eukcc 2.1.3__tar.gz → 2.2.0__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-2.1.3/eukcc.egg-info → eukcc-2.2.0}/PKG-INFO +6 -4
- {eukcc-2.1.3 → eukcc-2.2.0}/README.md +2 -2
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/__main__.py +11 -3
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/eukcc.py +5 -2
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/refine.py +1 -1
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/set_define.py +1 -1
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/treehandler.py +18 -7
- eukcc-2.2.0/eukcc/version.py +1 -0
- {eukcc-2.1.3 → eukcc-2.2.0/eukcc.egg-info}/PKG-INFO +6 -4
- {eukcc-2.1.3 → eukcc-2.2.0}/pyproject.toml +8 -1
- {eukcc-2.1.3 → eukcc-2.2.0}/setup.py +1 -1
- {eukcc-2.1.3 → eukcc-2.2.0}/tests/test_tree.py +20 -1
- eukcc-2.1.3/eukcc/version.py +0 -1
- {eukcc-2.1.3 → eukcc-2.2.0}/LICENSE +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/MANIFEST.in +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/__init__.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/base.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/bin.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/exec.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/fasta.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/file.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/find_markerset.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc/helper.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc.egg-info/SOURCES.txt +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc.egg-info/dependency_links.txt +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc.egg-info/entry_points.txt +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc.egg-info/requires.txt +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/eukcc.egg-info/top_level.txt +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/scripts/binlinks.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/scripts/filter_euk_bins.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/setup.cfg +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/tests/test_basic.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/tests/test_eukcc.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/tests/test_fasta.py +0 -0
- {eukcc-2.1.3 → eukcc-2.2.0}/tests/test_file.py +0 -0
|
@@ -1,11 +1,13 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: eukcc
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.2.0
|
|
4
4
|
Summary: Check eukaryotic genomes or MAGs for completeness and contamination
|
|
5
|
-
Home-page: https://github.com/
|
|
5
|
+
Home-page: https://github.com/EBI-Metagenomics/EukCC
|
|
6
6
|
Author: Paul Saary
|
|
7
7
|
Author-email: Paul Saary <eukcc@paulsaary.de>, MGnify team <metagenomics-help@ebi.ac.uk>
|
|
8
8
|
License: GPLv3
|
|
9
|
+
Project-URL: Homepage, https://github.com/EBI-Metagenomics/EukCC
|
|
10
|
+
Project-URL: Documentation, https://eukcc.readthedocs.io/
|
|
9
11
|
Keywords: bioinformatics,mags,eukaryotic,completeness,contamination
|
|
10
12
|
Classifier: Programming Language :: Python :: 3.6
|
|
11
13
|
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
|
|
@@ -87,11 +89,11 @@ In addition, you need to install mandatory requirements:
|
|
|
87
89
|
|
|
88
90
|
### eukcc single
|
|
89
91
|
|
|
90
|
-
- `eukcc.
|
|
92
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage
|
|
91
93
|
|
|
92
94
|
### eukcc folder
|
|
93
95
|
|
|
94
|
-
- `eukcc.
|
|
96
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage for **good** quality bins
|
|
95
97
|
- `merged_bins.csv` - table of merged refined bins
|
|
96
98
|
- `bad_quality.csv`- table with estimated completeness, contamination and taxonomy lineage for **bad** quality bins (chosen marker gene set is supported by less than half of the alignments)
|
|
97
99
|
- `missing_marker_genes.txt` - line separated list of bins with not defined set of marker genes
|
|
@@ -51,11 +51,11 @@ In addition, you need to install mandatory requirements:
|
|
|
51
51
|
|
|
52
52
|
### eukcc single
|
|
53
53
|
|
|
54
|
-
- `eukcc.
|
|
54
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage
|
|
55
55
|
|
|
56
56
|
### eukcc folder
|
|
57
57
|
|
|
58
|
-
- `eukcc.
|
|
58
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage for **good** quality bins
|
|
59
59
|
- `merged_bins.csv` - table of merged refined bins
|
|
60
60
|
- `bad_quality.csv`- table with estimated completeness, contamination and taxonomy lineage for **bad** quality bins (chosen marker gene set is supported by less than half of the alignments)
|
|
61
61
|
- `missing_marker_genes.txt` - line separated list of bins with not defined set of marker genes
|
|
@@ -27,6 +27,14 @@ def update(dbfile=None):
|
|
|
27
27
|
ncbi.update_taxonomy_database()
|
|
28
28
|
|
|
29
29
|
|
|
30
|
+
def no_estimate(E, state):
|
|
31
|
+
"""
|
|
32
|
+
It was not possible to estimate this genome. Write the result file with NAs and stop.
|
|
33
|
+
"""
|
|
34
|
+
E.write_result(E.state, os.path.join(state["out"], "eukcc.tsv"))
|
|
35
|
+
E.terminate(201)
|
|
36
|
+
|
|
37
|
+
|
|
30
38
|
def run_eukcc(args):
|
|
31
39
|
state = eukcc_state(workdir=None, options=vars(args))
|
|
32
40
|
logging.info("EukCC version {}".format(version.__version__))
|
|
@@ -77,7 +85,7 @@ def run_eukcc(args):
|
|
|
77
85
|
):
|
|
78
86
|
logging.info("Doing a first pass placement in the base database")
|
|
79
87
|
if E.placement() is None:
|
|
80
|
-
E
|
|
88
|
+
no_estimate(E, state)
|
|
81
89
|
# decide which db to use
|
|
82
90
|
clade = E.determine_subdb()
|
|
83
91
|
if clade != "base":
|
|
@@ -87,7 +95,7 @@ def run_eukcc(args):
|
|
|
87
95
|
|
|
88
96
|
# pick marker set and placement in one step
|
|
89
97
|
if E.pick_marker_set() is None:
|
|
90
|
-
E
|
|
98
|
+
no_estimate(E, state)
|
|
91
99
|
E.state["scmg_data"] = E.hmmsearch_scmg(
|
|
92
100
|
E.state["workdir"], E.state["faa"], E.state["marker_set"]["profiles"]
|
|
93
101
|
)
|
|
@@ -99,7 +107,7 @@ def run_eukcc(args):
|
|
|
99
107
|
# aggregate all the interesting data, such as estimated quality
|
|
100
108
|
# the expected and found SCMGs and the workdir
|
|
101
109
|
E.state.save_state()
|
|
102
|
-
E.write_result(E.state, os.path.join(state["out"], "eukcc.
|
|
110
|
+
E.write_result(E.state, os.path.join(state["out"], "eukcc.tsv"))
|
|
103
111
|
|
|
104
112
|
if state["extra"]:
|
|
105
113
|
# search for missing markers
|
|
@@ -942,6 +942,7 @@ class eukcc:
|
|
|
942
942
|
"""
|
|
943
943
|
if result is None:
|
|
944
944
|
logging.debug("Empty result given, so we write NAs for all values")
|
|
945
|
+
result = [self.state]
|
|
945
946
|
|
|
946
947
|
if type(result) == dict:
|
|
947
948
|
result = [result]
|
|
@@ -959,10 +960,12 @@ class eukcc:
|
|
|
959
960
|
else:
|
|
960
961
|
lng = "NA"
|
|
961
962
|
|
|
963
|
+
# quality is missing if we could not estimate this genome
|
|
964
|
+
quality = res.get("quality") or {}
|
|
962
965
|
row = {
|
|
963
966
|
"fasta": res["fasta"],
|
|
964
|
-
"completeness":
|
|
965
|
-
"contamination":
|
|
967
|
+
"completeness": quality.get("completeness", "NA"),
|
|
968
|
+
"contamination": quality.get("contamination", "NA"),
|
|
966
969
|
"ncbi_lng": lng,
|
|
967
970
|
}
|
|
968
971
|
writer.writerow(row)
|
|
@@ -150,7 +150,7 @@ def refine(state):
|
|
|
150
150
|
)
|
|
151
151
|
|
|
152
152
|
# initialize output tables
|
|
153
|
-
result_table = os.path.join(state["out"], "eukcc.
|
|
153
|
+
result_table = os.path.join(state["out"], "eukcc.tsv")
|
|
154
154
|
write_table(None, result_table, header=True)
|
|
155
155
|
# table for bad quality bins
|
|
156
156
|
bad_quality_result_table = os.path.join(state["out"], "bad_quality.csv")
|
|
@@ -166,20 +166,31 @@ def tax_LCA(
|
|
|
166
166
|
t = Tree(tree)
|
|
167
167
|
info = load_tax_info(taxinfo, dbfile=etedb)
|
|
168
168
|
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
169
|
+
# Split tree leaves into known references and queries:
|
|
170
|
+
#
|
|
171
|
+
# Tree leaves: ref_A ref_B query_1 query_2 query_3
|
|
172
|
+
# │ │ │ │ │
|
|
173
|
+
# └─ known ─┘ └──── queries ─────┘
|
|
174
|
+
# Taxonomy info: ref_A ref_B
|
|
175
|
+
# Placements: query_1 query_2 query_3
|
|
176
|
+
#
|
|
177
|
+
# A known leaf is a tree leaf with taxonomy information.
|
|
178
|
+
# Query leaves are everything else; if placements are provided,
|
|
179
|
+
# only queries present in the placement set are considered.
|
|
180
|
+
|
|
181
|
+
all_leafes = set(t.get_tree_root().get_leaf_names())
|
|
182
|
+
known_leafes = all_leafes & set(info.keys())
|
|
183
|
+
query_leafes = all_leafes - known_leafes
|
|
184
|
+
if placements is not None:
|
|
185
|
+
query_leafes = query_leafes & set(placements)
|
|
174
186
|
|
|
175
187
|
logging.debug(
|
|
176
188
|
"Determining the LCA in a tree with {} leafes".format(len(known_leafes))
|
|
177
189
|
)
|
|
178
190
|
|
|
179
191
|
leafes = set()
|
|
180
|
-
all_leafes = set(node.get_leaf_names())
|
|
181
192
|
pl_lngs = []
|
|
182
|
-
for place in
|
|
193
|
+
for place in query_leafes:
|
|
183
194
|
# jump to node
|
|
184
195
|
node = t.search_nodes(name=place)[0]
|
|
185
196
|
while True:
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "2.2.0"
|
|
@@ -1,11 +1,13 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: eukcc
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.2.0
|
|
4
4
|
Summary: Check eukaryotic genomes or MAGs for completeness and contamination
|
|
5
|
-
Home-page: https://github.com/
|
|
5
|
+
Home-page: https://github.com/EBI-Metagenomics/EukCC
|
|
6
6
|
Author: Paul Saary
|
|
7
7
|
Author-email: Paul Saary <eukcc@paulsaary.de>, MGnify team <metagenomics-help@ebi.ac.uk>
|
|
8
8
|
License: GPLv3
|
|
9
|
+
Project-URL: Homepage, https://github.com/EBI-Metagenomics/EukCC
|
|
10
|
+
Project-URL: Documentation, https://eukcc.readthedocs.io/
|
|
9
11
|
Keywords: bioinformatics,mags,eukaryotic,completeness,contamination
|
|
10
12
|
Classifier: Programming Language :: Python :: 3.6
|
|
11
13
|
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
|
|
@@ -87,11 +89,11 @@ In addition, you need to install mandatory requirements:
|
|
|
87
89
|
|
|
88
90
|
### eukcc single
|
|
89
91
|
|
|
90
|
-
- `eukcc.
|
|
92
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage
|
|
91
93
|
|
|
92
94
|
### eukcc folder
|
|
93
95
|
|
|
94
|
-
- `eukcc.
|
|
96
|
+
- `eukcc.tsv` - table with estimated completeness, contamination and taxonomy lineage for **good** quality bins
|
|
95
97
|
- `merged_bins.csv` - table of merged refined bins
|
|
96
98
|
- `bad_quality.csv`- table with estimated completeness, contamination and taxonomy lineage for **bad** quality bins (chosen marker gene set is supported by less than half of the alignments)
|
|
97
99
|
- `missing_marker_genes.txt` - line separated list of bins with not defined set of marker genes
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "eukcc"
|
|
3
|
-
|
|
3
|
+
dynamic = ["version"]
|
|
4
4
|
readme = "README.md"
|
|
5
5
|
license = {text = "GPLv3"}
|
|
6
6
|
authors = [
|
|
@@ -25,6 +25,10 @@ dependencies = [
|
|
|
25
25
|
"six"
|
|
26
26
|
]
|
|
27
27
|
|
|
28
|
+
[project.urls]
|
|
29
|
+
Homepage = "https://github.com/EBI-Metagenomics/EukCC"
|
|
30
|
+
Documentation = "https://eukcc.readthedocs.io/"
|
|
31
|
+
|
|
28
32
|
[build-system]
|
|
29
33
|
requires = ["setuptools>=61.0"]
|
|
30
34
|
build-backend = "setuptools.build_meta"
|
|
@@ -35,6 +39,9 @@ packages = [
|
|
|
35
39
|
"scripts",
|
|
36
40
|
]
|
|
37
41
|
|
|
42
|
+
[tool.setuptools.dynamic]
|
|
43
|
+
version = {attr = "eukcc.version.__version__"}
|
|
44
|
+
|
|
38
45
|
[project.scripts]
|
|
39
46
|
# eukcc
|
|
40
47
|
eukcc = "eukcc.__main__:main"
|
|
@@ -15,7 +15,7 @@ setuptools.setup(
|
|
|
15
15
|
description="Check eukaryotic genomes or MAGs for completeness and contamination",
|
|
16
16
|
long_description=long_description,
|
|
17
17
|
long_description_content_type="text/markdown",
|
|
18
|
-
url="https://github.com/
|
|
18
|
+
url="https://github.com/EBI-Metagenomics/EukCC",
|
|
19
19
|
py_modules=[],
|
|
20
20
|
entry_points={
|
|
21
21
|
"console_scripts": [
|
|
@@ -1,10 +1,11 @@
|
|
|
1
1
|
import unittest
|
|
2
2
|
import os
|
|
3
|
-
from eukcc.treehandler import tree_sets
|
|
3
|
+
from eukcc.treehandler import tree_sets, tax_LCA
|
|
4
4
|
|
|
5
5
|
TESTDATA_SCMG_GZ = os.path.join(os.path.dirname(__file__), "testfiles", "SCMG_TEST.csv.gz")
|
|
6
6
|
TESTDATA_SCTREE = os.path.join(os.path.dirname(__file__), "testfiles", "tree_scmg.csv")
|
|
7
7
|
TESTDATA_TAXINFO = os.path.join(os.path.dirname(__file__), "testfiles", "tree_taxinfo.csv")
|
|
8
|
+
TESTDATA_TAX_LCA = os.path.join(os.path.dirname(__file__), "testfiles", "tax_lca_taxinfo.csv")
|
|
8
9
|
|
|
9
10
|
|
|
10
11
|
class test_tree(unittest.TestCase):
|
|
@@ -21,3 +22,21 @@ class test_tree(unittest.TestCase):
|
|
|
21
22
|
s, placement, TESTDATA_SCTREE, set_species=4, set_size=2, set_prevalence=80, taxinfo=TESTDATA_TAXINFO
|
|
22
23
|
)
|
|
23
24
|
self.assertEqual(t.marker_set.profiles, set(["Marker100", "Marker80"]))
|
|
25
|
+
|
|
26
|
+
def test_tax_LCA_partial_placements(self):
|
|
27
|
+
tree = (
|
|
28
|
+
"(((GCA_015473125.1,metaeuk_OY253681.1_29),(((GCA_006384855.1,metaeuk_OY253673.1_71),"
|
|
29
|
+
"metaeuk_OY253685.1_62),((((metaeuk_OY253682.1_41,GCA_004138255.1),metaeuk_OY253672.1_198),"
|
|
30
|
+
"((GCA_011766145.1,metaeuk_OY253676.1_95),(GCA_004335775.1,metaeuk_OY253680.1_173))),"
|
|
31
|
+
"((GCA_010646915.1,metaeuk_OY253673.1_210),((metaeuk_OY253668.1_317,GCA_002794665.1),"
|
|
32
|
+
"GCA_000690575.1))))),metaeuk_OY253675.1_91);"
|
|
33
|
+
)
|
|
34
|
+
lng = tax_LCA(
|
|
35
|
+
tree,
|
|
36
|
+
TESTDATA_TAX_LCA,
|
|
37
|
+
placements=["metaeuk_OY253681.1_29", "metaeuk_OY253676.1_95"],
|
|
38
|
+
add_protist_common=False,
|
|
39
|
+
)
|
|
40
|
+
|
|
41
|
+
# root, cellular organisms, Eukaryota, Viridiplantae, Chlorophyta
|
|
42
|
+
self.assertEqual(lng, ["1", "131567", "2759", "33090", "3041"])
|
eukcc-2.1.3/eukcc/version.py
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "2.1.2"
|
|
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
|
|
File without changes
|
|
File without changes
|
|
File without changes
|