Skip to content

About

Deep neural autoencoder architecture for biological data storage, optimizing latent sequence representations under GC-content and homopolymer synthesis constraints.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

12 Commits

Folders and files

Repository files navigation

CSE443: Constrained DNA Data Storage Autoencoder

An end-to-end differentiable deep learning framework for translating binary digital payloads into biochemical-compliant DNA sequences ({A, C, G, T}).

Pipeline Overview

  • Differentiable Channel: Gumbel-Softmax continuous relaxation with simulated substitution noise.
  • Biochemical Loss Constraints: Differentiable penalties for GC-content window adherence (40%–60%) and homopolymer run suppression (max run < 3).
  • Architecture: Joint Source-Channel Coding (JSCC) autoencoder mapping 128-bit blocks to 80-nucleotide sequences.

Performance

  • Effective Code Rate: 1.62 bits/nucleotide
  • Bit Error Rate (BER): < 0.005
  • Biological Policy Violation Rate: Reduced from 34.2% to 2.1%

Repository Structure

  • data_generator.py: Generates uniform binary and structured ASCII payloads.
  • model.py: Neural autoencoder encoder-decoder architecture.
  • noise_channel.py: Continuous Gumbel-Softmax biological channel.
  • loss.py: Multi-objective loss with GC and homopolymer penalty terms.
  • train.py: Training pipeline.
  • evaluate.py: Evaluation benchmarks across BER, policy violations, and code rate.

About

Deep neural autoencoder architecture for biological data storage, optimizing latent sequence representations under GC-content and homopolymer synthesis constraints.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages