def run(self):
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
if re.search('\d', self.figsize):
self.figsize = [float(k) for k in self.figsize.split(',')]
else:
self.figsize = np.array(
[1, float(lens1.sum())/float(lens2.sum())])*10
plt.rcParams['ytick.major.pad'] = 0
fig, ax = plt.subplots(figsize=self.figsize)
ax.xaxis.set_ticks_position('top')
step1 = 1 / float(lens1.sum())
step2 = 1 / float(lens2.sum())
base.dotplot_frame(fig, ax, lens1, lens2, step1, step2,
self.genome1_name, self.genome2_name)
gff1 = base.newgff(self.gff1)
gff2 = base.newgff(self.gff2)
gff1 = base.gene_location(gff1, lens1, step1, self.position)
gff2 = base.gene_location(gff2, lens2, step2, self.position)
block_list = pd.read_csv(self.block_list, header=None)
bkinfo = pd.read_csv(self.blockinfo,index_col=0)
bkinfo['chr1'] = bkinfo['chr1'].astype(str)
bkinfo['chr2'] = bkinfo['chr2'].astype(str)
align = self.alignment(gff1, gff2, block_list, bkinfo)
alignment = align[gff1.columns[-int(len(block_list[0].drop_duplicates())):]]
alignment.to_csv(self.savefile, sep='\t', header=None)
df = self.pair_positon(
alignment, gff1['loc'], gff2['loc'], self.colors)
plt.scatter(df['loc2'], df['loc1'], s=float(self.markersize), c=df['color'],
alpha=0.5, edgecolors=None, linewidths=0, marker='o')
plt.subplots_adjust(left=0.07, right=0.97, top=0.93, bottom=0.03)
plt.savefig(self.savefig, dpi=500)
sys.exit(0)
def run(self):
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
if re.search('\d', self.figsize):
self.figsize = [float(k) for k in self.figsize.split(',')]
else:
self.figsize = np.array(
[1, float(lens1.sum()) / float(lens2.sum())]) * 10
plt.rcParams['ytick.major.pad'] = 0
fig, ax = plt.subplots(figsize=self.figsize)
ax.xaxis.set_ticks_position('top')
step1 = 1 / float(lens1.sum())
step2 = 1 / float(lens2.sum())
base.dotplot_frame(fig, ax, lens1, lens2, step1, step2,
self.genome1_name, self.genome2_name)
gff1 = base.newgff(self.gff1)
gff2 = base.newgff(self.gff2)
gff1 = base.gene_location(gff1, lens1, step1, self.position)
gff2 = base.gene_location(gff2, lens2, step2, self.position)
blast = base.newblast(self.blast, int(self.score), float(self.evalue),
gff1, gff2)
df = self.pair_positon(blast, gff1, gff2, int(self.multiple),
int(self.repnum))
plt.scatter(df['loc2'],
df['loc1'],
s=float(self.markersize),
c=df['color'],
alpha=0.5,
edgecolors=None,
linewidths=0,
marker='o')
plt.subplots_adjust(left=0.07, right=0.97, top=0.93, bottom=0.03)
plt.savefig(self.savefile, dpi=500)
sys.exit(0)
def run(self):
axis = [0, 1, 1, 0]
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
if re.search('\d', self.figsize):
self.figsize = [float(k) for k in self.figsize.split(',')]
else:
self.figsize = np.array(
[1, float(lens1.sum()) / float(lens2.sum())]) * 10
step1 = 1 / float(lens1.sum())
step2 = 1 / float(lens2.sum())
fig, ax = plt.subplots(figsize=self.figsize)
plt.rcParams['ytick.major.pad'] = 0
ax.xaxis.set_ticks_position('top')
base.dotplot_frame(fig, ax, lens1, lens2, step1, step2,
self.genome1_name, self.genome2_name, [1, 1])
bkinfo = pd.read_csv(self.blockinfo)
if self.blockinfo_reverse == True or self.blockinfo_reverse.upper(
) == 'TRUE':
bkinfo[['chr1', 'chr2']] = bkinfo[['chr2', 'chr1']]
bkinfo[['block1', 'block2']] = bkinfo[['block2', 'block1']]
bkinfo['chr1'] = bkinfo['chr1'].astype(str)
bkinfo['chr2'] = bkinfo['chr2'].astype(str)
bkinfo = bkinfo[(bkinfo['length'] > int(self.block_length))
& (bkinfo['chr1'].isin(lens1.index)) &
(bkinfo['chr2'].isin(lens2.index)) &
(bkinfo['pvalue'] < float(self.pvalue))]
if self.tandem == True or self.tandem == 'true' or self.tandem == 1:
bkinfo = self.remove_tandem(bkinfo)
pos, pairs = self.block_position(bkinfo, lens1, lens2, step1, step2)
cm = plt.cm.get_cmap('gist_rainbow') # gist_rainbow,hsv
df = pd.DataFrame(pairs, columns=['loc1', 'loc2', 'ks'])
df = df[(df['ks'] >= self.area[0]) & (df['ks'] <= self.area[1])]
df.drop_duplicates(inplace=True)
sc = plt.scatter(df['loc1'],
df['loc2'],
s=float(self.markersize),
c=df['ks'],
alpha=0.9,
edgecolors=None,
linewidths=0,
marker='o',
vmin=self.area[0],
vmax=self.area[1],
cmap=cm)
# sc = plt.scatter(df['loc1'], df['loc2'], s=float(self.markersize), c='dimgray',
# alpha=0.7, edgecolors=None, linewidths=0, marker='o', vmin=self.area[0], vmax=self.area[1])
cbar = fig.colorbar(sc, shrink=0.5, pad=0.03, fraction=0.1)
align = dict(family='Arial',
style='normal',
horizontalalignment="center",
verticalalignment="center")
cbar.set_label('Ks', labelpad=12.5, fontsize=18, **align)
ax.axis(axis)
plt.subplots_adjust(left=0.09, right=0.96, top=0.93, bottom=0.03)
plt.savefig(self.savefig, dpi=500)
plt.show()
sys.exit(0)
def run(self):
axis = [0, 1, 1, 0]
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
if re.search('\d', self.figsize):
self.figsize = [float(k) for k in self.figsize.split(',')]
else:
self.figsize = np.array(
[1, float(lens1.sum()) / float(lens2.sum())]) * 10
plt.rcParams['ytick.major.pad'] = 0
fig, ax = plt.subplots(figsize=self.figsize)
ax.xaxis.set_ticks_position('top')
step1 = 1 / float(lens1.sum())
step2 = 1 / float(lens2.sum())
base.dotplot_frame(fig, ax, lens1, lens2, step1, step2,
self.genome1_name, self.genome2_name, [0, 1])
gff1 = base.newgff(self.gff1)
gff2 = base.newgff(self.gff2)
gff1 = base.gene_location(gff1, lens1, step1, self.position)
gff2 = base.gene_location(gff2, lens2, step2, self.position)
bkinfo = pd.read_csv(self.blockinfo, index_col='id')
if self.blockinfo_reverse == True or self.blockinfo_reverse.upper(
) == 'TRUE':
bkinfo[['chr1', 'chr2']] = bkinfo[['chr2', 'chr1']]
bkinfo[['block1', 'block2']] = bkinfo[['block2', 'block1']]
bkinfo['chr1'] = bkinfo['chr1'].astype(str)
bkinfo['chr2'] = bkinfo['chr2'].astype(str)
bkinfo[self.classid] = bkinfo[self.classid].astype(str)
bkinfo = bkinfo[bkinfo['chr1'].isin(lens1.index)
& (bkinfo['chr2'].isin(lens2.index))]
align = self.alignment(gff1, gff2, bkinfo)
alignment = align[
gff1.columns[-int(len(bkinfo[self.classid].drop_duplicates())):]]
alignment.to_csv(self.savefile, header=None)
df = self.pair_positon(alignment, gff1['loc'], gff2['loc'],
self.colors)
plt.scatter(df['loc2'],
df['loc1'],
s=float(self.markersize),
c=df['color'],
alpha=0.5,
edgecolors=None,
linewidths=0,
marker='o')
ax.axis(axis)
plt.subplots_adjust(left=0.07, right=0.97, top=0.93, bottom=0.03)
plt.savefig(self.savefig, dpi=500)
plt.show()
sys.exit(0)
def run(self):
length = 1
axis = [0, 1, 1, 0]
left, right, top, bottom = 0.07, 0.97, 0.93, 0.03
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
step1 = 1 / float(lens1.sum())
step2 = 1 / float(lens2.sum())
if self.ancestor_left != None:
axis[0] = -0.02
lens_ancestor_left = pd.read_csv(self.ancestor_left,
sep="\t",
header=None)
lens_ancestor_left[0] = lens_ancestor_left[0].astype(str)
lens_ancestor_left[3] = lens_ancestor_left[3].astype(str)
lens_ancestor_left[4] = lens_ancestor_left[4].astype(int)
lens_ancestor_left[
4] = lens_ancestor_left[4] / lens_ancestor_left[4].max()
lens_ancestor_left = lens_ancestor_left[lens_ancestor_left[0].isin(
lens1.index)]
if self.ancestor_top != None:
axis[3] = -0.02
lens_ancestor_top = pd.read_csv(self.ancestor_top,
sep="\t",
header=None)
lens_ancestor_top[0] = lens_ancestor_top[0].astype(str)
lens_ancestor_top[3] = lens_ancestor_top[3].astype(str)
lens_ancestor_top[4] = lens_ancestor_top[4].astype(int)
lens_ancestor_top[
4] = lens_ancestor_top[4] / lens_ancestor_top[4].max()
lens_ancestor_top = lens_ancestor_top[lens_ancestor_top[0].isin(
lens2.index)]
if re.search('\d', self.figsize):
self.figsize = [float(k) for k in self.figsize.split(',')]
else:
self.figsize = np.array(
[1, float(lens1.sum()) / float(lens2.sum())]) * 10
plt.rcParams['ytick.major.pad'] = 0
fig, ax = plt.subplots(figsize=self.figsize)
ax.xaxis.set_ticks_position('top')
base.dotplot_frame(fig, ax, lens1, lens2, step1, step2,
self.genome1_name, self.genome2_name,
[axis[0], axis[3]])
gff1 = base.newgff(self.gff1)
gff2 = base.newgff(self.gff2)
gff1 = base.gene_location(gff1, lens1, step1, self.position)
gff2 = base.gene_location(gff2, lens2, step2, self.position)
if self.ancestor_top != None:
top = top
self.ancestor_posion(ax, gff2, lens_ancestor_top, 'top')
if self.ancestor_left != None:
left = left
self.ancestor_posion(ax, gff1, lens_ancestor_left, 'left')
blast = base.newblast(self.blast, int(self.score), float(self.evalue),
gff1, gff2, self.blast_reverse)
df = self.pair_positon(blast, gff1, gff2, int(self.multiple),
int(self.repeat_number))
ax.scatter(df['loc2'],
df['loc1'],
s=float(self.markersize),
c=df['color'],
alpha=0.5,
edgecolors=None,
linewidths=0,
marker='o')
ax.axis(axis)
plt.subplots_adjust(left=left, right=right, top=top, bottom=bottom)
plt.savefig(self.savefig, dpi=500)
plt.show()
sys.exit(0)