_TSS_PG(params.TssReader)
# 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 +
"mast_cells/RNA-seq/GSE75526_fpkm (1).pre.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)
params.pgs = [
OrientCtcfpg, NotOrientCTCFpg, OrientBlocksCTCFpg,
ConvergentPairPG, RNAseqPG