muted_dir = main_dir + 'mutation_counter/data/mutation_count/'
sims_dir = main_dir + 'mutation_counter/data/sims_dem/'
diffs = False
mutlog = 'toMut.log'
min_size = 70
sampling = [5, 100, 10]
bases = 'ATCG'
ksize = 3
sample_sim = 0
data, data_freqs = MC_sample_matrix_v1(min_size=min_size,
samp=sampling,
count_dir=count_dir,
dir_launch=dir_launch,
main_dir=main_dir,
sim_dir=sims_dir,
muted_dir=muted_dir,
diffs=diffs,
sample_sim=sample_sim,
exclude=False)
def md_reference_comp(data,
p_value=1e-5,
test_m='fisher',
individually=False,
Nbins=10,
exclude=False,
frequency_range=[0, 1],
data_freqs={},
extract='pval',
mutlog = 'toMut.log'
min_size = 40
sampling = [5, 100, 5]
bases = 'ATCG'
ksize = 3
sample_sim = 0
freq_extract = True
stepup = ''
data, data_freqs = MC_sample_matrix_v1(min_size=min_size,
samp=sampling,
stepup=stepup,
count_dir=count_dir,
dir_launch=dir_launch,
main_dir=main_dir,
sim_dir=sims_dir,
indfile=indfile,
muted_dir=muted_dir,
diffs=diffs,
sample_sim=sample_sim,
freq_extract=freq_extract,
exclude=False)
###
def run_stats(ref_sim, ref_pair, data, data_freqs={}):
'''
co-factor function to md counter comparisons, deploy heatmap and calculate kmer proportion differences
between pairs of population.
- ref pair: list of tuples. can't be dictionary because of repeated pops / reference tags.
os.makedirs(fig_dir, exist_ok=True)
fig_dir= fig_dir + '/'
mutlog= 'toMut.log'
min_size= 70
sampling= [5,100,10]
bases= 'ACGT'
ksize= 3
collapsed= False
row= 48
col= 4
sample_sim= 150
data, data_freqs = MC_sample_matrix_v1(min_size= min_size, samp= sampling, count_dir= count_dir,
dir_launch= dir_launch,main_dir= main_dir,sim_dir= sims_dir,
muted_dir= muted_dir, diffs= diffs, row= row,bases= bases,
exclude= False,sample_sim= sample_sim,collapsed= collapsed)
print("data extracted: data= {} elements".format(len(data)))
from tools.fasta_utilities import (
get_mutations, get_by_path, kmer_comp_index, kmer_mut_index,
fasta_get_freq,kmer_dict_init
)
def fasta_get_freq(seq,start= 0,end= 0,step= 1,ksize=3,bases= 'ATCG'):
'''return count of kmer across fasta region'''
kmer_dict= kmer_dict_init(ksize= ksize,bases=bases)
## directories
main_dir= os.getcwd() + '/'
count_dir= main_dir + 'mutation_counter/count/'
dir_launch= main_dir + 'mutation_counter'
muted_dir= main_dir + 'mutation_counter/data/mutation_count/'
sims_dir= main_dir + 'data/'
indfile= 'integrated_call_samples.20101123.ALL.panel_regions.txt'
diffs= True
mutlog= 'toMut.log'
min_size= 40
sampling= [5,100,5]
data = MC_sample_matrix_v1(min_size= min_size, samp= sampling, count_dir= count_dir,
dir_launch= dir_launch,main_dir= main_dir,sim_dir= sims_dir,
muted_dir= muted_dir, diffs= diffs, indfile= indfile,
exclude= False)
print(len(data))
### new - pair reference sims and subsetted populations.
### extract kmer comparisons (proportions or pvals) using heatmap_v2.
### make function.
from tools.mcounter_tools import mcounter_deploy
p_value= 1e-5
test_m= 'fisher'
individually= False
exclude= False