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]
local_ribo = pid_cai.iloc[local_ribo_indexes].reset_index(drop=True)
# let's also check our t.o. score
qH_all = pid_cai['CAI'].quantile(q=0.75)
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)
idx_for_prot.append(idx)
# get relative indexes of sampled cDNAs in 'cds_dat' ...
local_prot_indexes = prot_cds.index - cds_dat.index[0]
local_prot = pid_cai.iloc[local_prot_indexes].reset_index(drop=True)
# let's also check our t.o. score