debase 0.1.6__tar.gz → 0.1.7__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {debase-0.1.6 → debase-0.1.7}/PKG-INFO +1 -1
- {debase-0.1.6 → debase-0.1.7}/src/debase/_version.py +1 -1
- {debase-0.1.6 → debase-0.1.7}/src/debase/enzyme_lineage_extractor.py +6 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/PKG-INFO +1 -1
- {debase-0.1.6 → debase-0.1.7}/.gitignore +0 -0
- {debase-0.1.6 → debase-0.1.7}/CONTRIBUTING.md +0 -0
- {debase-0.1.6 → debase-0.1.7}/LICENSE +0 -0
- {debase-0.1.6 → debase-0.1.7}/MANIFEST.in +0 -0
- {debase-0.1.6 → debase-0.1.7}/README.md +0 -0
- {debase-0.1.6 → debase-0.1.7}/docs/README.md +0 -0
- {debase-0.1.6 → debase-0.1.7}/docs/examples/README.md +0 -0
- {debase-0.1.6 → debase-0.1.7}/environment.yml +0 -0
- {debase-0.1.6 → debase-0.1.7}/pyproject.toml +0 -0
- {debase-0.1.6 → debase-0.1.7}/setup.cfg +0 -0
- {debase-0.1.6 → debase-0.1.7}/setup.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/__init__.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/PIPELINE_FLOW.md +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/__init__.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/__main__.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/build_db.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/cleanup_sequence.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/lineage_format.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/reaction_info_extractor.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/substrate_scope_extractor.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase/wrapper.py +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/SOURCES.txt +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/dependency_links.txt +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/entry_points.txt +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/requires.txt +0 -0
- {debase-0.1.6 → debase-0.1.7}/src/debase.egg-info/top_level.txt +0 -0
|
@@ -1944,7 +1944,13 @@ def _merge_lineage_and_sequences(
|
|
|
1944
1944
|
df = pd.merge(df_lin, df_seq, on="variant_id", how="left")
|
|
1945
1945
|
|
|
1946
1946
|
# 2a. If we have unmatched sequences and a model, use Gemini to match them
|
|
1947
|
+
log.info(f"Model available: {model is not None}, Sequences found: {len(df_seq)}")
|
|
1947
1948
|
if model and len(df_seq) > 0:
|
|
1949
|
+
# Log initial state
|
|
1950
|
+
log.info(f"Merge attempt: {len(df_lin)} lineage entries, {len(df_seq)} sequences")
|
|
1951
|
+
log.info(f"Lineage IDs: {df_lin['variant_id'].tolist()[:5]}...")
|
|
1952
|
+
log.info(f"Sequence IDs: {df_seq['variant_id'].tolist()[:5]}...")
|
|
1953
|
+
|
|
1948
1954
|
# Find lineage entries without sequences
|
|
1949
1955
|
missing_seq = df['aa_seq'].isna() & df['dna_seq'].isna()
|
|
1950
1956
|
unmatched_lineage = df[missing_seq]['variant_id'].tolist()
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|