mgnify-pipelines-toolkit 1.0.3__py3-none-any.whl → 1.0.4__py3-none-any.whl

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/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/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.dist-info → mgnify_pipelines_toolkit-1.0.4.dist-info}/METADATA

@@ -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.dist-info → mgnify_pipelines_toolkit-1.0.4.dist-info}/RECORD

@@ -12,7 +12,7 @@ mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=B
 mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=Wu4tRtuRkgd3hoeuwPl_E5ghxIW7e_1vrcvFGWv_U4A,3173
 mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=yLpzkRJXAeXRUNgz60zopEwHcdprM2UDjquE-GkrFys,1722
 mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=K6gniytuItq5WzHLi1BsaUCOdP4Zm0_ZzW2_ns7-BTI,11114
-mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=HarDM6ay0MbyDfGGjmxP8epjsXciAJHOmqe8G64gLuM,4258
+mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=NZSNY2bqs_TQyz8riDqiEFPLKcwTgzh1C7DeVHT6V8Q,4366
 mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py,sha256=wXrw1B-z4hOu5oA27Vp1WYxGP2Mk6ZY4i_T5jDZgek0,6954
 mgnify_pipelines_toolkit/analysis/assembly/combined_gene_caller_merge.py,sha256=Pq-9RSt3RCxzDMQVW1VHlHF4NtpVwCWFbg2CMkvpZZc,19089
 mgnify_pipelines_toolkit/analysis/assembly/generate_gaf.py,sha256=2T4T7aXMGPac-LZUXJF3lOUzZZF50dAKkKTSaO-4idQ,3587
@@ -20,14 +20,14 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_annotation_utils.py,sha256=IlkeP4
 mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py,sha256=8kv_6KWznOVRkeAtghLf4pxKPhAqdn36LOK4MsTz9hU,3282
 mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py,sha256=uUIo97gmzO2zzN-pYF5paIzeHWBsmmjFp7zGAhf4PKY,5021
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=eay9e3Xdc8XxnlC_4SHHjN89k-M9i_cFMc2lI_ZFxqY,5596
-mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py,sha256=1nAgfjb1pT80Q82FZ2hSkWCGVD6BoKVP4MIqsFTmQ1c,4024
+mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py,sha256=uex2T6GagtYFBIc39-Xm4SFHL06KAQ5v0_loOmY_eaw,4289
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=TPaKlYkoy37_XgYNOskWCCoXtPNku_k5ygSeK4fT1VQ,6689
 mgnify_pipelines_toolkit/analysis/genomes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py,sha256=0Ot1j4LPsEPyPbySSAh6n9s5Dilm_8_M9YQvTnQ-1PQ,4415
 mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=hggPqv9QawWAccm5tmru4VF9VnQAHF5LCXnqyLw_BWI,6727
 mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=ye0Jka6_lNn4dQGb2QG3YT46y7QK0QvyaIitIaS8JVQ,4026
-mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=j_UN3hItF7KhJrhGrSqjvZMg-ZwKAMc2sc0vHdJzjQw,4908
+mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=UrU0CpZj3pfHZWI7Uuhv2a_C0JsO8pnVErY0sWGgNdw,4920
 mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=EH5RyzesLqsonnTQbSDs7kAOV6IskS4oyqZYlex1tAY,1934
 mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=6Ck2NhwRWw66GctUtKDdPT5fwJhWFR_YOZq-Vxwoa8A,1996
 mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=7-U0DN1joVu0ifLOoDUK2Pfqy8rb1RDKT6khVg3jky0,5559
@@ -44,9 +44,9 @@ mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pnH8LUH8i2ACNvFNWyG-n-eIHZcI5
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=lgYIR1S4crURY7C7nFtgE6QMV4u4zCNsUrVkcRnsEEo,3996
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=aS9bWrC9CP7tpxoEVg6eEYt18-pmjG7fJl5Mchz4YOU,798
-mgnify_pipelines_toolkit-1.0.3.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.0.3.dist-info/METADATA,sha256=9_2fpTUZw_ers9JvGS41z9rnvasCWl_Dnh4to-pfSV0,6203
-mgnify_pipelines_toolkit-1.0.3.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
-mgnify_pipelines_toolkit-1.0.3.dist-info/entry_points.txt,sha256=QZ6vY4w3lYG8Xmll_s9SIsOpkxa5gBVEIxU3GvoCF4I,2946
-mgnify_pipelines_toolkit-1.0.3.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.0.3.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.0.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.0.4.dist-info/METADATA,sha256=Coky89dC0Xh5wHLk7fPGEOk_-fXY3GvvMMtb2dz5krc,5810
+mgnify_pipelines_toolkit-1.0.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+mgnify_pipelines_toolkit-1.0.4.dist-info/entry_points.txt,sha256=QZ6vY4w3lYG8Xmll_s9SIsOpkxa5gBVEIxU3GvoCF4I,2946
+mgnify_pipelines_toolkit-1.0.4.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.0.4.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.0.3.dist-info → mgnify_pipelines_toolkit-1.0.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.0.2)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any