def read_similarity_graph(similarity_graph_file, fasta_file):
my_dict = FastaIO.read_fasta_file_as_dict(fasta_file)
with open(similarity_graph_file, 'r') as csvfile:
reader = list(csv.reader(csvfile, delimiter=','))
X = []
Y = []
for candidate_pair in reader:
read1 = my_dict[candidate_pair[0]].seq
read2 = my_dict[candidate_pair[1]].seq
if len(read1) < 400:
rest = ''
for i in range(400 - len(read1)):
rest += 'A'
read1 += rest
if len(read2) < 400:
rest = ''
for i in range(400 - len(read2)):
rest += 'A'
read2 += rest
read1 = read1[0:400]
read2 = read2[0:400]
pair = binarize_pair(read1, read2)
X.append(pair)
Y.append(1)
all_pairs = np.array(X)
all_labels = np.array(Y)
all_pairs = all_pairs.reshape(all_pairs.shape[0], all_pairs.shape[1],
all_pairs.shape[2], 1)
test = DataSet(all_pairs, all_labels)
ds = collections.namedtuple('Datasets', ['test'])
return ds(test=test)
import csv
import networkx
from DataOperations import graphOperations
import numpy as np
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt
import scipy.io
import community
from DataOperations import FastaIO
from collections import Counter
dataset = FastaIO.read_fasta_file('../files/isoseq_flnc1.fasta')
dataset_dict = FastaIO.read_fasta_file_as_dict('../files/isoseq_flnc1.fasta')
id_dict = {}
id_list = []
G = networkx.Graph()
print(dataset_dict[
'm150803_002149_42161_c100745121910000001823165807071563_s1_p0/14/1140_57_CCS']
.seq)
ind = 0
for item in dataset:
id_dict[item.id] = ind
ind += 1
id_list.append(item.id)
G.add_node(item.id)
print(id_list)
my_dict = []
"""
mat = scipy.io.loadmat('Data50.mat')