Mercurial > repos > tduigou > sculpt_sequences
changeset 1:ab59c68b6985 draft default tip
planemo upload for repository https://github.com/Edinburgh-Genome-Foundry/Examples/blob/master/templates/template1.ipynb commit db4ac861e1d03fcdfe94321d858839124e493930-dirty
| author | tduigou |
|---|---|
| date | Wed, 23 Jul 2025 09:47:44 +0000 |
| parents | a05746a5560f |
| children | |
| files | sculpt_sequences.py sculpt_sequences.xml test-data/test_json_workflow2.json |
| diffstat | 3 files changed, 268 insertions(+), 116 deletions(-) [+] |
line wrap: on
line diff
--- a/sculpt_sequences.py Wed Jun 11 09:39:02 2025 +0000 +++ b/sculpt_sequences.py Wed Jul 23 09:47:44 2025 +0000 @@ -1,11 +1,24 @@ import argparse +import json +import sys import os +import re import dnacauldron import dnachisel from Bio import SeqIO import proglog +def smart_number(val): + try: + float_val = float(val) + if float_val.is_integer(): + return int(float_val) + else: + return float_val + except ValueError: + raise ValueError(f"Invalid number: {val}") + def sculpt_sequances(files_to_sculpt, file_name_mapping, outdir_scul, outdir_unscul, use_file_names_as_id, avoid_patterns, enforce_gc_content, DnaOptimizationProblemClass, @@ -21,33 +34,63 @@ constraint_list = [] + # avoid_patterns pearsing for pattern in avoid_patterns: constraint_list.append(dnachisel.AvoidPattern(pattern)) print(f"AvoidPattern constraint: {pattern}") + # gc_constraints pearsing for constraint in enforce_gc_content: - try: - mini, maxi, window = map(float, constraint.split(';')) - constraint_list.append(dnachisel.EnforceGCContent(mini=mini, maxi=maxi, window=int(window))) - print(f"GC constraint: mini={mini}, maxi={maxi}, window={window}") - except ValueError: - print(f"Skipping invalid GC constraint: {constraint}") + constraints = [c.strip() for c in constraint.split(' ') if c.strip()] + for line in constraints: + if not line: + continue + print(f"GC constraint: {line}") + + try: + pairs = [kv.strip() for kv in line.split(',')] + params = {} + for pair in pairs: + key, val = pair.split('=') + key = key.strip() + val = val.strip() + params[key] = smart_number(val) + + constraint_list.append(dnachisel.EnforceGCContent(**params)) + + except Exception as e: + print(f"Skipping invalid gc_constraints: {line} ({e})") + # hairpin_constraints pearsing for constraint in hairpin_constraints: - try: - stem_size, hairpin_window = map(int, constraint.split(';')) - constraint_list.append(dnachisel.AvoidHairpins(stem_size=stem_size, hairpin_window=hairpin_window)) - print(f"Hairpin constraint: stem_size={stem_size}, hairpin_window={hairpin_window}") - except ValueError: - print(f"Skipping invalid hairpin constraint: {constraint}") + constraints = [c.strip() for c in constraint.split(' ') if c.strip()] + for line in constraints: + if not line: + continue + print(f"Hairpin constraint: {line}") + try: + pairs = [kv.strip() for kv in line.split(',')] + params = {} + for pair in pairs: + key, val = pair.split('=') + key = key.strip() + val = val.strip() + params[key] = smart_number(val) + + constraint_list.append(dnachisel.AvoidHairpins(**params)) + + except Exception as e: + print(f"Skipping invalid hairpin_constraints: {line} ({e})") + + # k_size pearsing for k_size in kmer_size: try: constraint_list.append(dnachisel.UniquifyAllKmers(k=int(k_size))) print(f"k-mer size is: {k_size}") except ValueError: print(f"Skipping invalid k-mer size: {k_size}") - + # refine the real record name dict if isinstance(file_name_mapping, str): file_name_mapping = dict( @@ -134,16 +177,20 @@ parser.add_argument("--outdir_unscul", required=True, help="unscul file dir") parser.add_argument("--use_file_names_as_id", type=lambda x: x.lower() == 'true', default=True, help="Use file names as IDs (True/False)") - parser.add_argument("--avoid_patterns", required=True, + parser.add_argument("--avoid_patterns", required=False, help="List of patterns to avoid (comma-separated, e.g., 'BsaI_site,BsmBI_site')") - parser.add_argument("--enforce_gc_content", required=True, + parser.add_argument("--gc_constraints", required=False, help="GC content constraints as 'min;max;window' (space-separated, e.g., '0.3;0.7;100 0.1;0.3;100')") - parser.add_argument("--DnaOptimizationProblemClass", required=True, + parser.add_argument("--DnaOptimizationProblemClass", required=False, help="the class to use for DnaOptimizationProblem") - parser.add_argument("--hairpin_constraints", required=True, + parser.add_argument("--hairpin_constraints", required=False, help="Hairpin constraints as 'stem_size;window_size' (space-separated, e.g., '20;200 30;250')") - parser.add_argument("--kmer_size", required = True, + parser.add_argument("--kmer_size", required = False, help="K-mer uniqueness size (e.g., '15')") + parser.add_argument("--json_params", required=False, + help="JSON params for the tool") + parser.add_argument("--use_json_param", required=True, + help="If use JSON as param source") return parser.parse_args() @@ -151,26 +198,92 @@ def extract_constraints_from_args(args): """Extract constraints directly from the command-line arguments.""" - avoid_patterns = args.avoid_patterns.split(',') + split_pattern = r'(?:__cn__|\s{2,})' + + # 1. Avoid patterns (split by any whitespace) + avoid_patterns = re.split(split_pattern, args.avoid_patterns.strip()) if args.avoid_patterns.strip() else [] + + # 2. Hairpin constraint: one dictionary (print as string later) + hairpin_constraints = re.split(split_pattern,args.hairpin_constraints.strip()) if args.hairpin_constraints.strip() else [] - gc_constraints = [gc.strip() for gc in args.enforce_gc_content.split(' ')] + # 3. GC constraints: split by 2+ spaces or newlines + gc_constraints = re.split(split_pattern, args.gc_constraints.strip()) if args.gc_constraints.strip() else [] + + # 4. k-mer size: single value or list + kmer_size = [int(k.strip()) for k in args.kmer_size.strip().split(',') if k.strip()] if args.kmer_size.strip() else [] + + # 5. DnaOptimizationProblemClass (as string) + DnaOptimizationProblemClass = args.DnaOptimizationProblemClass if args.DnaOptimizationProblemClass else None + + return avoid_patterns, hairpin_constraints, gc_constraints, kmer_size, DnaOptimizationProblemClass + - kmer_size = [int(k) for k in args.kmer_size.split(',')] +def load_constraints_from_json(json_path): + with open(json_path, 'r') as f: + params = json.load(f) + + def split_lines(val): + if isinstance(val, str): + return [line.strip() for line in val.strip().split('\n') if line.strip()] + return val - hairpin_constraints = [hp.strip() for hp in args.hairpin_constraints.split(' ')] + avoid_patterns = split_lines(params.get("avoid_patterns", "")) + hairpin_constraints = split_lines(params.get("hairpin_constraints", "")) + gc_constraints = split_lines(params.get("gc_constraints", "")) + kmer_size = [int(k.strip()) for k in str(params.get("kmer_size", "")).split(',') if k.strip()] + DnaOptimizationProblemClass = params.get("DnaOptimizationProblemClass", None) - return avoid_patterns, gc_constraints, kmer_size, hairpin_constraints - + return { + "avoid_patterns": avoid_patterns, + "hairpin_constraints": hairpin_constraints, + "gc_constraints": gc_constraints, + "kmer_size": kmer_size, + "DnaOptimizationProblemClass": DnaOptimizationProblemClass + } if __name__ == "__main__": args = parse_command_line_args() - avoid_patterns, gc_constraints, kmer_size, hairpin_constraints = extract_constraints_from_args(args) + avoid_patterns, hairpin_constraints, gc_constraints, kmer_size, DnaOptimizationProblemClass = extract_constraints_from_args(args) + + # Check if the flag --use_json_param is present and set to true + if "--use_json_param" in sys.argv: + use_json_index = sys.argv.index("--use_json_param") + 1 + use_json = sys.argv[use_json_index].lower() == "true" + else: + use_json = False + + # Now only check --json_params if use_json is True + if use_json: + if "--json_params" in sys.argv: + json_index = sys.argv.index("--json_params") + 1 + json_file = sys.argv[json_index] + if json_file.lower() != "none": + json_constraints = load_constraints_from_json(json_file) + avoid_patterns = json_constraints["avoid_patterns"] + hairpin_constraints = json_constraints["hairpin_constraints"] + gc_constraints = json_constraints["gc_constraints"] + kmer_size = json_constraints["kmer_size"] + DnaOptimizationProblemClass = json_constraints["DnaOptimizationProblemClass"] + + params = { + "files_to_sculpt": args.files_to_sculpt, + "file_name_mapping": args.file_name_mapping, + "outdir_unscul": args.outdir_unscul, + "outdir_scul": args.outdir_scul, + "use_file_names_as_id": args.use_file_names_as_id, + "avoid_patterns": avoid_patterns, + "hairpin_constraints": hairpin_constraints, + "gc_constraints": gc_constraints, + "kmer_size": kmer_size, + "DnaOptimizationProblemClass": DnaOptimizationProblemClass + } + sculpt_sequances( args.files_to_sculpt, args.file_name_mapping, args.outdir_scul, args.outdir_unscul, args.use_file_names_as_id, avoid_patterns, - gc_constraints, args.DnaOptimizationProblemClass, + gc_constraints, DnaOptimizationProblemClass, kmer_size, hairpin_constraints )
--- a/sculpt_sequences.xml Wed Jun 11 09:39:02 2025 +0000 +++ b/sculpt_sequences.xml Wed Jul 23 09:47:44 2025 +0000 @@ -1,8 +1,8 @@ <tool id="sculpt_sequences" name="Sculpt Sequences" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09"> <description>Optimize DNA sequences</description> <macros> - <token name="@VERSION_SUFFIX@">0</token> - <token name="@TOOL_VERSION@">0.1.0</token> + <token name="@VERSION_SUFFIX@">1</token> + <token name="@TOOL_VERSION@">0.2.0</token> </macros> <requirements> <requirement type="package" version="0.1.11">flametree</requirement> @@ -18,59 +18,67 @@ <requirement type="package" version="3.1.5">dna_features_viewer</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ - #set avoid_patterns_list = [] - #for $p in $rep_avoid_pattern - #silent avoid_patterns_list.append(str($p.avoid_pattern)) - #end for - #set avoid_patterns = ','.join($avoid_patterns_list) - #set gc_constraints_list = [] - #for $gc in $adv.rep_gc_constraints - #silent gc_constraints_list.append(str($gc.gc_min) + ';' + str($gc.gc_max) + ';' + str($gc.gc_window)) - #end for - #set enforce_gc_content = ' '.join($gc_constraints_list) - #set hairpin_constraints_list = [] - #for $h in $adv.rep_avoid_hairpins - #silent hairpin_constraints_list.append(str($h.hairpin_stem_size) + ';' + str($h.hairpin_window)) - #end for - #set hairpin_constraints = ' '.join($hairpin_constraints_list) + #if str($json_use.use_json_param) == "false": + #set avoid_list = [line.strip() for line in str($avoid_patterns).strip().split('\n') if line.strip()] + #set avoid_patterns = ','.join($avoid_list) + + #set hairpin_lines = [line.strip() for line in str($json_use.hairpin_constraints).strip().split('\n') if line.strip()] + #set hairpin_constraints = '__cn__'.join($hairpin_lines) + + #set gc_lines = [line.strip() for line in str($json_use.gc_constraints).strip().split('\n') if line.strip()] + #set gc_constraints = '__cn__'.join($gc_lines) + + #set kmer_size = $json_use.kmer_size + + #else: + #set avoid_patterns = '' + #set hairpin_constraints = '' + #set gc_constraints = '' + #set kmer_size = '' + #end if + #set genbank_file_paths = ','.join([str(f) for f in $genbank_files]) #set $file_name_mapping = ",".join(["%s:%s" % (file.file_name, file.name) for file in $genbank_files]) + mkdir 'outdir_scul' && mkdir 'outdir_unscul' && python '$__tool_directory__/sculpt_sequences.py' + --use_json_param '$json_use.use_json_param' --files_to_sculpt '$genbank_file_paths' --file_name_mapping '$file_name_mapping' --outdir_scul 'outdir_scul' --outdir_unscul 'outdir_unscul' - --use_file_names_as_id '$adv.use_file_names_as_ids' + --use_file_names_as_id '$use_file_names_as_ids' --avoid_patterns '$avoid_patterns' - --enforce_gc_content '$enforce_gc_content' - --DnaOptimizationProblemClass '$DnaOptimizationProblemClass' - --kmer_size '$adv.kmer_size' + --gc_constraints '$gc_constraints' + --kmer_size '$kmer_size' --hairpin_constraints '$hairpin_constraints' + #if $json_use.use_json_param: + --json_params '$json_use.json_params' + #else: + --json_params '' + --DnaOptimizationProblemClass '$json_use.DnaOptimizationProblemClass' + #end if ]]></command> <inputs> <param name="genbank_files" type="data_collection" collection_type="list" format="genbank" label="GenBank File(s)"/> - <param name="DnaOptimizationProblemClass" type="select" label="DnaOptimizationProblem Calss" help="select the assambly class"> - <option value="DnaOptimizationProblem" selected="True">DnaOptimizationProblem</option> - <option value="CircularDnaOptimizationProblem">CircularDnaOptimizationProblem</option> - </param> - <repeat name="rep_avoid_pattern" title="Avoid Pattern Constraints"> - <param name="avoid_pattern" type="text" label="Pattern to Avoid (e.g., BsaI_site and/or 8x1mer)" /> - </repeat> - <section name="adv" title="Advanced Options" expanded="false"> - <repeat name="rep_gc_constraints" title="Enforce GC Content Constraints"> - <param name="gc_min" type="float" label="Minimum GC Content" value="0.1" optional="true"/> - <param name="gc_max" type="float" label="Maximum GC Content" value="0.9" optional="true"/> - <param name="gc_window" type="integer" label="GC Content Window Size" value="50" optional="true"/> - </repeat> - <param name="kmer_size" type="integer" label="K-mer Uniqueness Size" value="15" optional="true"/> - <repeat name="rep_avoid_hairpins" title="Avoid Hairpins"> - <param name="hairpin_stem_size" type="integer" label="Stem Size" value="20" optional="true"/> - <param name="hairpin_window" type="integer" label="Window Size" value="200" optional="true"/> - </repeat> - <param name="use_file_names_as_ids" type="boolean" checked="True" label="Use File Names As Sequence IDs" /> - </section> + <conditional name='json_use'> + <param name="use_json_param" type="boolean" checked="false" label="Use parameter from a JSON file" /> + <when value="false"> + <param name="DnaOptimizationProblemClass" type="select" label="DnaOptimizationProblem Calss" help="select the assambly class"> + <option value="DnaOptimizationProblem" selected="True">DnaOptimizationProblem</option> + <option value="CircularDnaOptimizationProblem">CircularDnaOptimizationProblem</option> + </param> + <param name="avoid_patterns" type="text" area="true" label="Avoid Pattern Constraints" help="Each pattern on a line" /> + <param name="hairpin_constraints" type="text" area="true" label="Hairpins Constraints" optional="true" help="e.g. (you can add others Hairpins Constraints on a new line): stem_size=20, hairpin_window=200"/> + <param name="gc_constraints" type="text" area="true" label="Enforce GC Content Constraints" optional="true" help="e.g. (you can add others Enforce GC Content Constraints on a new line): mini=0.3, maxi=0.7, window=100"/> + <param name="kmer_size" type="integer" label="K-mer Uniqueness Size" value="" optional="true" help="e.g.: 15"/> + </when> + <when value="true"> + <param name="json_params" type="data" format="json" optional="true" label="JSON parameters file" help="Contains tool's parameters" /> + </when> + </conditional> + <param name="use_file_names_as_ids" type="boolean" checked="True" label="Use File Names As Sequence IDs" /> </inputs> <outputs> <collection name="scul" type="list" label="scul group" > @@ -82,7 +90,7 @@ </outputs> <tests> <test> - <!-- test for DnaOptimizationProblem --> + <!-- test for DnaOptimizationProblem --> <param name="genbank_files"> <collection type="list"> <element name="p15_PuroR" value="10_emma_genbanks/p15_PuroR.gb" /> @@ -97,36 +105,26 @@ <element name="HC_Amp_ccdB" value="10_emma_genbanks/HC_Amp_ccdB.gb" /> </collection> </param> - <param name="DnaOptimizationProblemClass" value="DnaOptimizationProblem" /> - <param name="adv|use_file_names_as_ids" value="True" /> - <!-- AvoidPatterns --> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="BsaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="NotI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="XbaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="ClaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="8x1mer" /> - </repeat> - <!-- EnforceGCContent --> - <repeat name="adv|rep_gc_constraints"> - <param name="gc_min" value="0.1" /> - <param name="gc_max" value="0.9" /> - </repeat> + <conditional name="json_use"> + <param name="use_json_param" value="false" /> + <param name="DnaOptimizationProblemClass" value="DnaOptimizationProblem" /> + <!-- AvoidPatterns --> + <param name="avoid_patterns" value="BsaI_site + NotI_site + XbaI_site + ClaI_site + 8x1mer" /> + <!-- EnforceGCContent --> + <param name="gc_constraints" value="mini=0.1, maxi=0.9, window=50"/> + </conditional> + <param name="use_file_names_as_ids" value="True" /> <output_collection name="scul" count="10"> </output_collection> <output_collection name="unscul" count="10"> </output_collection> </test> <test> - <!-- test for CircularDnaOptimizationProblem --> + <!-- test for CircularDnaOptimizationProblem --> <param name="genbank_files"> <collection type="list"> <element name="p15_PuroR" value="10_emma_genbanks/p15_PuroR.gb" /> @@ -141,29 +139,48 @@ <element name="HC_Amp_ccdB" value="10_emma_genbanks/HC_Amp_ccdB.gb" /> </collection> </param> - <param name="DnaOptimizationProblemClass" value="CircularDnaOptimizationProblem" /> - <param name="adv|use_file_names_as_ids" value="True" /> - <!-- AvoidPatterns --> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="BsaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="NotI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="XbaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="ClaI_site" /> - </repeat> - <repeat name="rep_avoid_pattern"> - <param name="avoid_pattern" value="8x1mer" /> - </repeat> - <!-- EnforceGCContent --> - <repeat name="adv|rep_gc_constraints"> - <param name="gc_min" value="0.1" /> - <param name="gc_max" value="0.9" /> - </repeat> + <conditional name="json_use"> + <param name="use_json_param" value="false" /> + <param name="DnaOptimizationProblemClass" value="CircularDnaOptimizationProblem" /> + <!-- AvoidPatterns --> + <param name="avoid_patterns" value="BsaI_site + NotI_site + XbaI_site + ClaI_site + 8x1mer" /> + <!-- EnforceGCContent --> + <param name="gc_constraints" value="mini=0.1, maxi=0.9 + mini=0.3, maxi=0.7, window=50"/> + <param name="hairpin_constraints" value="stem_size=20, hairpin_window=200 + stem_size=10, hairpin_window=100"/> + </conditional> + <param name="use_file_names_as_ids" value="True" /> + <output_collection name="scul" count="10"> + </output_collection> + <output_collection name="unscul" count="10"> + </output_collection> + </test> + <test> + <!-- test json params --> + <param name="genbank_files"> + <collection type="list"> + <element name="p15_PuroR" value="10_emma_genbanks/p15_PuroR.gb" /> + <element name="p9_PuroR" value="10_emma_genbanks/p9_PuroR.gb" /> + <element name="p15_Pup9_mTagBFP2roR" value="10_emma_genbanks/p9_mTagBFP2.gb" /> + <element name="p15_p9_BSDRPuroR" value="10_emma_genbanks/p9_BSDR.gb" /> + <element name="p8_Linker1" value="10_emma_genbanks/p8_Linker1.gb" /> + <element name="p7_L7Ae-Weiss" value="10_emma_genbanks/p7_L7Ae-Weiss.gb" /> + <element name="p6_Nt-IgKLsequence" value="10_emma_genbanks/p6_Nt-IgKLsequence.gb" /> + <element name="p6_Kozak-ATG" value="10_emma_genbanks/p6_Kozak-ATG.gb" /> + <element name="p4_Kt-L7Ae-Weiss" value="10_emma_genbanks/p4_Kt-L7Ae-Weiss.gb" /> + <element name="HC_Amp_ccdB" value="10_emma_genbanks/HC_Amp_ccdB.gb" /> + </collection> + </param> + <conditional name="json_use"> + <param name="use_json_param" value="true" /> + <param name="json_params" value="test_json_workflow2.json" /> + </conditional> + <param name="use_file_names_as_ids" value="True" /> <output_collection name="scul" count="10"> </output_collection> <output_collection name="unscul" count="10"> @@ -179,14 +196,20 @@ **Parameters**: --------------- * **GenBank File(s)**: List of GenBank files to be processed. +* **Use parameter from a JSON file**: + Yes/No parameter to indicate if user want to set parameter manually or using a json file + If Yes, user should provide a JSON file contains all parameters * **DnaOptimizationProblem Class**: - "DnaOptimizationProblem": is the class to define and solve an optimization problems. Its methods implement all the solver logics. - "CircularDnaOptimizationProblem": is a variant of DnaOptimizationProblem whose optimization algorithm assumes that the sequence is circular. * **Avoid Pattern Constraints**: is a sequence design rules that can be used as constraints. It define pattern(s) to avoid during problem optimisation. This can include enzyme sites like "BsaI_site", "NotI_site", "XbaI_site"... `enzyme dict <https://github.com/biopython/biopython/blob/master/Bio/Restriction/Restriction_Dictionary.py>`_ . Custom patterns are also supported, such as "5x3mer" means "any 5 consecutive 3-nucleotide sequences — typically 5 unique 3-mers in a row. -* **Enforce GC Content Constraints**: Define acceptable GC content ranges. For example min: 0.4, max: 0.6, window: 50 represents a 40–60% GC content requirement within a 50-base window. +* **Enforce GC Content Constraints**: + Define acceptable GC content ranges. For example min: 0.4, max: 0.6, window: 50 represents a 40–60% GC content requirement within a 50-base window. + (Parameters: `EnforceGCContent_params <https://edinburgh-genome-foundry.github.io/DnaChisel/ref/builtin_specifications#enforcegccontent>`_ ) * **Avoid Hairpins**: Avoid Hairpin patterns as defined by the IDT guidelines. A hairpin is defined by a sequence segment which has a reverse complement “nearby” in a given window. + (Parameters: `AvoidHairpins_params <https://edinburgh-genome-foundry.github.io/DnaChisel/ref/builtin_specifications#avoidhairpins>`_ ). * **K-mer Uniqueness Size**: Avoid sub-sequence of length k with homologies elsewhere. * **Use File Names As Sequence IDs**: Recommended if the GenBank file names represent the fragment names. ]]></help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_json_workflow2.json Wed Jul 23 09:47:44 2025 +0000 @@ -0,0 +1,16 @@ +{ + "DnaOptimizationProblemClass":"DnaOptimizationProblem", + "avoid_patterns": "BsaI_site\nNotI_site\nXbaI_site\nClaI_site\n8x1mer", + "hairpin_constraints": "stem_size=20, hairpin_window=200\nstem_size=10, hairpin_window=100", + "gc_constraints": "mini=0.1, maxi=0.9\nmini=0.3, maxi=0.7, window=50", + "kmer_size": "15", + "assembly_plan_name": "Type2sRestrictionAssembly", + "topology": "circular", + "enzyme": "auto", + "execution": "true", + "db_uri": "postgresql://postgres:RK17@localhost:5432/test_fragments_db", + "table": "sample", + "fragment_column": "fragment", + "sequence_column": "sequence", + "annotation_column": "annotation" +} \ No newline at end of file