def plot_cdf_pos_randoms(pospairs, ppis):
import plotting as pl
pl.figure()
pos,neg1 = pl.hist_pairs_nonpairs(ppis, pospairs, negmult=1, do_plot=False)
pos,neg100 = pl.hist_pairs_nonpairs(ppis, pospairs, negmult=100,
do_plot=False)
for pairs in pos, neg1, neg100:
pl.cdf(pairs,bins=np.arange(0,1.01,.01))
pl.xlabel("PPI score")
pl.ylabel("Cumulative fraction of population")
pl.title('Several percent of sequential enzymes are high-scoring,\ncompared to much less than one percent for random shufflings')
pl.legend(['Sequentials','Size-matched reshuffled','100x larger set of reshuffled'],loc=4)
def display_isophotes(data, isolist, bad='black', cbar_label='', cmap=cm.gray,
norm=LogNorm(), vmin=None, vmax=None) :
global currentFig
fig = plt.figure(currentFig)
currentFig += 1
plt.clf()
ax = fig.add_subplot(111)
cmap = cmap
cmap.set_bad(bad, 1)
frame = ax.imshow(data, origin='lower', cmap=cmap, norm=norm,
vmin=vmin, vmax=vmax)
cbar = plt.colorbar(frame)
cbar.set_label(cbar_label)
smas = isolist.sma
for i in range(len(isolist)) :
if (isolist.stop_code[i] == 0) and (isolist.nflag[i] == 0) :
iso = isolist.get_closest(isolist.sma[i])
x, y, = iso.sampled_coordinates()
ax.plot(x, y, color='white')
plt.tight_layout()
plt.show()
return
def plot_profiles(prots, eluts, sp='Hs', plot_sums=True, shape=None,
min_count=1):
"""
shape: (m,n) = m rows, n columns
eluts: [el.NormElut(f, sp, norm_rows=False, norm_cols=False) for f in
fs]
"""
import plotting as pl
gt = seqs.GTrans()
use_eluts = elutions_containing_prots(eluts, sp, seqs.names2ids(prots),
min_count)
shape = shape if shape else ut.sqrt_shape(len(use_eluts)+1)
fig = pl.figure()
for i,e in enumerate(use_eluts):
sp_target = ut.shortname(e.filename)[:2]
pl.subplot(shape[0],shape[1],i+1)
pl.title(ut.shortname(e.filename))
pids = [gt.name2id[p] for p in prots]
protsmax = max([np.max(e.normarr[r]) for p in pids if p in e.baseid2inds for
r in e.baseid2inds[p]])
plot_prots(e, pids, e.baseid2inds, protsmax)
if plot_sums:
# plot total spectral counts normalized to match biggest peak
sums = np.sum(e.normarr,axis=0)
fmax = np.max(sums)
pl.plot(range(sums.shape[1]),
np.log2(sums[0,:]).T*np.log2(protsmax)*len(pids)/np.log2(fmax),
color='k', linestyle='-', linewidth=.5)
# make legend with all prots
pl.subplot(shape[0],shape[1],0)
for p in prots: pl.plot(0,label=p)
pl.legend()
def plot_pairs_randoms_etc(sequentials, score_ppis, plusns=None):
import plotting as pl
pl.figure()
plus2s, plus3s4s = plusns or plusn(sequentials)
#plus2s = plusns or plusn(sequentials)
rand_pairs = random_pairs(sequentials, len(sequentials))
scores = [pl.hist_pairs_nonpairs(score_ppis, pairs, negmult=10,
do_plot=False)
for pairs in sequentials, plus2s, plus3s4s, rand_pairs]
#for pairs in sequentials, plus2s, plus3s, plus4s, rand_pairs]
ks_pvals = [ks_2samp(pos,neg)[1] for pos,neg in scores] # [1] is p-value
logvals = [-np.log10(pval) for pval in ks_pvals]
#pl.bar_plot(['%s\np < %0.3g' % (x,y) for x,y in zip('n,n+1 n,n+2 n,n+3 random'.split(), ks_pvals)], logvals)
pl.bar_plot(['%s\np < %0.3g' % (x,y) for x,y in zip('n,n+1 n,n+2 n,n+3/4 random'.split(), ks_pvals)], logvals)
pl.ylabel('-log10(p-value) : two-sample K/S test')
pl.title('Intersection of recon and kegg sequential pairs\nNpairs=%s; %s n+2s, %s n+3s,n+4s' % (len(sequentials), len(plus2s), len(plus3s4s)))
return logvals
def cluster_ids(gids, unnorm_eluts, sp, gt=None, dist='cosine', do_plot=True,
norm_rows=True, bigarr=None, **kwargs):
import plotting as pl
import hcluster
arr = (bigarr if bigarr is not None else single_array(gids, unnorm_eluts,
sp, norm_rows=norm_rows))
ymat = hcluster.pdist(arr, metric=dist)
zmat = hcluster.linkage(ymat)
zmat = np.clip(zmat, 0, 10**8)
if do_plot: pl.figure()
order = hcluster.dendrogram(zmat, no_plot=bool(1-do_plot),
**kwargs)['leaves']
if do_plot:
ax = pl.gca()
ax.axes.set_xticklabels([gt.id2name[gids[ind]] for ind in order])
pl.figure()
pl.imshow(arr[order,:])
return list(np.array(list(gids))[order])