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 main(filelist_df,tags_df=None,indir='./',seq_type=None):
""" Merges datasets listed in the filelist_df dataframe
"""
# Validate filelist
qc.validate_filelist(filelist_df)
# Read datasets into dictionary indexed by bin number
dataset_df_dict = {}
for item in filelist_df.iterrows():
# Autodetect fasta, fastq, or text file based on file extension
fn = indir+item[1]['file']
b = item[1]['bin']
if re.search(fasta_filename_patterns,fn):
df = io.load_dataset(fn,file_type='fasta',seq_type=seq_type)
elif re.search(fastq_filename_patterns,fn):
df = io.load_dataset(fn,file_type='fastq',seq_type=seq_type)
else:
df = io.load_dataset(fn,file_type='text',seq_type=seq_type)
dataset_df_dict[b] = df
# Merge datasets into one
out_df = merge_datasets(dataset_df_dict)
# Add seqs if given tags_df
if not tags_df is None:
qc.validate_tagkey(tags_df)
tag_col = 'tag'
# Test to make sure all tags in dataset are a subset of tags
data_tags = set(out_df[tag_col])
all_tags = set(tags_df[tag_col])
if not (data_tags <= all_tags):
sys.stderr.write('Some tags probably could not be identified.')
# Get name of seq column
seq_cols = qc.get_cols_from_df(tags_df, 'seqs')
if not len(seq_cols)==1:
raise SortSeqError('Multiple seq columns; exaclty 1 required.')
seq_col = seq_cols[0]
# Set tag to be index column of dataframe
tags_df = tags_df.set_index(tag_col)
# Add seqs corresponding to each tag
tags = out_df[tag_col]
seqs = tags_df[seq_col][tags].values
if not all([type(x)==str for x in seqs]):
raise SortSeqError('Some looked-up seqs are not strings.')
out_df[seq_col] = tags_df[seq_col][tags].values
qc.validate_dataset(out_df)
return out_df
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 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):
""" 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):
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 wrapper(args):
data_df = io.load_dataset(args.dataset)
# Take input from standard input or through the -i flag.
if args.model:
model_df = io.load_model(args.model)
else:
model_df = io.load_model(sys.stdin)
MI,Std = main(
data_df,model_df,start=args.start,
end=args.end,err=args.err)
output_df = pd.DataFrame([MI],columns=['info'])
if args.err:
output_df = pd.concat([output_df,pd.Series(Std,name='info_err')],axis=1)
if args.out:
outloc = open(args.out,'w')
else:
outloc = sys.stdout
pd.set_option('max_colwidth',int(1e8))
output_df.to_string(
outloc, index=False,col_space=10,float_format=utils.format_string)
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.')
import sortseq_tools.io as io
import sortseq_tools.qc as qc
import re
import pdb
from sortseq_tools import SortSeqError
# Filetypes and corrsponding load functions
filetype_to_loadfunc_dict = {
'filelist' : io.load_filelist,
'profile_info' : io.load_profile_info,
'profile_mut' : io.load_profile_mut,
'profile_ct' : io.load_profile_ct,
'profile_freq' : io.load_profile_freq,
'dataset' : io.load_dataset,
'dataset_fasta_dna' : \
lambda f: io.load_dataset(f,file_type='fasta',seq_type='dna'),
'dataset_fasta_rna' : \
lambda f: io.load_dataset(f,file_type='fasta',seq_type='rna'),
'dataset_fasta_protein' : \
lambda f: io.load_dataset(f,file_type='fasta',seq_type='protein'),
'dataset_fastq' : \
lambda f: io.load_dataset(f,file_type='fastq'),
'model' : io.load_model,
'tagkey' : io.load_tagkey,
'meanstd' : io.load_meanstd,
'sitelist' : io.load_sitelist
}
filetypes = filetype_to_loadfunc_dict.keys()
# Define commandline wrapper
def wrapper(args):
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.')
import pandas as pd
import sortseq_tools.qc as qc
import sortseq_tools.io as io
import os
import sortseq_tools.profile_ct as profile_ct
import pdb
from sortseq_tools import SortSeqError
import cProfile
import sortseq_tools.profile_info as profile_info
import sortseq_tools.learn_model as learn_model
import sortseq_tools.predictiveinfo as predictiveinfo
import pstats
#load in data sets for the test, we will just use the sort-seq crp-wt set
df = io.load_dataset('input/mpra.txt')
model_df = io.load_model('input/mpra_model')
#Profile profile_info
#stats_fn = 'Profile_profile_info'
#stats_fn_hr = 'Profile_profile_info_hr'
#Profile.run('''profile_info.main(df,method='nsb')''',stats_fn)
#Reformat and print to human readable profile
#p = pstats.Stats(stats_fn,stream=open(stats_fn_hr,'w'))
#p.strip_dirs()
#p.sort_stats('cumtime')
#p.print_stats()
df_copy = df.copy()
#profile learn_model lm=LS
import pandas as pd
import sortseq_tools.qc as qc
import sortseq_tools.io as io
import os
import sortseq_tools.profile_ct as profile_ct
import pdb
from sortseq_tools import SortSeqError
import cProfile
import sortseq_tools.profile_info as profile_info
import sortseq_tools.learn_model as learn_model
import sortseq_tools.predictiveinfo as predictiveinfo
import pstats
#load in data sets for the test, we will just use the sort-seq crp-wt set
df = io.load_dataset('input/dms_1_formatted')
model_df = io.load_model('input/dms_1_model')
#Profile profile_info
#stats_fn = 'Profile_profile_info'
#stats_fn_hr = 'Profile_profile_info_hr'
#Profile.run('''profile_info.main(df,method='nsb')''',stats_fn)
#Reformat and print to human readable profile
#p = pstats.Stats(stats_fn,stream=open(stats_fn_hr,'w'))
#p.strip_dirs()
#p.sort_stats('cumtime')
#p.print_stats()
df_copy = df.copy()
#profile learn_model lm=LS
import pandas as pd
import sortseq_tools.qc as qc
import sortseq_tools.io as io
import os
import sortseq_tools.profile_ct as profile_ct
import pdb
from sortseq_tools import SortSeqError
import cProfile
import sortseq_tools.profile_info as profile_info
import sortseq_tools.learn_model as learn_model
import sortseq_tools.predictiveinfo as predictiveinfo
import pstats
#load in data sets for the test, we will just use the sort-seq crp-wt set
df = io.load_dataset('input/rnap-wt-format.txt')
model_df = io.load_model('input/rnap_model')
#Profile profile_info
#stats_fn = 'Profile_profile_info'
#stats_fn_hr = 'Profile_profile_info_hr'
#Profile.run('''profile_info.main(df,method='nsb')''',stats_fn)
#Reformat and print to human readable profile
#p = pstats.Stats(stats_fn,stream=open(stats_fn_hr,'w'))
#p.strip_dirs()
#p.sort_stats('cumtime')
#p.print_stats()
df_copy = df.copy()
#profile learn_model lm=LS