🚧 apply auto fixes using "ruff check --fix"

Author: enryH

docs/source/tutorials/examples/dbg_variants_workflow.ipynb

@@ -99,7 +99,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from pathlib import Path\n",
     "\n",
     "repo_folder = Path(\"../\")\n",
     "\n",

docs/source/tutorials/examples/hybrid_workflow_with_figures.ipynb

@@ -39,7 +39,6 @@
     "import alignment as align\n",
     "import clustering as clus\n",
     "import preprocessing as prep\n",
-    "import compute_statistics as comp_stat\n",
     "\n",
     "# import model_peptide_selector as selector\n",
     "\n",
@@ -50,9 +49,7 @@
     "# import joblib\n",
     "import json\n",
     "import Bio\n",
-    "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns"
+    "import pandas as pd"
    ]
   },
   {
@@ -748,7 +745,7 @@
    "source": [
     "clus.cluster_fasta_files(input_folder=str(scaffolds_folder_out))\n",
     "\n",
-    "fasta_input = scaffolds_folder_out / f\"scaffolds.fasta\"\n",
+    "fasta_input = scaffolds_folder_out / \"scaffolds.fasta\"\n",
     "\n",
     "cluster_tsv_folder = clustering_out / run_id\n",
     "\n",

docs/source/tutorials/examples/hybrid_workflow_with_selector.ipynb

@@ -44,7 +44,6 @@
     "import alignment as align\n",
     "import clustering as clus\n",
     "import preprocessing as prep\n",
-    "import compute_statistics as comp_stat\n",
     "import model_peptide_selector as selector\n",
     "\n",
     "# import libraries\n",

src/instanexus/assembly.py

@@ -28,12 +28,11 @@
 from dataclasses import dataclass
 from itertools import combinations
 from pathlib import Path
-from typing import Any, Dict, Iterable, List, Optional, Tuple
+from typing import Dict, Iterable, List
 
 import Bio
 import networkx as nx
 import pandas as pd
-from Bio import SeqIO
 from tqdm import tqdm
 
 from . import helpers
@@ -696,7 +695,7 @@ def assemble_dbgX(self, sequences):
         return extended_contigs
 
     def assemble_fusion(self, sequences):
-        logger.info(f"[Assembler] Running FUSION (DBG weighted + greedy merge)")
+        logger.info("[Assembler] Running FUSION (DBG weighted + greedy merge)")
 
         contigs_dbg_weighted = self.assemble_dbg_weighted(sequences)
 
@@ -749,7 +748,7 @@ def main(
 
     protein_norm = None  # None means no reference mode
     if reference:
-        logger.info(f"Reference mode enabled. Loading reference protein...")
+        logger.info("Reference mode enabled. Loading reference protein...")
         if not metadata_json_path:
             raise ValueError(
                 "metadata_json_path is required when reference mode is enabled."

src/instanexus/consensus.py

@@ -35,8 +35,6 @@
 import pandas as pd
 import seaborn as sns
 from Bio import SeqIO
-from Bio.Seq import Seq
-from Bio.SeqRecord import SeqRecord
 from tqdm import tqdm
 
 logging.basicConfig(

src/instanexus/helpers.py

@@ -25,10 +25,6 @@
 from pathlib import Path
 
 # import libraries
-import numpy as np
-import pandas as pd
-import plotly.express as px
-import plotly.graph_objects as go
 
 PROJECT_ROOT = Path(__file__).resolve().parents[2]
 JSON_DIR = PROJECT_ROOT / "json"

src/instanexus/main.py

@@ -192,7 +192,7 @@ def run_pipeline(args):
     logger.info(f"All results will be saved to: {experiment_folder}")
 
     try:
-        logger.info(f"--- [Step 1/5] Running Preprocessing ---")
+        logger.info("--- [Step 1/5] Running Preprocessing ---")
         preprocessing.main(
             input_csv=args.input_csv,
             metadata_json=args.metadata_json_path,
@@ -207,7 +207,7 @@ def run_pipeline(args):
         return
 
     try:
-        logger.info(f"--- [Step 2/5] Running Assembly ---")
+        logger.info("--- [Step 2/5] Running Assembly ---")
         assembly.main(
             input_csv_path=str(cleaned_csv_path),
             output_scaffolds_path=str(scaffolds_fasta_path),
@@ -226,7 +226,7 @@ def run_pipeline(args):
         return
 
     try:
-        logger.info(f"--- [Step 3/5] Running Clustering ---")
+        logger.info("--- [Step 3/5] Running Clustering ---")
         clustering.main(
             input_scaffolds_folder=str(scaffolds_folder),  # Pass the folder
             min_seq_id=args.min_seq_id,
@@ -237,7 +237,7 @@ def run_pipeline(args):
         return
 
     try:
-        logger.info(f"--- [Step 4/5] Running Alignment ---")
+        logger.info("--- [Step 4/5] Running Alignment ---")
         alignment.main(
             input_cluster_fasta_folder=str(cluster_fasta_folder),
             output_alignment_folder=str(alignment_folder),
@@ -247,7 +247,7 @@ def run_pipeline(args):
         return
 
     try:
-        logger.info(f"--- [Step 5/5] Running Consensus ---")
+        logger.info("--- [Step 5/5] Running Consensus ---")
         consensus.main(
             input_alignment_folder=str(alignment_folder),
             output_consensus_folder=str(consensus_folder),
@@ -257,7 +257,7 @@ def run_pipeline(args):
         logger.error(f"Consensus failed: {e}")
         return
 
-    logger.info(f"--- InstaNexus Pipeline finished successfully! ---")
+    logger.info("--- InstaNexus Pipeline finished successfully! ---")
     logger.info(f"Final results in: {experiment_folder}")
 
 

src/instanexus/preprocessing.py

@@ -24,14 +24,11 @@
 import logging
 
 # import libraries
-import os
 import re
 from pathlib import Path
 
 import numpy as np
 import pandas as pd
-import plotly.express as px
-import plotly.graph_objects as go
 from Bio import SeqIO
 
 # PROJECT_ROOT = Path(__file__).resolve().parents[2]

tests/test_preprocessing.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 
-import pytest
 
 from instanexus.preprocessing import remove_modifications