def get_tf_ss(cluster = 0, trgnames = None, basic = False):
if basic:
trgs, tfs = nu.parse_net()
#grab a list of the tfs regulating 10 random trgs
tfl = []
for k in trgs.keys()[0:50]:
item = trgs[k]
tfs = item['tfs']
for t in tfs:
if not t in tfl:
tfl.append(t)
else:
min_regs = min_tf_perc
nat = greater(nu.net_affinity(),0)
tgkeys = nu.net_trg_keyidxs()
tg_sub = nat[[tgkeys[k] for k in trgnames],:]
mem_means = mean(array(tg_sub,float),0)
tfkeys = nu.net_tf_keyidxs()
tfl = []
tfhash = ['']* len(tfkeys.keys())
for k,v in tfkeys.items(): tfhash[v] = k
for n in nonzero(greater(mem_means,min_regs))[0]:
tfl.append(tfhash[n])
return tfl
def all_siblings(name = default_name, reset = 0):
donp = True
hardcopy = True
if not reset:
out, sxs = nw.rn2(default_name,
np = donp, hardcopy = hardcopy)
if reset or not sxs:
trgs, tfs = nu.parse_net(reset=mod(reset,2))
na = nu.net_affinity(reset = mod(reset,2))
na_thr = greater(na, min_thr)
nrms = sqrt(sum(power(na_thr,2),1))[:,newaxis]
nrms[equal(nrms,0)] = 1
nnn = array(na_thr,float)/nrms
gg = dot(nnn,nnn.T)
sibs = array(greater(gg, sib_thr), bool)
nw.wn2(default_name, sibs,
np = donp,
hardcopy = hardcopy)
out = sibs
return out
def coreg_keys(t0 = None, do_plot = False):
trgs, tfs = nu.parse_net()
btgs, btfs = trg_markov_blanket(t0)
if do_plot:
show_m(btgs,btfs,t0)
min_wt = .3
tgs_thr =nonzero( greater(btgs.values(),min_wt) )[0]
keys_thr =[btgs.keys()[i] for i in tgs_thr]
keys_thr.remove(t0)
na = nu.net_affinity()
ktf = nu.net_tf_keyidxs()
ktg = nu.net_trg_keyidxs()
shared = []
threshold_sims = True
for k in keys_thr:
# bg,bf = trg_markov_blanket(k, do_tgs = False)#
row1 = na[ktg[k]]
row0 = na[ktg[t0]]
if threshold_sims:
row0=array(greater(row0,min_wt),float)
row1=array(greater(row1,min_wt),float)
for r in [row0,row1]:
l = sqrt(sum(power(r,2)))
if l != 0: r /= l
shared.append(sum(row0*row1))
shared = array(shared)
min_sharing = .4
coreg_keys = [ keys_thr[i] for i in nonzero(greater(shared,min_sharing))[0]]
if do_plot:
plot_shared(shared)
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 draw_hclustered(clustered):
c = clustered['HCluster']
clusters = c.cut(0)
f = plt.figure(0)
f.clear()
ax = f.add_axes([0,0,1,1],aspect = 'auto')
ax.set_aspect('auto')
c0 = c.cut(0)
n = max(array(c0)) +1
nlvl = 100
h = zeros((nlvl,n))
cuts = linspace(0,.9,nlvl)
appearances = zeros(n)-1
hinds = zeros((nlvl,n),int)
for i in range(nlvl):
cut = cuts[i]
clusters = c.cut(cut)
for j in range(n):
cval = clusters[j]
if appearances[cval] == -1: appearances[cval] = j
h[i,j] = appearances[cval]
hinds[i,:] = argsort(h[i,:])
h[i,:]=h[i,hinds[i,:]]
for i in range(shape(h)[0]):
h[i,:] /= max(h[i,:])
ax.imshow(mycolors.imgcolor(h, BW = True), aspect = 'auto', interpolation = 'nearest')
saff,ks = nu.net_square_affinity()
raff,kt,ktf = nu.net_affinity()
tfidxs = []
for tf in ktf.keys():
tfidxs.append(ks.index(tf))
tfidxs= array(tfidxs)
is_clustered = tfidxs[nonzero(less(tfidxs,n))[0]]
ntf = len(is_clustered)
tf_alpha = zeros((nlvl,n))
for i in range(ntf):
tf_alpha +=equal(hinds,is_clustered[i])
tf_rgba = mycolors.imgcolor(tf_alpha,alpha = True,color = [1,0,0])
ax.imshow(tf_rgba, aspect = 'auto', interpolation = 'nearest')
def net_cluster_genes_by_tf(k= k, reset = 0):
hardcopy = True
try:
if reset: raise Exception('compute')
out,sxs = nw.rn2(name, hardcopy = hardcopy)
if not sxs: raise Exception()
except Exception as e:
if e.args[0] != 'compute': raise Exception()
nw.claim_reset()
gg = nu.net_affinity(reset = mod(reset,2))
kmeans = mlpy.Kmeans(k)
clustered = kmeans.compute(gg[0:maxgenes,:])
means = kmeans.means
out = (clustered,means)
nw.wn2(name, (clustered, means) ,hardcopy = hardcopy)
return out
def net_svd(name=nu.default_name, reset=0):
hardcopy = True
try:
if reset:
raise Exception("compute")
return nw.readnet(name=nu.default_name, hardcopy=hardcopy)
except Exception as e:
if e.args[0] != "compute":
raise Exception()
nw.claim_reset()
a = nu.net_affinity(reset=mod(reset, 2))[0]
N = a[0]
U, S, Vh = lin.svd(N)
V = Vh.T
U = U[:, len(S)]
dosave = (a[1], (U, S, V))
nw.writenet(name, dosave, hardcopy=hardcopy)
return dosave
def cluster( columns = False):
sqa = nu.net_affinity()[0]
#tfidxs = nonzero(np.max(sqa ,0))[0]
#raise Exception()
if columns:
arr = array(sqa.T)
else:
arr = array(sqa)
subarr = arr[:,:]
k = 20
kmeans = mlpy.Kmeans(k)
clustered = kmeans.compute(subarr)
means = kmeans.means
import compbio.learning.clusterview as cl
cl.specview(means,clustered)
def viewmany(all_means, all_clusters, fig = 12):
n = len(all_means)
f = plt.figure(fig)
f.clear()
print '''Running viewmany.py
For now, viewmany assumes that k is equal across clustering instances
this is not really important but has to do with how TF projections are
stored.
'''
#1 k.
k = len(all_means[0])
ax1 = f.add_axes([.05,.05,.95,.4])
ax2 = f.add_axes([.05,.55,.95,.4])
ct0 = mycolors.getct(n)
sqa = nu.net_square_affinity()[0]
aff = nu.net_affinity()[0]
#tf_sqidxs should have length = ntf
#with each element giving the coordinate of the
#i'th tf in sqa space.
sqidxs = nu.net_sq_keyidxs()
n_tfidxs = nu.net_tf_keyidxs()
trgs,tfs = nu.parse_net()
tf_sqidxs = [sqidxs[key] for key in tfs.keys()]
tfidxs = n_tfidxs.values()
ntf = len(tfidxs)
tfweights = zeros(ntf,int)
#find tfs of general interest, choosing at most ten for each clustering
ntf_each = 20
print '''...Computing representative TFs for each clustering.
In the current formulation, we project each mean on to associated tf
and then normalize each projection so that each mean has equal weight
in TF selection.
Not that we have handled the case where we have clusted in TF space
explicitly (e.g, dim = 541) and where we are in gene space explicitly,
(e.g., dim = 8321, GG matrix or svdU). svdV is emphatically not handled.
Neither would svdU of TF-TF which is actually the the exact same thing.'''
TFprojs= zeros((n,k,ntf))
for i in range(n):
m = all_means[i]
dim = shape(m)[1]
#we are now going to project clusters on to the tfs
#in this form, we only need rows corresponding to tfs.
if dim> 500:
#If dim = 541, we just read off the most important tfs
this_tf_sum = np.abs(m[:,tfidxs])
TFprojs[i,:,:] = this_tf_sum
#normalize clusters
this_tf_sum = this_tf_sum / np.sum(this_tf_sum,1)[:,newaxis]
this_tf_sum = np.sum(this_tf_sum,0)
#Now, since we are at the moment only working with GG
#and SVD_U, we are in gene space and can undo the mapping
#with sqaT
elif dim > 8000:
#remember, ROWS of the matrix correspond to the
#target space.
a = sqa.T[tf_sqidxs,:]
this_tf_sum = np.abs(np.sum(a[newaxis,:,:]*m[:,newaxis,:],2))
TFprojs[i,:,:] = this_tf_sum
#normalize so that each mean has the same weight
this_tf_sum = this_tf_sum / np.sum(this_tf_sum,1)[:,newaxis]
#sum over cluster means to find the most important tfs
this_tf_sum = np.sum(this_tf_sum,0)
best = argsort(this_tf_sum)[::-1]
tfweights[best[0:ntf_each]]=1
print '''Finished computing representative TFs
'''
tfs_of_interest = nonzero(tfweights)[0]
ntf = len(tfs_of_interest)
avg_unshared = float(ntf)/(n * ntf_each)
avg_shared = 1. - float(ntf)/(n * ntf_each)
print '''Allowing for each cluster to choose '+str(ntf_each) + 'tfs,
we got ''' + str(ntf) + ''' tfs of interest.
or a mean sharing ratio of ''' + str(round(avg_shared,3))+ '''.'''
#get a color table for clusters.
ct = mycolors.getct(n)
for i in range(n):
#p stands for 'point' as in datapoint.
#data points are labeled with clusters.
xax = linspace(0,1,ntf)
ax1.plot(xax,np.sum(TFprojs[i,:,tfs_of_interest],1)/np.max(TFprojs[i,:,tfs_of_interest],1),color = ct[i])
return TFprojs