def doWork( options ):
# open the input and output files
outCSV = open(options.outfile, 'w')
inCSV = open(options.infile, 'r')
if(options.header):
next(inCSV)
data_array = np.array([])
names_array = np.array([])
# convert the input csv into an array
print "loading data..."
num_rows = 0
num_cols = 0
max_rows = int(options.max_rows)
for line in inCSV:
row = line.rstrip().split(options.sep)
if(0 == num_rows):
num_cols = len(row)
num_rows += 1
names_array = np.append(names_array, [row[0]])
data_array = np.append(data_array, [float(x) for x in row[1:]])
if((max_rows != 0) and (num_rows >= max_rows)):
break
# adjust for the row names
num_cols -= 1
print "Loaded" ,num_rows, "rows across" , num_cols, "cols"
# do the PCA and extract the scores
data_array = np.reshape(data_array, (num_rows, num_cols))
print "Performing PCA ..." ,
Center(data_array,verbose=0)
p = PCA(data_array)
components = p.pc()
# scale PC0
min_score = float(min(components[:,0]))
max_score = float(max(components[:,0]))-min_score
scaled_scores = [(float(x)-min_score)/max_score for x in components[:,0]]
# write to file
outCSV.write(options.sep.join(["'name'","'value'"])+"\n")
for index in range (0,num_rows):
S = 1
V = 1
if(options.colors):
col = "#%s" % "".join(["%0.2X" % k for k in [int(i*255) for i in htr(scaled_scores[index], S, V)]])
outCSV.write(options.sep.join([str(x) for x in [names_array[index], col]])+"\n")
else:
outCSV.write(options.sep.join([str(x) for x in [names_array[index], scaled_scores[index]]])+"\n")
# plot the PCA if we've been asked to...
if(options.plot):
figure()
plot(components[:,0],components[:,1],'*g')
axis('equal')
show()
return 0
def createColorMapHSV(self):
S = 1.0
V = 1.0
return LinearSegmentedColormap.from_list('GC', [
htr((1.0 + np_sin(np_pi * (val / 1000.0) - np_pi / 2)) / 2., S, V)
for val in xrange(0, 1000)
],
N=1000)
def getColor(self, vector):
"""return a colour for a given weight vector"""
sn = np.linalg.norm(vector)
if sn > 0:
vv = vector / sn
ang_perc = self.getAngBetweenNormed(vv, self.cVec)/self.maxAngle
mag_perc = sn / self.largestMag
else:
ang_perc = 0.0
mag_perc = 0.0
V = 1 # VAL remain fixed at 1. Reduce to make pastels if that's your preference...
col = [int(i*255) for i in htr(ang_perc, mag_perc, V)]
return col
def getColor(self, vector):
"""return a colour for a given weight vector"""
sn = np.linalg.norm(vector)
if sn > 0:
vv = vector / sn
ang_perc = self.getAngBetweenNormed(vv, self.cVec) / self.maxAngle
mag_perc = sn / self.largestMag
else:
ang_perc = 0.0
mag_perc = 0.0
V = 1 # VAL remain fixed at 1. Reduce to make pastels if that's your preference...
col = [int(i * 255) for i in htr(ang_perc, mag_perc, V)]
return col
def randomizeCols(self, setLoaded=False):
"""choose colors randomly"""
S = 1.0
V = 1.0
if setLoaded:
for bid in self.bin2Str.keys():
self.loaded[bid] = True
num_bins = len(self.bin2Str)
offset = 0.5
step = 1. /(num_bins-1 + 2. * offset)
Hs = np.array([step*(i + offset) for i in range(num_bins)])
cols = [htr(H, S, V) for H in Hs]
np.random.shuffle(cols)
i = 0
for bid in self.bin2Str.keys():
if self.loaded[bid]:
# assign the color we picked
self.bin2Cols[bid] = cols[i]
else:
# set to the unbinned color
self.bin2Cols[bid] = self.unbinnedCol
i += 1
def doWork(args):
""" Main wrapper"""
esom_name_to_ids = []
num_esom_names = 0
all_named_contigs = {}
# parse names file and make the hash we'll be needing
try:
with open(args.names, "r") as fh:
for line in fh:
num_esom_names += 1
parts = line.rstrip().split("\t")
cid_parts = parts[1].split('_')
if 'leftover' in cid_parts:
base_name = "_".join(cid_parts[:len(cid_parts) - 2])
else:
base_name = "_".join(cid_parts[:len(cid_parts) - 1])
esom_name_to_ids.append(
(base_name, parts)
) # ('hydrocarbon_scaffold_82282', ['1', 'hydrocarbon_scaffold_82282_0'])
all_named_contigs[base_name] = True
except:
print "Error opening file:", args.names, sys.exc_info()[0]
raise
# parse the GM file
gm_bin_ids = {}
cid_2_gmbin = {}
try:
with open(args.gmbin, "r") as fh:
for line in fh:
parts = line.rstrip().split("\t")
bid = int(parts[0])
cid_2_gmbin[parts[1]] = bid
gm_bin_ids[bid] = True
except:
print "Error opening file:", args.names, sys.exc_info()[0]
raise
num_gm_bins = len(gm_bin_ids.keys())
# produce a whole heap of colors
color_steps = [float(i) / num_gm_bins for i in range(num_gm_bins)]
S = 1 # SAT and VAL remain fixed at 1. Reduce to make
V = 1 # Pastels if that's your preference...
raw_cols = np.array(
[np.array(htr(val, S, V)) * 255 for val in color_steps])
bin_cols = [[int(i) for i in j] for j in raw_cols]
# work out all the bin 0 contigs
for cid in all_named_contigs:
if cid not in cid_2_gmbin:
cid_2_gmbin[cid] = 0
# build the class file
print "%d" % num_esom_names + "%"
print "0%\tNOCLASS\t255\t255\t255"
for i in range(len(bin_cols)):
print "%d" % (i + 1) + "%" + "\t%d\t%d\t%d\t%d" % (
i + 1, bin_cols[i][0], bin_cols[i][1], bin_cols[i][2])
for i in range(len(esom_name_to_ids)):
# ('hydrocarbon_scaffold_82282', ['1', 'hydrocarbon_scaffold_82282_0'])
gm_bid = cid_2_gmbin[esom_name_to_ids[i][0]]
print "%d\t%d" % (i + 1, gm_bid)
def plotRegion(self, px, py, pz, fileName="", tag="", column=False):
"""Plot the region surrounding a point """
import matplotlib as mpl
disp_vals = np_array([])
disp_cols = np_array([])
num_points = 0
# plot all points within span
(z_lower, z_upper) = self.makeCoordRanges(pz, self.span)
if column:
z_lower = 0
z_upper = self.PM.scaleFactor - 1
(x_lower, x_upper) = self.makeCoordRanges(px, self.span)
(y_lower, y_upper) = self.makeCoordRanges(py, self.span)
for z in range(z_lower, z_upper):
realz = self.PM.scaleFactor - z - 1
for x in range(x_lower, x_upper):
for y in range(y_lower, y_upper):
if (x, y, realz) in self.im2RowIndicies:
for row_index in self.im2RowIndicies[(x, y, realz)]:
if (
row_index not in self.PM.binnedRowIndicies
and row_index not in self.PM.restrictedRowIndicies
):
num_points += 1
disp_vals = np_append(disp_vals, self.PM.transformedCP[row_index])
disp_cols = np_append(disp_cols, self.PM.contigColours[row_index])
# make a black mark at the max values
small_span = self.span / 2
(x_lower, x_upper) = self.makeCoordRanges(px, small_span)
(y_lower, y_upper) = self.makeCoordRanges(py, small_span)
(z_lower, z_upper) = self.makeCoordRanges(pz, small_span)
for z in range(z_lower, z_upper):
realz = self.PM.scaleFactor - z - 1
for x in range(x_lower, x_upper):
for y in range(y_lower, y_upper):
if (x, y, realz) in self.im2RowIndicies:
for row_index in self.im2RowIndicies[(x, y, realz)]:
if (
row_index not in self.PM.binnedRowIndicies
and row_index not in self.PM.restrictedRowIndicies
):
num_points += 1
disp_vals = np_append(disp_vals, self.PM.transformedCP[row_index])
disp_cols = np_append(disp_cols, htr(0, 0, 0))
# reshape
disp_vals = np_reshape(disp_vals, (num_points, 3))
disp_cols = np_reshape(disp_cols, (num_points, 3))
fig = plt.figure()
ax = fig.add_subplot(111, projection="3d")
cm = mpl.colors.LinearSegmentedColormap("my_colormap", disp_cols, 1024)
result = ax.scatter(
disp_vals[:, 0], disp_vals[:, 1], disp_vals[:, 2], edgecolors=disp_cols, c=disp_cols, cmap=cm, marker="."
)
title = str.join(" ", ["Focus at: (", str(px), str(py), str(self.PM.scaleFactor - pz - 1), ")\n", tag])
plt.title(title)
if fileName != "":
fig.set_size_inches(6, 6)
plt.savefig(fileName, dpi=300)
elif show:
plt.show()
plt.close(fig)
del fig
def doWork( args ):
""" Main wrapper"""
esom_name_to_ids = []
num_esom_names = 0
all_named_contigs = {}
# parse names file and make the hash we'll be needing
try:
with open(args.names, "r") as fh:
for line in fh:
num_esom_names += 1
parts = line.rstrip().split("\t")
cid_parts = parts[1].split('_')
if 'leftover' in cid_parts:
base_name = "_".join(cid_parts[:len(cid_parts)-2])
else:
base_name = "_".join(cid_parts[:len(cid_parts)-1])
esom_name_to_ids.append((base_name, parts)) # ('hydrocarbon_scaffold_82282', ['1', 'hydrocarbon_scaffold_82282_0'])
all_named_contigs[base_name] = True
except:
print "Error opening file:", args.names, sys.exc_info()[0]
raise
# parse the GM file
gm_bin_ids = {}
cid_2_gmbin = {}
try:
with open(args.gmbin, "r") as fh:
for line in fh:
parts = line.rstrip().split("\t")
bid = int(parts[0])
cid_2_gmbin[parts[1]] = bid
gm_bin_ids[bid] = True
except:
print "Error opening file:", args.names, sys.exc_info()[0]
raise
num_gm_bins = len(gm_bin_ids.keys())
# produce a whole heap of colors
color_steps = [float(i)/num_gm_bins for i in range(num_gm_bins)]
S = 1 # SAT and VAL remain fixed at 1. Reduce to make
V = 1 # Pastels if that's your preference...
raw_cols = np.array([np.array(htr(val, S, V))*255 for val in color_steps])
bin_cols = [[int(i) for i in j] for j in raw_cols]
# work out all the bin 0 contigs
for cid in all_named_contigs:
if cid not in cid_2_gmbin:
cid_2_gmbin[cid] = 0
# build the class file
print "%d" % num_esom_names + "%"
print "0%\tNOCLASS\t255\t255\t255"
for i in range(len(bin_cols)):
print "%d" % (i+1) + "%" + "\t%d\t%d\t%d\t%d" % (i+1, bin_cols[i][0],bin_cols[i][1],bin_cols[i][2])
for i in range(len(esom_name_to_ids)):
# ('hydrocarbon_scaffold_82282', ['1', 'hydrocarbon_scaffold_82282_0'])
gm_bid = cid_2_gmbin[esom_name_to_ids[i][0]]
print "%d\t%d" % (i+1,gm_bid)
def createColorMapHSV(self):
S = 1.0
V = 1.0
return LinearSegmentedColormap.from_list('GC', [htr((1.0 + np_sin(np_pi * (val/1000.0) - np_pi/2))/2., S, V) for val in xrange(0, 1000)], N=1000)
def loadData(self,
condition="", # condition as set by another function
bids=[], # if this is set then only load those contigs with these bin ids
verbose=True, # many to some output messages
silent=False, # some to no output messages
loadCovProfiles=True,
loadKmerSigs=True,
makeColours=True,
loadContigNames=True,
loadContigLengths=True,
loadBins=False,
loadLinks=False):
"""Load pre-parsed data"""
if(verbose):
print "Loading data from:", self.dbFileName
# check to see if we need to override the condition
if(len(bids) != 0):
condition = "((bid == "+str(bids[0])+")"
for index in range (1,len(bids)):
condition += " | (bid == "+str(bids[index])+")"
condition += ")"
if(silent):
verbose=False
try:
self.numStoits = self.getNumStoits()
self.condition = condition
if(verbose):
print " Loading indices (", condition,")"
self.indices = self.dataManager.getConditionalIndicies(self.dbFileName, condition=condition)
self.numContigs = len(self.indices)
if(not silent):
print " Working with: %d contigs" % self.numContigs
if(loadCovProfiles):
if(verbose):
print " Loading coverage profiles"
self.covProfiles = self.dataManager.getCoverageProfiles(self.dbFileName, indices=self.indices)
# work out average coverages
self.averageCoverages = np_array([sum(i)/self.numStoits for i in self.covProfiles])
if(loadKmerSigs):
if(verbose):
print " Loading kmer sigs"
self.kmerSigs = self.dataManager.getKmerSigs(self.dbFileName, indices=self.indices)
if(makeColours):
if(verbose):
print " Creating colour profiles"
self.makeColourProfile()
# use HSV to RGB to generate colours
S = 1 # SAT and VAL remain fixed at 1. Reduce to make
V = 1 # Pastels if that's your preference...
self.contigColours = np_array([htr(val, S, V) for val in self.kmerVals])
if(loadContigNames):
if(verbose):
print " Loading contig names"
self.contigNames = self.dataManager.getContigNames(self.dbFileName, indices=self.indices)
if(loadContigLengths):
if(verbose):
print " Loading contig lengths"
self.contigLengths = self.dataManager.getContigLengths(self.dbFileName, indices=self.indices)
print " Contigs contain %d BP" % ( sum(self.contigLengths) )
if(loadBins):
if(verbose):
print " Loading bins"
self.binIds = self.dataManager.getBins(self.dbFileName, indices=self.indices)
if len(bids) != 0: # need to make sure we're not restricted in terms of bins
tmp_bids = self.getBinStats()
for bid in bids:
self.validBinIds[bid] = tmp_bids[bid]
else:
self.validBinIds = self.getBinStats()
# fix the binned indices
self.binnedRowIndicies = {}
for i in range(len(self.indices)):
if(self.binIds[i] != 0):
self.binnedRowIndicies[i] = True
else:
# we need zeros as bin indicies then...
self.binIds = np_zeros(len(self.indices))
if(loadLinks):
self.loadLinks()
except:
print "Error loading DB:", self.dbFileName, exc_info()[0]
raise
