license	cc-by-4.0
language	en
tags	parkinsons-disease target-discovery drug-repurposing bioinformatics chembl knowledge-graph stem-cell-models omics streamlit
pretty_name	Parkinson's Disease Discovery Benchmark

Parkinson's Disease Discovery Benchmark Dashboard

Reusable benchmark, knowledge graph, manuscript resource, and Streamlit dashboard for Parkinson's disease target-to-intervention discovery.

This repository integrates evidence-synthesis priority scores, target tractability, omics/pathway recurrence, ChEMBL compound activity, RDKit physicochemical heuristics, Human Protein Atlas cell-type context, iPSC/stem-cell validation mappings, and publication-ready figures.

Scientific Scope

This is a research and hypothesis-generation resource. It is not clinical decision support, not a prevention guideline, not a treatment recommendation system, and not evidence that any intervention prevents or cures Parkinson's disease.

Main Assets

• data/pd_discovery_target_benchmark.csv
• data/compound_selectivity_safety_matrix.csv
• data/validated_repurposing_candidates.csv
• data/do_not_prioritise_or_comparator_compounds.csv
• data/experimental_validation_matrix.csv
• data/omics_recurrence/pd_multi_dataset_pathway_recurrence.csv
• data/pd_discovery_benchmark_knowledge_graph.graphml
• data/benchmark_graph_nodes.csv
• data/benchmark_graph_edges.csv
• figures/benchmark_target_ranking.png
• figures/benchmark_evidence_matrix.png
• figures/compound_selectivity_safety_triage.png
• figures/benchmark_knowledge_graph.png
• dashboard/app.py
• reports/resource_manuscript_target_to_intervention_benchmark.md

Run The Dashboard

pip install -r requirements.txt
streamlit run dashboard/app.py

Validate The Repository

python scripts/04_validate_resource.py
python -m py_compile dashboard/app.py

GitHub Actions runs these checks on push and pull request.

Rebuild

The complete rebuild expects the upstream folders to sit beside this repository:

• PD_AI_Evidence_to_Discovery_Project
• PD_Target_to_Intervention_Discovery_Extension

Then run:

python scripts/01_build_benchmark.py
python scripts/02_finalize_resource_outputs.py
Rscript scripts/03_multi_dataset_omics_recurrence.R

Appropriate Reuse

• benchmark target-prioritisation and drug-repurposing algorithms;
• inspect candidate target, compound, and validation-model links;
• design iPSC-derived dopaminergic-neuron or glial co-culture experiments;
• compare knowledge-graph scoring methods;
• teach reproducible translational bioinformatics.

Citation

Use the metadata in CITATION.cff. If using the dataset mirrors, cite the corresponding Hugging Face or Kaggle landing page together with the commit or dataset version used.

Public Mirrors

• GitHub release: https://github.com/hssling/pd-discovery-benchmark-dashboard/releases/tag/v1.0.0
• GitHub Zenodo-trigger release: https://github.com/hssling/pd-discovery-benchmark-dashboard/releases/tag/v1.0.1
• Hugging Face Datasets: https://huggingface.co/datasets/hssling/pd-discovery-benchmark-dashboard
• Kaggle Datasets: https://www.kaggle.com/datasets/jkhospital/pd-discovery-benchmark