User guide

These pages explain the choices behind a UniVI analysis. The tutorials show them in running code.

Page	Read it when you want to
Preparing data	get your AnnData objects, features, and splits into shape
How the model works	understand encoders, fusion, the training objective, and which latent representation to use
Training and tuning	pick hyperparameters, read the training curve, fix common problems
Using a trained model	embed, predict, denoise, generate, save and reload
Evaluating an integration	measure alignment and prediction quality
Advanced features	heads, refinement, transformers, alternative objectives, scripts
FAQ	quick answers