mgnify-pipelines-toolkit 1.1.2__tar.gz → 1.2.0__tar.gz

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.2
+Version: 1.2.0
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -8,7 +8,7 @@ Keywords: bioinformatics,pipelines,metagenomics
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: biopython>=1.85
@@ -20,10 +20,10 @@ 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<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: test
+Requires-Dist: pytest<9,>=8.3.5; extra == "test"
+Requires-Dist: pytest-md>=0.2.0; extra == "test"
+Requires-Dist: pytest-workflow==2.1.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: black>=25.1.0; extra == "dev"

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.0}/mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py

@@ -22,7 +22,6 @@ import pandas as pd
 
 
 def parse_args():
-
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "-i", "--input", required=True, type=str, help="Input JSON from antiSMASH"
@@ -64,7 +63,6 @@ def main():
         region_name = None
 
         for feature in record["features"]:
-
             if feature["type"] == "region":
                 # Annotate region features
                 region_name = (
@@ -129,35 +127,34 @@ def main():
             cds_by_protocluster = record["modules"][
                 "antismash.detection.hmm_detection"
             ]["rule_results"]["cds_by_protocluster"]
-            if len(cds_by_protocluster) > 0:
-                for feature in cds_by_protocluster[0][1]:
-                    if "cds_name" in feature.keys():
-                        locus_tag = feature["cds_name"]
-                        as_clusters = ",".join(
-                            list(feature["definition_domains"].keys())
+
+            if not cds_by_protocluster:
+                continue
+
+            for feature in cds_by_protocluster[0][1]:
+                if locus_tag := feature.get("cds_name"):
+                    as_clusters = ",".join(list(feature["definition_domains"].keys()))
+                    if locus_tag in attributes_dict:
+                        attributes_dict[locus_tag].update(
+                            {"as_gene_clusters": as_clusters}
                         )
-                        if locus_tag in attributes_dict.keys():
-                            attributes_dict[locus_tag].update(
-                                {"as_gene_clusters": as_clusters}
-                            )
 
         if "antismash.detection.genefunctions" in record["modules"].keys():
-            for tool in record["modules"]["antismash.detection.genefunctions"]["tools"]:
-                if tool["tool"] == "smcogs":
-                    for locus_tag in tool["best_hits"]:
-                        hit_id = tool["best_hits"][locus_tag]["hit_id"].split(":")[0]
-                        hit_desc = (
-                            tool["best_hits"][locus_tag]["hit_id"]
-                            .split(":")[1]
-                            .replace(" ", "_")
-                        )
-                        score = tool["best_hits"][locus_tag]["bitscore"]
-                        e_value = tool["best_hits"][locus_tag]["evalue"]
+            gene_function_tools = record["modules"][
+                "antismash.detection.genefunctions"
+            ]["tools"]
+            if tool_data := gene_function_tools.get("smcogs"):
+
+                for locus_tag in tool_data["best_hits"]:
+                    smcog_id = tool_data["best_hits"][locus_tag]["reference_id"]
+                    smcog_description = tool_data["best_hits"][locus_tag]["description"]
+
+                    score = tool_data["best_hits"][locus_tag]["bitscore"]
+                    e_value = tool_data["best_hits"][locus_tag]["evalue"]
 
-                        smcog_note = f"smCOG:{hit_id}:{hit_desc.replace(' ', '_')}(Score:{score}%3BE-value:{e_value})"
-                        if locus_tag in attributes_dict.keys():
-                            attributes_dict[locus_tag].update({"as_notes": smcog_note})
-                        break
+                    smcog_note = f"smCOG:{smcog_id}:{smcog_description.replace(' ', '_')}(Score:{score}%3BE-value:{e_value})"
+                    if locus_tag in attributes_dict.keys():
+                        attributes_dict[locus_tag].update({"as_notes": smcog_note})
 
     attributes = [
         ";".join(f"{k}={v}" for k, v in attrib_data.items() if v)

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.0}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.2
+Version: 1.2.0
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -8,7 +8,7 @@ Keywords: bioinformatics,pipelines,metagenomics
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: biopython>=1.85
@@ -20,10 +20,10 @@ 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<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: test
+Requires-Dist: pytest<9,>=8.3.5; extra == "test"
+Requires-Dist: pytest-md>=0.2.0; extra == "test"
+Requires-Dist: pytest-workflow==2.1.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: black>=25.1.0; extra == "dev"

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.0}/mgnify_pipelines_toolkit.egg-info/requires.txt

@@ -14,7 +14,7 @@ black>=25.1.0
 flake8>=7.1.2
 pep8-naming>=0.14.1
 
-[tests]
+[test]
 pytest<9,>=8.3.5
 pytest-md>=0.2.0
 pytest-workflow==2.1.0

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "1.1.2"
+version = "1.2.0"
 readme = "README.md"
 license = { text = "Apache Software License 2.0" }
 authors = [
@@ -8,7 +8,7 @@ authors = [
 ]
 keywords = ["bioinformatics", "pipelines", "metagenomics"]
 description = "Collection of scripts and tools for MGnify pipelines"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: Apache Software License",
@@ -89,7 +89,7 @@ fasta_to_delimited = "mgnify_pipelines_toolkit.utils.fasta_to_delimited:main"
 get_mpt_version = "mgnify_pipelines_toolkit.utils.get_mpt_version:main"
 
 [project.optional-dependencies]
-tests = [
+test = [
     "pytest>=8.3.5,<9",
     "pytest-md>=0.2.0",
     "pytest-workflow==2.1.0",