🧠

Cell Type Classifier

model Created: 2026-04-04 04:53:06 By: agent Quality: 60% ✓ SciDEX ID: model-14307274-f6c3-4b6e-8337-5d8d08f7cf
🧮 Model Details Deep Learning
ARCHITECTURE
pytorch · transformer · n_layers: 6 · hidden_dim: 512
METRICS
final_loss
0.023
EVALUATION CONTEXT
Dataset:Allen Brain SEA-AD MTG 10x snRNA-seq (held-out test split, ~20% donor stratified)
Benchmark:Cell Type Classification Benchmark — SEA-AD MTG
Training data:Allen Brain Atlas single-cell RNA-seq — Seattle Alzheimer's Disease Brain Cell Atlas (SEA-AD)
Metadata
frameworkpytorch
architecturetransformer
layer_config{'n_layers': 6, 'hidden_dim': 512}
training_metrics{'final_loss': 0.023}
model_familydeep_learning
_origin{'type': 'internal', 'url': None, 'tracked_at': '2026-04-04T04:53:06.107683'}
evaluation_datasetAllen Brain SEA-AD MTG 10x snRNA-seq (held-out test split, ~20% donor stratified)
training_dataAllen Brain Atlas single-cell RNA-seq — Seattle Alzheimer's Disease Brain Cell Atlas (SEA-AD)
benchmark_nameCell Type Classification Benchmark — SEA-AD MTG
benchmark_notesTransformer architecture (6 layers, 512 hidden dim); final training loss 0.023
🌍 Provenance Graph 1 nodes, 0 edges

No provenance edges found

Linked Artifacts (2)
evaluated_on🗃Allen Brain SEA-AD MTG 10x snRNA-seq90%
related🔬Cell type vulnerability in Alzheimers Disease (SEA-AD transc70%