data[p['name']] = pd.read_csv(os.path.join(out_path, p['file']),
comment='#')
data[p['name']].index = range(
0 + p.get('start_on_seq', 1),
p.get('start_on_seq', 1) + len(data[p['name']]))
data[p['name']].rename(columns={
p['datacolumn']: p['name'],
p.get('sitecolumn', 'Site'): 'Site_' + p['name']
},
inplace=True)
columns.append(p['name'])
site_column_df = pd.DataFrame(
{
'Site': [
'%d%s' % (n, l)
for n, l in zip(range(1, 1 + len(sets['seq'])), sets['seq'])
]
},
index=range(1, 1 + len(sets['seq'])))
result = pd.concat(data.values() + [site_column_df], axis=1)
# print result
temp = tempfile.TemporaryFile()
result.to_csv(temp)
temp.seek(0)
plot_prof_on_seq(temp,DNAseq=sets['seq'],\
graphshow=True,pngfileout=os.path.join(out_path,sets['pngfileout']),title=sets['name'],\
prof_columns=columns,seq_column="Site",rescale=sets['rescale'],zero_at=sets['zero_at'],\
ylab=sets.get('ylab',None),
colorb={'A':'#0b0','T':'#00b','G':'#fff','C':'#fff'},colorf={'A':'#fafafa','T':'#fafafa','G':'#000','C':'#000'},\
plot_options={'linewidth':1.0,'markersize':8.0,'figsize':(12,3),'fontsize':None,'legendloc':'upper right'})
temp.close()
'gg_601, Top Strand, Experiment B, Cleavage frequency profile along DNA'
}, {
'file':
'gg_601_BS_a_fitted_intensities.csv',
'seq':
BS_seq,
'pngfileout':
'gg_601_BS_a_cl_freq_profile.png',
'title':
'gg_601, Bottom Strand, Experiment A, Cleavage frequency profile along DNA'
}, {
'file':
'gg_601_BS_b_fitted_intensities.csv',
'seq':
BS_seq,
'pngfileout':
'gg_601_BS_b_cl_freq_profile.png',
'title':
'gg_601, Bottom Strand, Experiment B, Cleavage frequency profile along DNA'
}]
#Common code:
# will iterate through the lanes and plot the profile values along DNA sequence
# For interactive exploration of the plot set graphshow=True
###################################
for s in lane_data:
plot_prof_on_seq(os.path.join(out_path,s['file']),DNAseq=s['seq'],\
graphshow=True,pngfileout=os.path.join(out_path,s['pngfileout']),title=s['title'],\
prof_columns='Intensity',seq_column="Site",\
colorb={'A':'#0b0','T':'#00b','G':'#fff','C':'#fff'},colorf={'A':'#fafafa','T':'#fafafa','G':'#000','C':'#000'})
#by simply stacking columns from files together
#then provide column names to plotting functions as array
for p in sets['profiles']:
data[p['file']] = pd.read_csv(os.path.join(out_path, p['file']),
comment='#')
data[p['file']].index = range(1, 1 + len(data[p['file']]))
data[p['file']].rename(columns={
p['column']: p['name'],
'Site': 'Site_' + p['name']
},
inplace=True)
columns.append(p['name'])
site_column_df = pd.DataFrame(
{
'Site': [
'%d%s' % (n, l)
for n, l in zip(range(1, 1 + len(sets['seq'])), sets['seq'])
]
},
index=range(1, 1 + len(sets['seq'])))
result = pd.concat(data.values() + [site_column_df], axis=1)
temp = tempfile.TemporaryFile()
result.to_csv(temp)
temp.seek(0)
plot_prof_on_seq(temp,DNAseq=sets['seq'],\
graphshow=True,pngfileout=os.path.join(out_path,sets['pngfileout']),title=sets['name'],\
prof_columns=columns,seq_column="Site",normalize='together',zero_at=sets['zero_at'],\
colorb={'A':'#0b0','T':'#00b','G':'#fff','C':'#fff'},colorf={'A':'#fafafa','T':'#fafafa','G':'#000','C':'#000'})
temp.close()