mgnify-pipelines-toolkit 1.0.3__tar.gz → 1.0.4__tar.gz

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.3
+Version: 1.0.4
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -11,33 +11,24 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: biopython==1.82
-Requires-Dist: numpy==1.26.0
-Requires-Dist: pandas==2.0.2
-Requires-Dist: regex==2023.12.25
-Requires-Dist: requests==2.32.3
-Requires-Dist: click==8.1.7
-Requires-Dist: pandera==0.22.1
-Requires-Dist: pyfastx>=2.2.0
-Requires-Dist: intervaltree==3.1.0
+Requires-Dist: biopython>=1.85
+Requires-Dist: numpy<3,>=2.2.4
+Requires-Dist: pandas<3,>=2.2.3
+Requires-Dist: regex>=2024.11.6
+Requires-Dist: requests<3,>=2.32.3
+Requires-Dist: click<9,>=8.1.8
+Requires-Dist: pandera<0.24,>=0.23.1
+Requires-Dist: pyfastx<3,>=2.2.0
+Requires-Dist: intervaltree<4,>=3.1.0
 Provides-Extra: tests
-Requires-Dist: pytest==7.4.0; extra == "tests"
-Requires-Dist: pytest-md==0.2.0; extra == "tests"
-Requires-Dist: pytest-workflow==2.0.1; extra == "tests"
-Requires-Dist: biopython==1.82; extra == "tests"
-Requires-Dist: pandas==2.0.2; extra == "tests"
-Requires-Dist: numpy==1.26.0; extra == "tests"
-Requires-Dist: regex==2023.12.25; extra == "tests"
-Requires-Dist: requests==2.32.3; extra == "tests"
-Requires-Dist: click==8.1.7; extra == "tests"
-Requires-Dist: pandera==0.22.1; extra == "tests"
-Requires-Dist: pyfastx>=2.2.0; extra == "tests"
+Requires-Dist: pytest<9,>=8.3.5; extra == "tests"
+Requires-Dist: pytest-md>=0.2.0; extra == "tests"
+Requires-Dist: pytest-workflow==2.1.0; extra == "tests"
 Provides-Extra: dev
-Requires-Dist: mgnify_pipelines_toolkit[tests]; extra == "dev"
-Requires-Dist: pre-commit==3.8.0; extra == "dev"
-Requires-Dist: black==24.8.0; extra == "dev"
-Requires-Dist: flake8==7.1.1; extra == "dev"
-Requires-Dist: pep8-naming==0.14.1; extra == "dev"
+Requires-Dist: pre-commit>=4.2.0; extra == "dev"
+Requires-Dist: black>=25.1.0; extra == "dev"
+Requires-Dist: flake8>=7.1.2; extra == "dev"
+Requires-Dist: pep8-naming>=0.14.1; extra == "dev"
 Dynamic: license-file
 
 # mgnify-pipelines-toolkit
@@ -74,8 +65,9 @@ Before starting any development, you should do these few steps:
 - Clone the repo if you haven't already and create a feature branch from the `dev` branch (NOT `main`).
 - Create a virtual environment with the tool of your choice (i.e. `conda create --name my_new_env`)
 - Activate you new environment (i.e. `conda activate my_new_env`)
-- Install dev dependencies `pip install -e '.[dev]'`
+- Install dev dependencies `pip install -e '.[tests,dev]'`
 - Install pre-commit hooks `pre-commit install`
+- Run unit tests `pytest`
 
 When doing these steps above, you ensure that the code you add will be linted and formatted properly.
 

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/README.md

@@ -32,8 +32,9 @@ Before starting any development, you should do these few steps:
 - Clone the repo if you haven't already and create a feature branch from the `dev` branch (NOT `main`).
 - Create a virtual environment with the tool of your choice (i.e. `conda create --name my_new_env`)
 - Activate you new environment (i.e. `conda activate my_new_env`)
-- Install dev dependencies `pip install -e '.[dev]'`
+- Install dev dependencies `pip install -e '.[tests,dev]'`
 - Install pre-commit hooks `pre-commit install`
+- Run unit tests `pytest`
 
 When doing these steps above, you ensure that the code you add will be linted and formatted properly.
 

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py

@@ -78,7 +78,11 @@ def main():
         "--output",
         required=True,
         type=Path,
-        help="Output TSV file with columns: contig_id, protein_id, UniRef90 cluster, rhea_ids, CHEBI reaction participants",
+        help=(
+            "Output TSV file with columns: contig_id, protein_id, protein hash, "
+            "Rhea IDs, CHEBI reaction, reaction definition, 'top hit' if it is "
+            "the first hit for the protein"
+        ),
     )
     parser.add_argument(
         "-p",

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py

@@ -40,10 +40,12 @@ def import_nodes(nodes_dmp):
     taxid2rank = {}
 
     with open(nodes_dmp) as f1:
-        reader = csv.reader(f1, delimiter="\t")
-        for line in reader:
-            taxid = line[0]
-            rank = line[4]
+        for line in f1:
+            fields = [part.strip() for part in line.split("|")]
+            if len(fields) != 14:
+                raise ValueError(f"Unexpected number of columns in line: {line}")
+            taxid = fields[0]
+            rank = fields[2]
             taxid2rank[taxid] = rank
 
     return taxid2rank
@@ -54,11 +56,13 @@ def import_names(names_dmp):
     taxid2name = {}
 
     with open(names_dmp, newline="") as f1:
-        reader = csv.reader(f1, delimiter="\t")
-        for line in reader:
-            if line[6] == "scientific name":
-                taxid = line[0]
-                name = line[2]
+        for line in f1:
+            fields = [part.strip() for part in line.split("|")]
+            if len(fields) != 5:
+                raise ValueError(f"Unexpected number of columns in line: {line}")
+            if fields[3] == "scientific name":
+                taxid = fields[0]
+                name = fields[1]
                 taxid2name[taxid] = name
 
     return taxid2name

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/mgnify_pipelines_toolkit/analysis/shared/get_subunits.py

@@ -108,7 +108,7 @@ def main():
 
     open_files = {}
     for record in SeqIO.parse(args.input, "fasta"):
-        model = "-".join(record.id.split("/")[0].split("-")[-1:])
+        model = "-".join("/".join(record.id.split("/")[:-1]).split("-")[-1:])
         if model in SSU_MODELS:
             if SSU not in open_files:
                 file_out = open(pattern_dict[SSU], "w")

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.3
+Version: 1.0.4
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -11,33 +11,24 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: biopython==1.82
-Requires-Dist: numpy==1.26.0
-Requires-Dist: pandas==2.0.2
-Requires-Dist: regex==2023.12.25
-Requires-Dist: requests==2.32.3
-Requires-Dist: click==8.1.7
-Requires-Dist: pandera==0.22.1
-Requires-Dist: pyfastx>=2.2.0
-Requires-Dist: intervaltree==3.1.0
+Requires-Dist: biopython>=1.85
+Requires-Dist: numpy<3,>=2.2.4
+Requires-Dist: pandas<3,>=2.2.3
+Requires-Dist: regex>=2024.11.6
+Requires-Dist: requests<3,>=2.32.3
+Requires-Dist: click<9,>=8.1.8
+Requires-Dist: pandera<0.24,>=0.23.1
+Requires-Dist: pyfastx<3,>=2.2.0
+Requires-Dist: intervaltree<4,>=3.1.0
 Provides-Extra: tests
-Requires-Dist: pytest==7.4.0; extra == "tests"
-Requires-Dist: pytest-md==0.2.0; extra == "tests"
-Requires-Dist: pytest-workflow==2.0.1; extra == "tests"
-Requires-Dist: biopython==1.82; extra == "tests"
-Requires-Dist: pandas==2.0.2; extra == "tests"
-Requires-Dist: numpy==1.26.0; extra == "tests"
-Requires-Dist: regex==2023.12.25; extra == "tests"
-Requires-Dist: requests==2.32.3; extra == "tests"
-Requires-Dist: click==8.1.7; extra == "tests"
-Requires-Dist: pandera==0.22.1; extra == "tests"
-Requires-Dist: pyfastx>=2.2.0; extra == "tests"
+Requires-Dist: pytest<9,>=8.3.5; extra == "tests"
+Requires-Dist: pytest-md>=0.2.0; extra == "tests"
+Requires-Dist: pytest-workflow==2.1.0; extra == "tests"
 Provides-Extra: dev
-Requires-Dist: mgnify_pipelines_toolkit[tests]; extra == "dev"
-Requires-Dist: pre-commit==3.8.0; extra == "dev"
-Requires-Dist: black==24.8.0; extra == "dev"
-Requires-Dist: flake8==7.1.1; extra == "dev"
-Requires-Dist: pep8-naming==0.14.1; extra == "dev"
+Requires-Dist: pre-commit>=4.2.0; extra == "dev"
+Requires-Dist: black>=25.1.0; extra == "dev"
+Requires-Dist: flake8>=7.1.2; extra == "dev"
+Requires-Dist: pep8-naming>=0.14.1; extra == "dev"
 Dynamic: license-file
 
 # mgnify-pipelines-toolkit
@@ -74,8 +65,9 @@ Before starting any development, you should do these few steps:
 - Clone the repo if you haven't already and create a feature branch from the `dev` branch (NOT `main`).
 - Create a virtual environment with the tool of your choice (i.e. `conda create --name my_new_env`)
 - Activate you new environment (i.e. `conda activate my_new_env`)
-- Install dev dependencies `pip install -e '.[dev]'`
+- Install dev dependencies `pip install -e '.[tests,dev]'`
 - Install pre-commit hooks `pre-commit install`
+- Run unit tests `pytest`
 
 When doing these steps above, you ensure that the code you add will be linted and formatted properly.
 

mgnify_pipelines_toolkit-1.0.4/mgnify_pipelines_toolkit.egg-info/requires.txt

@@ -0,0 +1,20 @@
+biopython>=1.85
+numpy<3,>=2.2.4
+pandas<3,>=2.2.3
+regex>=2024.11.6
+requests<3,>=2.32.3
+click<9,>=8.1.8
+pandera<0.24,>=0.23.1
+pyfastx<3,>=2.2.0
+intervaltree<4,>=3.1.0
+
+[dev]
+pre-commit>=4.2.0
+black>=25.1.0
+flake8>=7.1.2
+pep8-naming>=0.14.1
+
+[tests]
+pytest<9,>=8.3.5
+pytest-md>=0.2.0
+pytest-workflow==2.1.0

{mgnify_pipelines_toolkit-1.0.3 → mgnify_pipelines_toolkit-1.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "1.0.3"
+version = "1.0.4"
 readme = "README.md"
 license = {text = "Apache Software License 2.0"}
 authors = [
@@ -16,15 +16,15 @@ classifiers = [
 ]
 
 dependencies = [
-    "biopython==1.82",
-    "numpy==1.26.0",
-    "pandas==2.0.2",
-    "regex==2023.12.25",
-    "requests==2.32.3",
-    "click==8.1.7",
-    "pandera==0.22.1",
-    "pyfastx>=2.2.0",
-    "intervaltree==3.1.0",
+    "biopython>=1.85",
+    "numpy>=2.2.4,<3",
+    "pandas>=2.2.3,<3",
+    "regex>=2024.11.6",
+    "requests>=2.32.3,<3",
+    "click>=8.1.8,<9",
+    "pandera>=0.23.1,<0.24",
+    "pyfastx>=2.2.0,<3",
+    "intervaltree>=3.1.0,<4",
 ]
 
 [build-system]
@@ -84,23 +84,14 @@ get_mpt_version = "mgnify_pipelines_toolkit.utils.get_mpt_version:main"
 
 [project.optional-dependencies]
 tests = [
-    "pytest==7.4.0",
-    "pytest-md==0.2.0",
-    "pytest-workflow==2.0.1",
-    "biopython==1.82",
-    "pandas==2.0.2",
-    "numpy==1.26.0",
-    "regex==2023.12.25",
-    "requests==2.32.3",
-    "click==8.1.7",
-    "pandera==0.22.1",
-    "pyfastx>=2.2.0"
+    "pytest>=8.3.5,<9",
+    "pytest-md>=0.2.0",
+    "pytest-workflow==2.1.0",
 ]
 
 dev = [
-    "mgnify_pipelines_toolkit[tests]",
-    "pre-commit==3.8.0",
-    "black==24.8.0",
-    "flake8==7.1.1",
-    "pep8-naming==0.14.1"
+    "pre-commit>=4.2.0",
+    "black>=25.1.0",
+    "flake8>=7.1.2",
+    "pep8-naming>=0.14.1"
 ]

mgnify_pipelines_toolkit-1.0.3/mgnify_pipelines_toolkit.egg-info/requires.txt

@@ -1,29 +0,0 @@
-biopython==1.82
-numpy==1.26.0
-pandas==2.0.2
-regex==2023.12.25
-requests==2.32.3
-click==8.1.7
-pandera==0.22.1
-pyfastx>=2.2.0
-intervaltree==3.1.0
-
-[dev]
-mgnify_pipelines_toolkit[tests]
-pre-commit==3.8.0
-black==24.8.0
-flake8==7.1.1
-pep8-naming==0.14.1
-
-[tests]
-pytest==7.4.0
-pytest-md==0.2.0
-pytest-workflow==2.0.1
-biopython==1.82
-pandas==2.0.2
-numpy==1.26.0
-regex==2023.12.25
-requests==2.32.3
-click==8.1.7
-pandera==0.22.1
-pyfastx>=2.2.0