def plot_asymmetry_comp(inputs, paths_in, paths_out, settings):
#sns.boxplot(data=iris, orient="h", palette="Set2")
files = inputs['files']
path_figure = paths_out['path_figures'] + 'Comparison/'
minlength = settings['minlength']
maxlength = settings['maxlength']
minlength_1 = str(minlength) + '_'
maxlength_1 = str(maxlength) + '_'
name_settings = minlength_1 + maxlength_1
data = {}
score_list = []
fname_list = []
plot_count = 0
fnames = ''
for fname in files:
fnames += fname
plot_count += 1
path_analysis = paths_out['path_analysis'] + fname + '/'
asymmetry_dict = ribo_util.unPickle(path_analysis + 'asymmetry')
df = pd.DataFrame(asymmetry_dict)
#display(df)
score = df['Score'].values.tolist()
for value in score:
fname_list.append(fname)
score_list.append(value)
data['file'] = fname_list
data['score'] = score_list
data = pd.DataFrame(data)
sns.set_style("white")
plot = plt.figure(figsize=(20, 10))
plot = sns.boxplot(x="score",
y='file',
data=data,
orient="h",
color="grey",
fliersize=0)
plot.axvline(linewidth=3, color='r')
plot.set(xlim=(-5, 5))
plot.tick_params(labelsize=18)
sns.despine(offset=5)
plt.savefig(path_figure + 'asymmetry/' + fnames + name_settings + '.pdf',
dpi=600,
bbox_inches="tight")
plt.show()
def plot_pausescore(inputs, paths_in, paths_out, settings, settings_plot):
files = inputs['files']
aa_codon = settings_plot['aa_or_codon']
aminoacids = settings_plot['amino_acid']
codons = settings_plot['codon']
ymax_dot = settings_plot['ymax_dot']
ymax_line = settings_plot['ymax_line']
vmax_HM = settings_plot['vmax_HM']
path_figure = paths_out['path_figures']
aa_plots = len(aminoacids)
codon_plots = len(codons)
aa_code, codon_code = ribo_util.get_genetic_code()
for fname in files:
minlength = settings['minlength']
maxlength = settings['maxlength']
plot_upstream = settings[
'plot_upstream'] / 3 * 3 #change window to interval of 3
plot_downstream = settings['plot_downstream'] / 3 * 3
start_trim = settings['start_trim'] / 3 * 3
stop_trim = settings['stop_trim'] / 3 * 3
frameshift = settings['frameshift']
A_site = settings['A_site shift']
minlength_1 = str(minlength) + '_'
maxlength_1 = str(maxlength) + '_'
plot_upstream_1 = str(plot_upstream) + '_'
plot_downstream_1 = str(plot_downstream) + '_'
start_trim_1 = str(start_trim) + '_'
stop_trim_1 = str(stop_trim) + '_'
frameshift_1 = str(frameshift) + '_'
a_site_1 = str(A_site) + '_'
name_settings = minlength_1 + maxlength_1 + plot_upstream_1 + plot_downstream_1
name_settings += start_trim_1 + stop_trim_1 + frameshift_1
path_pausescore = paths_out['path_analysis'] + fname + '/pause_score/'
### For aa_analysis ###
if aa_codon == 'aa':
aa_score = ribo_util.unPickle(path_pausescore + 'aa_scores' +
name_settings)
aa_HM = ribo_util.unPickle(path_pausescore + 'aa_HM_data' +
name_settings)
aa_plot = ribo_util.unPickle(path_pausescore + 'aa_plot_data' +
name_settings)
aa_df = pd.DataFrame(aa_score)
aa_df = aa_df.sort_values(by=['Amino Acid'])
sns.set_style("white")
sns.set_context("talk")
plt.figure(figsize=(8 + 4 * aa_plots, 5))
plt.subplot2grid((2, 2 + aa_plots), (0, 0), rowspan=2, colspan=2)
plot = sns.stripplot(x="Amino Acid",
y="A_site",
data=aa_df,
size=12)
plot = sns.stripplot(x="Amino Acid",
y="P_site",
data=aa_df,
size=6,
color='black')
plot = sns.stripplot(x="Amino Acid",
y="E_site",
data=aa_df,
size=6,
color='grey')
#sns.despine(offset=5, trim = True )
plt.ylim(0, ymax_dot)
plot.axhline(y=1,
xmin=0,
xmax=1,
dashes=[2, 2, 2, 2],
color='grey')
plt.title(fname + ' Amino Acid Pause Scores')
plt.xlabel("Amino Acid")
plt.ylabel("Pause Score")
aa_HM_dict = {}
aa_plot_dict = {}
for aa in aminoacids:
df_HM = pd.DataFrame(aa_HM[aa])
df_plot = pd.DataFrame(aa_plot[aa])
aa_HM_dict[aa] = df_HM
aa_plot_dict[aa] = df_plot
xlim_lower = aa_plot_dict[aa].index[0]
xlim_upper = aa_plot_dict[aa].index[-1]
sns.set_style("white")
sns.set_style("ticks")
plotnum = 0
for aa in aminoacids:
plt.subplot2grid((2, 2 + aa_plots), (0, 2 + plotnum),
rowspan=1,
colspan=1)
plot_2 = plt.plot(aa_plot_dict[aa], sns.xkcd_rgb["dark grey"])
plt.title(aa + ' Average Plot')
plt.ylabel("Pause Score")
plt.ylim(0, ymax_line)
plt.xlim(xlim_lower, xlim_upper)
sns.despine(offset=5)
plt.subplot2grid((2, 2 + aa_plots), (1, 2 + plotnum),
rowspan=1,
colspan=1)
plot_3 = sns.heatmap(aa_HM_dict[aa],
cmap="ocean_r",
vmin=0,
vmax=vmax_HM,
cbar=False,
xticklabels=15,
yticklabels=6)
sns.despine(offset=5)
plotnum += 1
plt.tight_layout()
plt.savefig(path_figure + fname + '/aa_pausescore' +
name_settings + '_aa_pause_scores.png',
dpi=400)
plt.show()
aa_plot_csv = pd.DataFrame(aa_plot)
aa_plot_csv.to_csv(path_pausescore + 'aa_plot_values.csv')
### For codon_analysis ###
if aa_codon == 'codon':
codon_score = ribo_util.unPickle(path_pausescore + 'codon_scores' +
name_settings)
codon_HM = ribo_util.unPickle(path_pausescore + 'codon_HM_data' +
name_settings)
codon_plot = ribo_util.unPickle(path_pausescore +
'codon_plot_data' + name_settings)
aa_list = []
for codon in codon_score['Codon']:
aa = codon_code[codon]
aa_list.append(aa)
codon_score['Amino_Acid'] = aa_list
codon_df = pd.DataFrame(codon_score)
codon_df = codon_df.sort_values(by=['Amino_Acid', 'Codon'])
sns.set_style("white")
sns.set_context("talk")
plt.figure(figsize=(28 + 4 * codon_plots, 5))
plt.subplot2grid((2, 7 + codon_plots), (0, 0),
rowspan=2,
colspan=7)
plot = sns.stripplot(x="Codon", y="A_site", data=codon_df, size=12)
plot = sns.stripplot(x="Codon",
y="P_site",
data=codon_df,
size=6,
color='black')
plot = sns.stripplot(x="Codon",
y="E_site",
data=codon_df,
size=6,
color='grey')
#sns.despine(offset=5, trim = True )
plt.ylim(0, ymax_dot)
plot.axhline(y=1,
xmin=0,
xmax=1,
dashes=[2, 2, 2, 2],
color='grey')
plot.axvline(x=3.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(1, 4, 'A', fontsize=30) #add text
plot.axvline(x=5.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(4, 4, 'C', fontsize=30) #add text
plot.axvline(x=7.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(6, 4, 'D', fontsize=30) #add text
plot.axvline(x=9.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(8, 4, 'E', fontsize=30) #add text
plot.axvline(x=11.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(10, 4, 'F', fontsize=30) #add text
plot.axvline(x=15.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(13, 4, 'G', fontsize=30) #add text
plot.axvline(x=17.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(16, 4, 'H', fontsize=30) #add text
plot.axvline(x=20.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(18.8, 4, 'I', fontsize=30) #add text
plot.axvline(x=22.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(21, 4, 'K', fontsize=30) #add text
plot.axvline(x=28.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(25, 4, 'L', fontsize=30) #add text
plot.axvline(x=29.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(28.6, 4, 'M', fontsize=30) #add text
plot.axvline(x=31.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(30, 4, 'N', fontsize=30) #add text
plot.axvline(x=35.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(33, 4, 'P', fontsize=30) #add text
plot.axvline(x=37.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(36, 4, 'Q', fontsize=30) #add text
plot.axvline(x=43.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(40, 4, 'R', fontsize=30) #add text
plot.axvline(x=49.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(46, 4, 'S', fontsize=30) #add text
plot.axvline(x=53.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(51, 4, 'T', fontsize=30) #add text
plot.axvline(x=57.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(55, 4, 'V', fontsize=30) #add text
plot.axvline(x=60.5, ymin=0, ymax=ymax_dot, color='grey', lw=.8)
plt.text(58.4, 4, 'W', fontsize=30) #add text
plt.text(61.5, 4, '_', fontsize=30) #add text'''
plt.title(fname + ' Codon Pause Scores')
plt.xlabel("Codon")
plt.ylabel("Pause Score")
codon_HM_dict = {}
codon_plot_dict = {}
for codon in codons:
df_HM = pd.DataFrame(codon_HM[codon])
df_plot = pd.DataFrame(codon_plot[codon])
codon_HM_dict[codon] = df_HM
codon_plot_dict[codon] = df_plot
xlim_lower = codon_plot_dict[codon].index[0]
xlim_upper = codon_plot_dict[codon].index[-1]
sns.set_style("white")
sns.set_style("ticks")
plotnum = 0
for codon in codons:
plt.subplot2grid((2, 7 + codon_plots), (0, 7 + plotnum),
rowspan=1,
colspan=1)
plot_2 = plt.plot(codon_plot_dict[codon],
sns.xkcd_rgb["dark grey"])
plt.title(codon + ' Average Plot')
plt.ylabel("Pause Score")
plt.ylim(0, ymax_line)
plt.xlim(xlim_lower, xlim_upper)
sns.despine(offset=5)
plt.subplot2grid((2, 7 + codon_plots), (1, 7 + plotnum),
rowspan=1,
colspan=1)
plot_3 = sns.heatmap(codon_HM_dict[codon],
cmap="ocean_r",
vmin=0,
vmax=vmax_HM,
cbar=False,
xticklabels=15,
yticklabels=6)
sns.despine(offset=5)
plotnum += 1
plt.tight_layout()
plt.savefig(path_figure + fname + '/codon_pausescore' +
name_settings + '.pdf',
dpi=400)
plt.show()