def df_list0(self, col_name, sep1=None, sep2=None):
outlist = []
inlist = list(self.df[col_name])
if sep1 is None:
outlist = list(set(inlist))
else:
out_dict = {}
if sep2 is None: #sep1 only
for ele1 in inlist:
ele1_list = ele1.split(sep1)
for item in ele1_list:
out_dict[item] = 0
else:#sep1 and spe2 both
print('sep12')
for ele1 in inlist:
ele1 = str(ele1)
ele1_list = ele1.split(sep1)
for ele2 in ele1_list:
item = ele2.split(sep2)[0]
out_dict[item] = 0
#print len(out_dict.keys())
#unique items
#print(out_dict)
outlist = myList.basic(out_dict.keys()).sort_list()
return outlist
def permute_taxon_blast(self, hits_num):
print('permutation of viral blast:{}\t{}'.format(self.par['type'], hits_num))
#
counts_df = pd.DataFrame()
outfile = '{}{}.txt'.format(myIO.dir_os(self.par['dir_out']).create_dir(), hits_num)
if os.path.isfile(outfile):
print('Read file: ', outfile)
counts_df = pd.read_csv(outfile, header=0, index_col=0, sep="\t", low_memory=False)
else:
#1: permutated peptides
pep_names = list(self.par['binary_aln_df'].index)
pep_df = myList.basic(pep_names).permute_list(self.par['permutation_times'], hits_num)
#2: permutation based on the non-overlapped hits num
for col, perm_pep in pep_df.items():
perm_zb = self.par['binary_aln_df'].ix[perm_pep]
p_collapse_zb, p_sim_tag = myDataframe.basic(perm_zb).unispecie(self.par['sim_threshold'])
counts_df[col] = p_collapse_zb.apply(sum,axis=0) + p_sim_tag
#print list(perm_tmp[col])
#export
counts_df.to_csv(outfile, sep='\t', header=True, index_label=self.par['type'])
#combine permuated counts
#print counts_df.shape
perm_mean = counts_df.apply(lambda x: np.mean(np.floor(x)), axis=1).round()
#print perm_mean
return perm_mean
def df_list(self, col_name, sep1=None, sep2=None):
outlist = []
out_dict = {}
try:
inlist = list(self.df[col_name])
except:
print('No column name in the data frame:', col_name)
else:
if sep1 is None:
outlist = list(set(inlist))
else:
#out_dict={}
if sep2 is None: #sep1 only
for ele1 in inlist:
ele1 = str(ele1)# avoid null list export
ele1_list = ele1.split(sep1)
for item in ele1_list:
out_dict[item] = 0
else:#sep1 and spe2 both
out_dict = {}
for ele1 in inlist:
ele1 = str(ele1) # avoid null list export
ele1_list = ele1.split(sep1)
for ele2 in ele1_list:
item = ele2.split(sep2)[0]
out_dict[item] = 0
#unique items
outlist = myList.basic(out_dict.keys()).sort_list()
finally:
#print outlist
pass
return outlist
def combine_fa(self, fa_dict):
chrs = myList.basic(fa_dict.keys()).sort_list()
out_obj = open(self.biofile, 'wt')
for chr_name in chrs:
fa_file = fa_dict[chr_name]
seq = genome(fa_file).read_fa_first()
out_obj.write('>{}\n{}\n'.format(chr_name, seq))
print('\t{}:{}'.format(chr_name, fa_file))
out_obj.close()
print('Combine fa files into ', self.biofile)
def hits_func(x, peps, threshold, pro_id):
#signficant hits
hits = x[x >= threshold]
#non_overlapping peptides
peps = [str(x) for x in peps]
hit_peps = [str(x) for x in hits.index]
none_overlapped_hits_num = myList.basic(peps).un_neighbours(
hit_peps, return_type='hits_num')
#if none_overlapped_hits_num>1: print "%d,%d" %(len(list(hits.index)), none_overlapped_hits_num)
#if len(hit_peps)>0: print pro_id, peps, hit_peps
#if pro_id == 'Q9YLJ1': print pro_id, peps, hit_peps
return len(list(
hits.index)), none_overlapped_hits_num, ','.join(hit_peps)
def __init__(self, par):
#data frame
if 'df' in par.keys():
self.data = par['df']
self.nrow = self.data.shape[0]
self.ncol = self.data.shape[1]
self.colnames = self.data.columns
self.xlabel = par['xlabel'] if 'xlabel' in par.keys() else list(
self.data)[0]
self.ylabel = par['ylabel'] if 'ylabel' in par.keys() else list(
self.data)[1]
self.xlim = par['xlim'] if 'xlim' in par.keys() else myList.basic(
self.data.ix[:, 0]).min_max()
self.ylim = par['ylim'] if 'ylim' in par.keys() else myList.basic(
self.data.ix[:, 1]).min_max()
#initiate plot window
plt.clf()
elif 'list' in par.keys():
self.data = par['list']
self.xlabel = par['xlabel'] if 'xlabel' in par.keys() else 'x'
self.ylabel = par['ylabel'] if 'ylabel' in par.keys() else 'y'
self.xlim = par['xlim'] if 'xlim' in par.keys() else None
self.ylim = par['ylim'] if 'ylim' in par.keys() else None
else:
self.data = None
print('Error:No data frame input as long as drawing a plot!')
#file
self.picfile = par['picfile'] if 'picfile' in par.keys() else None
#colors
self.col = 'bgrcmykw'
#line styles:solid, dashed, dotted, dashdot
self.title = par['title'] if 'title' in par.keys() else 'Plot'
self.text = par['text'] if 'text' in par.keys() else None
self.legend = par['legend'] if 'legend' in par.keys() else False
self.pch = par['pch'] if 'pch' in par.keys() else 'o'
self.lty = par['lty'] if 'lty' in par.keys() else 'solid'
self.lwd = par['lwd'] if 'lwd' in par.keys() else 1
def taxon_blast2(self, file_aln, zscore_file):
taxon_type = myIO.file_os(file_aln).name_prefix()
print("\n{}:{}\n".format(taxon_type, zscore_file))
#read zscore_df
zdf = myDataframe.basic().standard_df(zscore_file)
#match order of align score and zscore,replace na
#read alignment file for specie alignment
binary_b = myDataframe.basic().aln_df(file_aln,
self.par['align_score'])
#binary_b = myDataframe.basic(binary_b).filter_aln()
binary_b = binary_b.reindex(zdf.index).fillna(0)
#print binary_b
#sample names in columns, and specie in rows
sum_df = pd.DataFrame(0, index=list(binary_b), columns=list(zdf))
pep_df = pd.DataFrame(np.nan, index=list(binary_b), columns=list(zdf))
p_df = pd.DataFrame(index=list(binary_b), columns=list(zdf))
#perm_df=pep_df.copy()
#print binary_z.apply(sum, axis=0)
#n=0
for sample_name, column in zdf.iteritems():
#n += 1
#1: select peptides
#column=zscore_df.ix[:,20]
#first remove all nont-hits
hits = column[
column >= self.par['specieZ_threshold']].copy() #all hits
hits.sort_values(axis=0, ascending=False, inplace=True)
#print hits
#remove overlapped hits
nonoverlap_hits = myList.basic(hits).gen_ind_hits(
self.par['dependent_pep'])
input_num = len(nonoverlap_hits)
print("{}:\thits={}, nonoverlapped={}".format(
sample_name, len(hits), input_num))
#2: remove overlap hits between species
if input_num > 0:
zb_df = binary_b.loc[nonoverlap_hits.index]
#print list(binary_b.apply(lambda x: sum(x), axis=0))
#loop
collapse_zb, sim_tag, p_series = myDataframe.basic(
zb_df).binom_unispecie(self.par['dir_ref_seq'], input_num,
self.par['p_threshold'],
self.par['x_threshold'])
#counts of hits
sum_df[sample_name] = collapse_zb.apply(sum, axis=0) + sim_tag
#all peptide_id list
pep_df[sample_name] = collapse_zb.apply(
lambda x: myList.basic(x).names_string(0.001), axis=0)
p_df[sample_name] = p_series
#padjust_df[sample_name]=p_adjust_series
#if n==5: break
#n+=1
#export to file
file_head = myIO.file_os(
zscore_file).file_prefix() + '_' + taxon_type + '_'
#file_head='random_min_HI_HC_'+taxon_type+'_'
sum_df.to_csv(file_head + 'counting.txt',
sep='\t',
header=True,
index_label='Specie')
pep_df.to_csv(file_head + 'peptides.txt',
sep='\t',
header=True,
index_label='Specie')
p_df.to_csv(file_head + 'p-values.txt',
sep='\t',
header=True,
index_label='Specie')
#Adjusted p-values using B-H
'''
stats = importr('stats')
for i in p_df:
pvalue_list = p_df[i].values
p_adjust = list(stats.p_adjust(FloatVector(pvalue_list), method = 'BH'))
padjust_df[i] = p_adjust
padjust_df.to_csv(file_head+'p-adjusted.txt', sep='\t', header=True, index_label='Specie')
'''
padjust_df = pd.DataFrame(index=list(binary_b), columns=list(zdf))
for i in p_df.columns:
pvals = np.array(p_df[i].values)
if not np.isnan(pvals).all():
mask = [j for j in np.where(np.isfinite(pvals))[0]]
pval_corrected = np.empty(pvals.shape)
pval_corrected.fill(np.nan)
pval_corrected[mask] = multipletests(pvals[mask],
method='fdr_bh')[1]
padjust_df[i] = pval_corrected
padjust_df.to_csv(file_head + 'padjusted.txt',
sep='\t',
header=True,
index_label='Specie')
#perm_df.to_csv(file_head+'permutation.txt', sep='\t', header=True, index_label='Specie')
#end
def taxon_blast(self, file_aln, zscore_file):
print(
'###Signficant taxon by removing overlapped hits based on blast alignment.'
)
taxon_type = myIO.file_os(file_aln).name_prefix()
print('{}: {}'.format(taxon_type, zscore_file))
#read zscore_df
zdf = myDataframe.basic().standard_df(zscore_file)
#match order of align score and zscore,replace na
#read alignment file for specie alignment
binary_b = myDataframe.basic().aln_df(file_aln,
self.par['align_score'])
binary_b = binary_b.reindex(zdf.index).fillna(0)
#print binary_b
#sample names in columns, and specie in rows
sum_df = pd.DataFrame(0, index=list(binary_b), columns=list(zdf))
pep_df = pd.DataFrame(np.nan, index=list(binary_b), columns=list(zdf))
#perm_df = pep_df.copy()
#print binary_z.apply(sum, axis = 0)
#n = 1
for sample_name, column in zdf.items():
#1: select peptides
#column = zscore_df.ix[:,20]
#first remove all nont-hits
hits = column[
column >= self.par['specieZ_threshold']].copy() #all hits
hits.sort_values(axis=0, ascending=False, inplace=True)
#print hits
#remove overlapped hits
nonoverlap_hits, overlap_debug = myList.basic(hits).remove_overlap(
self.par['dependent_pep'])
input_num = len(nonoverlap_hits)
print('{}: hits={}, nonoverlapped={}'.format(
sample_name, len(hits), input_num))
#2: remove overlap hits between species
if input_num > 0:
###2-1: export peptides
try:
outfile = '{}{}/{}.csv'.format(self.par['dir_result'],
sample_name, taxon_type)
overlap_debug.to_csv(outfile,
header=True,
index_label='peptides')
except FileNotFoundError:
myIO.file_os(self.par['file_err'], "\t").line_replace(
{'taxon_blast': sample_name})
###2-2: specie-specific hits based on non-overlapped hits
#sample zscore-alignscore matrix times by zscore
#print(nonoverlap_hits.index)
zb_df = binary_b.ix[nonoverlap_hits.index]
#print(list(binary_b.apply(lambda x: sum(x), axis = 0)))
#loop
collapse_zb, sim_tag = myDataframe.basic(zb_df).unispecie(
self.par['sim_threshold'])
#counts of hits
sum_df[sample_name] = collapse_zb.apply(sum, axis=0) + sim_tag
#print(list(sum_df[sample_name]))
#high_sum = sum_df[sample_name]
#print(high_sum[high_sum>0])
#all peptide_id list
pep_df[sample_name] = collapse_zb.apply(
lambda x: myList.basic(x).names_string(0.001), axis=0)
#2-3:permutation
#perm_df[sample_name] = self.specie_alignment_permutation(input_num)
#if n == 10: break
#n+ = 1
#export to file
file_head = '{}_{}_'.format(
myIO.file_os(zscore_file).file_prefix(), taxon_type)
sum_df.to_csv(file_head + 'counting.txt',
sep='\t',
header=True,
index_label='Specie')
pep_df.to_csv(file_head + 'peptides.txt',
sep='\t',
header=True,
index_label='Specie')
def count_reads(self):
#key is ref name, value is reads string sep by comma, the first is ref seq
unique_seq = dict((a, []) for a in self.par['ref_dict'].keys())
#unique and multiple counts in dict
unique = {} #key is ref name, value is counts
multiple = {} # key is query name, value is the list of refs
num = {}# counts statistics
saturation = {0:{1:0, 5:0, 10:0, 'max':0 }} # count number for saturation analysis
last_index = 0
print('\tread sam file: {}.gz'.format(self.par['sample_sam_file']))
IN = gzip.open(self.par['sample_sam_file']+'.gz', 'rt')
UN = gzip.open(self.par['sample_dir']+self.par['sample_name']+'_unknown.fa.gz', 'wt')
maxRC = 0
for line in IN:
#print(line)
#counts
num['raw_reads_num'] = num.setdefault('raw_reads_num',0)+1
#analyze sam line
info = self.analyze_SAM(line)
qname, ref= info['qname'], info['ref']
#unique alignment
if info['aligned'] == '1':
unique[ref] = unique.setdefault(ref,0) + 1
if unique[ref] > maxRC: maxRC = unique[ref]
#counting of saturation
if unique[ref] in [1,5,10]:
last_counts = saturation[last_index].copy()# copy() is essential!!!!!
last_counts[unique[ref]] += 1
last_counts['max'] = maxRC#the maximum RC at the time of raw reads we get
saturation[num['raw_reads_num']] = last_counts
#print num['raw_reads_num'], last_index, saturation[num['raw_reads_num']]
last_index = num['raw_reads_num']
#export aligned sequences of reads
unique_seq[ref].append(info['seq'])
num['unique_aligned_reads_num'] = num.setdefault('unique_aligned_reads_num',0)+1
#multiple alignment
elif info['aligned'] == '3':
multiple[qname] = multiple[qname] + [ref] if qname in multiple else [ref]
num['multialigned_reads_num'] = num.setdefault('multialigned_reads_num',0)+1
#unalignment
else:
UN.write('>'+qname+'\n'+info['seq']+'\n')
num['unaligned_reads_num'] = num.setdefault('unaligned_reads_num',0) + 1
IN.close()
UN.close()
#counting of saturation
if num['raw_reads_num'] > last_index:
saturation[num['raw_reads_num']] = saturation[last_index].copy()
#for key in sorted(saturation.keys()):
# print key, saturation[key]
#upate num statistics
myIO.file_os(self.par['sample_log'], '=').line_add(num)
print('\tcombine RCs from unique and multiple alignments of ', self.par['sample_name'])
#reversed multiple
#print multiple
rev_multiple = myDict.basic(multiple).counting_reversed_dict()
#print unique
RC_dict = self.multiple_counts(unique, rev_multiple)
#export
print('\tSave read counts into ', self.par['sample_RC_file'])
myDict.basic(RC_dict).dict2_to_file(self.par['sample_RC_file'], pattern='\t')
myDict.basic(saturation).dict2_to_file(self.par['sample_saturation_file'], pattern='\t')
#
seq_counts = {}
for ref, reads_list in unique_seq.items():
key=ref+'\t'+self.par['ref_dict'][ref]+'\t'+str(len(reads_list))
if len(reads_list)>0:
freq_dict = myList.basic(reads_list).elements_frequency0()
seq_counts[key] = ';'.join(str(a)+':'+str(b) for a,b in freq_dict.items())
else:
seq_counts[key] = 'NA'
myDict.basic(seq_counts).dict_to_file(self.par['sample_dir']+'unique_aligned_reads.txt', pattern='\t')
def __init__(self, dictionary=None, dict_keys=None):
self.dict = dictionary
if isinstance(self.dict, dict):
self.dict_keys = myList.basic(self.dict.keys()).sort_list(
) if dict_keys is None else dict_keys
self.out_dict = {}
def __init__(self, dictionary=None):
self.dict = dictionary
if isinstance(self.dict, dict):
self.sorted_keys = myList.basic(self.dict.keys()).sort_list()
self.out_dict = {}
def QC_saturation(self):
print("###saturation analysis\n")
combined_df = {}
combined_dynamics = {}
#plot suaturation curve per sample
#n=1
for sample_name in self.par['sample_names']:
file_head = '{}{}/'.format(self.par['dir_result'], sample_name)
#read saturation file
df = pd.read_table(file_head + 'QC_saturation.txt',
sep="\t",
index_col=False)
#print list(df)
#print list(df.index)
#saturation curves
saturation_df = df[['row_name', '1', '5', '10']]
#shrink dict
shrinked_index = myList.basic(list(
saturation_df.index)).interval_list()
#print shrinked_index
sample_df = saturation_df.ix[shrinked_index] #select rows
#sample_df=sample_df.transpose().astype(float)
sample_df.ix[:, 0] = sample_df.ix[:, 0] / 1e6
#print sample_df
#scatter plot
plot_par = {
'df': sample_df,
'legend': 'upper left',
'title': 'Saturation analysis (Sequencing depth)',
'picfile': file_head + 'QC_saturation_analysis.png',
'xlabel': 'Number of raw reads (million)',
'ylabel': 'Number of references'
}
myPlot.plot(plot_par).lineP()
#combine data frame
sample_df.index = range(sample_df.shape[0])
for cutoff in ['1', '5', '10']:
sub_df = sample_df[['row_name', cutoff]].copy()
sub_df.columns = ['raw_reads:' + sample_name, sample_name]
if cutoff in combined_df:
combined_df[cutoff] = pd.merge(combined_df[cutoff],
sub_df,
left_index=True,
right_index=True,
how='outer')
else:
combined_df[cutoff] = sub_df.copy()
#dynamics analysis
dynamics_df = df[['row_name', 'max']] #select df
#shrink dict
shrinked_index = myList.basic(list(
dynamics_df.index)).interval_list()
sample_df = dynamics_df.ix[shrinked_index] #select rows
sample_df.ix[:, 0] = sample_df.ix[:, 0] / 1e6 #divided by millions
sample_df.reset_index(drop=True, inplace=True)
#combined
combined_dynamics[sample_name] = sample_df
#plot
plot_par = {
'df': sample_df,
'legend': 'upper left',
'title': 'Saturation analysis:dynamics of read conts',
'picfile': file_head + 'QC_read_counts_dynamics.png',
'xlabel': 'Number of raw reads (million)',
'ylabel': 'Maximum read counts'
}
myPlot.plot(plot_par).lineP()
#export saturated curves
for cutoff in ['1', '5', '10']:
plot_par = {
'df':
combined_df[cutoff],
'legend':
None,
'title':
'samples={}, RC-cutoff={}'.format(
len(self.par['sample_names']), cutoff),
'picfile':
'{}saturation_cuttoff_{}.png'.format(self.par['dir_QC'],
cutoff),
'xlabel':
'Number of raw reads (million)',
'ylabel':
'Number of references'
}
myPlot.plot(plot_par).lineP(x_value=1)
#export dynamics curves
combined_dynamics = pd.concat(combined_dynamics, axis=1)
combined_dynamics.columns = [
':'.join(x) for x in list(combined_dynamics)
]
#print combined_dynamics.shape
#print combined_dynamics
plot_par = {
'df':
combined_dynamics,
'legend':
None,
'title':
'Sequencing depth,sample={}'.format(len(self.par['sample_names'])),
'picfile':
'{}saturation_dynamics.png'.format(self.par['dir_QC']),
'xlabel':
'Number of raw reads (million)',
'ylabel':
'Maximum read counts'
}
myPlot.plot(plot_par).lineP(x_value=1)
