Assessing the reliability of point mutation as data augmentation for deep learning with genomic data

Abstract

Background: Deep neural networks (DNNs) have the potential to revolutionize our understanding and treatment of genetic diseases. An inherent limitation of deep neural networks, however, is their high demand for data during training. To overcome this challenge, other fields, such as computer vision, use various data augmentation techniques to artificially increase the available training data for DNNs. Unfortunately, most data augmentation techniques used in other domains do not transfer well to genomic data.

Results: Most genomic data possesses peculiar properties and data augmentations may significantly alter the intrinsic properties of the data. In this work, we propose a novel data augmentation technique for genomic data inspired by biology: point mutations. By employing point mutations as substitutes for codons, we demonstrate that our newly proposed data augmentation technique enhances the performance of DNNs across various genomic tasks that involve coding regions, such as translation initiation and splice site detection.

Conclusion: Silent and missense mutations are found to positively influence effectiveness, while nonsense mutations and random mutations in non-coding regions generally lead to degradation. Overall, point mutation-based augmentations in genomic datasets present valuable opportunities for improving the accuracy and reliability of predictive models for DNA sequences.

Keywords: Data augmentation; Deep learning; Point mutations; Splicing; Translation initiation.

Fig. 1

Arrangement of coding and non-coding regions in the six datasets used for TIS or splice site detection. Each sequence consists of either a TIS or a splice site, flanked by a coding or non-coding region of fixed length, as indicated in the figure

Fig. 2

Changes in neural network performance for each of the five datasets after introducing up to 10 point mutations of different types in the coding region. Applying a moderate number of silent and missense mutations improves the performance, while large numbers of missense and nonsense mutations are generally detrimental

Fig. 3

Changes in neural network performance for each of the five datasets after introducing up to 10 random mutations in the non-coding region. Applying random mutations generally has a detrimental effect on performance

Fig. 4

Effect of applying different mutation types for each dataset under comparison. Up to three mutations are applied, since higher mutation counts generally have a detrimental effect. The vertical dashed line indicates the median accuracy for the baseline case, in which no mutations are applied. Dots in the scatter plot indicate repetitions of the same experiment, with a different random seed, as explained in the body of the text