Merge pull request #1 from TsumaR/vclean_for_rev1

vClean update to v0.2.1
TsumaR · Oct 14, 2024 · 275ba73 · 275ba73
2 parents 65561e4 + f484706
commit 275ba73
Show file tree

Hide file tree

Showing 15 changed files with 7 additions and 27 deletions.
diff --git a/MANIFEST.in b/MANIFEST.in
diff --git a/environment.yml b/environment.yml
diff --git a/pyproject.toml b/pyproject.toml
@@ -28,5 +28,5 @@ Source = "https://github.com/TsumaR/vclean"
 [project.scripts]
 vclean = "vclean.cli:cli"
 
-[tool.setuptools.package-data]
-"vclean" = ["db/*.txt", "models/*.txt"]
+[tool.flit.sdist]
+include = ["vclean/**", "db/**", "models/**", "LICENSE", "README.md"]
diff --git a/vclean/__init__.py b/vclean/__init__.py
@@ -2,4 +2,4 @@
 vClean: Assessing the contamination of viral genomes
 """
 
-__version__ = "0.1.4"
+__version__ = "0.2.1"
diff --git a/vclean/db/__init__.py b/vclean/db/__init__.py
diff --git a/db/single_pfam.txt → vclean/db/single_pfam.txt b/db/single_pfam.txt → vclean/db/single_pfam.txt
diff --git a/db/single_pfam_099.txt → vclean/db/single_pfam_099.txt b/db/single_pfam_099.txt → vclean/db/single_pfam_099.txt
diff --git a/db/unique_single_pfam.txt → vclean/db/unique_single_pfam.txt b/db/unique_single_pfam.txt → vclean/db/unique_single_pfam.txt
diff --git a/models/best_lgb_model_fold0.txt → vclean/models/best_lgb_model_fold0.txt b/models/best_lgb_model_fold0.txt → vclean/models/best_lgb_model_fold0.txt
diff --git a/models/best_lgb_model_fold1.txt → vclean/models/best_lgb_model_fold1.txt b/models/best_lgb_model_fold1.txt → vclean/models/best_lgb_model_fold1.txt
diff --git a/models/best_lgb_model_fold2.txt → vclean/models/best_lgb_model_fold2.txt b/models/best_lgb_model_fold2.txt → vclean/models/best_lgb_model_fold2.txt
diff --git a/models/best_lgb_model_fold3.txt → vclean/models/best_lgb_model_fold3.txt b/models/best_lgb_model_fold3.txt → vclean/models/best_lgb_model_fold3.txt
diff --git a/models/best_lgb_model_fold4.txt → vclean/models/best_lgb_model_fold4.txt b/models/best_lgb_model_fold4.txt → vclean/models/best_lgb_model_fold4.txt
diff --git a/models/best_lgb_model_v1.3.2.pickle → vclean/models/best_lgb_model_v1.3.2.pickle b/models/best_lgb_model_v1.3.2.pickle → vclean/models/best_lgb_model_v1.3.2.pickle
diff --git a/vclean/modules/run_for_cli.py b/vclean/modules/run_for_cli.py
@@ -34,7 +34,7 @@
 def process_file(input_fasta, outdir, run_mode, tmpout, cpu, checkv_db_dir, pfam_db,
                 input_protein, input_gene, trans_table, single_like_pfam):
     gene_set_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-    single_like_pfam = os.path.join(gene_set_dir, 'db', 'single_pfam_099.txt')
+    single_like_pfam = os.path.join(gene_set_dir, 'vclean','db', 'single_pfam_099.txt')
 
     fasta_file_name = os.path.basename(input_fasta)
     basename = os.path.splitext(fasta_file_name)[0]
@@ -252,7 +252,7 @@ def main(args):
     checkv_db_dir, pfam_db = path_to_db(db_dir)
 
     gene_set_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-    single_like_pfam = os.path.join(gene_set_dir, 'db', 'single_pfam_099.txt')
+    single_like_pfam = os.path.join(gene_set_dir, 'vclean','db', 'single_pfam_099.txt')
 
     # --------------------------------------------------------------------------
     # sp.run(['mkdir', '-p', tmpout])
@@ -285,12 +285,12 @@ def main(args):
 
         script_dir = os.path.dirname(os.path.abspath(__file__))
         model_dir = os.path.dirname(os.path.dirname(script_dir))
-        model_path = os.path.join(model_dir, 'models', 'best_lgb_model_v1.3.2.pickle')
+        model_path = os.path.join(model_dir, 'vclean', 'models', 'best_lgb_model_v1.3.2.pickle')
 
         y_pred_proba_list = []
         for i in range(5):
             model_name = f'best_lgb_model_fold{i}.txt'
-            model_path = os.path.join(model_dir, 'models', model_name)
+            model_path = os.path.join(model_dir, 'vclean', 'models', model_name)
             loaded_model = lgb.Booster(model_file=model_path)
             y_pred_proba = loaded_model.predict(result_for_input)
             y_pred_proba_list.append(y_pred_proba)