def clustersamples(exp,minreads=0):
"""
cluster samples in an experiment according to similar behavior
input:
exp :Experiment
minreads : int
the minimal original number of reads per sample to keep it
output:
newexp : Experiment
the filtered and clustered experiment
"""
params=locals()
newexp=hs.filterorigreads(exp,minreads)
# normalize each row (bacteria) to sum 1
dat=copy.copy(newexp.data)
dat=np.transpose(dat)
dat[dat<=2]=2
dat=np.log2(dat)
# cluster
dm=spatial.distance.pdist(dat,metric='braycurtis')
ll=cluster.hierarchy.single(dm)
order=cluster.hierarchy.leaves_list(ll)
newexp=hs.reordersamples(newexp,order)
hs.addcommand(newexp,"clustersamples",params=params,replaceparams={'exp':exp})
newexp.filters.append("cluster samples minreads=%d" % minreads)
return newexp
def filterorigreads(self):
items=self.bMainList.selectedItems()
if len(items)!=1:
print("Need 1 item")
return
for citem in items:
cname=str(citem.text())
cexp=self.explist[cname]
val,ok=QtGui.QInputDialog.getInt(self,'Filter Original Reads','Minimal number of reads per sample',5000,0,100000)
if ok:
newexp=hs.filterorigreads(cexp,minreads=val)
newexp.studyname=newexp.studyname+'_for'
self.addexp(newexp)
def subsample(expdat,numreads=10000,inplace=False):
"""
subsample (rarify) reads from all samples in an experiment
input:
expdat
numreads - number of reads to subsample to
inplace - true to replace current experiment
output:
newexp - the new subsampled experiment
"""
import biom
params=locals()
newexp=hs.filterorigreads(expdat,numreads,inplace)
newexp=hs.toorigreads(newexp,inplace=True)
table=biom.table.Table(newexp.data,newexp.seqs,newexp.samples)
table=table.subsample(numreads,axis='observation')
tids=table.ids(axis='sample')
for idx,cid in enumerate(tids):
if not cid==newexp.samples[idx]:
print('problem with sample ids!!!!')
newpos=[]
for cseq in table.ids(axis='observation'):
newpos.append(newexp.seqdict[cseq])
newexp=hs.reorderbacteria(newexp,newpos,inplace=True)
newexp.data=table.matrix_data.todense().A
newexp=normalizereads(newexp,numreads=10000,inplace=True,fixorig=False)
for cidx in range(len(newexp.samples)):
newexp.origreads[cidx]=numreads
newexp=updateorigreads(newexp)
newexp.filters.append("subsample to %d" % numreads)
hs.addcommand(newexp,"subsample",params=params,replaceparams={'expdat':expdat})
return newexp
