def savetobiom(expdat,filename,format='hdf5',addtax=True,useorigreads=True,exporthistory=True,logtransform=False):
"""
Save an experiment to a biom table
input:
expdat : Experiment
filename : string
Name of the file to save to
format : string
Format of the file ('hdf5','json','txt')
addtax : bool
True to add taxonomy metadata, False to not add
useorigreads : bool
True (default) to use original number of reads, False to use normalized (sum=10k)
exporthistory : bool
True (default) to save also the history (to filename.commands.txt)
logtransform : bool
True to log transform the data, false (default) to save original data
"""
savemap(expdat,filename+'.map.txt')
if exporthistory:
savecommands(expdat,filename+'.commands.txt')
hs.Debug(1,'Saving biom table %s' % filename)
if useorigreads:
newexp=hs.toorigreads(expdat)
else:
newexp=expdat
# if we need to log tranfrom the reads
if logtransform:
lowcutoff=1
ldat=newexp.data
ldat[np.where(ldat<lowcutoff)]=lowcutoff
ldat=np.log2(ldat)
tab=createbiomtablefromexp(newexp,addtax=addtax)
if format=='hdf5':
with biom.util.biom_open(filename, 'w') as f:
tab.to_hdf5(f, "heatsequer")
elif format=='json':
with open(filename,'w') as f:
tab.to_json("heatsequer",f)
elif format=='txt':
s=tab.to_tsv()
with open(filename,'w') as f:
f.write(s)
else:
hs.Debug(9,'file format not supported')
return
hs.Debug(6,'table saved to file %s' % filename)
return
def savetobiom(expdat,filename,format='hdf5',addtax=True,useorigreads=True):
"""
Save an experiment to a biom table
input:
expdat : Experiment
filename : string
Name of the file to save to
format : string
Format of the file ('hdf5','json','txt')
addtax : bool
True to add taxonomy metadata, False to not add
useorigreads : bool
True (default) to use original number of reads, False to use normalized (sum=10k)
"""
savemap(expdat,filename+'.map.txt')
hs.Debug(1,'Saving biom table %s' % filename)
if useorigreads:
newexp=hs.toorigreads(expdat)
else:
newexp=expdat
tab=createbiomtablefromexp(newexp,addtax=addtax)
if format=='hdf5':
with biom.util.biom_open(filename, 'w') as f:
tab.to_hdf5(f, "heatsequer")
elif format=='json':
with open(filename,'w') as f:
tab.to_json("heatsequer",f)
elif format=='txt':
s=tab.to_tsv()
with open(filename,'w') as f:
f.write(s)
else:
hs.Debug(9,'file format not supported')
return
hs.Debug(6,'table saved to file %s' % filename)
return
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
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