Fix GitHub Actions

.github/workflows/build.yaml

@@ -47,16 +47,15 @@ jobs:
         uses: actions/checkout@v3
       - name: Setup conda
         id: setup_conda
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
-          python-version: 3.9
-          miniforge-variant: Mambaforge-pypy3
           channels: umccr,bioconda,conda-forge,defaults
           channel-priority: true
+          python-version: 3.9
       - name: Prepare env
         id: prepare_env
         run: |
-          mamba install boa anaconda-client bump2version
+          conda install bump2version conda-build anaconda-client
       # When on development branch (inferred from bump_version value), append '-dev' to package name and set
       # commit-specific version
       - name: Set package name and version
@@ -69,7 +68,7 @@ jobs:
             --no-commit
       - name: Build and upload conda package
         run: |
-          conda mambabuild \
+          conda build \
             --token "${{ secrets.ANACONDA_TOKEN }}" \
             conda/bactabolize/
 

.github/workflows/lint.yaml

@@ -9,10 +9,8 @@ jobs:
         shell: bash -l {0}
     steps:
       - uses: actions/checkout@v2
-      - uses: conda-incubator/setup-miniconda@v2
+      - uses: conda-incubator/setup-miniconda@v3
         with:
-          python-version: 3.9
-          miniforge-variant: Mambaforge-pypy3
           environment-file: requirements-dev.yaml
       - name: execute_precommit_hooks
         run: |

.github/workflows/test.yaml

@@ -9,10 +9,8 @@ jobs:
         shell: bash -l {0}
     steps:
       - uses: actions/checkout@v2
-      - uses: conda-incubator/setup-miniconda@v2
+      - uses: conda-incubator/setup-miniconda@v3
         with:
-          python-version: 3.9
-          miniforge-variant: Mambaforge-pypy3
           environment-file: requirements-dev.yaml
       - name: prepare_environment
         run: |

.mdlrc

@@ -1,2 +1,2 @@
-rules "~MD024"
+rules "~MD024,~MD036"
 style "#{File.dirname(__FILE__)}/.mdl_style.rb"

.pylintrc

@@ -1,5 +1,5 @@
 [MESSAGE CONTROL]
-disable=logging-fstring-interpolation,duplicate-code,missing-module-docstring,use-dict-literal,use-list-literal,invalid-name,too-many-locals,too-few-public-methods,unspecified-encoding,missing-function-docstring,consider-using-f-string,missing-class-docstring,subprocess-run-check,too-many-arguments
+disable=logging-fstring-interpolation,duplicate-code,missing-module-docstring,use-dict-literal,use-list-literal,invalid-name,too-many-locals,too-few-public-methods,unspecified-encoding,missing-function-docstring,consider-using-f-string,missing-class-docstring,subprocess-run-check,too-many-arguments,import-error
 
 [FORMAT]
 max-line-length=120

README.md

@@ -3,11 +3,13 @@
 A high-throughput genome-scale metabolic reconstruction and growth simulation pipeline.
 
 ## How to run
+
 **Install and quick start [here](https://github.com/kelwyres/Bactabolize/wiki/1.-Quick-start)**
 
 **Visit the [wiki](https://github.com/kelwyres/Bactabolize/wiki) to find out more!**
 
 ## Description
+
 Bactabolize is designed for rapid generation of strain-specific metabolic reconstructions from bacterial genome data
 using the approach described in [Norsigian et al. Nature Protocols
 2020](https://www.nature.com/articles/s41596-019-0254-3). It leverages the [COBRApy
@@ -29,8 +31,7 @@ can be performed under a variety of growth conditions and mediums.
 Bactabolize is freely available under a [GNU General Public License v3.0](https://www.gnu.org/licenses/gpl-3.0.en.html).
 Please cite the following papers if you make use of Bactabolize:
 
-* Vezina B. / Watts S.C. et al. 'Bactabolize: A tool for high-throughput generation of bacterial strain-specific metabolic models'. eLife (2023). 
-  [https://doi.org/10.7554/eLife.87406.3](https://doi.org/10.7554/eLife.87406.3)
+* Vezina B. / Watts S.C. et al. 'Bactabolize: A tool for high-throughput generation of bacterial strain-specific
+  metabolic models'. eLife (2023).  [https://doi.org/10.7554/eLife.87406.3](https://doi.org/10.7554/eLife.87406.3)
 * Ebrahim, A., Lerman, J.A., Palsson, B.O. et al. 'COBRApy: COnstraints-Based Reconstruction and Analysis for Python'. BMC
   Syst Biol 7, 74 (2013). <https://doi.org/10.1186/1752-0509-7-74>
-

bactabolize/alignment.py

@@ -38,6 +38,7 @@ def __str__(self):
 
 
 def run_blastp(query_fp, subject_fp):
+    # pylint: disable=no-else-return
     # Create a database
     create_blast_database(subject_fp, 'prot')
     # Run alignment
@@ -51,6 +52,7 @@ def run_blastp(query_fp, subject_fp):
 
 
 def run_blastn(query_fp, subject_fp):
+    # pylint: disable=no-else-return
     # Create database
     create_blast_database(subject_fp, 'nucl')
     # Run alignment

bactabolize/annotate.py

@@ -33,6 +33,8 @@ def run(assembly_fp, output_fp):
     elif assembly_filetype == 'fasta':
         assembly_genbank_fp = None
         assembly_fasta_fp = assembly_fp
+    else:
+        assert False
     print('========================================')
     prodigal_data = run_prodigal(assembly_fasta_fp)
     prodigal_orfs = parse_prodigal_output(prodigal_data)
@@ -114,6 +116,7 @@ def get_qual_note(partial_str):
 
 
 def match_existing_orfs_updated_annotations(new_fp, existing_fp, overlap_min=0.80):
+    # pylint: disable=too-many-branches
     # Get features and create list of start and end objects for each
     features_new = collect_all_features(new_fp)
     features_existing = collect_all_features(existing_fp)
@@ -126,17 +129,17 @@ def match_existing_orfs_updated_annotations(new_fp, existing_fp, overlap_min=0.8
         # Find overlaps
         positions = contig_positions_new[contig] + contig_positions_existing[contig]
         features_matched = discover_overlaps(positions, overlap_min)
-        
+
         # Discover those not matched using location comparison
         features_matched_new = [f[0] for f in features_matched]
         features_matched_existing = [f[1] for f in features_matched]
-        
+
         # Find unmatched features by comparing locations
         new_unmatched = []
         for feature in features_new[contig]:
             if not any(f.location == feature.location for f in features_matched_new):
                 new_unmatched.append(feature)
-                
+
         existing_unmatched = []
         for feature in features_existing[contig]:
             if not any(f.location == feature.location for f in features_matched_existing):
@@ -151,7 +154,7 @@ def match_existing_orfs_updated_annotations(new_fp, existing_fp, overlap_min=0.8
                     continue
                 feature_new.qualifiers[qual] = feature_existing.qualifiers[qual]
             features_updated.append(feature_new)
-            
+
         # Add existing ORFs that had no match
         features_updated.extend(new_unmatched)
         features_updated.extend(existing_unmatched)
@@ -163,7 +166,7 @@ def match_existing_orfs_updated_annotations(new_fp, existing_fp, overlap_min=0.8
         print(f'\t{len(existing_unmatched)} existing features unmatched')
         print(f'\t{len(new_unmatched)} re-annotated features unmatched')
         print(f'\t{len(features_updated)} total features')
-        
+
     # Update new genbank with new feature set
     update_genbank_annotations(new_fp, contig_features_updated)
 
@@ -214,7 +217,7 @@ def discover_overlaps(positions, overlap_min):
                     continue
                 # Check if this pair is already matched by comparing locations
                 already_matched = any(
-                    fn.location == feature_new.location and fe.location == feature_existing.location 
+                    fn.location == feature_new.location and fe.location == feature_existing.location
                     for fn, fe in features_matched
                 )
                 if already_matched:

bactabolize/draft_model.py

@@ -56,13 +56,13 @@ def run(config):
         original_genes.append(gene.id)
     model_draft.notes['Original_Genes'] = original_genes
 
-    # Same gene dictionary of reference model and genome annotations to csv 
+    # Same gene dictionary of reference model and genome annotations to csv
     gene_dict_fp = config.output_fp.parent / f'{config.output_fp.stem}_gene_dictionary.csv'
     with open(gene_dict_fp, 'w') as csv_file:
         writer = csv.writer(csv_file)
         for key, value in isolate_orthologs.items():
             writer.writerow([key, value])
-            
+
     # Mutate a copy of the model and rename genes
     cobra.manipulation.modify.rename_genes(model_draft, isolate_orthologs)
 

bactabolize/model_fba.py

@@ -21,6 +21,9 @@ def run(config):
             model = cobra.io.load_json_model(fh)
         elif config.model_fp.suffix == '.xml':
             model = read_sbml_model(fh)
+        else:
+            assert False
+
     if config.fba_spec_fp:
         spec = parse_spec(config.fba_spec_fp)
     elif config.fba_spec_name:

bactabolize/patch_model.py

@@ -20,12 +20,16 @@ def run(config):
             model_draft = cobra.io.load_json_model(fh)
         elif config.draft_model_fp.suffix == '.xml':
             model_draft = read_sbml_model(fh)
+        else:
+            assert False
 
     with config.ref_model_fp.open('r') as fh:
         if config.ref_model_fp.suffix == '.json':
             model_ref = cobra.io.load_json_model(fh)
         elif config.ref_model_fp.suffix == '.xml':
             model_ref = read_sbml_model(fh)
+        else:
+            assert False
 
     patch = parse_patch(config.patch_fp, model_draft.id)
     # Apply patch