fix: Resolve merge conflicts by accepting local formatted/cleaned versions

Author: marcoreverenna

docs/source/tutorials/case_studies/prot_optimization_dbg.ipynb

@@ -519,7 +519,7 @@
     "        sequence_type=\"contigs\",\n",
     "        output_folder=RESULTS_DIR,\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "\n",
     "    coverage_contigs = stat_contigs.get(\"coverage\")\n",
@@ -553,7 +553,7 @@
     "        sequence_type=\"scaffolds\",\n",
     "        output_folder=RESULTS_DIR,\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "\n",
     "    coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
@@ -814,7 +814,7 @@
     "        sequence_type=\"contigs\",\n",
     "        output_folder=RESULTS_DIR,\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "    coverage_contigs = stat_contigs.get(\"coverage\")\n",
     "\n",
@@ -847,7 +847,7 @@
     "        sequence_type=\"scaffolds\",\n",
     "        output_folder=RESULTS_DIR,\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "\n",
     "    coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",

docs/source/tutorials/case_studies/prot_optimization_greedy.ipynb

@@ -508,7 +508,7 @@
     "        sequence_type=\"contigs\",\n",
     "        output_folder=\".\",\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "\n",
     "    coverage_contigs = stat_contigs.get(\"coverage\")\n",
@@ -556,7 +556,7 @@
     "        sequence_type=\"scaffolds\",\n",
     "        output_folder=\".\",\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "    coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
     "\n",
@@ -740,7 +740,7 @@
     "        sequence_type=\"contigs\",\n",
     "        output_folder=\".\",\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "    coverage_contigs = stat_contigs.get(\"coverage\")\n",
     "\n",
@@ -784,7 +784,7 @@
     "        sequence_type=\"scaffolds\",\n",
     "        output_folder=\".\",\n",
     "        reference=protein_norm,\n",
-    "        **params\n",
+    "        **params,\n",
     "    )\n",
     "    coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
     "\n",

docs/source/tutorials/examples/dbg_variants_workflow.ipynb

@@ -48,7 +48,7 @@
    "outputs": [],
    "source": [
     "# read a pre cleaned data file\n",
-    "#data = pd.read_csv(\"../outputs/bsa/comb_dbg_c0.9_ks7_ts12_mo3/cleaned/cleaned_data.csv\")"
+    "# data = pd.read_csv(\"../outputs/bsa/comb_dbg_c0.9_ks7_ts12_mo3/cleaned/cleaned_data.csv\")"
    ]
   },
   {
@@ -62,9 +62,9 @@
     "\n",
     "import re\n",
     "\n",
-    "file_name = 'bsa'\n",
+    "file_name = \"bsa\"\n",
     "\n",
-    "data = pd.read_csv(f'../inputs/{file_name}.csv'.format(file_name=file_name))\n",
+    "data = pd.read_csv(f\"../inputs/{file_name}.csv\".format(file_name=file_name))\n",
     "\n",
     "data[\"log_probs\"] = data[\"log_probs\"].replace(-1, -10)\n",
     "\n",
@@ -103,8 +103,8 @@
     "repo_folder = Path(\"../\")\n",
     "\n",
     "filtered_psms = instanexus.preprocessing.filter_contaminants(\n",
-    "        cleaned_psms, run, repo_folder / \"fasta/contaminants.fasta\"\n",
-    "    )\n",
+    "    cleaned_psms, run, repo_folder / \"fasta/contaminants.fasta\"\n",
+    ")\n",
     "\n",
     "data = data[data[\"preds\"].isin(filtered_psms)]"
    ]
@@ -157,10 +157,10 @@
    "source": [
     "assembler = Assembler(\n",
     "    mode=\"dbg_weighted\",\n",
-    "    kmer_size=7,          \n",
-    "    size_threshold=0,    \n",
-    "    min_weight=2,         # filter low-weight edges\n",
-    "    refine_rounds=3,      # optional iterative refinement\n",
+    "    kmer_size=7,\n",
+    "    size_threshold=0,\n",
+    "    min_weight=2,  # filter low-weight edges\n",
+    "    refine_rounds=3,  # optional iterative refinement\n",
     ")"
    ]
   },
@@ -171,7 +171,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "scaffolds_dbg_w = assembler.run(sequences, output_folder=output_folder, protein_norm=None)"
+    "scaffolds_dbg_w = assembler.run(\n",
+    "    sequences, output_folder=output_folder, protein_norm=None\n",
+    ")"
    ]
   },
   {
@@ -241,7 +243,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "mapped_contigs = map.process_protein_contigs_scaffold(scaffolds_dbg_w, protein_norm, max_mismatches = 10, min_identity = 0.8)"
+    "mapped_contigs = map.process_protein_contigs_scaffold(\n",
+    "    scaffolds_dbg_w, protein_norm, max_mismatches=10, min_identity=0.8\n",
+    ")"
    ]
   },
   {
@@ -337,8 +341,8 @@
     "assembler_dbgx = Assembler(\n",
     "    mode=\"dbgX\",\n",
     "    kmer_size=7,\n",
-    "    size_threshold=10,     \n",
-    "    min_weight=2,         \n",
+    "    size_threshold=10,\n",
+    "    min_weight=2,\n",
     ")"
    ]
   },
@@ -350,9 +354,7 @@
    "outputs": [],
    "source": [
     "scaffolds_dbgx = assembler_dbgx.run(\n",
-    "    sequences=sequences,\n",
-    "    output_folder=output_folder,\n",
-    "    protein_norm=None\n",
+    "    sequences=sequences, output_folder=output_folder, protein_norm=None\n",
     ")"
    ]
   },
@@ -363,7 +365,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "mapped_scaffolds_dbgx = map.process_protein_contigs_scaffold(scaffolds_dbgx, protein_norm, max_mismatches = 10, min_identity = 0.8)"
+    "mapped_scaffolds_dbgx = map.process_protein_contigs_scaffold(\n",
+    "    scaffolds_dbgx, protein_norm, max_mismatches=10, min_identity=0.8\n",
+    ")"
    ]
   },
   {
@@ -426,7 +430,7 @@
     "    mode=\"fusion\",\n",
     "    kmer_size=7,\n",
     "    size_threshold=10,\n",
-    "    min_overlap=3,    \n",
+    "    min_overlap=3,\n",
     "    min_weight=2,\n",
     ")"
    ]
@@ -449,9 +453,7 @@
    "outputs": [],
    "source": [
     "scaffolds_fusion = assembler_fusion.run(\n",
-    "    sequences=sequences,\n",
-    "    output_folder=output_folder_fusion,\n",
-    "    protein_norm=None\n",
+    "    sequences=sequences, output_folder=output_folder_fusion, protein_norm=None\n",
     ")"
    ]
   },
@@ -462,7 +464,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "mapped_scaffolds_fusion = map.process_protein_contigs_scaffold(scaffolds_fusion, protein_norm, max_mismatches=10, min_identity=0.8)\n",
+    "mapped_scaffolds_fusion = map.process_protein_contigs_scaffold(\n",
+    "    scaffolds_fusion, protein_norm, max_mismatches=10, min_identity=0.8\n",
+    ")\n",
     "\n",
     "# top 20\n",
     "mapped_scaffolds_fusion = mapped_scaffolds_fusion[:20]"