def view_in():
na = nu.net_affinity()
f = plt.figure(0)
f.clear()
ax = f.add_subplot(111)
in_degree = sum(na, 0)
srt = argsort(in_degree)
sm.seismic([in_degree[srt]], ax=ax)
myplots.maketitle(ax, 'In degree, sorted')
def tree_similarity(dist1, dist2, run_id,criterion = 'knn', k = 6):
if criterion == 'knn':
nq = len(dist1)
nb1 = argsort(dist1, 1)[:,1:k+1]
nb2 = argsort(dist2, 1)[:,1:k+1]
all_nbs = [set(n1).union(set(n2)) for n1, n2 in zip(nb1, nb2)]
nb_intersection = [set(n1).intersection(set(n2)) for n1, n2 in zip(nb1, nb2)]
nb_dists = [ array([[dist1[i, n], dist2[i,n]]for n in nbs ]) for i,nbs in enumerate(all_nbs)]
#take the first k distances.
n_disagreements = [len(nbd) - k for nbd in nb_dists]
nb_dists = array([ sorted(nbd, key = lambda x: min(x))[:k] for nbd in nb_dists])
frac_diffs = [abs(diff(elt, 1).flatten()) / mean(elt,1) for elt in nb_dists]
abs_diffs = [abs(diff(elt, 1).flatten()) for elt in nb_dists]
ct = mycolors.getct(nq)
f = myplots.fignum(4, (10,8))
ax = f.add_axes([.05,.08,.25,.87])
seismic.seismic(abs_diffs, ax = ax, colors = ct)
jaccard = mean([float(len(nb_intersection[i])) / float(len(all_nbs[i])) for i in range(nq)])
ax2 = f.add_axes([.34,.08,.6,.87])
for i,d in enumerate(nb_dists):
ax2.scatter(d[:,0], d[:,1], 20, alpha = .5,color =ct[i])
lin = linregress(nb_dists[:,:,0].flatten(),nb_dists[:,:,1].flatten())
rsquared = lin[2]**2
ax2.annotate('NN dists for multi/struct-aligned trees.\nK = {0}'.format(k),
[0,1], xycoords = 'axes fraction', va = 'top',
xytext = [10,-10],textcoords = 'offset pixels')
ax2.annotate('R-Squared: {0:3.3}\nJaccard Index: {1:3.3}'.format(rsquared, mean(jaccard)),
[1,0], xycoords = 'axes fraction', ha = 'right',
xytext = [-10,10],textcoords = 'offset pixels')
ax2.set_xlabel('Muscle aligned tree distances')
ax2.set_ylabel('Struct algined tree distances')
datafile = cfg.dataPath('figs/gpm2/pt2_mus_cm_tree_dists_{0}_k{1}.tiff'.format(run_id, k))
f.savefig(datafile)
def cluster_exprs(all_members, ct_data,
do_plot = False,
cluster_type = '4d',
cluster_id = 4):
mrnas = nio.getBDTNP()
misc = nio.getBDTNP(misc = True)
c = all_members[cluster_id]
c_unq = set(list(c))
tissues = dict([('t_{0}'.format(i) , dict(cts = ct_data[equal(c,elt)]))
for i, elt in enumerate(c_unq)])
nt = 6
counts = array([[sum(equal(v['cts'][:,1],t))
for t in range(nt) ]
for v in tissues.values() ])
if do_plot:
f = plt.figure(1)
f.clear()
ax1 = f.add_subplot('121')
ax2 = f.add_subplot('122')
seismic.seismic(counts , ax = ax1,stacked = True,colors = mycolors.getct(len(counts)))
#seismic.seismic(np.sort(counts,0) , ax = ax2,stacked = False,colors = mycolors.getct(len(counts)))
ax2.hist(np.sum(counts,1))
all_exprs = {}
for t, v in tissues.iteritems():
ct_all = v['cts']
for time in set([c[1] for c in ct_all]):
ct = [ct for ct in ct_all if ct[1] == time]
exprs =dict( [(k,elt['vals'][zip(*ct)]) for k, elt in mrnas.iteritems()])
ys = misc['y']['vals'][zip(*ct)] #zip(*sim_xy)]
zs = misc['z']['vals'][zip(*ct)] #zip(*sim_xy)]
xs = misc['x']['vals'][zip(*ct)] #zip(*sim_xy)]
f = plt.figure(1)
f.clear()
ax1 = f.add_subplot('121', title = 'X-Z axis view for tissue {0}'.\
format(t))
ax2 = f.add_subplot('122',title = 'Y-Z axis view for tissue {0}'.\
format(t))
ax1.scatter(xs, zs)
ax2.scatter(ys, zs)
v['exprs'] = exprs
all_exprs['tiss_{0}_time_{1}'.format(t,time)]=exprs
sio.savemat(open(cfg.dataPath('soheil/expression_c{0}_n{1}_tissue{2}_time{3}.mat'.\
format(cluster_type,cluster_id,t,time)),'w'),
exprs)
f.savefig(open(cfg.dataPath('soheil/expression_c{0}_n{1}_tissue{2}_time{3}.tiff'.\
format(cluster_type,cluster_id,t,time)),'w'))
exprs_out = dict([( k, [ mean(sub[k]) for sub in all_exprs[k].values() ])
for k in all_exprs.keys() ])
sio.savemat(open(cfg.dataPath('soheil/expression_c{0}_n{1}_intercluster.mat'.\
format(cluster_type,cluster_id)),'w'),
exprs_out)
raise Exception()
def sig_grid(num = 1 , method = 'tree', reset = False,
plot_kcs = True,
bp_means = False,
bp_zeros = True, zero_ofs = 1e-6,
bp_logs = True,
show_kos = False,
filter_rows_and_cols = False):
#Make and annotate the heatmap figure
f = plt.figure(1, facecolor = 'w')
f.clear()
axdims= .9
ax_box = array([.05,.05,axdims,axdims])
sg_big_hm_annotations(f, ax_box)
#Set up the sizes of each group axis in the heatmap figure
kwts = float(sum([len(v) for v in exps.values()]))
mwidth = .015
msize = mwidth*kwts
kw_total = kwts + ( msize * (len(exps)-1))
ofs = 0
allow_tf_kn = False
if not allow_tf_kn: grid[zip(*knockout_cells)] = 0
#Some more heatmap cfguration.
saturation = [np.percentile(grid[nonzero(greater(grid,0))],10),
np.percentile(grid[nonzero(greater(grid,0))],90)]
tf_srt = argsort(np.mean(grid,1))
all_bps = []
expsums = [np.mean( grid.T[v,:], 1) for v in exps.values()]
max_sum = np.max((list(it.chain(*expsums))))
#For each experiment class, plot a heatmap and overlay per exp sums
for k , v in exps.iteritems():
#Axes positioning
wid = len(v)
ax_ofs = array([ofs/kw_total, 0, (wid) / kw_total,1.])
ax_box = array([.05,.05,0.,0.])
ax_ofs = (ax_ofs * axdims) + ax_box
#Make heatmap axes.
ax = f.add_axes(ax_ofs, frameon = False)
sums = np.mean(grid.T[v,:],1)
exp_srt = argsort(sums)[::-1]
hm.heatMap( grid.T[v[exp_srt],:][:,tf_srt], axes = ax,
vmin = saturation[0],
vmax = saturation[1])
#Make overlay axes.
ax2 = f.add_axes(array(ax_ofs) + array([0,0,0,0]),
frameon = True,
axisbg = 'none',
xticks = [],
yticks = [])
#Make the axes look the way I like em
for a in ax2.spines.values():
a.set_linewidth(2)
a.set_alpha(.5)
these_knockouts = nonzero([c [1]in v for c in knockout_cells])
kc = knockout_cells[these_knockouts]
kv = knockout_vals[these_knockouts]
#If plot kcs is selected, plot the cells corresponding to TF deletion/OE
if plot_kcs:
if len(kc) > 0:
ax.scatter(*zip(*[( list(v).index(x[1]),x[0]) for x in kc]), s =50,
color = 'none', edgecolor = 'black', linewidth = 3)
color = 'blue'
ax2.plot(sums[exp_srt],
linewidth = 4, color = color)
if bp_means: bpelts = sums
else: bpelts = grid.T[v,:].flatten()
if not( bp_zeros ): bpelts = bpelts[nonzero(bpelts)]
all_bps.append(bpelts)
ax2.set_xlim([0,wid])
ax2.set_ylim([0,max_sum])
ax.set_xlim([0,wid])
ax.set_ylim([0,shape(grid)[0]])
ax2.set_xticks([])
#Annotate each axios
tbb = matplotlib.transforms.Bbox(ax2.bbox).translated(0,-20)
t = ax2.text(-2,0, k,
va = 'bottom', ha = 'right',
rotation = 90, color = 'black',
size = 'x-large', family = 'serif')
ofs += wid + msize
#Make the boxplot figure
f2 = plt.figure(3)
plt.clf()
if bp_means: bp_kos = array([ mean(grid.T[g[0],:],0)
for g in it.groupby(sorted(\
[ko[1] for ko in knockout_cells]))
])
else: bp_kos = array(knockout_vals)
if not bp_zeros: bp_kos = bp_kos[nonzero(bp_kos)]
all_bps = all_bps + [bp_kos]
ax3 = f2.add_subplot('111')
if bp_logs: all_bps = [log(b + zero_ofs) for b in all_bps]
bp_lzero = log(zero_ofs)
boxplots = ax3.boxplot([bp for bp in all_bps], widths= .5)
for p in boxplots.values():
for e in p: e.set_linewidth(4)
#Annotate the boxplot figure
ann_str = ''
for i in range(8):
ann_str += '{0}: {1}\n'.format(i+1, (exps.keys() + ['TF Knockout/OE'])[i])
ax3.annotate(ann_str, [0,1],xycoords = 'axes fraction',
xytext = [10,-10], textcoords = 'offset pixels',
va = 'top', ha = 'left')
ax3.set_title('''Boxplot of significances per experiment type for {3} learning method, Net {4}
Filtered out were {0} cells corresponding to {1} TFs Knocked out or OverExpressed.
{2} of these cells have nonzero importance and are plotted at x=9,
Showing Means: {5}, Showing zeros: {6}, Plotting logs {7}'''.\
format(len(knockout_cells), len(knockout_tfs),
len(nonzero(knockout_vals)[0]),
method, num,
bp_means, bp_zeros, bp_logs))
ax3.set_ylabel('significance')
ax3.set_xlabel('experiment class')
f.savefig(cfg.dataPath('daniel/figs/{0}_net{1}_heatmaps.tiff'.format(method, num)),
format = 'tiff')
plam = lambda: filter_rows_and_cols and 'nonzero_exps_and_tfs_cells_log/'\
or bp_zeros and not bp_logs and bp_means and 'zeros_means_nolog/'\
or not bp_zeros and bp_means and not bp_logs and 'nozeros_means_nolog/'\
or not bp_zeros and bp_means and bp_logs and 'nozeros_means_log/'\
or bp_zeros and not bp_means and not bp_logs and 'zeros_cells_nolog/'\
or not bp_zeros and not bp_means and not bp_logs and 'nozeros_cells_nolog/'\
or not bp_zeros and not bp_means and bp_logs and 'nozeros_cells_log/'
dataDir = cfg.dataPath('daniel/figs/{2}{0}_net{1}_boxplots.tiff'.\
format(method, num,plam()))
print 'saving {0}'.format(dataDir)
if not os.path.isdir(os.path.dirname(dataDir)): os.mkdir(os.path.dirname(dataDir))
if os.path.isfile(dataDir): os.remove(dataDir)
f2.savefig(dataDir, format = 'tiff')
mean_xvals = [ mean(all_bps[i][nonzero(greater(all_bps[i],bp_lzero))]) for i in range(len(all_bps))]
pdfs, xvals = zip(*[histogram(x, bins=50, range=[-15,8], normed=False) for x in all_bps])
import compbio.utils.colors as colors
c = colors.getct(len(pdfs))
f3 = plt.figure(3)
f3.clear()
sax = f3.add_subplot('111')
seismic.seismic([array(x,float)/ sum(x) for x in pdfs], xax = xvals[0][:-1],stacked = False, colors = c, xmarkpts = mean_xvals, ax = sax)
f4 = plt.figure(4)
f4.clear()
ax = f4.add_subplot('121')
ax.set_title('(log base 10) of Percentage Nonzero for Experiment Classes')
percs = log10(array([100*float(len(nonzero(greater(x,bp_lzero))[0])) / len(x) for x in all_bps]))
ax.plot(percs,linewidth = 6)
ax.set_yticks(percs)
names = exps.keys() + ['TF Knockout/OE']
ax.set_yticklabels(['{1}\n{0}'.format('%2.2f' % (10**p), names[idx]) for idx,p in enumerate(percs)])
ax2 = f4.add_subplot('122')
ax2.set_title('Mean of Nonzero Experiments for Experiment Classes')
means = array([mean(bp[nonzero(greater(bp,bp_lzero))]) for bp in all_bps])
ax2.plot(arange(1,9), means,linewidth = 6)
ax2.boxplot( [bp[nonzero(greater(bp,bp_lzero))] for bp in all_bps], widths = .5)
ax2.set_yticks(means)
names = exps.keys() + ['TF Knockout/OE']
ax2.set_yticklabels(['{1}\n{0}'.format('%2.2f' % (p), names[idx]) for idx,p in enumerate(means)])