if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\ 'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Enhancers_set2' dirpath = yzer.get_path(dirpath) save_path = yzer.get_and_create_path( dirpath, 'Figures', 'Enhancer_counts') datasets = {} breed_sets = get_breed_sets() for i, (samples, short_names) in enumerate(breed_sets): oth_breed = breed_sets[1 - i] for j, sample_prefix in enumerate(short_names): sample_dirpath = yzer.get_filename(dirpath, sample_prefix) filename = yzer.get_filename(sample_dirpath, sample_prefix + '_enhancers.txt') data = yzer.import_file(filename) data = data.fillna(0) min_thresh = get_threshold('atac') data = data[data['tag_count'] >= min_thresh] datasets[sample_prefix] = data # How many denovo d7 enhancers are also in foxo1 kos? for celltype in ('hi', 'lo'): d7 = datasets['klrg{}_d7'.format(celltype)]
@author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/ThioMacs/Analysis_2013_02/' dirpath_bmdc = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/BMDCs/Analysis_2013_03/' dirpath = yzer.get_path(dirpath) dirpath_bmdc = yzer.get_path(dirpath_bmdc) img_dirpath = yzer.get_and_create_path(dirpath, 'bmdc_vs_thiomac') thio = yzer.import_file( yzer.get_filename(dirpath, 'transcript_vectors.txt')) bmdc = yzer.import_file( yzer.get_filename(dirpath_bmdc, 'transcript_vectors.txt')) sets = [] for data in (thio, bmdc): data = data.fillna(0) refseq = yzer.get_refseq(data) # Remove low tag counts #refseq = refseq[refseq['transcript_score'] >= 4] sets.append(refseq)
@author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'peak_scatterplots') if True: for main, compare, basal_cond in (('p65', 'GR', 'KLA'), ('GR', 'p65', 'Dex')): data = yzer.import_file( yzer.get_filename(dirpath, 'motifs', 'from_peaks', '{0}_kla_dex_vectors.txt'.format(main))) data = data.fillna(0) data = data.groupby(['id', 'chr_name'], as_index=False).mean() xcolname, ycolname = 'tag_count_2', 'tag_count' #'p65_kla_tag_count', 'p65_kla_dex_tag_count', data = data[data[ycolname] >= 10] cond_1 = (data['tag_count_3'] == 0) cond_2 = (data['tag_count_3'] > 0) & (data['tag_count_3'] < data['tag_count_4']) cond_3 = (data['tag_count_3'] > 0) & (data['tag_count_3'] >= data['tag_count_4']) ax = None for show_points in (True, False): ax = yzer.scatterplot(
from matplotlib import pyplot import numpy if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'piecharts_from_p65_gr') if True: for main, compare, basal_cond in ( ('GR', 'p65', 'Dex'), ('p65', 'GR', 'KLA'), ): data = yzer.import_file( yzer.get_filename(dirpath, 'motifs', 'from_peaks', '{0}_kla_dex_vectors.txt'.format(main))) # Get nearby peaks first ids_with_nearby = data[ (data['distance_to_tss_2'].isnull() == False) & (data['distance_to_peak_2'] <= 1000)]['id'] data = data.fillna(0) data = data.groupby(['id', 'chr_name'], as_index=False).mean() data = data[data['tag_count'] >= 10] total = len(data) has_nearby_peak = data['id'].isin(ids_with_nearby) bound_by_main_not_comp_not_basal = data[~has_nearby_peak & (data['tag_count_3'] < 10)]
''' from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.dataanalysis.misc.rodrigo.samples import sample_name,\ get_threshold if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/' +\ 'Miscellaneous_Collaborations/Rodrigo_CD8s_2014_09/Promoters' dirpath = yzer.get_path(dirpath) cond, seq, breed = ('naive', 'atac', '') wt_prefix = sample_name(cond, seq, breed) ko_prefix = sample_name(cond, seq, 'foxo1_ko_') wt_dirpath = yzer.get_filename(dirpath, wt_prefix) ko_dirpath = yzer.get_filename(dirpath, ko_prefix) wt_filename = yzer.get_filename(wt_dirpath, wt_prefix + '_promoters.txt') ko_filename = yzer.get_filename(ko_dirpath, ko_prefix + '_promoters.txt') wt_data = yzer.import_file(wt_filename) wt_data = wt_data.fillna(0) ko_data = yzer.import_file(ko_filename) ko_data = ko_data.fillna(0) min_thresh = get_threshold(seq) wt_data = wt_data[wt_data['tag_count'] >= min_thresh] ko_data = ko_data[ko_data['tag_count'] >= min_thresh]
''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero from glasslab.dataanalysis.misc.gr_project_2012.v1.enhancer_subsets_for_supershift import ucsc_link_cleanup import numpy if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) peak_type = 'p65' img_dirpath = yzer.get_and_create_path(dirpath, 'boxplots_non_refseq_by_{0}'.format(peak_type)) transcripts = yzer.import_file(yzer.get_filename(dirpath, 'motifs', 'transcript_vectors_with_nearby_peaks.txt')) if True: pu_1 = False for ratio in (1.5, 2, 3): data = transcripts[transcripts['refseq'] == 'f'] data = data[data['has_infrastructure'] == 0] data = data[data['length'] < 6000] data = data[data['dex_1_lfc'] < 1] data = data[data['kla_1_lfc'] >= 1] data = data[data['gr_kla_dex_tag_count'] > 0] data = data[data['gr_fa_kla_dex_tag_count'] == 0] print len(data) if pu_1: data = data[data['pu_1_kla_tag_count'] + data['pu_1_kla_tag_count'] > 0]
''' Created on Jun 26, 2012 @author: karmel ''' from glasslab.dataanalysis.misc.gr_project_2012.elongation import set_up_sequencing_run_ids, \ get_sequencing_run_id_sets, get_rep_string, total_tags_per_run from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer if __name__ == '__main__': grapher = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = grapher.get_path(dirpath) filename = grapher.get_filename(dirpath, 'transcript_vectors.txt') data = grapher.import_file(filename) run_ids = set_up_sequencing_run_ids() dmso, kla, kla_dex, all_dmso, all_kla, all_kla_dex = get_sequencing_run_id_sets( ) total_tags = total_tags_per_run() # Norm sum scalars listed for all, group 1, group 2, group 3, group 4 kla_scalars = [1.223906, 1.281572, 1.118363, 1.104860, 1.503260] kla_dex_scalars = [1.182574, 1.147695, 1.248636, 1.069588, 1.388871] dex_over_kla_scalars = [1.069073, 0.967659, 1.122628, 1.008758, 0.927466] for i, scalar in enumerate(kla_scalars): data = grapher.normalize(data, 'kla_{0}tag_count'.format(get_rep_string(i)),
Note: Made font.weight = bold and axes.titlesize = 24, font.size = 16 in matplotlibrc ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/vs_homer' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots') data = yzer.import_file( yzer.get_filename(dirpath, 'tag_count_by_refseq.txt')) data['sum'] = nonzero(data['sum'].fillna(0)) homer_data = yzer.import_file( yzer.get_filename(dirpath, 'RNA_GroSeq_CountsGenes.txt')) homer_data['sequence_identifier'] = homer_data['Gene ID'] homer_data['homer_tag_count'] = nonzero(homer_data[ 'ThioMac-GroSeq-notx-110513/ genes (Total: 12166480.0) normFactor 0.82'] .fillna(0)) homer_data = homer_data[['sequence_identifier', 'homer_tag_count']] merged = data.merge(homer_data, how='inner', on='sequence_identifier') merged = merged.fillna(1) if True: ax = yzer.scatterplot(merged,
@author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells/Oshea_enhancers/ctcf_stat1_overlap' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'figures') data = yzer.import_file( yzer.get_filename(dirpath, 'ctcf_with_stat1_binding.txt')).fillna(0) with_stat1 = data[data['p2_tag_count'] > 0] without_stat1 = data[data['p2_tag_count'] == 0] if True: ax = yzer.piechart( [len(with_stat1), len(without_stat1)], ['CTCF sites with STAT1', 'CTCF sites without STAT1'], title='DP Thymocyte CTCF Sites with STAT1 in Th1 Cells', save_dir=img_dirpath, show_plot=True) data['tag_count_nonzero'] = nonzero(data['tag_count']) data['p2_tag_count_nonzero'] = nonzero(data['p2_tag_count']) ax = yzer.scatterplot( data, 'tag_count_nonzero',
return none, lt, lt_with_gain, nc, nc_with_gain, gt, gt_with_gain def get_filters_transcript(subdata, xcol, ycol): down_in_kla = subdata['kla_1_lfc'] <= -1 nc_in_kla = subdata['kla_1_lfc'].abs() < 1 up_in_kla = subdata['kla_1_lfc'] >= 1 & (subdata['dex_over_kla_1_lfc'] > -.58) trans = up_in_kla & (subdata['dex_over_kla_1_lfc'] <= -.58) return down_in_kla, nc_in_kla, up_in_kla, trans if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'bargraphs_from_p65_gr') data = yzer.import_file(yzer.get_filename(dirpath, 'motifs','transcript_vectors.txt')) data = data[data['has_refseq'] == 1] if True: for main, compare, basal_cond, comp_cond in (('p65','GR', 'KLA', 'Dex'),('GR','p65', 'Dex', 'KLA')): data = data.fillna(0) data = data.groupby(['id','chr_name'],as_index=False).mean() tag_count_1 = '{0}_kla_dex_tag_count'.format(main.lower()) tag_count_2 = '{0}_{1}_tag_count'.format(main.lower(), basal_cond.lower()) tag_count_3 = '{0}_kla_dex_tag_count'.format(compare.lower()) tag_count_4 = '{0}_{1}_tag_count'.format(compare.lower(), comp_cond.lower()) datasets = [data[filterset] for filterset in get_filters_many(data, tag_count_1, tag_count_2, tag_count_3, tag_count_4)]
condition, or with an unequal number of genes in each condition. For those, we will sort genes in each condition by number of interactions, and allow for null values when there is a number mismatch. ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher import numpy kla_col = 'kla_6h_lfc' if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_sets') img_dirpath = yzer.get_and_create_path(dirpath, 'genes_to_average_enhancer_lfc') keys = ('all', 'notx', 'kla', 'notx_only', 'kla_only', 'shared_enh') if True: interactions = yzer.import_file( yzer.get_filename(data_dirpath, 'transcript_pairs_refseq_with_me2.txt')) interactions = interactions[interactions['count'] > 1] all_transcripts = yzer.import_file( yzer.get_filename(data_dirpath, 'transcript_vectors.txt')) transcripts = all_transcripts[['id', 'kla_lfc', 'kla_6h_lfc']]
data['ucsc_link_nod'] = data['ucsc_link_nod'].map( lambda x: '<a href={0} target="_blank">UCSC</a>'.format( x.replace('nod_balbc', 'gr_project_2012'))) return data if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) save_dirpath = yzer.get_and_create_path(dirpath, 'subgroups_for_supershift') transcripts = yzer.import_file( yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt')) data = transcripts[transcripts['refseq'] == 'f'] data = data[data['has_infrastructure'] == 0] data = data[data['length'] < 6000] data = data[data['dex_1_lfc'] < 1] data = data[data['kla_1_lfc'] >= 1] data = data.fillna(0) data = ucsc_link_cleanup(data) if False: # First get sets for Negative controls tfs = ['p65', 'pu_1', 'gr', 'gr_fa'] for tf in tfs:
@author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells/Oshea_enhancers/ctcf_across_celltypes' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'figures') dp = yzer.import_file( yzer.get_filename(dirpath, 'dp_with_thiomac_ctcf.txt')).fillna(0) thio = yzer.import_file( yzer.get_filename(dirpath, 'thiomac_with_dp_ctcf.txt')).fillna(0) # Get venn-diagram sets only_dp = dp[dp['thiomac_ctcf_tag_count'] == 0] only_thio = thio[thio['dp_ctcf_tag_count'] == 0] shared = dp[dp['thiomac_ctcf_tag_count'] != 0] shared_check = thio[thio['dp_ctcf_tag_count'] != 0] print len(only_dp), len(only_thio), len(shared), len(shared_check) data = shared.append(only_dp, ignore_index=True) data = data.append(only_thio, ignore_index=True) data['dp_nonzero'] = nonzero(data['dp_ctcf_tag_count']) data['thio_nonzero'] = nonzero(data['thiomac_ctcf_tag_count'])
data['region_end'] = data.apply(lambda row: int( max(row['transcription_end'], row['transcription_end_5'])), axis=1) # Get rid of pairs that are really just overlapping data = data[data['region_end'] - data['region_start'] >= 300] #data = data[data['region_end'] - data['region_start'] <= 10000] return data if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) motif_dirpath = yzer.get_filename(dirpath, 'motifs', 'from_peaks') transcripts = yzer.import_file( yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt')) transcripts['glass_transcript_id'] = transcripts['id'] if True: all_data = yzer.import_file( yzer.get_filename( dirpath, 'redistribution', 'p65_peaks_bigger_in_kla_dex_with_nearby_bigger_kla_peaks.txt') ) data = get_high_quality_pairs(all_data, transcripts) ''' # Print these out to send to collaborators.
@author: karmel What do enhancers that are gaining methyl with KLA look like? ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero from collections import OrderedDict if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_sets') kla_col = 'kla_lfc' tss_only = False img_dirpath = yzer.get_and_create_path( dirpath, 'interactions_by_kla_lfc', tss_only and 'genic' or 'all_interactions', 'lfc_2') # File generated in novel_me2_sites enhancers = yzer.import_file( yzer.get_filename( data_dirpath, 'all_enhancers_with_me2_and_{0}interaction_stats.txt'.format( tss_only and 'tss_' or '')))
@author: karmel What do enhancers that are gaining methyl with KLA look like? ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero from collections import OrderedDict if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_sets') kla_col = 'kla_lfc' tss_only = False img_dirpath = yzer.get_and_create_path( dirpath, 'novel_me2_sites', tss_only and 'genic' or 'all_interactions', 'ratio_10') if False: enhancers = yzer.import_file( yzer.get_filename(data_dirpath, 'all_distal_enhancers_inc_me2.txt')) all_transcripts = yzer.import_file( yzer.get_filename(data_dirpath, 'transcript_vectors.txt'))
''' Created on Jan 3, 2013 @author: karmel Plot gen-enhancer me2 LFC; do we see correlation? ''' from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero import numpy if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_sets') img_dirpath = yzer.get_and_create_path(dirpath, 'gene_enhancer_me2_lfc', 'scatterplots') interactions = yzer.import_file( yzer.get_filename( data_dirpath, 'transcript_pairs_enhancer_with_anything_with_me2_inc_me2_counts.txt' )) interactions = interactions[interactions['count'] > 1] all_transcripts = yzer.import_file( yzer.get_filename(data_dirpath, 'transcript_vectors.txt')) for me2_timepoint in ('6h', '24h'): me2_col = 'me2_{0}_ratio'.format(me2_timepoint) kla_col = 'kla_lfc'
from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells/Oshea_enhancers/peak_overlaps' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'figures') peak_pretty = 'p300' peak = peak_pretty.lower() th1 = yzer.import_file( yzer.get_filename(dirpath, 'th1_with_th2_{0}.txt'.format(peak))).fillna(0) th2 = yzer.import_file( yzer.get_filename(dirpath, 'th2_with_th1_{0}.txt'.format(peak))).fillna(0) # Filter out promoters th1 = th1[th1['tss_id'] == 0] th2 = th2[th2['tss_id'] == 0] # Get venn-diagram sets only_th1 = th1[th1['p2_id'] == 0] only_th2 = th2[th2['p2_id'] == 0] shared = th1[th1['p2_id'] != 0] shared_check = th2[th2['p2_id'] != 0] print len(only_th1), len(only_th2), len(shared), len(shared_check)
''' Created on Oct 8, 2012 @author: karmel ''' from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from matplotlib import pyplot from glasslab.dataanalysis.misc.gr_project_2012.boxplots_redistribution_pairs import get_high_quality_pairs if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' dirpath = yzer.get_path(dirpath) motif_dirpath = yzer.get_filename(dirpath, 'motifs', 'from_peaks') transcripts = yzer.import_file( yzer.get_filename(dirpath, 'motifs', 'transcript_vectors.txt')) transcripts['glass_transcript_id'] = transcripts['id'] if True: all_data = yzer.import_file( yzer.get_filename( dirpath, 'redistribution', 'p65_peaks_bigger_in_kla_dex_with_nearby_bigger_kla_peaks.txt') ) data = get_high_quality_pairs(all_data, transcripts) data = data.groupby(['id', 'chr_name'], as_index=False).mean()
Note: Made font.weight = bold and axes.titlesize = 24 in matplotlibrc ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import pandas_min from glasslab.dataanalysis.misc.demoatlas.rpkm_to_score import PrettyAxisGrapher if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/Post_gene_transcripts' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots') data = yzer.import_file(yzer.get_filename(dirpath,'within_1kb_gap_500bp_with_nc.txt')) refseq = yzer.import_file(yzer.get_filename(dirpath,'expressed_refseq_gap_500bp.txt')) refseq_with_runoff = refseq[refseq['id'].isin(data['gene_id'])] refseq_no_runoff = refseq[~refseq['id'].isin(data['gene_id'])] if True: print len(refseq_no_runoff) print refseq_no_runoff.tail(100).to_string() # Calculate length of runoff data['length'] = data['transcription_end'] - data['transcription_start'] + 1 data['gene_length'] = data['gene_end'] - data['gene_start'] + 1 # What might be correlated with length of runoff? if False: yzer.scatterplot(data, 'gene_length', 'length', log=True)
''' Created on Oct 26, 2012 @author: karmel ''' from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from matplotlib import pyplot if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/enhancer_classification' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'piecharts_for_genes_by_mechanism') data = yzer.import_file(yzer.get_filename(dirpath, 'enhancers_with_nearest_gene.txt')) data['ucsc_link_nod'] = data['ucsc_link_nod'].apply(lambda s: s.replace('nod_balbc','gr_project_2012')) draw_pies = True min_tags = 30 ratio = 1.5 # Make sure we have dimethyl data = data[data.filter(like='h3k4me2').max(axis=1) > min_tags] data = data[data['minimal_distance'] >= 1000] #data = yzer.collapse_strands(data) transcripts = yzer.import_file(yzer.get_filename(dirpath, 'transcript_vectors.txt')) transcripts['nearest_refseq_transcript_id'] = transcripts['id'] # Join, keeping all transcripts data = data.merge(transcripts, how='left', on='nearest_refseq_transcript_id', suffixes=['','_trans'])
if __name__ == '__main__': enhancer_counts = True # Are we looking at enhancer interactions (False) or counts (True)? yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/enhancers_by_gene_length' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots') counted = enhancer_counts and 'enhancer' or 'interaction' # The first set has length with interaction counts; # the second has length for all transcripts, even those without interactions. # We want to merge such that we add the interaction-less genes with a count of 0. data = yzer.import_file(yzer.get_filename(dirpath,'{0}_counts_by_refseq.txt'.format(counted))) all_data = yzer.import_file(yzer.get_filename(dirpath,'refseq_all.txt')) all_data = all_data[~all_data['id'].isin(data['id'])] data = pandas.concat([data, all_data]) data = data.reset_index().fillna(0) notx = data[data['sequencing_run_id'] == 765] kla_30m = data[data['sequencing_run_id'] == 766] kla_4h = data[data['sequencing_run_id'] == 773] no_intxns = data[data['sequencing_run_id'] == 0] # Zero won't show up in a log plot, so add one. no_intxns['count'] = 1 ax = yzer.scatterplot(no_intxns,
Note: Made font.weight = bold and axes.titlesize = 24, font.size = 16 in matplotlibrc ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/Demo-data' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'refseq_to_homer/large_gap_500bp') data = yzer.import_file( yzer.get_filename(dirpath, 'refseq_tag_counts_500bp.txt')) data['sum'] = nonzero(data['sum'].fillna(0)) homer_data = yzer.import_file( yzer.get_filename(dirpath, 'RNA_GroSeq_CountsGenes.txt')) homer_data['sequence_identifier'] = homer_data['Gene ID'] homer_data['homer_tag_count'] = nonzero(homer_data[ 'ThioMac-GroSeq-notx-110513/ genes (Total: 12166480.0) normFactor 0.82'] .fillna(0)) homer_data = homer_data[['sequence_identifier', 'homer_tag_count']] merged = data.merge(homer_data, how='inner', on='sequence_identifier') merged = merged.fillna(1) if True: ax = yzer.scatterplot(merged,
@author: karmel Note: Made font.weight = normal and axes.titlesize = 24 in matplotlibrc ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.dataanalysis.misc.demoatlas.rpkm_to_score import PrettyAxisGrapher if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/Glass Atlas/NAR_review_data/Post-gene' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'scatterplots') data = yzer.import_file( yzer.get_filename(dirpath, 'post_gene_transcripts.txt')) refseq = yzer.import_file( yzer.get_filename(dirpath, 'all_expressed_refseq.txt')) refseq_with_runoff = refseq[refseq['id'].isin(data['gene_id'])] refseq_no_runoff = refseq[~refseq['id'].isin(data['gene_id'])] if False: print len(refseq_no_runoff) print refseq_no_runoff.tail(100).to_string() # Calculate length of runoff data[ 'length'] = data['transcription_end'] - data['transcription_start'] + 1 data['gene_length'] = data['gene_end'] - data['gene_start'] + 1 # What might be correlated with length of runoff?
from matplotlib import pyplot from glasslab.utils.functions import nonzero from glasslab.dataanalysis.misc.gr_project_2012.v1.elongation import total_tags_per_run if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/GR_Analysis/enhancer_classification' dirpath = yzer.get_path(dirpath) consistent = False img_dirpath = yzer.get_and_create_path( dirpath, 'boxplots_by_expression', consistent and 'consistent' or 'rep1') data = yzer.import_file( yzer.get_filename(dirpath, 'enhancers_with_nearest_gene.txt')) data['ucsc_link_nod'] = data['ucsc_link_nod'].apply( lambda s: s.replace('nod_balbc', 'gr_project_2012')) draw_pies = True min_tags = 30 ratio = 1.5 # Make sure we have dimethyl data = data[data.filter(like='h3k4me2').max(axis=1) > min_tags] data = data[data['minimal_distance'] >= 1000] transcripts = yzer.import_file( yzer.get_filename(dirpath, 'transcript_vectors.txt')) transcripts['nearest_refseq_transcript_id'] = transcripts['id'] data = data.merge(transcripts, how='left',
''' Created on Jan 9, 2013 @author: karmel Do novel interactions gain or lose me2? ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_sets') img_dirpath = yzer.get_and_create_path(dirpath, 'novel_interactions_kla_lfc', 'all_interactions') interactions = yzer.import_file( yzer.get_filename( data_dirpath, 'transcript_pairs_enhancer_with_anything_with_me2_inc_me2_counts.txt' )) interactions = interactions[interactions['count'] > 1] all_transcripts = yzer.import_file( yzer.get_filename(data_dirpath, 'transcript_vectors.txt')) kla_col = 'kla_lfc'
''' Created on Sep 7, 2012 @author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher if __name__ == '__main__': grapher = SeqGrapher() base_dirpath = 'karmel/Desktop/Projects/Classes/Rotations/Finland_2012/GR_Project/' base_dirpath = grapher.get_path(base_dirpath) dirpath = grapher.get_filename(base_dirpath, 'motifs') filename = grapher.get_filename(dirpath, 'transcript_vectors.txt') data = grapher.import_file(filename) # Boxplots for gr_dex peaks by lfc in Dex if False: #data = data[data['distal'] == 't'] data = data[data['has_refseq'] == 1] down = data[data['dex_1_lfc'] <= -1] up = data[data['dex_1_lfc'] >= 1] nc = data[abs(data['dex_1_lfc']) < 1] key = 'p65_kla_tag_count' datasets = [down[key],nc[key],up[key]] datasets = [d['p65_kla_dex_tag_count'] - d[key] for d in [down, nc, up]]
Created on Feb 12, 2013 @author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.dataanalysis.motifs.motif_analyzer import MotifAnalyzer if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/NOD_BALBc/ThioMacs/Analysis_2013_02/' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'srf_binding') data = yzer.import_file( yzer.get_filename(dirpath, 'transcript_vectors.txt')) data = data.fillna(0) data = data[data[['nod_notx_1h_tag_count', 'balb_notx_1h_tag_count']].max( axis=1) >= 10] subsets = [ data, data[(data['has_refseq'] == 1) & (data['transcript_score'] >= 4)], data[(data['distal'] == 't') & (data['h3k4me2_tag_count'] > 10)] ] # Add in nearest genes for enhancers enh = subsets[2].copy() nearest_genes = yzer.import_file( yzer.get_filename(dirpath, 'enhancers_with_nearest_genes.txt'))
''' Created on Jan 30, 2013 @author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from collections import OrderedDict if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/HiC/' dirpath = yzer.get_path(dirpath) data_dirpath = yzer.get_filename(dirpath, 'enhancer_rewiring_lfc') transcripts = yzer.import_file( yzer.get_filename(dirpath, 'enhancer_sets', 'transcript_vectors.txt')) sets = OrderedDict(( ('all', yzer.import_file(yzer.get_filename(data_dirpath, 'all_vectors.cdt'))), #('all_6h', yzer.import_file(yzer.get_filename(data_dirpath,'kla_6h','all_vectors.cdt'))), ('rewired', yzer.import_file( yzer.get_filename(data_dirpath, 'rewired_vectors.cdt'))), #('rewired_6h', yzer.import_file(yzer.get_filename(data_dirpath,'kla_6h','rewired_vectors.cdt'))), ('shared', yzer.import_file(yzer.get_filename(data_dirpath, 'shared_vectors.cdt'))), )) for key, val in sets.items():
@author: karmel ''' from __future__ import division from glasslab.dataanalysis.graphing.seq_grapher import SeqGrapher from glasslab.utils.functions import nonzero if __name__ == '__main__': yzer = SeqGrapher() dirpath = 'karmel/Desktop/Projects/GlassLab/Notes_and_Reports/CD4TCells/Oshea_enhancers/peak_overlaps' dirpath = yzer.get_path(dirpath) img_dirpath = yzer.get_and_create_path(dirpath, 'figures') peak = 'p300' th1 = yzer.import_file( yzer.get_filename(dirpath, 'th1_with_th2_{0}.txt'.format(peak))).fillna(0) th2 = yzer.import_file( yzer.get_filename(dirpath, 'th2_with_th1_{0}.txt'.format(peak))).fillna(0) # Filter out promoters th1 = th1[th1['tss_id'] == 0] th2 = th2[th2['tss_id'] == 0] th1['th1_tag_count'] = nonzero(th1['tag_count']) th1['th2_tag_count'] = nonzero(th1['p2_tag_count']) th2['th1_tag_count'] = nonzero(th2['tag_count']) th2['th2_tag_count'] = nonzero(th2['p2_tag_count']) with_ctcf = th1[th1['ctcf_tag_count'] > 0] without_ctcf = th1[th1['ctcf_tag_count'] == 0]