def degree_hist(dg_txt=None):
if dg_txt is None:
dg_txt = '/Share/home/zhangqf7/gongjing/zebrafish/data/paris/shi-zp-5-rep-combine/27-DG.txt'
dg_dict = read_dg_txt(dg_txt)
trans_dict = loadTransGtfBed2()
RRI_dict = nested_dict(2, list)
for i,j in dg_dict.items():
if j['lchr'] != j['rchr']:
RRI_dict[j['RRI_type']][j['lchr']].append(j['rchr'])
RRI_dict[j['RRI_type']][j['rchr']].append(j['lchr'])
else:
RRI_dict[j['RRI_type']][j['lchr']].append(j['rchr'])
for i in ['inter', 'intra']:
savefn = dg_txt.replace('.txt', '.%s.degree.txt'%(i))
degree_ls_ls = [[], [], []]
with open(savefn, 'w') as SAVEFN:
for k,v in RRI_dict[i].items():
print >>SAVEFN, '\t'.join(map(str, [ k, trans_dict[k]['type'], len(v), len(set(v)), ','.join(list(set(v))) ]))
degree_ls_ls[0].append(len(set(v)))
if trans_dict[k]['type'] == 'mRNA':
degree_ls_ls[1].append(len(set(v)))
if trans_dict[k]['type'] == 'lncRNA':
degree_ls_ls[2].append(len(set(v)))
degree_mean_ls = [np.mean(i) for i in degree_ls_ls]
gj.cumulate_dist_plot(ls_ls=degree_ls_ls,ls_ls_label=['%s, mean=%.2f'%(i,j) for i,j in zip(['all', 'mRNA', 'lncRNA'], degree_mean_ls)], bins=40,title='degree distribution',ax=None,savefn=savefn.replace('.txt', '.pdf'),xlabel='log2(# of interacting partners)',ylabel=None,add_vline=None,add_hline=None,log2transform=1,xlim=None,ylim=None)
def read_len_dist_all(
savefn='/Share/home/zhangqf5/gongjing/Kethoxal_RNA_structure/data/PE100/read_len_dist_all.png'
):
gj.printFuncRun('read_len_dist_all')
gj.printFuncArgs()
library_info_dict = library_info()
trimmed_dict = library_info_dict['lib']['trimmed']
print trimmed_dict
read_len_ls_ls = []
read_cut_len_ls_ls = []
fig, ax = plt.subplots(3, 1, sharex=True, figsize=(14, 16))
color_ls = gj.sns_color_ls()
sample_ls = []
for n, (i, j) in enumerate(trimmed_dict.items()):
sample_ls.append(i)
print i, j
fq_len_txt = j + '.len.txt'
trimlog = j + '.trimlog'
df = pd.read_csv(fq_len_txt, sep='\s+', header=None)
df.columns = ['# of reads', 'read length']
df.plot(ax=ax[0], x='read length', y='# of reads', label=i)
df_trimlog = pd.read_csv(trimlog, header=None, sep='\s+')
df_trimlog.columns = [
'seq_name', 'sample_name', 'survive_len', 'survive_start',
'survive_end', 'cut_len'
]
df_trimlog = df_trimlog[df_trimlog['cut_len'] > 0]
cut_len_ls = list(df_trimlog['cut_len'])
n = [[i] * j for i, j in zip(df['read length'], df['# of reads'])]
n = gj.ls_ls_flat(n)
read_len_ls_ls.append(n)
read_cut_len_ls_ls.append(cut_len_ls)
gj.cumulate_dist_plot(read_len_ls_ls,
ls_ls_label=sample_ls,
bins=40,
title=None,
ax=ax[1],
savefn=None,
xlabel='Length',
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0)
gj.cumulate_dist_plot(read_cut_len_ls_ls,
ls_ls_label=sample_ls,
bins=40,
title=None,
ax=ax[2],
savefn=None,
xlabel='Length',
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0)
plt.tight_layout()
plt.savefig(savefn)
plt.close()
gj.printFuncRun('read_len_dist_all')
def read_len_dist(
fq='/Share/home/zhangqf5/gongjing/Kethoxal_RNA_structure/data/PE100/CHe-XC-M1K_S3_L005_R1_001.trimmed.fastq'
):
gj.printFuncRun('read_len_dist')
gj.printFuncArgs()
fq_len_txt = fq + '.len.txt'
subprocess.call([
"awk '{if(NR%%4==2) print length($1)}' %s| sort|uniq -c|sort -k2,2n > %s "
% (fq, fq_len_txt)
],
shell=True) # use double % to escape
df = pd.read_csv(fq_len_txt, sep='\s+', header=None)
df.columns = ['# of reads', 'read length']
df_plot = df[['read length', '# of reads']]
print df_plot
fig, ax = plt.subplots(2, 1, sharex=True)
df.plot(ax=ax[0], x='read length', y='# of reads')
df.plot(kind='scatter', ax=ax[0], x='read length', y='# of reads')
df_trimlog = pd.read_csv(fq + '.trimlog', header=None, sep='\s+')
df_trimlog.columns = [
'seq_name', 'sample_name', 'survive_len', 'survive_start',
'survive_end', 'cut_len'
]
df_trimlog = df_trimlog[df_trimlog['cut_len'] > 0]
cut_len_ls = list(df_trimlog['cut_len'])
n = [[i] * j for i, j in zip(df['read length'], df['# of reads'])]
n = gj.ls_ls_flat(n)
gj.cumulate_dist_plot(
[n, cut_len_ls],
ls_ls_label=['kethoxal read length', 'kethoxal read cut length'],
bins=40,
title=None,
ax=ax[1],
savefn=None,
xlabel='Length',
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0)
plt.tight_layout()
plt.savefig(fq + '.len.png')
plt.close()
gj.printFuncRun('read_len_dist')
def main():
notreat = compare_corr(
out1=
'/Share/home/zhangqf5/gongjing/Kethoxal_RNA_structure/data/16-11-14_7_library_total_Kethoxal_remove/kethoxalseq_noTreat.out',
savefn=
'/Share2/home/zhangqf5/gongjing/Kethoxal_RNA_structure/Keth-seq/results/F2b.kethoxal-notreat.icshape.corr.txt',
label='kethoxalseq:icSHAPE')
gj.cumulate_dist_plot(
ls_ls=[notreat[-2]],
ls_ls_label=[
'kethoxal vs icshape',
],
bins=40,
title=None,
ax=None,
savefn=
'/Share2/home/zhangqf5/gongjing/Kethoxal_RNA_structure/Keth-seq/results/F2b.kethoxal_icshape_corr.pdf',
xlabel=None,
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0)
tx_corr_scatter()
from glob import glob
ls_ls, ls_ls_label = [], []
file_ls = sys.argv[1:-1]
savefn = sys.argv[-1]
print "input: ", file_ls
print "output: ", savefn
for sample_fn in file_ls:
df = pd.read_csv(sample_fn,
header=None,
sep='\t',
keep_default_na=False,
na_values=['n/a'])
df.dropna(axis=0, how='any', inplace=True)
ls_ls.append(list(df[4]))
ls_ls_label.append(sample_fn.split('/')[-1])
# savefn = './test.png'
gj.cumulate_dist_plot(ls_ls=ls_ls,
ls_ls_label=ls_ls_label,
bins=40,
title=None,
ax=None,
savefn=savefn,
xlabel=None,
ylabel='',
add_vline=[0.6, 0.7],
add_hline=[0, 0.3, 0.4, 1],
log2transform=0,
xlim=[-0.05, 1.05],
ylim=[-0.05, 1.05])
def TE_rep_corr(TE1, TE2, savefn, label1='control', label2='RK33'):
df_TE1 = pd.read_csv(TE1, header=0, sep='\t')
df_TE2 = pd.read_csv(TE2, header=0, sep='\t')
fig, ax = plt.subplots()
ls_ls = [
list(df_TE2['log2(TE(%s))' % (label1)]),
list(df_TE2['log2(TE(%s))' % (label2)])
]
# df_TE1[['log2(TE(control))', 'log2(TE(RK33))']].plot(kind='bar', ax=ax)
gj.cumulate_dist_plot(ls_ls=ls_ls,
ls_ls_label=[label1, label2],
bins=40000,
title=None,
ax=None,
savefn=TE1 + '.cumulate.png',
xlabel=None,
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0,
xlim=None,
ylim=None)
df_merge = df_TE1.merge(df_TE2, on='transcript', how='inner')
df_merge['mean(TE(%s))' %
(label1)] = (df_merge['TE(%s)_x' %
(label1)] + df_merge['TE(%s)_y' %
(label1)]) / 2.0
df_merge['mean(TE(%s))' %
(label2)] = (df_merge['TE(%s)_x' %
(label2)] + df_merge['TE(%s)_y' %
(label2)]) / 2.0
df_merge['log2(mean(TE(%s)))' % (label1)] = np.log2(
df_merge['mean(TE(%s))' % (label1)])
df_merge['log2(mean(TE(%s)))' % (label2)] = np.log2(
df_merge['mean(TE(%s))' % (label2)])
ls_ls = [
list(df_merge['log2(mean(TE(%s)))' % (label1)]),
list(df_merge['log2(mean(TE(%s)))' % (label2)])
]
p = gj.ks_2samp(ls_ls[0], ls_ls[1])
print "pvalue: %s" % (p)
gj.cumulate_dist_plot(ls_ls=ls_ls,
ls_ls_label=[label1, label2],
bins=40000,
title=None,
ax=None,
savefn=TE1 + '.cumulate.mean.pdf',
xlabel=None,
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0,
xlim=[-5, 5],
ylim=None)
df_merge.to_csv(savefn, header=True, index=False, sep='\t')
fig, ax = plt.subplots(figsize=(8, 8))
df_merge.plot(kind='scatter',
x='log2(TE(%s))_x' % (label1),
y='log2(TE(%s))_y' % (label1),
ax=ax)
r, p = stats.pearsonr(df_merge['log2(TE(%s))_x' % (label1)],
df_merge['log2(TE(%s))_y' % (label1)])
plt.title("r: %s, p:%s" % (r, p))
lims = [
np.min([ax.get_xlim(), ax.get_ylim()]), # min of both axes
np.max([ax.get_xlim(), ax.get_ylim()]), # max of both axes
]
# now plot both limits against eachother
ax.plot(lims, lims, 'k-', alpha=0.75, zorder=0)
ax.set_aspect('equal')
ax.set_xlim(lims)
ax.set_ylim(lims)
plt.tight_layout()
plt.savefig(savefn.replace('.txt', '.%s.pdf' % (label1)))
plt.close()
fig, ax = plt.subplots(figsize=(8, 8))
df_merge.plot(kind='scatter',
x='log2(TE(%s))_x' % (label2),
y='log2(TE(%s))_y' % (label2),
ax=ax)
r, p = stats.pearsonr(df_merge['log2(TE(%s))_x' % (label2)],
df_merge['log2(TE(%s))_y' % (label2)])
plt.title("r: %s, p:%s" % (r, p))
lims = [
np.min([ax.get_xlim(), ax.get_ylim()]), # min of both axes
np.max([ax.get_xlim(), ax.get_ylim()]), # max of both axes
]
# now plot both limits against eachother
ax.plot(lims, lims, 'k-', alpha=0.75, zorder=0)
ax.set_aspect('equal')
ax.set_xlim(lims)
ax.set_ylim(lims)
plt.tight_layout()
plt.savefig(savefn.replace('.txt', '.%s.pdf' % (label2)))
plt.close()
def plot_gini_compare(save_dir=None):
save_dir = save_dir if save_dir is not None else '/Share/home/zhangqf5/gongjing/Kethoxal_RNA_structure/result/16-08-08_16_library_invivo_invitro/gini'
fn_ls = os.listdir(save_dir)
T_t_ls = ['T%st%s' % (i, j) for i in [0, 1, 2] for j in [0, 20, 200]]
fn_ls = [
i for i in fn_ls if i.endswith('.txt') and i.split('.')[1] in T_t_ls
]
print fn_ls
df_ls = []
for fn in fn_ls:
fn_path = save_dir + '/' + fn
print "process: %s" % (fn_path)
df = pd.read_csv(fn_path, header=0, sep='\t')
condition = fn.split('.')[0].split('_')[2]
T_t_cutoff = fn.split('.')[1]
df['condition'] = condition
df['T_t_cutoff'] = T_t_cutoff
print df.head()
df_ls.append(df)
df_all = pd.concat(df_ls)
savefn = save_dir + '/' + 'vivo_vitro_gini_all.txt'
df_all.to_csv(savefn, index=False, header=True, sep='\t')
print df_all.head()
# df_all_melt = pd.melt(df_all, id_vars=['tx', 'null_pct_cutoff', 'condition', 'T_t_cutoff'], value_vars=['vivo', 'vitro'], var_name='vivo/vitro', value_name='Gini')
# df_all_melt['condition'] = ['%s,%s'%(i,j) for i,j in zip(df_all_melt['condition'], df_all_melt['vivo/vitro'])]
# print df_all_melt.head()
# df_all_melt.sort_values(by=['condition', 'T_t_cutoff'], inplace=True)
# df_all_melt = df_all_melt[df_all_melt['null_pct_cutoff'].isin([0.4, 0.6])]
# df_all_melt = df_all_melt[df_all_melt['T_t_cutoff'].isin(['T0t0', 'T0t20', 'T1t20'])]
# df_all_melt.to_csv(savefn.replace('.txt', '.plot.txt'), index=False, header=True, sep='\t')
# g = sns.FacetGrid(data=df_all_melt, row='T_t_cutoff', col='null_pct_cutoff', sharey=True, margin_titles=True)
# g = g.map(sns.boxplot, 'condition', 'Gini', )
# g.set_xticklabels(rotation=90)
# g.set(ylim=(0.5,1))
# g.savefig(savefn.replace('.txt', '.png'))
# plt.close()
# g = sns.FacetGrid(data=df_all_melt, row='T_t_cutoff', col='null_pct_cutoff', sharey=True, margin_titles=True)
# g = g.map(sns.countplot, 'condition',)
# g.set_xticklabels(rotation=90)
# g.savefig(savefn.replace('.txt', '.count.png'))
# plt.close()
df_select = df_all_melt[(df_all_melt['null_pct_cutoff'] == 0.4)
& (df_all_melt['T_t_cutoff'] == 'T1t20')
& df_all_melt['condition'].isin(
['mRNA,vivo', 'mRNA,vitro'])]
print df_select
fig, ax = plt.subplots(figsize=(4, 6))
sns.boxplot(x='condition', y='Gini', data=df_select, ax=ax)
plt.tight_layout()
ax.set_xticklabels(ax.xaxis.get_majorticklabels(), rotation=45)
plt.savefig(savefn.replace('.txt', '.select.png'))
plt.close()
condition_ls = []
condition_gini_ls = []
for i in df_select['condition'].value_counts().keys():
print i
df_select[df_select['condition'] == i]
condition_ls.append(i)
condition_gini_ls.append(
list(df_select[df_select['condition'] == i]['Gini']))
savefn = savefn.replace('.txt', '.select2.png')
gj.cumulate_dist_plot(ls_ls=condition_gini_ls,
ls_ls_label=condition_ls,
bins=40,
title=None,
ax=None,
savefn=savefn,
xlabel=None,
ylabel=None,
add_vline=None,
add_hline=None,
log2transform=0)
stat, pval = stats.ks_2samp(condition_gini_ls[0], condition_gini_ls[1])
print pval