def add_sample_legend(ax):
handles, labels = ax.get_legend_handles_labels()
h1s = np.array(
handles
)[xlsx_tab.set_index(
'SAMPLE').loc[labels].reset_index().reset_index().set_index('CODE')
# .loc[xlsx_tab.query('GENDER=="male"')['CODE'],'index'].dropna().astype(int)
.reindex(index=xlsx_tab.query('GENDER=="male"')['CODE'])
['index'].dropna().astype(int).values]
h2s = np.array(handles)[xlsx_tab.set_index(
'SAMPLE').loc[labels].reset_index().reset_index().set_index(
'CODE').loc[xlsx_tab.query('GENDER=="female"')['CODE'],
'index'].values]
lg1 = ax.legend(
h1s,
map(lambda x: '{:02d}'.format(x), np.arange(1, h1s.shape[0] + 1)),
loc='upper left',
title='M',
prop={'size': smallsize},
handletextpad=-0.5,
columnspacing=-0.5,
labelspacing=0,
edgecolor='k',
ncol=3,
markerfirst=False,
)
lg1.get_title().set_fontsize(smallsize)
for h in lg1.legendHandles:
h.set_alpha(0.9)
h.set_sizes([50])
ax.add_artist(lg1)
lg2 = ax.legend(
h2s,
map(lambda x: '{:02d}'.format(x), np.arange(1, h2s.shape[0] + 1)),
loc='upper right',
title='F',
prop={'size': smallsize},
handletextpad=-0.5,
columnspacing=-0.5,
labelspacing=0,
edgecolor='k',
ncol=3,
markerfirst=False,
borderpad=0.2,
)
lg2.get_title().set_fontsize(smallsize)
for h in lg2.legendHandles:
h.set_alpha(0.9)
h.set_sizes([50])
def add_clone_legend(ax, FSAMPLE=True):
handles, labels = ax.get_legend_handles_labels()
legend_df1 = (
pd.Series(labels).drop_duplicates().reset_index().set_index(0).merge(
xlsx_tab.set_index('SAMPLE'),
left_index=True,
right_index=True,
).sort_values('CODE'))
if not FSAMPLE:
legend_df1 = legend_df1.replace('M11', 'M10')
ax.legend(
np.array(handles).flatten()[legend_df1['index'].values],
legend_df1['CODE'].str.replace('M', '').str.replace('F', '').values,
loc='upper right',
prop={'size': smallsize},
handletextpad=0.5,
columnspacing=-0.5,
labelspacing=0,
edgecolor='k',
ncol=2,
markerfirst=False,
borderpad=0.2,
)
for h in ax.get_legend().legendHandles:
h.set_width(10)
lg = ax.get_legend()
return lg
def female_genome_plot(ax1, ax2):
# f, (ax1, ax2) = plt.subplots(2, 1, sharex=True, figsize=(12,2), gridspec_kw={'height_ratios':[3,1], 'hspace':0.1})
n = pd.concat(
[
cells_tab,
xlsx_tab.set_index('SAMPLE')
], axis=1, sort=False
).query('GENDER=="female"')['n_pf'].sum()
big_cnv_gain =(
sum_df
.loc[big_cnv_idx]
.query('cnvTag=="Gain" & Gender=="female"')
)
big_cnv_loss =(
sum_df
.loc[big_cnv_idx]
.query('cnvTag=="Loss" & Gender=="female"')
)
bin_bed = BedTools.from_dataframe(ref.loc[good_df.index])
gain_bed = BedTools.from_dataframe(big_cnv_gain)
loss_bed = BedTools.from_dataframe(big_cnv_loss)
gain_s = BedTools.intersect(self=bin_bed,b=gain_bed,wa=True,c=True).to_dataframe().set_index(good_df.index)['score']
loss_s = BedTools.intersect(self=bin_bed,b=loss_bed,wa=True,c=True).to_dataframe().set_index(good_df.index)['score']
tmpCleanUp()
ax1.plot(np.arange(female_fig_df.columns.shape[0]), 100*gain_s[female_fig_df.columns].fillna(0)/n, '-', lw=2, color='darkorange', label='Gain')
ax2.plot(np.arange(female_fig_df.columns.shape[0]), 100*gain_s[female_fig_df.columns].fillna(0)/n, '-', lw=2, color='darkorange', label='Gain')
ax1.plot(np.arange(female_fig_df.columns.shape[0]), -100*loss_s[female_fig_df.columns].fillna(0)/n, '-', lw=2, color='deepskyblue', label='Loss')
ax2.plot(np.arange(female_fig_df.columns.shape[0]), -100*loss_s[female_fig_df.columns].fillna(0)/n, '-', lw=2, color='deepskyblue', label='Loss')
# Plot chroms. boundary
g = ref.groupby('space').min()['abs_pos']
for pos in chr_pos:
ax1.plot(np.tile(pos,10), np.linspace(-5, 9, 10), '-', color='black', alpha=0.5, lw=1, zorder=0)
ax2.plot(np.tile(pos,10), np.linspace(-5, 9, 10), '-', color='black', alpha=0.5, lw=1, zorder=0)
ax1.set_xticks([])
ax2.set_xticks([])
ax1.tick_params(axis='x', bottom=False, length=0)
ax2.tick_params(axis='x', bottom=False, length=0)
ax1.tick_params(axis='y', length=5)
ax2.tick_params(axis='y', length=5)
ax1.set_ylim(-0.4, 0.4)
ax2.set_ylim(-4.5, -1.5)
ax1.spines['bottom'].set_visible(False)
ax2.spines['top'].set_visible(False)
# d = 0.01 # how big to make the diagonal lines in axes coordinates
# kwargs = dict(transform=ax1.transAxes, color='k', clip_on=False)
# ax1.plot((-d, +d), (0, 0), **kwargs) # top-left diagonal
# ax1.plot((1 - d, 1 + d), (0, 0), **kwargs) # top-right diagonal
# kwargs.update(transform=ax2.transAxes) # switch to the bottom axes
# ax2.plot((-d, +d), (1, 1), **kwargs) # bottom-left diagonal
# ax2.plot((1 - d, 1 + d), (1, 1), **kwargs) # bottom-right diagonal
ax1.set_ylabel('Freq.\n(%)', fontsize=midsize)
ax1.set_yticks([0.3,0,-0.3])
ax1.set_yticklabels(['0.3','0.0','0.3'], fontsize=smallsize)
ax2.set_yticks([-3])
ax2.set_yticklabels(['3'], fontsize=smallsize)
return
def male_genome_plot(ax, FSAMPLE=True):
# fig, ax = plt.subplots(figsize=(20,4))
n = pd.concat(
[
cells_tab,
xlsx_tab.set_index('SAMPLE')
], axis=1, sort=False
).query('GENDER=="male"')
big_cnv_gain =(
sum_df
.loc[big_cnv_idx]
.query('cnvTag=="Gain" & Gender=="male"')
)
big_cnv_loss =(
sum_df
.loc[big_cnv_idx]
.query('cnvTag=="Loss" & Gender=="male"')
)
if not FSAMPLE:
big_cnv_gain = big_cnv_gain.query('Sample!="$FSAMPLE"')
big_cnv_loss = big_cnv_loss.query('Sample!="$FSAMPLE"')
n = n.drop('$FSAMPLE')['n_pf'].sum()
else:
n = n['n_pf'].sum()
bin_bed = BedTools.from_dataframe(ref.loc[good_df.index])
gain_bed = BedTools.from_dataframe(big_cnv_gain)
loss_bed = BedTools.from_dataframe(big_cnv_loss)
gain_s = BedTools.intersect(self=bin_bed,b=gain_bed,wa=True,c=True).to_dataframe().set_index(good_df.index)['score']
loss_s = BedTools.intersect(self=bin_bed,b=loss_bed,wa=True,c=True).to_dataframe().set_index(good_df.index)['score']
tmpCleanUp()
ax.plot(np.arange(male_fig_df.columns.shape[0]), 100*gain_s[male_fig_df.columns].fillna(0)/n, '-', lw=2, color='darkorange', label='Gain', zorder=1)
ax.plot(np.arange(male_fig_df.columns.shape[0]), -100*loss_s[male_fig_df.columns].fillna(0)/n, '-', lw=2, color='deepskyblue', label='Loss', zorder=1)
# Plot chroms. boundary
g = ref.groupby('space').min()['abs_pos']
for pos in chr_pos:
ax.plot(np.tile(pos,10), np.linspace(-3, 9, 10), '-', color='black', alpha=0.5, lw=1, zorder=0)
ax.set_ylabel('Freq.\n(%)', fontsize=midsize)
ax.set_xticks( pd.Series(chr_pos).rolling(2).mean()[1:] )
ax.set_xticklabels(
ref['space'].drop_duplicates()[:-1].str.replace('chr','').replace('19',' 19').replace('21',' 21').replace('X',' X'),
fontsize=smallsize-4,
ha='center',
rotation=90,
)
ax.xaxis.set_ticks_position('top')
ax.set_ylim(-0.4,0.4)
ax.set_yticks( [-0.3, 0, 0.3] )
ax.set_yticklabels( [0.3, 0 ,0.3], fontsize=smallsize )
ax.tick_params(axis='x', bottom=False, length=0, pad=5)
ax.tick_params(axis='y', length=5)
return
# +
male_heatmap = pd.read_csv('male_heatmap.csv', index_col=0)
female_heatmap = pd.read_csv('female_heatmap.csv', index_col=0)
cmap_CNV = LinearSegmentedColormap.from_list('forCNV', ['blueviolet', 'deepskyblue', 'black', 'darkorange', 'orangered'])
# # Sort fraction
tmp_df = sum_df.loc[big_cnv_idx].sort_values('chrom_fraction', ascending=False)
tmp_df['chrom_fraction'] = (tmp_df['chrom_fraction']/10).round()
# # Sort chroms.
heatmap_order = (
tmp_df.set_index('Cell')
.loc[tmp_df['Cell']]
.reset_index()
.groupby('Cell',sort=False).first()
.replace({'Sample':xlsx_tab.set_index('SAMPLE')['CODE'].to_dict()})
# .sort_values(['chr_id','chrom_fraction','cnvTag','binSize','Cell'], ascending=[True, False, True, False, True])
.sort_values(
['chr_id','chrom_fraction','cnvTag','Sample','binSize','Cell'],
ascending=[True, False, True, True, False, True]
)
.index
)
# # Sort fraction
# tmp_df = cell_chr_cnv_size.sort_values('chrom_fraction', ascending=False)
# # Sort chroms.
# heatmap_order = (
# tmp_df.reset_index().set_index('Cell')
# .loc[tmp_df['Cell']]
# .reset_index()
matrix_2d = pd.read_pickle('matrix_2d.pkl')
# +
cell_info = pd.concat([
sum_df.loc[big_cnv_idx].groupby(['Cell', 'Chromosome', 'cnvTag'
])['Gender'].first(),
sum_df.loc[big_cnv_idx].groupby(['Cell', 'Chromosome', 'cnvTag'
])['Sample'].first(),
sum_df.loc[big_cnv_idx].groupby(['Cell', 'Chromosome', 'cnvTag'
])['chrom_fraction'].max(),
],
axis=1).reset_index().set_index('Cell')
cell_info['Age'] = cell_info['Sample'].replace(
xlsx_tab.set_index('SAMPLE')['AGE'].to_dict())
matrix_2d = pd.merge(
matrix_2d,
cell_info,
right_index=True,
left_index=True,
how='left',
)
matrix_2d['Whole'] = 'False'
matrix_2d['Whole'] = matrix_2d.where(matrix_2d['chrom_fraction'] < 80,
other='True')['Whole']
# +
two_colors = sns.xkcd_palette(['bright blue', 'red'])
def clone_plot(ax1, ax2, ax3, ax4, FSAMPLE=True):
fig_df3 = pd.DataFrame(columns=['Sample', 'Clone_size', 'Cells'])
for s, df in male_edis_df.query('d<10').groupby('s'):
G = nx.Graph()
G.add_nodes_from(df['a'].unique().tolist())
G.add_edges_from(df[['a', 'b']].values, length=df['d'].values)
for h in nx.connected_components(G):
fig_df3 = fig_df3.append(
{
'Sample': s,
'Clone_size': len(h),
'Cells': list(h)
},
ignore_index=True)
fig_df4 = pd.DataFrame(columns=['Sample', 'Clone_size', 'Cells'])
for s, df in female_edis_df.query('d<10').groupby('s'):
G = nx.Graph()
G.add_nodes_from(df['a'].unique().tolist())
G.add_edges_from(df[['a', 'b']].values, length=df['d'].values)
for h in nx.connected_components(G):
fig_df4 = fig_df4.append(
{
'Sample': s,
'Clone_size': len(h),
'Cells': list(h)
},
ignore_index=True)
for g, df in fig_df3.query('Clone_size>2').groupby('Clone_size'):
df = df.set_index('Sample').loc[
xlsx_tab['SAMPLE']].dropna().reset_index().copy()
df['ncum'] = np.arange(df.shape[0])
df.apply(lambda row: ax1.bar(g,
1,
bottom=row['ncum'],
width=0.6,
color=color_dict[row['Sample']],
edgecolor='k'),
axis=1)
df.apply(lambda row: ax2.bar(g,
1,
bottom=row['ncum'],
width=0.6 * 6 * 5 / 4,
color=color_dict[row['Sample']],
edgecolor='k',
label=row['Sample']),
axis=1)
for g, df in fig_df4.query('Clone_size>2').groupby('Clone_size'):
df = df.set_index('Sample').loc[
xlsx_tab['SAMPLE']].dropna().reset_index().copy()
df['ncum'] = np.arange(df.shape[0])
df.apply(lambda row: ax3.bar(g,
1,
bottom=row['ncum'],
width=0.6,
color=color_dict[row['Sample']],
edgecolor='k'),
axis=1)
df.apply(lambda row: ax4.bar(g,
1,
bottom=row['ncum'],
width=0.6 * 6 * 5 / 4,
color=color_dict[row['Sample']],
edgecolor='k',
label=row['Sample']),
axis=1)
# ax1.set_xlim(0,32)
# ax3.set_xlim(0,32)
# ax2.set_xlim(40,120)
# ax4.set_xlim(40,120)
# ax1.set_xticks(np.arange(0,31,10))
# ax3.set_xticks(np.arange(0,31,10))
# ax2.set_xticks(np.arange(50,121,20))
# ax4.set_xticks(np.arange(50,121,20))
ax1.set_xlim(0, 15)
ax3.set_xlim(0, 15)
ax2.set_xlim(25, 115)
ax4.set_xlim(25, 115)
ax1.set_xticks(np.arange(0, 20, 5))
ax3.set_xticks(np.arange(0, 20, 5))
ax2.set_xticks(np.arange(30, 121, 20))
ax4.set_xticks(np.arange(30, 121, 20))
ax1.set_ylim(0, 15)
ax2.set_ylim(0, 15)
ax3.set_ylim(0, 15)
ax4.set_ylim(0, 15)
ax1.set_yticks(np.arange(0, 16, 5))
ax3.set_yticks(np.arange(0, 16, 5))
ax2.set_yticks([])
ax4.set_yticks([])
# ax2.set_title(' '*12+'Male', fontsize=bigsize)
# ax4.set_title(' '*12+'Female', fontsize=bigsize)
# ax1.set_xlabel(' '*32+'Clone size', fontsize=midsize)
# ax3.set_xlabel(' '*32+'Clone size', fontsize=midsize)
ax1.spines['right'].set_visible(False)
ax2.spines['left'].set_visible(False)
ax3.spines['right'].set_visible(False)
ax4.spines['left'].set_visible(False)
ax1.set_ylabel('Counts', fontsize=midsize)
ax1.tick_params(axis='both', labelsize=smallsize, length=5)
ax2.tick_params(axis='both', labelsize=smallsize, length=5)
ax3.tick_params(axis='both', labelsize=smallsize, length=5)
ax4.tick_params(axis='both', labelsize=smallsize, length=5)
d = 0.015 # how big to make the diagonal lines in axes coordinates
kwargs = dict(transform=ax1.transAxes, color='k', clip_on=False)
ax1.plot((1 - d, 1 + d), (1 - d, 1 + d), **kwargs)
kwargs.update(transform=ax2.transAxes)
ax1.plot((-d * 3 / 2, +d * 3 / 2), (1 - d, 1 + d), **kwargs)
kwargs.update(transform=ax1.transAxes)
ax2.plot((1 - d, 1 + d), (-d, +d), **kwargs)
kwargs.update(transform=ax2.transAxes)
ax2.plot((-d * 3 / 2, +d * 3 / 2), (-d, +d), **kwargs)
kwargs = dict(transform=ax3.transAxes, color='k', clip_on=False)
ax3.plot((1 - d, 1 + d), (1 - d, 1 + d), **kwargs)
kwargs.update(transform=ax4.transAxes)
ax3.plot((-d * 3 / 2, +d * 3 / 2), (1 - d, 1 + d), **kwargs)
kwargs.update(transform=ax3.transAxes)
ax4.plot((1 - d, 1 + d), (-d, +d), **kwargs)
kwargs.update(transform=ax4.transAxes)
ax4.plot((-d * 3 / 2, +d * 3 / 2), (-d, +d), **kwargs)
anot_kws = {
'fontsize': smallsize,
'ha': 'center',
'va': 'center',
'arrowprops': dict(arrowstyle="->")
}
n_df = fig_df3.query('Clone_size==31')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
if not FSAMPLE:
lid = lid.replace('M11', 'M10')
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax2.annotate(lid + '\n' + cid, xy=(31, 1.5), xytext=(50, 5), **anot_kws)
n_df = fig_df4.query('Clone_size==11')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax3.annotate(
lid + '\n' + cid,
xy=(11, 1.5),
xytext=(7, 10),
fontsize=smallsize,
ha='center',
va='center',
color=two_colors[1],
arrowprops=dict(arrowstyle="->"),
# bbox=dict(boxstyle='round4', fc="w", pad=0.5)
)
n_df = fig_df4.query('Clone_size==12')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax3.annotate(lid + '\n' + cid,
xy=(12, 1.5),
xytext=(13, 10),
**anot_kws,
zorder=1)
n_df = fig_df4.query('Clone_size==13')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax3.annotate(lid + '\n' + cid,
xy=(13, 1.5),
xytext=(14, 5),
**anot_kws,
zorder=1)
n_df = fig_df4.query('Clone_size==31')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax4.annotate(lid + '\n' + cid,
xy=(31, 2),
xytext=(13, 10),
**anot_kws,
zorder=0,
color='w',
alpha=0)
n_df = fig_df4.query('Clone_size==46')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax4.annotate(lid + '\n' + cid, xy=(46, 1.5), xytext=(40, 7), **anot_kws)
n_df = fig_df4.query('Clone_size==53')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax4.annotate(lid + '\n' + cid, xy=(53, 1.5), xytext=(70, 7), **anot_kws)
n_df = fig_df4.query('Clone_size==105')
lid = xlsx_tab.set_index('SAMPLE').loc[n_df['Sample'], 'CODE'].values[0]
cid = sum_df.set_index('Cell').loc[n_df['Cells'].tolist()[0],
'Space'].value_counts().index[0]
ax4.annotate(lid + '\n' + cid, xy=(105, 1.5), xytext=(100, 7), **anot_kws)
return fig_df3, fig_df4
'_', expand=True)[0].unique()[0]]
nx.draw_networkx(
G,
pos=pos,
nodelist=h,
node_color=[s_color],
node_size=70,
edgecolors='k',
with_labels=False,
ax=ax,
zorder=1,
)
s = pd.DataFrame(pos).T.loc[h]
note = sum_df.set_index('Cell').loc[h].groupby(
['Space', 'cnvTag'])['Pos'].count().sort_values().index[-1]
code = xlsx_tab.set_index('SAMPLE').loc[
s.index.str.split('_', expand=True).to_frame()[0].unique()[0], 'CODE']
# if code not in lg_dict:
# ax.scatter(xmax+1e2, ymax+1e2, s=70, color=s_color, label=code, zorder=0)
# lg_dict[code] = True
if len(h) > 9:
ax.text(s.mean()[0] + 85,
s.mean()[1] - 85,
cid,
ha='center',
va='center',
fontsize=midsize)
ax.text(xmax + 200,
ymax - cid * 100,
'C{}: {} {} {}'.format(cid, code, note[0], note[1]),
def kde_plot_chrX(chroms, ax1, ax2, tag):
if tag == 'size':
fig_df = snp_per_base
xi, yi = np.mgrid[
0 : 5 : 100*1j,
0 : 5 : 100*1j
]
# x_label = r'$\dfrac{{\mathrm{{{}\,SNPs\,on\,{}}}}}{{\mathrm{{Size\,of\,{}}}}}$'.format('\#',chroms,chroms)
# y_label = r'$\dfrac{{\mathrm{{{}\,SNPs\,on\,{}}}}}{{\mathrm{{Size\,of\,{}}}}}$'.format('\#','chrX','chrX')
x_label = r'$\dfrac{{\mathrm{{{}\,of\,SNPs\,reads}}}}{{\mathrm{{Size\,(Mb)}}}}\;\mathrm{{on\;{}}}$'.format('\#',chroms)
y_label = r'$\dfrac{{\mathrm{{{}\,of\,SNPs\,reads}}}}{{\mathrm{{Size\,(Mb)}}}}\;\mathrm{{on\;{}}}$'.format('\#','chrX')
ax1.set_ylim(0,1.2)
ax2.set_ylim(0,1.2)
ax1.set_yticks([0,0.4,0.8,1.2])
ax2.set_yticks([0,0.4,0.8,1.2])
ax1.set_xlim(0,3.6)
ax2.set_xlim(0,3.6)
levels = np.arange(0,7)
extend = 'neither'
elif tag == 'reads':
fig_df = snp_per_reads
xi, yi = np.mgrid[
0 : 100 : 100*1j,
0 : 100 : 100*1j
]
# x_label = r'$\dfrac{{\mathrm{{{}\,SNPs\,on\,{}}}}}{{\mathrm{{{}\,Reads\,on\,{}}}}}$'.format('\#',chroms,'\#',chroms)
# y_label = r'$\dfrac{{\mathrm{{{}\,SNPs\,on\,{}}}}}{{\mathrm{{{}\,Reads\,on\,{}}}}}$'.format('\#','chrX','\#','chrX')
x_label = r'$\dfrac{{\mathrm{{{}\,of\,SNPs\,reads}}}}{{\mathrm{{{}\,reads\,(M)}}}}\;\mathrm{{on\;{}}}$'.format('\#','\#',chroms)
y_label = r'$\dfrac{{\mathrm{{{}\,of\,SNPs\,reads}}}}{{\mathrm{{{}\,reads\,(M)}}}}\;\mathrm{{on\;{}}}$'.format('\#','\#','chrX')
ax1.set_xlim(30,80)
ax2.set_xlim(30,80)
ax1.set_ylim(10,35)
ax2.set_ylim(5,30)
levels = np.arange(0,0.018,0.002)
extend = 'max'
else:
return
# .drop(sum_df.loc[big_cnv_idx].query('Sample=="XXX"')['Cell'].unique())
k_XXX = gaussian_kde( fig_df.loc[ fig_df.index[fig_df.index.str.contains('XXX')], [chroms,'chrX']].T )
k_XXX = gaussian_kde( fig_df.loc[ fig_df.index[fig_df.index.str.contains('XXX') ], [chroms,'chrX']].T )
z_XXX = k_XXX( np.vstack([xi.flatten(), yi.flatten()]) )
z_XXX = k_XXX( np.vstack([xi.flatten(), yi.flatten()]) )
cs1 = ax1.contourf(xi, yi, z_XXX.reshape(xi.shape), levels=levels, cmap='Greens', zorder=0, extend=extend)
cs2 = ax2.contourf(xi, yi, z_XXX.reshape(xi.shape), levels=levels, cmap='Greens', zorder=0, extend=extend)
ax1.plot(
fig_df.loc[XXX_pie_df.query('pA==True').index, chroms],
fig_df.loc[XXX_pie_df.query('pA==True').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color=two_colors[0], label='Maternal'
)
ax1.plot(
fig_df.loc[XXX_pie_df.query('pB==True').index, chroms],
fig_df.loc[XXX_pie_df.query('pB==True').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color=two_colors[1], label='Paternal'
)
ax1.plot(
fig_df.loc[XXX_pie_df.query('~(pA or pB)').index, chroms],
fig_df.loc[XXX_pie_df.query('~(pA or pB)').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color='gray', label='Undeterminate'
)
ax2.plot(
fig_df.loc[XXX_pie_df.query('pA==True').index, chroms],
fig_df.loc[XXX_pie_df.query('pA==True').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color=two_colors[0], label='Maternal'
)
ax2.plot(
fig_df.loc[XXX_pie_df.query('pB==True').index, chroms],
fig_df.loc[XXX_pie_df.query('pB==True').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color=two_colors[1], label='Paternal'
)
ax2.plot(
fig_df.loc[XXX_pie_df.query('~(pA or pB)').index, chroms],
fig_df.loc[XXX_pie_df.query('~(pA or pB)').index, 'chrX'],
'.', ms=15, alpha=0.7, markeredgecolor='k', color='gray', label='Undeterminate'
)
ax1.set_ylabel(y_label, fontsize=midsize)
ax2.set_ylabel('')
ax1.set_xlabel(x_label, fontsize=midsize)
ax2.set_xlabel(x_label, fontsize=midsize)
ax1.tick_params(length=5, labelsize=smallsize)
ax2.tick_params(length=5, labelsize=smallsize)
ax1.set_title(xlsx_tab.set_index('SAMPLE').loc['XXX','CODE'],fontsize=hugesize)
ax2.set_title(xlsx_tab.set_index('SAMPLE').loc['XXX', 'CODE'],fontsize=hugesize)
ax1.legend(loc='upper left', prop={'size':smallsize}, handletextpad=0, frameon=False,)
ax2.legend(loc='upper left', prop={'size':smallsize}, handletextpad=0, frameon=False,)
return cs1, cs2
Path.CURVE4,
Path.CLOSEPOLY,
]
np.random.seed(0)
# -
# # Get data
max_alpha = 4
max_pie = 40
# +
good_cells = good_df.xs(key='copy',axis=1,level=1).columns
sample_code_dict = xlsx_tab.set_index('SAMPLE')['CODE'].to_dict()
chrom_dict = (ref.groupby('space').max()['end']//1e6).astype(int).to_dict()
two_colors = sns.xkcd_palette(['red', 'bright blue'])
def name2code(name):
code = []
for i in name.split('_'):
if i in sample_code_dict:
code.append(sample_code_dict[i])
else:
code.append(i)
return '_'.join(code)