produce_N_motifs_in_TEs.py
f61890f69f76master

produce_N_motifs_in_TEs.py
View Options

			#! /usr/bin/env python3

			import os
			import subprocess
			import pandas as pd

			TE_motifs = pd.read_csv('../results/hg19_TEs_no_exons.txt', sep='\t', usecols=[0, 1, 2])


			windows_subfam_intersect_no_exonic_TEs = pd.read_csv('../data/windows_subfam_intersect_no_exonic_TEs.bed', header=None, sep='\t')

			windows_subfam_intersect_no_exonic_TEs[14] = windows_subfam_intersect_no_exonic_TEs[6] + '' + windows_subfam_intersect_no_exonic_TEs[7].astype(str) + '' + windows_subfam_intersect_no_exonic_TEs[8].astype(str) + "**" + \
			windows_subfam_intersect_no_exonic_TEs[9] + '' + windows_subfam_intersect_no_exonic_TEs[10].astype(str) + '' + windows_subfam_intersect_no_exonic_TEs[11] + '' + windows_subfam_intersect_no_exonic_TEs[12] + '' + windows_subfam_intersect_no_exonic_TEs[13]

			windows_subfam_intersect_no_exonic_TEs = windows_subfam_intersect_no_exonic_TEs.rename(columns={14:'TEs'})

			motifs_in_TEs_genes = windows_subfam_intersect_no_exonic_TEs.merge(TE_motifs, how='left', left_on='TEs', right_on='sequence_name')

			N = motifs_in_TEs_genes[[3, 'motif_id']].groupby([3, 'motif_id'])['motif_id'].aggregate('count').unstack(fill_value=0)
			N.index.name = None
			N.columns.name = None

			N.to_csv('../results/N_motifs_in_TEs.tsv', header=True, sep='\t')