Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions

TL;DR

This paper introduces Feedback GAN (FBGAN), a novel architecture that uses a feedback loop with an external analyzer to optimize synthetic DNA sequences for specific protein properties, applicable even when the analyzer isn't differentiable.

Contribution

The paper presents a new feedback-loop architecture for GANs that enhances the generation of biologically relevant DNA sequences with desired properties, expanding GAN applications in synthetic biology.

Findings

Generated genes exhibit desirable biophysical properties

Feedback mechanism improves optimization of target properties

Applicable to domains beyond genomics

Abstract

Generative Adversarial Networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins, or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer. The proposed architecture also has the advantage that the analyzer need not be differentiable. We apply the feedback-loop mechanism to two examples: 1) generating synthetic genes coding for antimicrobial peptides, and 2) optimizing synthetic genes for the secondary structure of their resulting peptides. A suite of metrics demonstrate that the GAN generated proteins have desirable biophysical properties. The FBGAN architecture can also be used to optimize GAN-generated datapoints for useful properties in domains beyond genomics.