| tags: | |
| - transcriptomics | |
| - dimensionality-reduction | |
| - classical | |
| - TRACERx | |
| - UMAP | |
| - PCA | |
| license: mit | |
| # Classical Models (PCA + UMAP) - transcriptome mode - 64D | |
| Pre-trained PCA and UMAP models for transcriptomic data compression. | |
| **UMAP models support transform()** - new data can be projected into the same embedding space. | |
| ## Details | |
| - **Mode**: transcriptome-centric compression | |
| - **Dimensions**: 64 | |
| - **Training data**: TRACERx lung cancer transcriptomics | |
| - **Created**: 2026-01-13T17:03:21.452424 | |
| - **UMAP transform**: Enabled (low_memory=False) | |
| ## Usage | |
| ```python | |
| import joblib | |
| from huggingface_hub import snapshot_download | |
| # Download model | |
| local_dir = snapshot_download("jruffle/classical_transcriptome_64d") | |
| model = joblib.load(f"{local_dir}/model.joblib") | |
| # Model contains: 'pca', 'umap', 'robust_scaler', 'gene_order' | |
| # Use UMAP transform on new data: | |
| new_embeddings = model['umap'].transform(preprocessed_new_data) | |
| ``` | |