Deep Learning-Enhanced Gap Filling in Drosophila Melanogaster Genomic Data

This study introduces deep learning (DL) methods for imputing missing allele-frequency information in large-scale genome-wide pooled re-sequencing (Pool-Seq) data, using the comprehensive DEST dataset based on over 270 global samples of the vinegar fly Drosophila melanogaster as a use case. The primary challenge addressed here is gap filling in DNA sequences, a critical issue in large-scale genomic studies. An empirical baseline for missing allele frequencies was established using an inverse-distance-weighting (IDW) method, leveraging geographical and temporal proximity among densely sampled populations. Additionally, a machine learning (ML) approach with k-means clustering grouped populations based on allele frequencies, independent of their spatiotemporal context. The core contribution of this research is the application of advanced DL models, specifically Masked Autoencoders (MAE), Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN). These models excel in learning the data distribution and generating plausible imputations for missing sequences, outperforming the IDW and k-means based methods. Their effectiveness is due to their ability to handle high-dimensional genetic sequences and capture complex data correlations while maintaining sequential integrity. The study demonstrates the efficacy of DL in genomic data analysis, particularly for large-scale, complex datasets. VAE and GAN models offer a significant advancement over traditional ML methods, providing more accurate and efficient solutions for gap filling in genetic sequences. This research highlights the potential of DL in genomics, setting a precedent for future AI applications in biological data analysis and demonstrating a novel application area for deep learning techniques in handling complex long-sequence biological datasets.