1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
--- a/flye/assembly/scaffolder.py
+++ b/flye/assembly/scaffolder.py
@@ -12,7 +12,6 @@
import flye.utils.fasta_parser as fp
import flye.config.py_cfg as cfg
-from six import iteritems
logger = logging.getLogger()
@@ -128,7 +127,7 @@
contigs_stats[tokens[0]].coverage = tokens[2]
scaffolds_stats = {}
- for scf, scf_seq in iteritems(scaffolds):
+ for scf, scf_seq in scaffolds.items():
scaffolds_stats[scf] = SeqStats(scf)
scf_length = sum([int(contigs_stats[unsigned(c)].length) for c in scf_seq])
scf_length += (len(scf_seq) - 1) * cfg.vals["scaffold_gap"]
--- a/flye/config/configurator.py
+++ b/flye/config/configurator.py
@@ -12,7 +12,6 @@
import flye.utils.fasta_parser as fp
import flye.config.py_cfg as cfg
-from six import iteritems
logger = logging.getLogger()
@@ -37,7 +36,7 @@
passing_reads = 0
for read_file in args.reads:
- for _, seq_len in iteritems(fp.read_sequence_lengths(read_file)):
+ for _, seq_len in fp.read_sequence_lengths(read_file).items():
if seq_len > MAX_READ_LEN:
raise ConfigException("Length of single read in '{}' exceeded maximum ({})".format(read_file, MAX_READ_LEN))
if seq_len > lowest_read_len:
--- a/flye/polishing/alignment.py
+++ b/flye/polishing/alignment.py
@@ -18,7 +18,6 @@
import flye.utils.fasta_parser as fp
from flye.utils.utils import which, get_median
from flye.utils.sam_parser import AlignmentException
-from six import iteritems
@@ -47,7 +46,7 @@
def get_contigs_info(contigs_file):
contigs_info = {}
contigs_fasta = fp.read_sequence_dict(contigs_file)
- for ctg_id, ctg_seq in iteritems(contigs_fasta):
+ for ctg_id, ctg_seq in contigs_fasta.items():
contig_type = ctg_id.split("_")[0]
contigs_info[ctg_id] = ContigInfo(ctg_id, len(ctg_seq),
contig_type)
--- a/flye/polishing/consensus.py
+++ b/flye/polishing/consensus.py
@@ -11,7 +11,6 @@
import logging
from collections import defaultdict
-from six import itervalues
import multiprocessing
import traceback
@@ -160,10 +159,10 @@
pos_nucl = elem.nucl
ins_group.clear()
- for ins_str in itervalues(pos_insertions):
+ for ins_str in pos_insertions.values():
ins_group[ins_str] += 1
- match_and_del_num = sum(itervalues(pos_matches))
+ match_and_del_num = sum(pos_matches.values())
del_num = pos_matches["-"]
num_ins = len(pos_insertions)
--- a/flye/polishing/polish.py
+++ b/flye/polishing/polish.py
@@ -21,7 +21,6 @@
import flye.utils.fasta_parser as fp
from flye.utils.utils import which
import flye.config.py_cfg as cfg
-from six import iteritems
@@ -329,7 +328,7 @@
polished_fasta = {}
polished_stats = {}
polished_coverages = {}
- for ctg_id, seqs in iteritems(consensuses):
+ for ctg_id, seqs in consensuses.items():
seqs.sort(key=lambda p: (p[0], p[1]))
sorted_seqs = [p[3] for p in seqs]
bubble_coverages = [(len(p[3]), p[2]) for p in seqs]
--- a/flye/short_plasmids/circular_sequences.py
+++ b/flye/short_plasmids/circular_sequences.py
@@ -9,7 +9,6 @@
import flye.utils.fasta_parser as fp
from flye.utils.sam_parser import read_paf, read_paf_grouped
import logging
-from six import iteritems
logger = logging.getLogger()
@@ -47,7 +46,7 @@
def trim_circular_reads(circular_reads, unmapped_reads):
trimmed_circular_reads = dict()
- for i, (read, hit) in enumerate(iteritems(circular_reads)):
+ for i, (read, hit) in enumerate(circular_reads.items()):
sequence = unmapped_reads[read][:hit.target_start].upper()
trimmed_circular_reads["circular_read_" + str(i)] = sequence
--- a/flye/short_plasmids/unmapped_reads.py
+++ b/flye/short_plasmids/unmapped_reads.py
@@ -9,7 +9,6 @@
from flye.utils.sam_parser import read_paf_grouped
import logging
from collections import defaultdict
-from six import iteritems
logger = logging.getLogger()
@@ -76,7 +75,7 @@
contigs = mapping_rates.get(hdr)
if contigs is not None:
is_unmapped = True
- for _, mapping_rate in iteritems(contigs):
+ for _, mapping_rate in contigs.items():
if mapping_rate >= mapping_rate_threshold:
is_unmapped = False
--- a/flye/trestle/graph_resolver.py
+++ b/flye/trestle/graph_resolver.py
@@ -13,7 +13,6 @@
import flye.utils.fasta_parser as fp
from flye.repeat_graph.graph_alignment import iter_alignments
-from six import iteritems
logger = logging.getLogger()
@@ -146,7 +145,7 @@
def dump_repeats(repeats_info, filename):
with open(filename, "w") as f:
- for repeat_id, info in iteritems(repeats_info):
+ for repeat_id, info in repeats_info.items():
f.write("#Repeat {0}\t{1}\n\n".format(repeat_id, info.multiplicity))
f.write("#All reads\t{0}\n".format(len(info.all_reads)))
--- a/flye/utils/sam_parser.py
+++ b/flye/utils/sam_parser.py
@@ -33,7 +33,6 @@
_BYTES = str.encode
-from six import iteritems
import flye.utils.fasta_parser as fp
from flye.utils.utils import get_median
@@ -209,7 +208,7 @@
#self.shared_manager = multiprocessing.Manager()
self.ref_fasta = dict() if multiproc_manager == None else multiproc_manager.dict()
- for (h, s) in iteritems(reference_fasta):
+ for (h, s) in reference_fasta.items():
self.ref_fasta[_BYTES(h)] = _BYTES(s)
def get_region_sequence(self, region_id, region_start=None, region_end=None):
|
