Simulating realistic short tandem repeat capillary electrophoretic signal using a generative adversarial network

TL;DR

This paper introduces a GAN-based method to generate realistic electrophoretic DNA signal data, facilitating improved training of neural networks for DNA profile analysis by reducing the need for extensive labeled datasets.

Contribution

The study develops a modified pix2pix GAN to simulate realistic DNA electrophoretic signals, enabling efficient training of classifiers without large labeled datasets.

Findings

GAN successfully simulates DNA electrophoretic signals with realistic noise and artefacts.

The generated data can be used to train neural networks for DNA profile analysis.

The approach reduces the need for extensive labeled training data.

Abstract

DNA profiles are made up from multiple series of electrophoretic signal measuring fluorescence over time. Typically, human DNA analysts 'read' DNA profiles using their experience to distinguish instrument noise, artefactual signal, and signal corresponding to DNA fragments of interest. Recent work has developed an artificial neural network, ANN, to carry out the task of classifying fluorescence types into categories in DNA profile electrophoretic signal. But the creation of the necessarily large amount of labelled training data for the ANN is time consuming and expensive, and a limiting factor in the ability to robustly train the ANN. If realistic, prelabelled, training data could be simulated then this would remove the barrier to training an ANN with high efficacy. Here we develop a generative adversarial network, GAN, modified from the pix2pix GAN to achieve this task. With 1078 DNA profiles we train the GAN and achieve the ability to simulate DNA profile information, and then use the generator from the GAN as a 'realism filter' that applies the noise and artefact elements exhibited in typical electrophoretic signal.