jruffle/classical_transcriptome_16d

Classical Models (PCA + UMAP) - transcriptome mode - 16D

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: 16
• Training data: TRACERx lung cancer transcriptomics
• Created: 2026-01-13T12:08:46.201545
• UMAP transform: Enabled (low_memory=False)

Usage

import joblib
from huggingface_hub import snapshot_download

# Download model
local_dir = snapshot_download("jruffle/classical_transcriptome_16d")
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)