Skip to content

aesenthilvanan-coder/Celery

Repository files navigation

celery-xeno

Deep learning scaffolding for context-conditioned protein sequence generation and rule-based safety checks, as described in the Project Celery specification.

Note: The PyPI package name is celery-xeno and the CLI is celery-xeno, not celery, to avoid conflicting with the widely used Celery distributed task queue.

Install

cd "/path/to/Celery Project"
pip install -e ".[dev]"

fair-esm is a core dependency; ESM-2 weights are fetched when the encoder first loads (network required unless cached).

Commands

Build training batches from real .h5ad + FASTA, then train (config must set batches_path, or pass --batches):

python scripts/preprocess_all.py --h5ad path/to/cells.h5ad --fasta path/to/proteins.fasta \
  --cell-type keratinocyte --output data/processed/training_batches.pt
celery-xeno train --config configs/training/adversarial.yaml --batches data/processed/training_batches.pt --dry-run

Design requires a checkpoint on disk, the same scRNA matrix used for training (or one preprocessed with matching QC / HVG settings), and n_genes in the checkpoint (or --n-genes):

celery-xeno design --cell-type keratinocyte --checkpoint checkpoints/best_model.pt \
  --scrna-h5ad path/to/cells.h5ad --n-candidates 4 --output outputs/

Evaluate a protein + RNA pair:

celery-xeno evaluate --sequence MKVLWAIVLFGDWGCVGC --cell-type keratinocyte --rna GGCCUGCUGAG...

Layout

  • celery/ — library code (models, training, inference, safety)
  • configs/ — YAML configs
  • scripts/ — Python entry scripts
  • tests/ — pytest

Disclaimer

This repository is research software. It does not validate therapeutic safety, regulatory compliance, or wet-lab feasibility. Any use toward therapeutics requires independent expert review.

License

Apache-2.0 (see LICENSE).

About

A conditional generative model for designing oncogenically safe, cell-type-specific synthetic telomerase systems with multi-layer fail-safe architecture.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages