def __init__(self,
fasta_file,
matrix_path,
feature_file_path,
phenotypes,
phenotype_mapping,
selected_samples,
p_value_threshold=0.01,
remove_redundants=False,
num_p=4,
blastn_path=''):
if len(blastn_path) > 0:
os.environ['PATH'] += ':' + blastn_path
self.num_p = num_p
self.seq_IDS = FileUtility.read_fasta_sequences_ids(fasta_file)
self.remove_redundants = remove_redundants
self.ez_taxa_dict = {
x.split()[0]: x.split()[1].split(';')
for x in FileUtility.load_list('db/ez_idx_taxonomy.txt')
}
self.mat = FileUtility.load_sparse_csr(matrix_path)
self.mat = self.mat.toarray()
self.mat = self.mat[selected_samples, :]
self.mat = csr_matrix(self.mat)
self.features = FileUtility.load_list(feature_file_path)
self.align_markers_parallel(p_value_threshold)
self.redundant_columns_indentification()
self.phenotype_mapping = phenotype_mapping
self.phenotypes = phenotypes
import collections
import pandas as pd
import tqdm
import itertools
import numpy as np
from make_representations.cpe_efficient import train_cpe
from multiprocessing import Pool
#############################################################
# Simple script for learning segmentation steps from a fasta file
# Output: the file containing merging steps (i.e., "path_to_mergings"),
# can be used instead of Swiss-Prot merging steps
#############################################################
# Inputs
seq_dict = FileUtility.read_fasta_sequences_ids('sequences.fasta')
max_symbols = 10000
min_freq_for_merging = 10
# Output
path_to_mergings = 'ppe_mergings.txt'
path_to_merging_freqs = 'ppe_freq.txt'
#############################################################
SID = list(seq_dict.keys())
SID.sort()
seqs = [seq_dict[seqID][0] for seqID in SID]
train_cpe(seqs,
path_to_mergings,
max_symbols,
