Formatting and linting

docs/source/conf.py

@@ -6,23 +6,22 @@
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
-project = 'InstaNexus'
-copyright = '2025, Marco Reverenna'
-author = 'Marco Reverenna'
-release = '0.2.0'
+project = "InstaNexus"
+copyright = "2025, Marco Reverenna"
+author = "Marco Reverenna"
+release = "0.2.0"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
 extensions = []
 
-templates_path = ['_templates']
+templates_path = ["_templates"]
 exclude_patterns = []
 
 
-
 # -- Options for HTML output -------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
-html_theme = 'alabaster'
-html_static_path = ['_static']
+html_theme = "alabaster"
+html_static_path = ["_static"]

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",
@@ -99,13 +99,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from pathlib import Path\n",
     "\n",
     "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)]"
    ]
@@ -158,10 +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",
     ")"
    ]
   },
@@ -172,7 +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",
+    ")"
    ]
   },
   {
@@ -242,7 +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",
+    ")"
    ]
   },
   {
@@ -338,8 +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",
     ")"
    ]
   },
@@ -351,9 +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",
     ")"
    ]
   },
@@ -364,7 +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",
+    ")"
    ]
   },
   {
@@ -427,7 +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",
     ")"
    ]
@@ -450,9 +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",
     ")"
    ]
   },
@@ -463,7 +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]"

docs/source/tutorials/examples/hybrid_workflow_with_figures.ipynb

@@ -39,19 +39,17 @@
     "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 model_peptide_selector as selector\n",
     "\n",
     "# import libraries\n",
     "from pathlib import Path\n",
     "from Bio import SeqIO\n",
     "\n",
-    "#import joblib\n",
+    "# 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"
    ]
   },
   {
@@ -131,16 +129,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def get_combination_name(\n",
-    "    ass_method,\n",
-    "    conf,\n",
-    "    kmer_size,\n",
-    "    size_threshold,\n",
-    "    min_overlap\n",
-    "):\n",
+    "def get_combination_name(ass_method, conf, kmer_size, size_threshold, min_overlap):\n",
     "    if ass_method in (\"dbg\", \"hybrid\"):\n",
     "        return f\"comb_{ass_method}_c{conf}_ks{kmer_size}_ts{size_threshold}_mo{min_overlap}\"\n",
-    "    \n",
+    "\n",
     "    elif ass_method == \"greedy\":\n",
     "        return f\"comb_{ass_method}_c{conf}_ts{size_threshold}_mo{min_overlap}\""
    ]
@@ -186,12 +178,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "comb = get_combination_name(\n",
-    "    ass_method,\n",
-    "    conf,\n",
-    "    kmer_size,\n",
-    "    size_threshold,\n",
-    "    min_overlap)\n",
+    "comb = get_combination_name(ass_method, conf, kmer_size, size_threshold, min_overlap)\n",
     "\n",
     "print(comb)"
    ]
@@ -207,7 +194,7 @@
     "    \"ass_method\": ass_method,\n",
     "    \"conf\": conf,\n",
     "    \"size_threshold\": size_threshold,\n",
-    "    \"min_overlap\": min_overlap\n",
+    "    \"min_overlap\": min_overlap,\n",
     "}"
    ]
   },
@@ -346,7 +333,9 @@
     "    filtered_df = df[mask].copy()\n",
     "    removed_count = (~mask).sum()\n",
     "\n",
-    "    print(f\"Removed {removed_count} contaminant sequences, {len(filtered_df)} remaining.\")\n",
+    "    print(\n",
+    "        f\"Removed {removed_count} contaminant sequences, {len(filtered_df)} remaining.\"\n",
+    "    )\n",
     "    return filtered_df"
    ]
   },
@@ -492,9 +481,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "greedy_scaffolds = greedy.scaffold_iterative_greedy(assembled_contigs,\n",
-    "                                                   min_overlap,\n",
-    "                                                   size_threshold)"
+    "greedy_scaffolds = greedy.scaffold_iterative_greedy(\n",
+    "    assembled_contigs, min_overlap, size_threshold\n",
+    ")"
    ]
   },
   {
@@ -655,10 +644,12 @@
    "outputs": [],
    "source": [
     "mapped_scaffolds = map.process_protein_contigs_scaffold(\n",
-    "    all_scaffolds, protein_norm, max_mismatches = 0, min_identity = 0.90\n",
+    "    all_scaffolds, protein_norm, max_mismatches=0, min_identity=0.90\n",
     ")\n",
     "\n",
-    "map.mapping_substitutions(mapped_scaffolds, protein_norm, title= \"scaffolds mapped in RF-selected peptides\")"
+    "map.mapping_substitutions(\n",
+    "    mapped_scaffolds, protein_norm, title=\"scaffolds mapped in RF-selected peptides\"\n",
+    ")"
    ]
   },
   {
@@ -754,14 +745,14 @@
    "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",
+    "\n",
     "clus.process_fasta_and_clusters(\n",
-    "        fasta_file=str(fasta_input),\n",
-    "        input_folder=str(scaffolds_folder_out),\n",
-    "        )"
+    "    fasta_file=str(fasta_input),\n",
+    "    input_folder=str(scaffolds_folder_out),\n",
+    ")"
    ]
   },
   {
@@ -798,10 +789,10 @@
    "outputs": [],
    "source": [
     "cons.process_alignment_files(\n",
-    "        align_folder=str(alignment_out),\n",
-    "        output_folder=str(consensus_out),\n",
-    "        run_id=run_id,\n",
-    "    )"
+    "    align_folder=str(alignment_out),\n",
+    "    output_folder=str(consensus_out),\n",
+    "    run_id=run_id,\n",
+    ")"
    ]
   }
  ],