def renormalize(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]
newexp=hs.normalizereads(cexp)
newexp.studyname=newexp.studyname+'_norm'
self.addexp(newexp)
def filterandnormalize(expdat,seqs,exclude=False,subseq=False,numreads=10000):
"""
filter away sequences in seqs
and then renormalize the data and recalculate origreads per sample
input:
expdat
seqs - a list of sequences (ACGT) to remove
exclude - False to remove seqs, True to only keep seqs
subseq - False to look for exact match only, True to look for subsequence match (slower)
output:
newexp - the experiment without seqs and renormalied to 10k reads/sample
"""
params=locals()
newexp=hs.filterseqs(expdat,seqs,exclude=not(exclude),subseq=subseq)
newexp=hs.normalizereads(newexp,fixorig=True,numreads=numreads)
newexp.filters.append("filter sequences and normalize to numreads %d" % numreads)
hs.addcommand(newexp,"filterandnormalize",params=params,replaceparams={'expdat':expdat})
return newexp
def cleantaxonomy(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]
ctwin = CleanTaxonomyWindow(cexp)
res=ctwin.exec_()
if res==QtGui.QDialog.Accepted:
newexp=hs.copyexp(cexp)
if ctwin.cMitochondria.checkState():
newexp=hs.filtertaxonomy(newexp,'mitochondria',exclude=True)
if ctwin.cChloroplast.checkState():
newexp=hs.filtertaxonomy(newexp,'Streptophyta',exclude=True)
newexp=hs.filtertaxonomy(newexp,'Chloroplast',exclude=True)
if ctwin.cUnknown.checkState():
newexp=hs.filtertaxonomy(newexp,'nknown',exclude=True)
if ctwin.cBacteria.checkState():
newexp=hs.filtertaxonomy(newexp,'Bacteria;',exclude=True,exact=True)
newexp=hs.normalizereads(newexp)
newexp.studyname=cexp.studyname+'.ct'
self.addexp(newexp)
def filtern(expdat):
"""
delete sequences containing "N" from experiment and renormalize
input:
expdat : Experiment
output:
newexp : Experiment
experiment without sequences containing "N"
"""
params=locals()
keeplist=[]
for idx,cseq in enumerate(expdat.seqs):
if "N" in cseq:
continue
if "n" in cseq:
continue
keeplist.append(idx)
newexp=hs.reorderbacteria(expdat,keeplist)
newexp=hs.normalizereads(newexp)
newexp.filters.append('Filter sequences containing N')
hs.addcommand(newexp,"filtern",params=params,replaceparams={'expdat':expdat})
hs.Debug(6,'%d sequences before filtering, %d after' % (len(expdat.seqs),len(newexp.seqs)))
return newexp
def cleantaxonomy(expdat,mitochondria=True,chloroplast=True,bacteria=True,unknown=True,exclude=True):
"""
remove common non-16s sequences from the experiment and renormalize
input:
expdat : Experiment
mitochondria : bool
remove mitochondrial sequences
chloroplast : bool
remove chloroplast sequences
bacteria : bool
remove sequences only identified as "Bacteria" (no finer identification)
unknown : bool
remove unknown sequences
exclude : bool
True (default) to remove these sequecnes, False to keep them and throw other
output:
newexp : Experiment
the renormalized experiment without these bacteria
"""
params=locals()
newexp=hs.copyexp(expdat)
if mitochondria:
if exclude:
newexp=hs.filtertaxonomy(newexp,'mitochondria',exclude=True)
else:
ne1=hs.filtertaxonomy(newexp,'mitochondria',exclude=False)
if chloroplast:
if exclude:
newexp=hs.filtertaxonomy(newexp,'Streptophyta',exclude=True)
newexp=hs.filtertaxonomy(newexp,'Chloroplast',exclude=True)
else:
ne2=hs.filtertaxonomy(newexp,'Streptophyta',exclude=False)
ne3=hs.filtertaxonomy(newexp,'Chloroplast',exclude=False)
if unknown:
if exclude:
newexp=hs.filtertaxonomy(newexp,'Unknown',exclude=True)
newexp=hs.filtertaxonomy(newexp,'Unclassified;',exclude=True,exact=True)
else:
ne4=hs.filtertaxonomy(newexp,'Unknown',exclude=False)
ne5=hs.filtertaxonomy(newexp,'Unclassified;',exclude=False,exact=True)
if bacteria:
if exclude:
newexp=hs.filtertaxonomy(newexp,'Bacteria;',exclude=True,exact=True)
else:
ne6=hs.filtertaxonomy(newexp,'Bacteria;',exclude=False,exact=True)
if exclude:
newexp=hs.normalizereads(newexp)
else:
allseqs=[]
allseqs+=(ne1.seqs)
allseqs+=(ne2.seqs)
allseqs+=(ne3.seqs)
allseqs+=(ne4.seqs)
allseqs+=(ne5.seqs)
allseqs+=(ne6.seqs)
allseqs=list(set(allseqs))
newexp=hs.filterseqs(newexp,allseqs)
newexp.filters.append('Clean Taxonomy (remove mitochondria etc.)')
hs.addcommand(newexp,"cleantaxonomy",params=params,replaceparams={'expdat':expdat})
hs.Debug(6,'%d sequences before filtering, %d after' % (len(expdat.seqs),len(newexp.seqs)))
return newexp
def filtersimilarsamples(expdat,field,method='mean'):
"""
join similar samples into one sample (i.e. to remove samples of same individual)
input:
expdat : Experiment
field : string
Name of the field containing the values (for which similar values will be joined)
method : string
What to do with samples with similar value. options:
'mean' - replace with a sample containing the mean of the samples
'median'- replace with a sample containing the median of the samples
'random' - replace with a single random sample out of these samples
'sum' - replace with sum of original reads in all samples, renormalized after to 10k and orignumreads updated
'fracpres' - replace with fraction of samples where the bacteria is present
output:
newexp : Experiment
like the input experiment but only one sample per unique value in field
"""
params=locals()
newexp=hs.copyexp(expdat)
if method=='sum':
newexp=hs.toorigreads(newexp)
uvals=hs.getfieldvals(expdat,field,ounique=True)
keep=[]
for cval in uvals:
cpos=hs.findsamples(expdat,field,cval)
if len(cpos)==1:
keep.append(cpos[0])
continue
if method=='random':
keep.append(cpos[np.random.randint(len(cpos))])
continue
# set the mapping file values
cmap=expdat.smap[expdat.samples[cpos[0]]]
for ccpos in cpos[1:]:
for cfield in cmap.keys():
if cmap[cfield]!=expdat.smap[expdat.samples[ccpos]][cfield]:
cmap[cfield]='NA'
if method=='mean':
cval=np.mean(expdat.data[:,cpos],axis=1)
newexp.data[:,cpos[0]]=cval
keep.append(cpos[0])
elif method=='median':
cval=np.median(expdat.data[:,cpos],axis=1)
newexp.data[:,cpos[0]]=cval
keep.append(cpos[0])
elif method=='sum':
cval=np.sum(newexp.data[:,cpos],axis=1)
newexp.data[:,cpos[0]]=cval
newexp.origreads[cpos[0]]=np.sum(hs.reorder(expdat.origreads,cpos))
keep.append(cpos[0])
elif method=='fracpres':
cval=np.sum(expdat.data[:,cpos]>0,axis=1)
newexp.data[:,cpos[0]]=cval/len(cpos)
keep.append(cpos[0])
else:
hs.Debug(9,'method %s not supported' % method)
return False
newexp.smap[expdat.samples[cpos[0]]]=cmap
newexp=hs.reordersamples(newexp,keep)
if method=='sum':
newexp=hs.normalizereads(newexp)
newexp.filters.append('Filter similar samples field %s method %s' % (field,method))
hs.addcommand(newexp,"filtersimilarsamples",params=params,replaceparams={'expdat':expdat})
hs.Debug(6,'%d samples before filtering, %d after' % (len(expdat.samples),len(newexp.samples)))
return newexp
