examples/downstream/README.md

Downstream Examples

This folder now contains both ready-to-run examples and legacy scripts from the original GeneMamba project.

Ready-to-run scripts

• 10_finetune_classification.py
  Fine-tune AutoModelForSequenceClassification for cell-type annotation.

• 11_zero_shot_logreg.py
  Freeze GeneMamba, extract pooled_embedding, train LogisticRegression on train split, evaluate on test split.

• 12_batch_integration_eval.py
  Batch integration proxy evaluation using silhouette score by obs['batch'].

Reference training scripts

• 20_continue_pretraining_reference.py
• 21_pretrain_from_scratch_reference.py

Legacy scripts from original repo

• legacy_from_gene_mamba/mamba2_classification_finetune_with_label.py
• legacy_from_gene_mamba/mamba2_classification_finetune_without_label.py
• legacy_from_gene_mamba/mamba2_classification_finetune_without_label_zero_shot.py

Required h5ad conventions

For downstream compatibility, standardize columns in adata.obs:

• celltype for label
• batch for batch id
• partition in {train, test} for train/test split

This matches conventions described in the original dataset/downstream/README.md.