PyCascades is a demonstration project for PyCascades 2025.
The project focuses on building tools for genomic research, particularly in customizing a submission process in Python for the Gen3 platform and machine learning for predicting molecular subtypes:
- Customizing a submission process for the Gen3 Platform
- Predicting molecular subtypes using data tutorial with scikit-learn
| Python Notebook | Colab Notebook |
|---|---|
| pathway_ea.ipynb ⚡ |  |
| streamline_cancer_subtype_classification.ipynb | |
| grip_and_fhir.ipynb | |
| subtype_features.ipynb | |
| subtype_prediction_gdc_metabric.ipynb | |
If anything interests you please reach out — we love to share ideas and hear your thoughts (we also welcome PR's, forks, and issues)!
- FHIRizer: Transforming and Harmonizing GDC, Cellosaurus, and ICGC into FHIR format
- Galaxy Workflow: The Cancer Galaxy serves as a hub for tools commonly used in analysis of cancer datasets
- Cancer Data Aggregator (Docs)
- Multi-omics Cohort Building with Cancer Data Aggregator (Colab Notebook)
- TES on Azure
- nf-core: Nextflow Pipelines
- Clinical Interpretation of Variants in Cancer
- vrs-annotator: Annotates VCF Variants with VRS IDs