Upload folder using huggingface_hub

README.md

@@ -1,63 +1,35 @@
 ---
-title: Classical Methods (Transcriptome-centric, 32D)
-emoji: 📊
-colorFrom: purple
-colorTo: blue
-sdk: python
 tags:
 - transcriptomics
 - dimensionality-reduction
-- pca
-
+- classical
+- TRACERx
 license: mit
 ---
 
-# Classical Dimensionality Reduction (Transcriptome-centric, 32D)
-
-Pre-trained PCA models for transcriptomics data compression, part of the TRACERx Datathon 2025 project.
-
-## Model Details
+# CLASSICAL Model - transcriptome mode - 32D
 
-- **Methods**: PCA
-- **Compression Mode**: Transcriptome-centric
-- **Output Dimensions**: 32
-- **Training Data**: TRACERx open dataset (VST-normalized counts)
+Pre-trained classical model for transcriptomic data compression.
 
-## Contents
-
-The model file contains:
-- **PCA**: Principal Component Analysis model
-- **UMAP**: Uniform Manifold Approximation and Projection model (2-4D only)
-- **Scaler**: StandardScaler fitted on TRACERx data
-- **Feature Order**: Gene/sample order for alignment
+## Details
+- **Mode**: transcriptome-centric compression
+- **Dimensions**: 32
+- **Training data**: TRACERx lung cancer transcriptomics
+- **Created**: 2026-01-09T20:55:40.333646
 
 ## Usage
 
-These models are designed to be used with the TRACERx Datathon 2025 analysis pipeline.
-They will be automatically downloaded and cached when needed.
-
 ```python
 import joblib
+from huggingface_hub import snapshot_download
 
-# Load the model bundle
-model_data = joblib.load("model.joblib")
+# Download model
+local_dir = snapshot_download("jruffle/classical_transcriptome_32d")
+model = joblib.load(f"{local_dir}/model.joblib")
 
-# Access components
-pca = model_data['pca']
-scaler = model_data['scaler']
-gene_order = model_data.get('gene_order')  # For sample-centric
+# For classical models (PCA/UMAP):
+# model contains: 'pca', 'umap', 'robust_scaler', 'gene_order'
 
-# Transform new data
-scaled_data = scaler.transform(aligned_data)
-embeddings = pca.transform(scaled_data)
+# For TabPFN models:
+# model contains: 'tabpfn_embedding', 'pca_final', 'input_scaler', etc.
 ```
-
-## Training Details
-
-- **Input Features**: 1,051 samples
-- **Training Samples**: 20,136 genes
-- **Preprocessing**: StandardScaler normalization
-
-## Files
-
-- `model.joblib`: Model bundle containing PCA, scaler, and feature order

metadata.json

@@ -0,0 +1,16 @@
+{
+  "model_type": "classical",
+  "mode": "transcriptome",
+  "dimensions": 32,
+  "created": "2026-01-09T20:55:40.333915",
+  "keys": [
+    "robust_scaler",
+    "norm_params",
+    "pca",
+    "preprocessing_method",
+    "preprocessing_quantile_range",
+    "gene_ids",
+    "sample_order",
+    "umap"
+  ]
+}

model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5bbc85834784c5a52a4bf70335c71ca4b61eaddada562e4426c5e80da954d1
-size 498324
+oid sha256:c1481d13c98c9476963d157f2edd125a35d635839febc814de4773309aab29de
+size 351168542