Tutorials

Getting Started

The A minimal CPP analysis notebook is the shortest complete loop — load a dataset, run CPP, read out the signature — and pairs with the Prediction tasks concept page. For a fuller introduction, explore our Quick start and Slow start tutorials, both offering the same examples with the latter explaining the conceptual background. The Plotting Prelude tutorial can help you to create publication-ready plots.

• A minimal CPP analysis
• Quick start with AAanalysis
• Slow start with AAanalysis

Data Handling

Learn how to load protein benchmarking datasets and amino acid scale sets in the Data Loader and Scale Loader tutorials.

• Data loading
• Scale loading

Feature Engineering

Explore interpretable feature engineering, the core of AAanalysis, with the AAclust, SequenceFeature, and CPP tutorials, then see how CPP turns different data representations (scales, embeddings, structure) into features. Because SequenceFeature.feature_matrix returns a plain numeric matrix, these features drop directly into a stock scikit-learn Pipeline — the prediction protocol demonstrates this end to end.

• AAclust: Selecting redundancy-reduced scale sets
• SequenceFeature: Creation of CPP feature components
• CPP: Identification of physicochemical signatures
• CPP across data representations: sequence, structure, embeddings, annotation

PU Learning

Start positive-Unlabeled (PU) learning to tackle unbalanced and small data through our dPULearn tutorial.

• dPULearn: Learning from unbalanced data

Explainable AI

Explaining sample level predictions at single-residue resolution is introduced in our ShapModel tutorial.

• ShapModel: Explaining with single-residue resolution