eukcc 2.3.0__tar.gz → 2.3.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {eukcc-2.3.0/eukcc.egg-info → eukcc-2.3.1}/PKG-INFO +1 -1
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/__main__.py +3 -2
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/constants.py +1 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/eukcc.py +16 -1
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/refine.py +2 -2
- {eukcc-2.3.0 → eukcc-2.3.1/eukcc.egg-info}/PKG-INFO +1 -1
- {eukcc-2.3.0 → eukcc-2.3.1}/pyproject.toml +1 -1
- {eukcc-2.3.0 → eukcc-2.3.1}/scripts/binlinks.py +30 -25
- {eukcc-2.3.0 → eukcc-2.3.1}/scripts/filter_euk_bins.py +4 -40
- {eukcc-2.3.0 → eukcc-2.3.1}/LICENSE +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/MANIFEST.in +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/README.md +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/__init__.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/base.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/bin.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/exec.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/fasta.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/file.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/find_markerset.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/helper.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/set_define.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc/treehandler.py +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc.egg-info/SOURCES.txt +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc.egg-info/dependency_links.txt +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc.egg-info/entry_points.txt +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc.egg-info/requires.txt +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/eukcc.egg-info/top_level.txt +0 -0
- {eukcc-2.3.0 → eukcc-2.3.1}/setup.cfg +0 -0
|
@@ -220,9 +220,10 @@ def run_eukcc(args):
|
|
|
220
220
|
)
|
|
221
221
|
@click.option(
|
|
222
222
|
"--use_placement",
|
|
223
|
-
type=
|
|
223
|
+
type=click.Path(exists=True, dir_okay=False),
|
|
224
224
|
default=None,
|
|
225
|
-
help="
|
|
225
|
+
help="Marker gene set of a previous run, to use the exact same set: savestate.json.gz in the output "
|
|
226
|
+
"folder of eukcc single, or <name>.json.gz of eukcc define_set",
|
|
226
227
|
)
|
|
227
228
|
@click.option(
|
|
228
229
|
"--set_number_species",
|
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
# extensions of the bins used by eukcc folder, plain or gzip compressed
|
|
2
2
|
FASTA_EXTENSIONS = (".fa", ".fna", ".fasta")
|
|
3
|
+
FASTA_SUFFIXES = FASTA_EXTENSIONS + tuple(f"{ext}.gz" for ext in FASTA_EXTENSIONS)
|
|
3
4
|
|
|
4
5
|
# extension of the merged bins written by eukcc folder
|
|
5
6
|
DEFAULT_EXTENSION = ".fa"
|
|
@@ -237,6 +237,16 @@ class eukcc:
|
|
|
237
237
|
# load the old info
|
|
238
238
|
old_state.load_state(self.state["use_placement"])
|
|
239
239
|
self.state["marker_set"] = old_state["marker_set"]
|
|
240
|
+
# the placement tree was in the workdir of the previous run, so its lineage is reused;
|
|
241
|
+
# a set from define_set has no lineage
|
|
242
|
+
for key in ("lng", "lng_names"):
|
|
243
|
+
if old_state.get(key) is not None:
|
|
244
|
+
self.state[key] = old_state[key]
|
|
245
|
+
# the profiles of the set are only in the database of the clade it was defined in
|
|
246
|
+
if old_state["clade"] is not None and old_state["clade"] != self.state["clade"]:
|
|
247
|
+
logging.info(f"Using the {old_state['clade']} database of the loaded set")
|
|
248
|
+
self.state["clade"] = old_state["clade"]
|
|
249
|
+
self.state["dbinfo"] = self.load_db(self.state["db"], clade=self.state["clade"])
|
|
240
250
|
logging.info(
|
|
241
251
|
f"Loaded precomputed set with {len(self.state['marker_set']['profiles'])} profiles"
|
|
242
252
|
)
|
|
@@ -245,7 +255,8 @@ class eukcc:
|
|
|
245
255
|
# figure placement
|
|
246
256
|
if self.placement() is None:
|
|
247
257
|
return None
|
|
248
|
-
|
|
258
|
+
# the set is defined on the genomes, so there is no placement in the tree to use
|
|
259
|
+
if self.state["comparison_genomes"] is not None:
|
|
249
260
|
logging.info(
|
|
250
261
|
"Will create custom marker set based on input genomes/proteomes"
|
|
251
262
|
)
|
|
@@ -379,6 +390,10 @@ class eukcc:
|
|
|
379
390
|
|
|
380
391
|
def add_taxid(self):
|
|
381
392
|
pl = self.state["placement"]
|
|
393
|
+
# with --use_placement the lineage of the loaded set is kept, with --genomes there is none
|
|
394
|
+
if pl is None or "placements" not in pl.keys():
|
|
395
|
+
logging.debug("No placements in the tree, the lineage is not inferred")
|
|
396
|
+
return
|
|
382
397
|
tree = pl["tog"]
|
|
383
398
|
if "marker_set" in self.state.keys():
|
|
384
399
|
places = self.state["marker_set"]["covered_pl"]
|
|
@@ -7,7 +7,7 @@ from collections import defaultdict
|
|
|
7
7
|
from eukcc.eukcc import eukcc, eukcc_state
|
|
8
8
|
from eukcc.fasta import merge_fasta, valid_fastas
|
|
9
9
|
from eukcc import __version__
|
|
10
|
-
from eukcc.constants import
|
|
10
|
+
from eukcc.constants import FASTA_SUFFIXES, DEFAULT_EXTENSION
|
|
11
11
|
from eukcc.fasta import Fasta
|
|
12
12
|
from eukcc.bin import bin, merge_bins
|
|
13
13
|
from eukcc.file import file
|
|
@@ -62,7 +62,7 @@ def eukcc_folder(args):
|
|
|
62
62
|
state["input_bins"] = valid_fastas(
|
|
63
63
|
_path
|
|
64
64
|
for _path in glob.glob(os.path.join(state["binfolder"], "*"))
|
|
65
|
-
if _path.lower().endswith(
|
|
65
|
+
if _path.lower().endswith(FASTA_SUFFIXES)
|
|
66
66
|
)
|
|
67
67
|
logging.info(f"Found {len(state['input_bins'])} bins")
|
|
68
68
|
if len(state["input_bins"]) == 0:
|
|
@@ -1,11 +1,12 @@
|
|
|
1
1
|
#!/usr/bin/env python3
|
|
2
2
|
import pysam
|
|
3
|
-
from Bio import SeqIO
|
|
4
3
|
from collections import defaultdict
|
|
5
4
|
import os
|
|
6
5
|
import argparse
|
|
7
6
|
import logging
|
|
8
7
|
import csv
|
|
8
|
+
from eukcc.constants import FASTA_SUFFIXES
|
|
9
|
+
from eukcc.fasta import Fasta
|
|
9
10
|
|
|
10
11
|
|
|
11
12
|
def is_in(read, contig_map, within=1000):
|
|
@@ -35,30 +36,28 @@ def keep_read(read, contig_map, within=1000, min_ANI=98, min_cov=0):
|
|
|
35
36
|
return False
|
|
36
37
|
|
|
37
38
|
|
|
38
|
-
def
|
|
39
|
+
def bin_files(bindir):
|
|
40
|
+
"""
|
|
41
|
+
the bins used by eukcc folder, so the bin names match its own
|
|
42
|
+
"""
|
|
43
|
+
return [f for f in os.listdir(bindir) if f.lower().endswith(FASTA_SUFFIXES)]
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
def contig_map(bindir):
|
|
39
47
|
m = {}
|
|
40
|
-
for f in
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
path = os.path.join(bindir, f)
|
|
44
|
-
with open(path, "r") as handle:
|
|
45
|
-
for record in SeqIO.parse(handle, "fasta"):
|
|
46
|
-
m[record.name] = len(record.seq)
|
|
48
|
+
for f in bin_files(bindir):
|
|
49
|
+
for record in Fasta(os.path.join(bindir, f)):
|
|
50
|
+
m[record.name] = len(record.seq)
|
|
47
51
|
return m
|
|
48
52
|
|
|
49
53
|
|
|
50
|
-
def bin_map(bindir
|
|
54
|
+
def bin_map(bindir):
|
|
51
55
|
contigs = defaultdict(str)
|
|
52
56
|
contigs_per_bin = defaultdict(int)
|
|
53
|
-
for
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
binname = os.path.basename(f)
|
|
58
|
-
with open(path, "r") as handle:
|
|
59
|
-
for record in SeqIO.parse(handle, "fasta"):
|
|
60
|
-
contigs[record.name] = binname
|
|
61
|
-
contigs_per_bin[binname] += 1
|
|
57
|
+
for binname in bin_files(bindir):
|
|
58
|
+
for record in Fasta(os.path.join(bindir, binname)):
|
|
59
|
+
contigs[record.name] = binname
|
|
60
|
+
contigs_per_bin[binname] += 1
|
|
62
61
|
return contigs, contigs_per_bin
|
|
63
62
|
|
|
64
63
|
|
|
@@ -107,14 +106,20 @@ def main():
|
|
|
107
106
|
# set arguments
|
|
108
107
|
# arguments are passed to classes
|
|
109
108
|
parser = argparse.ArgumentParser(
|
|
110
|
-
description="
|
|
109
|
+
description="Count the read pairs linking bins, for eukcc folder --links."
|
|
110
|
+
)
|
|
111
|
+
parser.add_argument(
|
|
112
|
+
"--binfolder",
|
|
113
|
+
type=str,
|
|
114
|
+
required=True,
|
|
115
|
+
help="Folder with the bins: .fa, .fna or .fasta files, optionally gzip compressed",
|
|
111
116
|
)
|
|
112
|
-
parser.add_argument("bindir", type=str, help="Run script on these bins")
|
|
113
117
|
parser.add_argument(
|
|
114
|
-
"
|
|
118
|
+
"--alignment",
|
|
115
119
|
type=str,
|
|
116
|
-
|
|
120
|
+
required=True,
|
|
117
121
|
nargs="+",
|
|
122
|
+
help="Bam file(s) with paired reads aligned against all contigs making up the bins",
|
|
118
123
|
)
|
|
119
124
|
parser.add_argument(
|
|
120
125
|
"--out",
|
|
@@ -170,7 +175,7 @@ def main():
|
|
|
170
175
|
level=logLevel,
|
|
171
176
|
)
|
|
172
177
|
|
|
173
|
-
bindir = args.
|
|
178
|
+
bindir = args.binfolder
|
|
174
179
|
|
|
175
180
|
cm = contig_map(bindir)
|
|
176
181
|
bm, contigs_per_bin = bin_map(bindir)
|
|
@@ -180,7 +185,7 @@ def main():
|
|
|
180
185
|
bin_table = defaultdict(lambda: defaultdict(int))
|
|
181
186
|
|
|
182
187
|
# iterate all bam files
|
|
183
|
-
for bamf in args.
|
|
188
|
+
for bamf in args.alignment:
|
|
184
189
|
link_table = read_bam_file(bamf, link_table, cm, args.within, args.ANI)
|
|
185
190
|
|
|
186
191
|
logging.debug(f"Created link table with {len(link_table)} entries")
|
|
@@ -24,43 +24,7 @@ import tempfile
|
|
|
24
24
|
import gzip
|
|
25
25
|
from multiprocessing import Pool
|
|
26
26
|
from functools import partial
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
# backup fasta handler, so we can use readonly directories
|
|
30
|
-
class fa_class:
|
|
31
|
-
def __init__(self, seq, name, long_name):
|
|
32
|
-
self.seq = seq
|
|
33
|
-
self.name = name
|
|
34
|
-
self.long_name = long_name
|
|
35
|
-
|
|
36
|
-
def __str__(self):
|
|
37
|
-
return self.seq
|
|
38
|
-
|
|
39
|
-
def __len__(self):
|
|
40
|
-
return len(self.seq)
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
def Fasta(path):
|
|
44
|
-
"""
|
|
45
|
-
Iterator for fasta files
|
|
46
|
-
"""
|
|
47
|
-
entry = False
|
|
48
|
-
|
|
49
|
-
with open(path) as fin:
|
|
50
|
-
for line in fin:
|
|
51
|
-
if line.startswith(">"):
|
|
52
|
-
if entry is not False:
|
|
53
|
-
entry.seq = "".join(entry.seq)
|
|
54
|
-
yield entry
|
|
55
|
-
# define new entry
|
|
56
|
-
long_name = line.strip()[1:]
|
|
57
|
-
name = long_name.split()[0]
|
|
58
|
-
entry = fa_class([], name, long_name)
|
|
59
|
-
else:
|
|
60
|
-
entry.seq.append(line.strip())
|
|
61
|
-
# yield last one
|
|
62
|
-
entry.seq = "".join(entry.seq)
|
|
63
|
-
yield entry
|
|
27
|
+
from eukcc.fasta import Fasta
|
|
64
28
|
|
|
65
29
|
|
|
66
30
|
def gunzip(path, tmp_dir):
|
|
@@ -190,10 +154,10 @@ def evaluate_bin(path, args):
|
|
|
190
154
|
eukfile = os.path.join(tmp_dir, "euks.fna")
|
|
191
155
|
bacfile = os.path.join(tmp_dir, "bacs.fna")
|
|
192
156
|
# EukRep can not deal with Gzipped Fasta files, so we unzip it in case it is a Gzip file
|
|
193
|
-
|
|
157
|
+
eukrep_path = gunzip(path, tmp_dir)
|
|
194
158
|
# Launching EukRep
|
|
195
|
-
logging.debug(f"Starting EukRep on {
|
|
196
|
-
eukrep_result = EukRep(
|
|
159
|
+
logging.debug(f"Starting EukRep on {eukrep_path}")
|
|
160
|
+
eukrep_result = EukRep(eukrep_path, eukfile, bacfile, minl=args.minl)
|
|
197
161
|
eukrep_result.run()
|
|
198
162
|
b = bin(path, eukrep_result)
|
|
199
163
|
b.stats()
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|