def _getCisDistance(self, chrom=None):
"""
Get all chromosome cis distance.
Returns:
----------
out: dict
Examples:
----------
>>> vp.getCisDistance()
{'Chr1': [32, 4434, 23223, ...], 'Chr2': [2342, ...]}
"""
cis_dist_db = OrderedDict()
for vpl in self.getCisLine():
if chrom:
chrom = listify(chrom)
if vpl.chr1 in chrom:
if vpl.chr1 not in cis_dist_db:
cis_dist_db[vpl.chr1] = []
cis_dist_db[vpl.chr1].append(vpl.getCisDistance())
else:
if vpl.chr1 not in cis_dist_db:
cis_dist_db[vpl.chr1] = []
cis_dist_db[vpl.chr1].append(vpl.getCisDistance())
self.cis_dist_db = cis_dist_db
return self.cis_dist_db
def __init__(self, filename, exclude=None,
exclude_contig=['tig', 'Un', 'Sy', 'scaffold', 'ctg', 'Pt', 'Mt'],
mem_cache='.'):
check_file_exists(filename)
self.filename = filename
self.exclude = listify(exclude)
self.exclude_contig = listify(exclude_contig)
self.getChrSizes()
self.idx2label = dict((i, chrom)
for i, chrom in enumerate(self.chromLabels))
self.label2idx = dict((chrom, i)
for i, chrom in enumerate(self.chromLabels))
self.mem_cache = mem_cache
self.memory = Memory(mem_cache, verbose=0)
self.getGCBin = self.memory.cache(self._getGCBin)
def _getGCBin(self, window, chr=[], correct=True, thread=24):
"""
Calculate GC content of a series of windows, and return a OrderedDict
Params:
--------
window: `int` window of bin
chr: `list` default: `[]`
thread: `int` thread of parallel running default: `24`
Returns:
--------
out: `list` and gc store in array-like
Examples:
--------
>>> getGCbin(1000000)
[[0.5, 0.2, 0.5 ...], ...]
"""
self.gcBin = []
chroms = listify(chr) if chr else self.chromLabels
_chromsidx = [self.label2idx[i] for i in chroms]
"""
def subgc(chrom):
chromWindow = int(self.chromSizes[chrom] // self.window) + 1
_gc = np.ones(chromWindow, dtype=np.float)
for i in range(chromWindow):
_gc[i] = self.getGC(chrom, i*self.window,
(i+1)*self.window, correct=correct)
return _gc
res = Parallel(thread)(delayed(subgc)(args)
for args in _chromsidx)
"""
for chrom in _chromsidx:
chromWindow = int(self.chromSizes[chrom] // self.window) + 1
self.gcBin.append(np.ones(chromWindow, dtype=np.float))
for i in range(chromWindow - 1):
self.gcBin[chrom][i] = self.getGC(chrom,
i * self.window,
(i + 1) * self.window,
correct=correct)
else:
self.gcBin[chrom][chromWindow - 1] = self.getGC(
chrom, (chromWindow - 1) * self.window,
chromWindow * self.window,
correct=correct)
logging.debug('Successful getGCBin')
return self.gcBin
def savefig(figname, dpi=300, bbox_inches=None,
formats=['pdf', 'png'], cleanup=True):
"""
function for savefig, can save multi format
Params:
-------
figname: `str`
figname
dpi: `int`
dpi for figure [default: 300]
formats: `list` or `str`
picture formats [default: ["pdf", "png"]]
bbox_inches: `str`
bbox_inches params for plt.savefig [defult: None]
cleanup: `bool`
if cleanup rcParms after savefig [default: True]
Returns:
--------
out: output figure
Examples:
--------
>>> savefig('out')
"""
formats = listify(formats)
try:
if not op.splitext(figname)[-1]:
raise
else:
fmt = op.splitext(figname)[-1].lower()
except:
fmt = "pdf"
if fmt not in formats:
formats.append(fmt)
for fmt in formats:
figprefix = op.splitext(figname)[0]
outname = "{}.{}".format(figprefix, fmt)
plt.savefig(outname, dpi=dpi, format=fmt,
bbox_inches=bbox_inches)
msg = "Figure saved to `{}`".format(outname)
logging.debug(msg)
## reset rcParams after savefig
if cleanup:
plt.rcdefaults()
def plotMultiLR(data,
species,
output='out_multiSpecies',
workdir='./',
ncols=5):
"""
plot multi linregression scatter picture
Params:
--------
data: `dict`
data of pc values after synteny analysis
output: `str`
output figname [default: out_multiSpecies]
workdir: `str`
path to workdir [default: ./]
ncols: int
columns of picture [default: 5]
Returns:
--------
out: picutre
Examples:
--------
>>> data = getPCValues(species)
>>> plotMultiLR(data)
"""
nrows = int(math.ceil(len(data) * 1.0 / ncols))
ncols = min(ncols, len(data))
if ncols < 2:
fig, ax = plt.subplots(nrows, ncols, figsize=(ncols * 5.2, nrows * 5))
axes = listify(ax)
else:
fig, axes = plt.subplots(nrows,
ncols,
figsize=(ncols * 5.2, nrows * 5))
plt.subplots_adjust(wspace=0.28)
axes = trim_axes(axes, len(data))
for i, pairs in enumerate(data):
bg1, bg2 = data[pairs]
ax = plotLineRegress(axes[i],
bg1.score,
bg2.score,
xlabel=pairs[0],
ylabel=pairs[1])
savefig("{}/{}".format(workdir, output), bbox_inches='tight')
def __init__(self, cmds, threads=4):
self.cmds = listify(cmds)
self.threads = threads
self.run()