Skip to content

Latest commit

 

History

History

scripts

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
doi_corrections
doi_corrections
 
 
doi_validation
doi_validation
 
 
enrichment
enrichment
 
 
export
export
 
 
pdf_downloads
pdf_downloads
 
 
reporting
reporting
 
 
schema
schema
 
 
README.md
README.md
 
 
TEMPLATE_generate_vXX_maxpro_design_long.py
TEMPLATE_generate_vXX_maxpro_design_long.py
 
 
add_chebi_labels_to_recommendations.py
add_chebi_labels_to_recommendations.py
 
 
add_mp_medium_mappings.py
add_mp_medium_mappings.py
 
 
analyze_euclidean_distance.py
analyze_euclidean_distance.py
 
 
analyze_mp_medium_osmotic.py
analyze_mp_medium_osmotic.py
 
 
analyze_plate_replicates.py
analyze_plate_replicates.py
 
 
analyze_response_surfaces.py
analyze_response_surfaces.py
 
 
annotate_am1_with_bakta.py
annotate_am1_with_bakta.py
 
 
archive_outputs.py
archive_outputs.py
 
 
benchmark_maxpro_performance.py
benchmark_maxpro_performance.py
 
 
build_model_cobrapy.py
build_model_cobrapy.py
 
 
calculate_growth_improvement.py
calculate_growth_improvement.py
 
 
calculate_nd_depletion_improvement.py
calculate_nd_depletion_improvement.py
 
 
cleanup_old_outputs.py
cleanup_old_outputs.py
 
 
cluster_heatmap_replicates.py
cluster_heatmap_replicates.py
 
 
compare_all_models.py
compare_all_models.py
 
 
compare_plate_vs_protocol.py
compare_plate_vs_protocol.py
 
 
compare_v7_designs.py
compare_v7_designs.py
 
 
complete_v7_random_outputs.py
complete_v7_random_outputs.py
 
 
convert_ree_xlsx_to_plates.py
convert_ree_xlsx_to_plates.py
 
 
convert_svg_to_png.py
convert_svg_to_png.py
 
 
create_full_template_model.py
create_full_template_model.py
 
 
create_minimal_working_model.py
create_minimal_working_model.py
 
 
create_proxy_model.py
create_proxy_model.py
 
 
create_test_fasta.py
create_test_fasta.py
 
 
create_v7_from_v6.py
create_v7_from_v6.py
 
 
create_v7_random_from_v7.py
create_v7_random_from_v7.py
 
 
demo_analogy_agent.py
demo_analogy_agent.py
 
 
demo_analogy_examples.py
demo_analogy_examples.py
 
 
demo_evidence_based_validation.py
demo_evidence_based_validation.py
 
 
demo_hierarchical_search.py
demo_hierarchical_search.py
 
 
demo_three_tier_validation.py
demo_three_tier_validation.py
 
 
download_genome_fasta.sh
download_genome_fasta.sh
 
 
enrich_skill_metadata.py
enrich_skill_metadata.py
 
 
enrich_skill_metadata_ast.py
enrich_skill_metadata_ast.py
 
 
expand_mp_plus_v5_recommendations.py
expand_mp_plus_v5_recommendations.py
 
 
extract_plate_sheets_to_tsv.py
extract_plate_sheets_to_tsv.py
 
 
filter_embeddings.py
filter_embeddings.py
 
 
gapfill_model.py
gapfill_model.py
 
 
gapfill_model_advanced.py
gapfill_model_advanced.py
 
 
generate_am1_lanthanide_genes.py
generate_am1_lanthanide_genes.py
 
 
generate_am1_lanthanide_genes_core.py
generate_am1_lanthanide_genes_core.py
 
 
generate_am1_lanthanide_genes_curated.py
generate_am1_lanthanide_genes_curated.py
 
 
generate_architecture_diagrams_simplified.py
generate_architecture_diagrams_simplified.py
 
 
generate_architecture_diagrams_v2.py
generate_architecture_diagrams_v2.py
 
 
generate_citrate_correction_strategies.py
generate_citrate_correction_strategies.py
 
 
generate_cofactor_table_methylobacterium.py
generate_cofactor_table_methylobacterium.py
 
 
generate_concentration_summary.py
generate_concentration_summary.py
 
 
generate_culturebotai_multi_logos.py
generate_culturebotai_multi_logos.py
 
 
generate_evidence_heatmap_baseline.py
generate_evidence_heatmap_baseline.py
 
 
generate_ingredient_cofactor_mapping.py
generate_ingredient_cofactor_mapping.py
 
 
generate_lhs_plate_design.py
generate_lhs_plate_design.py
 
 
generate_lhs_plate_design_v3_phosphate_stock.py
generate_lhs_plate_design_v3_phosphate_stock.py
 
 
generate_lhs_plate_design_v4_no_citrate.py
generate_lhs_plate_design_v4_no_citrate.py
 
 
generate_lhs_plate_design_v5_conservative.py
generate_lhs_plate_design_v5_conservative.py
 
 
generate_lhs_plate_design_v6_replicated.py
generate_lhs_plate_design_v6_replicated.py
 
 
generate_lhs_scatterplot_matrix.py
generate_lhs_scatterplot_matrix.py
 
 
generate_mp_plus_output_files.py
generate_mp_plus_output_files.py
 
 
generate_mp_plus_v10_complete.py
generate_mp_plus_v10_complete.py
 
 
generate_mp_plus_v10_with_audit.py
generate_mp_plus_v10_with_audit.py
 
 
generate_mp_plus_v11_agentic.py
generate_mp_plus_v11_agentic.py
 
 
generate_mp_plus_v12_agentic.py
generate_mp_plus_v12_agentic.py
 
 
generate_mp_plus_v2_recommendations.py
generate_mp_plus_v2_recommendations.py
 
 
generate_mp_plus_v3_recommendations.py
generate_mp_plus_v3_recommendations.py
 
 
generate_mp_plus_v5_recommendations.py
generate_mp_plus_v5_recommendations.py
 
 
generate_mp_plus_v7_recommendations.py
generate_mp_plus_v7_recommendations.py
 
 
generate_mp_plus_v9_from_prompt.py
generate_mp_plus_v9_from_prompt.py
 
 
generate_optimization_report.py
generate_optimization_report.py
 
 
generate_project_logos.py
generate_project_logos.py
 
 
generate_scatterplot_for_existing_design.py
generate_scatterplot_for_existing_design.py
 
 
generate_simple_init.py
generate_simple_init.py
 
 
generate_v10_maxpro_design_long.py
generate_v10_maxpro_design_long.py
 
 
generate_v11_maxpro_design_long.py
generate_v11_maxpro_design_long.py
 
 
generate_v12_maxpro_design_long.py
generate_v12_maxpro_design_long.py
 
 
generate_v7_maxpro_design.py
generate_v7_maxpro_design.py
 
 
generate_v7_maxpro_design_long.py
generate_v7_maxpro_design_long.py
 
 
generate_v8_maxpro_design_long.py
generate_v8_maxpro_design_long.py
 
 
generate_v9_maxpro_design_long.py
generate_v9_maxpro_design_long.py
 
 
import_am1_bakta_annotations.py
import_am1_bakta_annotations.py
 
 
import_am1_ncbi_annotations.py
import_am1_ncbi_annotations.py
 
 
init_genome_schema.py
init_genome_schema.py
 
 
init_sheet_schema.py
init_sheet_schema.py
 
 
install_carveme_docker.sh
install_carveme_docker.sh
 
 
install_gapmind.sh
install_gapmind.sh
 
 
install_grodon2.R
install_grodon2.R
 
 
investigate_hierarchical_ingredients.py
investigate_hierarchical_ingredients.py
 
 
lhs_step9_fixed.py
lhs_step9_fixed.py
 
 
load_genomes.py
load_genomes.py
 
 
load_kegg_pathways.py
load_kegg_pathways.py
 
 
load_sheets.py
load_sheets.py
 
 
migrate_provenance_schema.py
migrate_provenance_schema.py
 
 
migrate_skills.py
migrate_skills.py
 
 

README.md

Scripts Directory

Reusable utility scripts organized by function.

Directory Structure

doi_validation/

Scripts for validating DOI resolution and finding corrections:

  • validate_failed_dois.py - Check if DOIs resolve (200/403/404 status)
  • validate_new_corrections.py - Validate correction candidates before applying
  • find_correct_dois.py - Research and find correct DOI alternatives
  • generate_search_links.py - Generate search links for manual DOI lookup

doi_corrections/

Scripts for applying validated corrections to the CSV:

  • apply_doi_corrections.py - Apply validated corrections from YAML definition
  • apply_additional_corrections.py - Apply batch corrections
  • clean_invalid_dois.py - Remove or clean invalid DOIs from CSV
  • manual_doi_correction.py - Interactive tool for manual correction

pdf_downloads/

Scripts for downloading citation PDFs and abstracts:

  • download_all_pdfs_automated.py - Automated PDF download for all DOIs
  • download_all_csv_pdfs.py - Download PDFs based on CSV DOI columns
  • download_corrected_dois_pdfs.py - Download PDFs for corrected DOIs
  • retry_failed_dois_with_fallbackpdf.py - Use fallback PDF service for failed downloads
  • test_fallbackpdf_integration.py - Test fallback PDF integration
  • debug_fallbackpdf_html.py - Debug fallback PDF HTML responses

enrichment/

Scripts for enriching ingredient data:

  • enrich_ingredient_effects.py - Enrich ingredient properties with additional data
  • run_enrichment_cleaned.py - Run enrichment on cleaned CSV

schema/

Scripts for schema and CSV structure modifications:

  • add_role_columns.py - Add organism/role context columns to CSV
  • migrate_schema.py - Migrate LinkML schema to new versions

Usage

All scripts use uv for dependency management:

# Run a validation script
uv run python scripts/doi_validation/validate_failed_dois.py

# Apply corrections
uv run python scripts/doi_corrections/apply_doi_corrections.py

# Download PDFs
uv run python scripts/pdf_downloads/download_all_pdfs_automated.py

Related Files

  • Correction Definitions: ../data/corrections/
  • Results/Logs: ../data/results/
  • Documentation: ../notes/
  • Project Status: ../docs/STATUS.md