---
title: Autoencoder TRACERx-focused 16D
emoji: 🧬
colorFrom: blue
colorTo: green
sdk: pytorch
tags:
- transcriptomics
- dimensionality-reduction
- ae
- tracerx
license: mit
---

# Autoencoder (TRACERx-focused, 16D)

This model is part of the TRACERx Datathon 2025 transcriptomics analysis pipeline.

## Model Details

- **Model Type**: Autoencoder
- **Dataset**: TRACERx-focused
- **Latent Dimensions**: 16
- **Compression Mode**: samples
- **Framework**: PyTorch

## Usage

This model is designed to be used with the TRACERx Datathon 2025 analysis pipeline.
It will be automatically downloaded and cached when needed.

## Model Architecture

- Input: Gene expression data
- Hidden layers: [input_size, 512, 256, 128, 16]
- Output: 16-dimensional latent representation
- Activation: ELU with batch normalization

## Training Data

Trained exclusively on TRACERx open dataset

## Files

- `autoencoder_16_latent_dims_oos_mode.pt`: Main model weights
- `latent_df.csv`: Example latent representations (if available)