Welcome to the QBioCode tutorials! These Jupyter notebooks provide hands-on examples demonstrating how to use various features and applications of QBioCode for quantum healthcare and life sciences applications.
Before running these tutorials, make sure you have:
- Installed QBioCode following the Installation Guide
- Set up your Python environment with all required dependencies
- Access to quantum computing resources (if running quantum algorithms)
Learn how to generate synthetic datasets for testing and benchmarking quantum machine learning algorithms.
Learn how to use QProfiler to systematically benchmark and compare quantum and classical machine learning models on artificial datasets. This tutorial demonstrates:
What You'll Learn:
- Generate artificial datasets with specific characteristics
- Configure and run QProfiler experiments via YAML configuration
- Evaluate multiple ML models (quantum and classical) automatically
- Analyze performance metrics (accuracy, F1-score, AUC)
- Visualize model comparisons and correlations
- Interpret results for model selection
Explore QSage, an intelligent meta-learning system that predicts which machine learning models will perform best on your dataset before you run them. By learning from data complexity patterns across multiple datasets, QSage provides data-driven model recommendations. This tutorial shows how to:
What You'll Learn:
- Load pre-trained QSage models
- Analyze dataset characteristics (intrinsic dimension, Fisher discriminant ratio, etc.) from compiled ML benchmark results
- Apply QSAGE to predict the model
Learn how to use quantum ensemble methods to improve classification performance by leveraging quantum superposition to evaluate multiple training set configurations simultaneously. This tutorial demonstrates two quantum ensemble approaches.
What You'll Learn:
- Generate blob datasets for binary classification
- Implement fixed swap-based quantum ensemble method
- Implement random unitary-based quantum ensemble method
- Use quantum SWAP test for cosine similarity measurement
- Compare quantum ensemble with classical baselines (Random Forest, XGBoost)
- Evaluate performance using accuracy and Brier score metrics
- Understand quantum superposition for ensemble learning
Key Concepts:
- Quantum ensemble learning via superposition
- SWAP test for quantum state comparison
- Controlled-SWAP operations for deterministic data rearrangement
- Haar-random unitaries for general mixing
- One-hot encoding for quantum state preparation
- Quantum advantage in ensemble methods
Methods:
- Swap Method: Uses fixed controlled-SWAP operations to create deterministic permutations of training data
- Random Unitary Method: Applies Haar-random unitary transformations for more general data mixing
References:
- Macaluso et al. (2023) - "A variational algorithm for quantum neural networks"
- Rhrissorrakrai et al. (2025) - "Quantum Ensemble Learning" (arXiv:2506.02213)
Learn about Quantum Projection Learning (QPL), a technique that combines quantum feature maps with multiple classical machine learning algorithms. This comprehensive tutorial demonstrates how to systematically evaluate quantum-enhanced features across different learners.
What You'll Learn:
- Generate synthetic datasets with controlled complexity
- Apply quantum feature maps to create quantum projections
- Train multiple classical models (SVC, RF, XGBoost, MLP, LR) on quantum features
- Compare quantum-enhanced vs. classical baseline performance
- Visualize and analyze comprehensive performance metrics
- Use QProfiler for automated QPL experiments
Key Concepts:
- Quantum projection methods and expectation value measurements
- Ensemble learning with quantum features
- Data complexity analysis for quantum advantage prediction
- Systematic model comparison and evaluation
- Integration with classical ML pipelines
Workflow:
- Generate or load classification datasets
- Configure QPL experiments via YAML files
- Apply quantum feature maps (ZZ, Pauli, etc.)
- Extract quantum projections from circuits
- Train 5+ classical models on quantum features
- Compare with classical baselines
- Analyze results and identify quantum advantages
Learn how to apply Projected Quantum Kernels (PQK) to real-world cancer genomics data for survival prediction. This advanced tutorial demonstrates quantum-enhanced machine learning on multi-omics ovarian cancer data from the Multi-Omics Cancer Benchmark (TCGA preprocessed data).
What You'll Learn:
- Automatically download and process multi-omics cancer data
- Create 3-year survival labels from clinical data
- Apply quantum feature maps to high-dimensional genomics data
- Use PQK to create quantum feature representations
- Compare quantum-enhanced vs. classical SVM performance
- Work with multi-omics data (miRNA, methylation, gene expression)
- Perform comprehensive hyperparameter tuning for quantum kernels
- Evaluate quantum performance on real biomedical datasets
Dataset:
- Ovarian cancer (OV) multi-omics data from Multi-Omics Cancer Benchmark
- TCGA preprocessed data with automatic download
- 3-year survival prediction task
- Four data modalities: miRNA, DNA methylation, gene expression, and integrated
Key Techniques:
- Automated data download and preprocessing pipeline
- Patient ID standardization across multi-omics datasets
- Survival label creation from clinical data
- Quantum kernel methods with ZZ feature maps
- Pairwise qubit entanglement strategies
- PCA dimensionality reduction for quantum encoding
- Stratified cross-validation for robust evaluation
- API Documentation - Detailed API reference
- QProfiler App - Standalone profiling application
- QSage App - Feature selection application
- GitHub Repository - Source code and examples
If you encounter any issues or have questions about the tutorials:
- Check the GitHub Issues
- Review the Contributing Guide
- Consult the API documentation for detailed function references