Skip to content

Commit 0779fed

Browse files
enryHenryH
committed
🎨 format all files
1 parent af0f373 commit 0779fed

File tree

6 files changed

+110
-103
lines changed

6 files changed

+110
-103
lines changed

‎docs/source/conf.py‎

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -6,23 +6,22 @@
66
# -- Project information -----------------------------------------------------
77
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
88

9-
project = 'InstaNexus'
10-
copyright = '2025, Marco Reverenna'
11-
author = 'Marco Reverenna'
12-
release = '0.2.0'
9+
project = "InstaNexus"
10+
copyright = "2025, Marco Reverenna"
11+
author = "Marco Reverenna"
12+
release = "0.2.0"
1313

1414
# -- General configuration ---------------------------------------------------
1515
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
1616

1717
extensions = []
1818

19-
templates_path = ['_templates']
19+
templates_path = ["_templates"]
2020
exclude_patterns = []
2121

2222

23-
2423
# -- Options for HTML output -------------------------------------------------
2524
# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
2625

27-
html_theme = 'alabaster'
28-
html_static_path = ['_static']
26+
html_theme = "alabaster"
27+
html_static_path = ["_static"]

‎docs/source/tutorials/case_studies/prot_optimization_dbg.ipynb‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -519,7 +519,7 @@
519519
" sequence_type=\"contigs\",\n",
520520
" output_folder=RESULTS_DIR,\n",
521521
" reference=protein_norm,\n",
522-
" **params\n",
522+
" **params,\n",
523523
" )\n",
524524
"\n",
525525
" coverage_contigs = stat_contigs.get(\"coverage\")\n",
@@ -553,7 +553,7 @@
553553
" sequence_type=\"scaffolds\",\n",
554554
" output_folder=RESULTS_DIR,\n",
555555
" reference=protein_norm,\n",
556-
" **params\n",
556+
" **params,\n",
557557
" )\n",
558558
"\n",
559559
" coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
@@ -814,7 +814,7 @@
814814
" sequence_type=\"contigs\",\n",
815815
" output_folder=RESULTS_DIR,\n",
816816
" reference=protein_norm,\n",
817-
" **params\n",
817+
" **params,\n",
818818
" )\n",
819819
" coverage_contigs = stat_contigs.get(\"coverage\")\n",
820820
"\n",
@@ -847,7 +847,7 @@
847847
" sequence_type=\"scaffolds\",\n",
848848
" output_folder=RESULTS_DIR,\n",
849849
" reference=protein_norm,\n",
850-
" **params\n",
850+
" **params,\n",
851851
" )\n",
852852
"\n",
853853
" coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",

‎docs/source/tutorials/case_studies/prot_optimization_greedy.ipynb‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -508,7 +508,7 @@
508508
" sequence_type=\"contigs\",\n",
509509
" output_folder=\".\",\n",
510510
" reference=protein_norm,\n",
511-
" **params\n",
511+
" **params,\n",
512512
" )\n",
513513
"\n",
514514
" coverage_contigs = stat_contigs.get(\"coverage\")\n",
@@ -556,7 +556,7 @@
556556
" sequence_type=\"scaffolds\",\n",
557557
" output_folder=\".\",\n",
558558
" reference=protein_norm,\n",
559-
" **params\n",
559+
" **params,\n",
560560
" )\n",
561561
" coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
562562
"\n",
@@ -740,7 +740,7 @@
740740
" sequence_type=\"contigs\",\n",
741741
" output_folder=\".\",\n",
742742
" reference=protein_norm,\n",
743-
" **params\n",
743+
" **params,\n",
744744
" )\n",
745745
" coverage_contigs = stat_contigs.get(\"coverage\")\n",
746746
"\n",
@@ -784,7 +784,7 @@
784784
" sequence_type=\"scaffolds\",\n",
785785
" output_folder=\".\",\n",
786786
" reference=protein_norm,\n",
787-
" **params\n",
787+
" **params,\n",
788788
" )\n",
789789
" coverage_scaffolds = stat_scaffolds.get(\"coverage\")\n",
790790
"\n",

‎docs/source/tutorials/examples/dbg_variants_workflow.ipynb‎

Lines changed: 26 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,7 @@
4848
"outputs": [],
4949
"source": [
5050
"# read a pre cleaned data file\n",
51-
"#data = pd.read_csv(\"../outputs/bsa/comb_dbg_c0.9_ks7_ts12_mo3/cleaned/cleaned_data.csv\")"
51+
"# data = pd.read_csv(\"../outputs/bsa/comb_dbg_c0.9_ks7_ts12_mo3/cleaned/cleaned_data.csv\")"
5252
]
5353
},
5454
{
@@ -62,9 +62,9 @@
6262
"\n",
6363
"import re\n",
6464
"\n",
65-
"file_name = 'bsa'\n",
65+
"file_name = \"bsa\"\n",
6666
"\n",
67-
"data = pd.read_csv(f'../inputs/{file_name}.csv'.format(file_name=file_name))\n",
67+
"data = pd.read_csv(f\"../inputs/{file_name}.csv\".format(file_name=file_name))\n",
6868
"\n",
6969
"data[\"log_probs\"] = data[\"log_probs\"].replace(-1, -10)\n",
7070
"\n",
@@ -104,8 +104,8 @@
104104
"repo_folder = Path(\"../\")\n",
105105
"\n",
106106
"filtered_psms = instanexus.preprocessing.filter_contaminants(\n",
107-
" cleaned_psms, run, repo_folder / \"fasta/contaminants.fasta\"\n",
108-
" )\n",
107+
" cleaned_psms, run, repo_folder / \"fasta/contaminants.fasta\"\n",
108+
")\n",
109109
"\n",
110110
"data = data[data[\"preds\"].isin(filtered_psms)]"
111111
]
@@ -158,10 +158,10 @@
158158
"source": [
159159
"assembler = Assembler(\n",
160160
" mode=\"dbg_weighted\",\n",
161-
" kmer_size=7, \n",
162-
" size_threshold=0, \n",
163-
" min_weight=2, # filter low-weight edges\n",
164-
" refine_rounds=3, # optional iterative refinement\n",
161+
" kmer_size=7,\n",
162+
" size_threshold=0,\n",
163+
" min_weight=2, # filter low-weight edges\n",
164+
" refine_rounds=3, # optional iterative refinement\n",
165165
")"
166166
]
167167
},
@@ -172,7 +172,9 @@
172172
"metadata": {},
173173
"outputs": [],
174174
"source": [
175-
"scaffolds_dbg_w = assembler.run(sequences, output_folder=output_folder, protein_norm=None)"
175+
"scaffolds_dbg_w = assembler.run(\n",
176+
" sequences, output_folder=output_folder, protein_norm=None\n",
177+
")"
176178
]
177179
},
178180
{
@@ -242,7 +244,9 @@
242244
"metadata": {},
243245
"outputs": [],
244246
"source": [
245-
"mapped_contigs = map.process_protein_contigs_scaffold(scaffolds_dbg_w, protein_norm, max_mismatches = 10, min_identity = 0.8)"
247+
"mapped_contigs = map.process_protein_contigs_scaffold(\n",
248+
" scaffolds_dbg_w, protein_norm, max_mismatches=10, min_identity=0.8\n",
249+
")"
246250
]
247251
},
248252
{
@@ -338,8 +342,8 @@
338342
"assembler_dbgx = Assembler(\n",
339343
" mode=\"dbgX\",\n",
340344
" kmer_size=7,\n",
341-
" size_threshold=10, \n",
342-
" min_weight=2, \n",
345+
" size_threshold=10,\n",
346+
" min_weight=2,\n",
343347
")"
344348
]
345349
},
@@ -351,9 +355,7 @@
351355
"outputs": [],
352356
"source": [
353357
"scaffolds_dbgx = assembler_dbgx.run(\n",
354-
" sequences=sequences,\n",
355-
" output_folder=output_folder,\n",
356-
" protein_norm=None\n",
358+
" sequences=sequences, output_folder=output_folder, protein_norm=None\n",
357359
")"
358360
]
359361
},
@@ -364,7 +366,9 @@
364366
"metadata": {},
365367
"outputs": [],
366368
"source": [
367-
"mapped_scaffolds_dbgx = map.process_protein_contigs_scaffold(scaffolds_dbgx, protein_norm, max_mismatches = 10, min_identity = 0.8)"
369+
"mapped_scaffolds_dbgx = map.process_protein_contigs_scaffold(\n",
370+
" scaffolds_dbgx, protein_norm, max_mismatches=10, min_identity=0.8\n",
371+
")"
368372
]
369373
},
370374
{
@@ -427,7 +431,7 @@
427431
" mode=\"fusion\",\n",
428432
" kmer_size=7,\n",
429433
" size_threshold=10,\n",
430-
" min_overlap=3, \n",
434+
" min_overlap=3,\n",
431435
" min_weight=2,\n",
432436
")"
433437
]
@@ -450,9 +454,7 @@
450454
"outputs": [],
451455
"source": [
452456
"scaffolds_fusion = assembler_fusion.run(\n",
453-
" sequences=sequences,\n",
454-
" output_folder=output_folder_fusion,\n",
455-
" protein_norm=None\n",
457+
" sequences=sequences, output_folder=output_folder_fusion, protein_norm=None\n",
456458
")"
457459
]
458460
},
@@ -463,7 +465,9 @@
463465
"metadata": {},
464466
"outputs": [],
465467
"source": [
466-
"mapped_scaffolds_fusion = map.process_protein_contigs_scaffold(scaffolds_fusion, protein_norm, max_mismatches=10, min_identity=0.8)\n",
468+
"mapped_scaffolds_fusion = map.process_protein_contigs_scaffold(\n",
469+
" scaffolds_fusion, protein_norm, max_mismatches=10, min_identity=0.8\n",
470+
")\n",
467471
"\n",
468472
"# top 20\n",
469473
"mapped_scaffolds_fusion = mapped_scaffolds_fusion[:20]"

‎docs/source/tutorials/examples/hybrid_workflow_with_figures.ipynb‎

Lines changed: 25 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -40,13 +40,14 @@
4040
"import clustering as clus\n",
4141
"import preprocessing as prep\n",
4242
"import compute_statistics as comp_stat\n",
43-
"#import model_peptide_selector as selector\n",
43+
"\n",
44+
"# import model_peptide_selector as selector\n",
4445
"\n",
4546
"# import libraries\n",
4647
"from pathlib import Path\n",
4748
"from Bio import SeqIO\n",
4849
"\n",
49-
"#import joblib\n",
50+
"# import joblib\n",
5051
"import json\n",
5152
"import Bio\n",
5253
"import pandas as pd\n",
@@ -131,16 +132,10 @@
131132
"metadata": {},
132133
"outputs": [],
133134
"source": [
134-
"def get_combination_name(\n",
135-
" ass_method,\n",
136-
" conf,\n",
137-
" kmer_size,\n",
138-
" size_threshold,\n",
139-
" min_overlap\n",
140-
"):\n",
135+
"def get_combination_name(ass_method, conf, kmer_size, size_threshold, min_overlap):\n",
141136
" if ass_method in (\"dbg\", \"hybrid\"):\n",
142137
" return f\"comb_{ass_method}_c{conf}_ks{kmer_size}_ts{size_threshold}_mo{min_overlap}\"\n",
143-
" \n",
138+
"\n",
144139
" elif ass_method == \"greedy\":\n",
145140
" return f\"comb_{ass_method}_c{conf}_ts{size_threshold}_mo{min_overlap}\""
146141
]
@@ -186,12 +181,7 @@
186181
"metadata": {},
187182
"outputs": [],
188183
"source": [
189-
"comb = get_combination_name(\n",
190-
" ass_method,\n",
191-
" conf,\n",
192-
" kmer_size,\n",
193-
" size_threshold,\n",
194-
" min_overlap)\n",
184+
"comb = get_combination_name(ass_method, conf, kmer_size, size_threshold, min_overlap)\n",
195185
"\n",
196186
"print(comb)"
197187
]
@@ -207,7 +197,7 @@
207197
" \"ass_method\": ass_method,\n",
208198
" \"conf\": conf,\n",
209199
" \"size_threshold\": size_threshold,\n",
210-
" \"min_overlap\": min_overlap\n",
200+
" \"min_overlap\": min_overlap,\n",
211201
"}"
212202
]
213203
},
@@ -346,7 +336,9 @@
346336
" filtered_df = df[mask].copy()\n",
347337
" removed_count = (~mask).sum()\n",
348338
"\n",
349-
" print(f\"Removed {removed_count} contaminant sequences, {len(filtered_df)} remaining.\")\n",
339+
" print(\n",
340+
" f\"Removed {removed_count} contaminant sequences, {len(filtered_df)} remaining.\"\n",
341+
" )\n",
350342
" return filtered_df"
351343
]
352344
},
@@ -492,9 +484,9 @@
492484
"metadata": {},
493485
"outputs": [],
494486
"source": [
495-
"greedy_scaffolds = greedy.scaffold_iterative_greedy(assembled_contigs,\n",
496-
" min_overlap,\n",
497-
" size_threshold)"
487+
"greedy_scaffolds = greedy.scaffold_iterative_greedy(\n",
488+
" assembled_contigs, min_overlap, size_threshold\n",
489+
")"
498490
]
499491
},
500492
{
@@ -655,10 +647,12 @@
655647
"outputs": [],
656648
"source": [
657649
"mapped_scaffolds = map.process_protein_contigs_scaffold(\n",
658-
" all_scaffolds, protein_norm, max_mismatches = 0, min_identity = 0.90\n",
650+
" all_scaffolds, protein_norm, max_mismatches=0, min_identity=0.90\n",
659651
")\n",
660652
"\n",
661-
"map.mapping_substitutions(mapped_scaffolds, protein_norm, title= \"scaffolds mapped in RF-selected peptides\")"
653+
"map.mapping_substitutions(\n",
654+
" mapped_scaffolds, protein_norm, title=\"scaffolds mapped in RF-selected peptides\"\n",
655+
")"
662656
]
663657
},
664658
{
@@ -757,11 +751,11 @@
757751
"fasta_input = scaffolds_folder_out / f\"scaffolds.fasta\"\n",
758752
"\n",
759753
"cluster_tsv_folder = clustering_out / run_id\n",
760-
" \n",
754+
"\n",
761755
"clus.process_fasta_and_clusters(\n",
762-
" fasta_file=str(fasta_input),\n",
763-
" input_folder=str(scaffolds_folder_out),\n",
764-
" )"
756+
" fasta_file=str(fasta_input),\n",
757+
" input_folder=str(scaffolds_folder_out),\n",
758+
")"
765759
]
766760
},
767761
{
@@ -798,10 +792,10 @@
798792
"outputs": [],
799793
"source": [
800794
"cons.process_alignment_files(\n",
801-
" align_folder=str(alignment_out),\n",
802-
" output_folder=str(consensus_out),\n",
803-
" run_id=run_id,\n",
804-
" )"
795+
" align_folder=str(alignment_out),\n",
796+
" output_folder=str(consensus_out),\n",
797+
" run_id=run_id,\n",
798+
")"
805799
]
806800
}
807801
],

0 commit comments

Comments
 (0)