def wrapper(args):
try:
npar = args.noiseparam.strip('[').strip(']').split(',')
except:
npar = []
nbins = args.nbins
# Run funciton
if args.i:
df = pd.io.parsers.read_csv(
args.i,delim_whitespace=True,
dtype={'seqs':str,'batch':int})
else:
df = pd.io.parsers.read_csv(
sys.stdin,delim_whitespace=True,
dtype={'seqs':str,'batch':int})
if len(utils.get_column_headers(df)) > 0:
raise SortSeqError('Library already sorted!')
model_df = io.load_model(args.model)
output_df = main(
df,model_df,args.noisemodel,npar,
nbins,start=args.start,end=args.end)
if args.out:
outloc = open(args.out,'w')
else:
outloc = sys.stdout
pd.set_option('max_colwidth',int(1e8))
# Validate dataframe for writting
output_df = qc.validate_dataset(output_df,fix=True)
io.write(output_df,outloc)
def wrapper(args):
#validate some of the input arguments
qc.validate_input_arguments_for_learn_model(
foreground=args.foreground,background=args.background,alpha=args.penalty,
modeltype=args.modeltype,learningmethod=args.learningmethod,
start=args.start,end=args.end,iteration=args.iteration,
burnin=args.burnin,thin=args.thin,pseudocounts=args.pseudocounts,)
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
input_df = io.load_dataset(inloc)
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
#pdb.set_trace()
output_df = main(input_df,lm=args.learningmethod,\
modeltype=args.modeltype,db=args.db_filename,\
LS_means_std=args.LS_means_std,\
iteration=args.iteration,\
burnin=args.burnin,thin=args.thin,start=args.start,end=args.end,\
runnum=args.runnum,initialize=args.initialize,\
foreground=args.foreground,background=args.background,\
alpha=args.penalty,pseudocounts=args.pseudocounts,
verbose=args.verbose)
io.write(output_df,outloc)
def wrapper(args):
""" Commandline wrapper for main()
"""
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
input_df = io.load_dataset(inloc)
output_df = main(input_df,bin=args.bin,start=args.start,end=args.end)
io.write(output_df,outloc)
def wrapper(args):
""" Commandline wrapper for main()
"""
output_df = main(wtseq=args.wtseq, mutrate=args.mutrate,\
numseq=args.numseqs,dicttype=args.type,tags=args.tags,\
tag_length=args.tag_length)
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
io.write(output_df,outloc)
def wrapper(args):
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
dataset_df = io.load_dataset(inloc)
model_df = io.load_model(args.model)
output_df = main(dataset_df=dataset_df, model_df=model_df,\
left=args.left, right=args.right)
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
io.write(output_df,outloc,fast=args.fast)
def wrapper(args):
""" Commandline wrapper for main()
"""
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
input_df = io.load_dataset(inloc)
output_df = main(input_df, start=args.start,end=args.end,\
err=args.err, method=args.method, pseudocount=args.pseudocount)
io.write(output_df,outloc)
def test_profile_ct_bincounts(self):
""" Test the ability of sortseq_tools.profile_ct to count frequencies
"""
print '\nIn test_profile_ct_bincounts...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
good_bin_num = 2
bad_bin_num = 5
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda:\
profile_ct.main(io.load_dataset(file_name),bin=good_bin_num)
print '(bin=%d)'%good_bin_num,
# If bad or library, then profile_ct.main should raise SortSeqError
if ('_bad' in file_name) or ('library' in file_name):
try:
self.assertRaises(SortSeqError,executable)
print 'badtype,',
except:
print 'good (ERROR).'
raise
# If good, then profile_ct.main should produce a valid df
elif ('_good' in file_name) or ('dataset' in file_name):
try:
df = executable()
qc.validate_profile_ct(df)
out_file = self.output_dir+\
'profile_ct_bin_%s.txt'%description
io.write(df,out_file)
io.load_profile_ct(out_file)
print 'good,',
except:
print 'bad (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
# Should always raise an error if bin num is too large
executable = lambda:\
profile_ct.main(io.load_dataset(file_name),bin=bad_bin_num)
print '(bin=%d)'%bad_bin_num,
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
def test_preprocess(self):
""" Test the ability of sortseq_tools.preprocess to collate data in multiple sequence files
"""
print '\nIn test_preprocess...'
file_names = glob.glob(self.input_dir+'files_*.txt')
# Make sure there are files to test
self.assertTrue(len(file_names)>0)
for file_name in file_names:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
# If fasta or fastq, assume dna
if ('fasta' in file_name) or ('fastq' in file_name):
seq_type = 'dna'
else:
seq_type = None
executable = lambda: preprocess.main(io.load_filelist(file_name),indir=self.input_dir, seq_type=seq_type)
# If _good_, then preprocess.main should produce a valid df
if ('_good' in file_name) or ('_fix' in file_name):
try:
df = executable()
qc.validate_dataset(df)
out_file = self.output_dir+'dataset_%s.txt'%description
io.write(df,out_file) # Test write
io.load_dataset(out_file) # Test loading
print 'good.'
except:
print 'bad (ERROR).'
raise
# If _bad, then preprocess.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def wrapper(args):
""" Wrapper for functions io.load_* and io.write
"""
# Determine input and output
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
try:
# Get load function corresponding to file type
func = filetype_to_loadfunc_dict[str(args.type)]
# Run load function on input
df = func(inloc)
# Write df to stdout or to outfile
io.write(df,outloc,fast=args.fast)
except SortSeqError:
raise
def wrapper(args):
""" Commandline wrapper for main()
"""
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
# Get filelist
filelist_df = io.load_filelist(inloc)
inloc.close()
# Get tagkeys dataframe if provided
if args.tagkeys:
tagloc = io.validate_file_for_reading(args.tagkeys)
tags_df = io.load_tagkey(tagloc)
tagloc.close()
else:
tags_df = None
output_df = main(filelist_df,tags_df=tags_df,seq_type=args.seqtype)
io.write(output_df,outloc,fast=args.fast)
def generic_test(self,test_name,function_str,file_names,allbad=False):
"""
Standardizes tests for different dataframe loading functions.
The argument function_str must have "%s" where file_name goes.
Example:
generic_test('test_io_load_tagkey','io.load_tagkey("%s"),file_names)'
"""
print '\nIn %s...'%test_name
# Make sure there are files to test
self.assertTrue(len(file_names)>0)
# For each file, run test
for file_name in file_names:
executable = lambda: eval(function_str%file_name)
print '\t%s ='%file_name,
if not allbad and any([c in file_name for c in \
['_good','_fix','_badio','_badtype']]):
try:
df = executable()
self.assertTrue(df.shape[0]>=1)
# Write df
base_filename = file_name.split('/')[-1]
io.write(df,self.output_dir+'loaded_'+base_filename)
print 'good.'
except:
print 'bad (ERROR).'
raise
elif allbad or ('_bad' in file_name):
try:
self.assertRaises(SortSeqError,executable)
print 'bad.'
except:
print 'good (ERROR).'
raise
else:
print 'what should I expect? (ERROR)'
raise
print '\tDone.'
def test_profile_info(self):
""" Test the ability of sortseq_tools.profile_info to compute mutation rates based on total count values
"""
print '\nIn test_profile_info...'
file_names = glob.glob(self.input_dir+'dataset_*.txt')
for err in [True,False]:
for file_name in file_names:
print '\t%s, err=%s ='%(file_name,str(err)),
description = file_name.split('_')[-1].split('.')[0]
executable = lambda: \
profile_info.main(io.load_dataset(file_name),err=err)
# If good, then profile_info.main should produce a valid df
if '_good' in file_name:
try:
df = executable()
qc.validate_profile_info(df)
out_file = self.output_dir+\
'profile_info_%s_err_%s.txt'%(description,str(err))
io.write(df,out_file)
io.load_profile_info(out_file)
print 'good.'
except:
print 'bad (ERROR).'
raise
# If bad, then profile_info.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def test_profile_ct_totalcounts(self):
""" Test the ability of sortseq_tools.profile_ct to count frequencies based on total count values
"""
print '\nIn test_profile_ct_totalcounts...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable = lambda: profile_ct.main(io.load_dataset(file_name))
# If good, then profile_ct.main should produce a valid df
if '_good' in file_name:
try:
df = executable()
qc.validate_profile_ct(df)
out_file = self.output_dir+\
'profile_ct_total_%s.txt'%description
io.write(df,out_file)
io.load_profile_ct(out_file)
print 'good.'
except:
print 'bad (ERROR).'
raise
# If bad, then profile_ct.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable)
print 'badtype.'
except:
print 'good (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def test_profile_ct_seqslicing(self):
""" Test the ability of sortseq_tools.profile_ct to slice sequences properly, and to raise the correct errors
"""
print '\nIn test_profile_ct_seqslicing...'
library_files = glob.glob(self.input_dir+'library_*.txt')
library_files += glob.glob(self.input_dir+'dataset_*.txt')
for file_name in library_files:
print '\t%s ='%file_name,
description = file_name.split('_')[-1].split('.')[0]
executable_good1 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
start=2,end=10)
executable_good2 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
start=2)
executable_good3 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
end=2)
executable_nopro =\
lambda: profile_ct.main(io.load_dataset(file_name),\
start=50,end=60)
executable_bad1 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
start=-1)
executable_bad2 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
end=100)
executable_bad3 =\
lambda: profile_ct.main(io.load_dataset(file_name),\
start=20,end=10)
# If good, then sequences will be valid
if 'good' in file_name:
try:
df = executable_good1()
io.write(df,self.output_dir+\
'profile_ct_splice2-10_%s.txt'%description)
executable_good2()
executable_good3()
self.assertRaises(SortSeqError,executable_bad1)
self.assertRaises(SortSeqError,executable_bad2)
self.assertRaises(SortSeqError,executable_bad3)
if '_pro' in file_name:
self.assertRaises(SortSeqError,executable_nopro)
else:
df = executable_nopro()
print 'ok.'
except:
print 'ok (ERROR).'
raise
# If bad, then profile_ct.main should raise SortSeqError
elif '_bad' in file_name:
try:
self.assertRaises(SortSeqError,executable_good1)
self.assertRaises(SortSeqError,executable_good2)
self.assertRaises(SortSeqError,executable_good3)
self.assertRaises(SortSeqError,executable_nopro)
self.assertRaises(SortSeqError,executable_bad1)
self.assertRaises(SortSeqError,executable_bad2)
self.assertRaises(SortSeqError,executable_bad3)
print 'ok.'
except:
print 'not ok (ERROR).'
raise
# There are no other options
else:
raise SortSeqError('Unrecognized class of file_name.')
def wrapper(args):
""" Wrapper for function for scan_model.main()
"""
# Prepare input to main
model_df = io.load_model(args.model)
seqtype, modeltype = qc.get_model_type(model_df)
L = model_df.shape[0]
if modeltype=='NBR':
L += 1
chunksize = args.chunksize
if not chunksize>0:
raise SortSeqError(\
'chunksize=%d must be positive'%chunksize)
if args.numsites <= 0:
raise SortSeqError('numsites=%d must be positive.'%args.numsites)
if args.i and args.seq:
raise SortSeqError('Cannot use flags -i and -s simultaneously.')
# If sequence is provided manually
if args.seq:
pos_offset=0
contig_str = args.seq
# Add a bit on end if circular
if args.circular:
contig_str += contig_str[:L-1]
contig_list = [(contig_str,'manual',pos_offset)]
# Otherwise, read sequence from FASTA file
else:
contig_list = []
inloc = io.validate_file_for_reading(args.i) if args.i else sys.stdin
for i,record in enumerate(SeqIO.parse(inloc,'fasta')):
name = record.name if record.name else 'contig_%d'%i
# Split contig up into chunk)size bits
full_contig_str = str(record.seq)
# Add a bit on end if circular
if args.circular:
full_contig_str += full_contig_str[:L-1]
# Define chunks containing chunksize sites
start = 0
end = start+chunksize+L-1
while end < len(full_contig_str):
contig_str = full_contig_str[start:end]
contig_list.append((contig_str,name,start))
start += chunksize
end = start+chunksize+L-1
contig_str = full_contig_str[start:]
contig_list.append((contig_str,name,start))
if len(contig_list)==0:
raise SortSeqError('No input sequences to read.')
# Compute results
outloc = io.validate_file_for_writing(args.out) if args.out else sys.stdout
output_df = main(model_df,contig_list,numsites=args.numsites,\
verbose=args.verbose)
# Write df to stdout or to outfile
io.write(output_df,outloc,fast=args.fast)
