def do_work(idx):
# IMPORTANT!!!
np.random.seed()
#
cds_dat = orgs.get_group(idx)
#
genetic_table = cds_dat['table'].iloc[0]
genetic_code = Data.CodonTable.unambiguous_dna_by_id[genetic_table]
SynonymousCodons = dict([(aa,[]) for aa in genetic_code.protein_alphabet.letters])
# SynonymousCodons['STOP'] = genetic_code.stop_codons # STOP codons are excluded from analysis ...
for codon,aa in genetic_code.forward_table.iteritems():
SynonymousCodons[aa].append(codon)
#
#
# prot_cds_rnd = cds_dat['cDNA'].sample(PROT_COUNT) # cDNA sample proteins ...
prot_cds_rnd = cds_dat['cDNA'] # let's use ALL cDNA to get the codon bias ...
codon_usage = cairi.count_codons(prot_cds_rnd)
#
# generate codon weights based on codon counts ...
codon_weights = {}
for aa in SynonymousCodons:
aa_codon_usage = [ codon_usage[codon] for codon in SynonymousCodons[aa] ]
total_codons = sum(aa_codon_usage)
# normalize ...
codon_weights[aa] = np.true_divide(aa_codon_usage,float(total_codons))
#
# now rewrite (back translate) protein sequences keeping their index ...
cdna_shuffled = ( (ix,pid,back_translate(protein,SynonymousCodons,codon_weights)) for ix,pid,protein in cds_dat[['pid','protein']].itertuples() )
cdna_shuffled = pd.DataFrame(cdna_shuffled,columns=['ix','pid','cDNA_rnd'])
cdna_shuffled = cdna_shuffled.set_index(keys='ix')
#
#
# shuffled_cdna_list.append( cdna_shuffled )
return cdna_shuffled
def do_work(idx):
# IMPORTANT!!!
np.random.seed()
#
cds_dat = orgs.get_group(idx)
#
genetic_table = cds_dat['table'].iloc[0]
genetic_code = Data.CodonTable.unambiguous_dna_by_id[genetic_table]
SynonymousCodons = dict([
(aa, []) for aa in genetic_code.protein_alphabet.letters
])
# SynonymousCodons['STOP'] = genetic_code.stop_codons # STOP codons are excluded from analysis ...
for codon, aa in genetic_code.forward_table.iteritems():
SynonymousCodons[aa].append(codon)
#
#
# prot_cds_rnd = cds_dat['cDNA'].sample(PROT_COUNT) # cDNA sample proteins ...
prot_cds_rnd = cds_dat[
'cDNA'] # let's use ALL cDNA to get the codon bias ...
codon_usage = cairi.count_codons(prot_cds_rnd)
#
# generate codon weights based on codon counts ...
codon_weights = {}
for aa in SynonymousCodons:
aa_codon_usage = [
codon_usage[codon] for codon in SynonymousCodons[aa]
]
total_codons = sum(aa_codon_usage)
# normalize ...
codon_weights[aa] = np.true_divide(aa_codon_usage,
float(total_codons))
#
# now rewrite (back translate) protein sequences keeping their index ...
cdna_shuffled = (
(ix, pid, back_translate(protein, SynonymousCodons, codon_weights))
for ix, pid, protein in cds_dat[['pid', 'protein']].itertuples())
cdna_shuffled = pd.DataFrame(cdna_shuffled,
columns=['ix', 'pid', 'cDNA_rnd'])
cdna_shuffled = cdna_shuffled.set_index(keys='ix')
#
#
# shuffled_cdna_list.append( cdna_shuffled )
return cdna_shuffled
ribo_counts = [(idx, orgs.get_group(idx)["ribosomal"].nonzero()[0].size) for idx in genom_id]
ribo_cai_info = pd.DataFrame(ribo_counts, columns=["GenomicID", "ribo_count"])
#############
#
#
cix_prot = {}
cix_ribo = {}
#
#
#############
for idx, ribo_count in ribo_cai_info.itertuples(index=False):
#
cds_dat = orgs.get_group(idx)
prot_cds_rnd = cds_dat["cDNA"].sample(PROT_COUNT) # cDNA sample proteins ...
codon_usage_rnd = cairi.count_codons(prot_cds_rnd)
codon_index_rnd = cairi.generate_codon_index(
codon_usage_rnd, genetic_table=list(cds_dat["table"])[0]
) # fix that ...
cix_prot[idx] = codon_index_rnd
#
if ribo_count >= RIBO_LIMIT:
pass
ribo_cds = cds_dat[cds_dat["ribosomal"]]["cDNA"] # cDNA of ribosomal proteins ...
codon_usage = cairi.count_codons(ribo_cds)
codon_index = cairi.generate_codon_index(codon_usage, genetic_table=list(cds_dat["table"])[0]) # fix that ...
cix_ribo[idx] = codon_index
######################
ribo_cai_info = pd.DataFrame(ribo_counts,columns=['assembly_accession','ribo_count'])
# some lists to describe organism's CAI distribution features ...
percentile = []
median = []
mean = []
sigma = []
idx_for_ribo = []
ribo_count_for_df = []
#
pid_cai_list = []
for idx,ribo_count in ribo_cai_info.itertuples(index=False):
if ribo_count >= RIBO_LIMIT:
cds_dat = orgs.get_group(idx)
ribo_cds = cds_dat[cds_dat['ribosomal']]['cDNA'] # cDNA of ribosomal proteins ...
codon_usage = cairi.count_codons(ribo_cds)
codon_index = cairi.generate_codon_index(codon_usage,genetic_table=list(cds_dat['table'])[0]) # fix that ...
# we need to track index from 'dat', as there are some stupid duplications ...
pid_cai = pd.DataFrame(((dat_idx,pid,cairi.cai_for_gene(sequence,codon_index)) for dat_idx,pid,sequence in cds_dat[['pid','cDNA']].itertuples()),columns=['dat_idx','pid','CAI'])
pid_cai = pid_cai.set_index(keys='dat_idx')
# characterize CAI distribution for a given organism ...
local_mean = pid_cai['CAI'].mean()
local_median = pid_cai['CAI'].median()
local_sigma = pid_cai['CAI'].std()
mean.append(local_mean)
median.append(local_median)
sigma.append(local_sigma)
idx_for_ribo.append(idx)
ribo_count_for_df.append(ribo_count)
#
local_ribo_indexes = cds_dat['ribosomal'].nonzero()[0]
genom_id = orgs.groups.keys()
# some lists to describe organism's CAI distribution features ...
percentile = []
median = []
mean = []
sigma = []
idx_for_prot = []
#
pid_cai_list = []
for idx in genom_id:
cds_dat = orgs.get_group(idx)
# instead of taking specific group of proteins, let's take RANDOM sample of 50 cDNA ...
prot_cds = cds_dat['cDNA'].sample(PROT_COUNT) # cDNA sample proteins ...
codon_usage = cairi.count_codons(prot_cds)
codon_index = cairi.generate_codon_index(
codon_usage, genetic_table=list(cds_dat['table'])[0]) # fix that ...
# we need to track index from 'dat', as there are some stupid duplications ...
pid_cai = pd.DataFrame(
((dat_idx, pid, cairi.cai_for_gene(sequence, codon_index))
for dat_idx, pid, sequence in cds_dat[['pid', 'cDNA']].itertuples()),
columns=['dat_idx', 'pid', 'CAI'])
pid_cai = pid_cai.set_index(keys='dat_idx')
# characterize CAI distribution for a given organism ...
local_mean = pid_cai['CAI'].mean()
local_median = pid_cai['CAI'].median()
local_sigma = pid_cai['CAI'].std()
mean.append(local_mean)
median.append(local_median)
sigma.append(local_sigma)
mean = []
sigma = []
idx_for_prot = []
#
pid_cai_list = []
for idx in genom_id:
# cds_dat = orgs.get_group(idx) # old stuff ...
org_cai = cai.get_group(idx)
condition = org_cai['CAI'].notnull().all()
if not condition:
print "skipping", idx, " as it has no CAI ..."
else:
q30 = org_cai['CAI'].quantile(q=0.30)
# take 50 random proteins from the bottom 30% OF ORIGINAL CAI ...
prot_cds = org_cai[org_cai.CAI<q30]['cDNA'].sample(PROT_COUNT)
codon_usage = cairi.count_codons(prot_cds)
codon_index = cairi.generate_codon_index(codon_usage,genetic_table=list(org_cai['table'])[0]) # fix that ...
# we need to track index from 'dat', as there are some stupid duplications ...
pid_cai = pd.DataFrame(((dat_idx,pid,cairi.cai_for_gene(sequence,codon_index)) for dat_idx,pid,sequence in org_cai[['pid','cDNA']].itertuples()),columns=['dat_idx','pid','CAI'])
pid_cai = pid_cai.set_index(keys='dat_idx')
# characterize CAI distribution for a given organism ...
local_mean = pid_cai['CAI'].mean()
local_median = pid_cai['CAI'].median()
local_sigma = pid_cai['CAI'].std()
mean.append(local_mean)
median.append(local_median)
sigma.append(local_sigma)
idx_for_prot.append(idx)
#
# get relative indexes of sampled cDNAs in 'org_cai' ...
local_prot_indexes = prot_cds.index - org_cai.index[0]
ribo_cai_info = pd.DataFrame(ribo_counts, columns=['GenomicID', 'ribo_count'])
#############
#
#
cix_prot = {}
cix_ribo = {}
#
#
#############
for idx, ribo_count in ribo_cai_info.itertuples(index=False):
#
cds_dat = orgs.get_group(idx)
prot_cds_rnd = cds_dat['cDNA'].sample(
PROT_COUNT) # cDNA sample proteins ...
codon_usage_rnd = cairi.count_codons(prot_cds_rnd)
codon_index_rnd = cairi.generate_codon_index(
codon_usage_rnd,
genetic_table=list(cds_dat['table'])[0]) # fix that ...
cix_prot[idx] = codon_index_rnd
#
if ribo_count >= RIBO_LIMIT:
pass
ribo_cds = cds_dat[cds_dat['ribosomal']][
'cDNA'] # cDNA of ribosomal proteins ...
codon_usage = cairi.count_codons(ribo_cds)
codon_index = cairi.generate_codon_index(
codon_usage,
genetic_table=list(cds_dat['table'])[0]) # fix that ...
cix_ribo[idx] = codon_index