A study on phenotype prediction using an artificial intelligence-based data augmentation approach

Global food security is increasingly at risk due to factors like climate change and population growth, necessitating advancements in agricultural technology. Digital breeding, a method centered around genotype-phenotype selection using next-generation sequencing (NGS), offers a solution by enabling the identification of genetic mutations and predicting crop traits with greater speed and precision compared to traditional approaches. This automated breeding process efficiently gathers and analyzes genotype and phenotype data, improving key traits such as growth, yield, and tolerance while minimizing human intervention. Despite advancements in sequencing technologies, challenges remain due to the high cost and impracticality of acquiring extensive genomic datasets. To address these limitations, this study explores data augmentation strategies using deep learning techniques, focusing on their success in other fields like computer vision. Unlike conventional Generative Adversarial Networks (GANs), which face stability issues, we present a novel approach using a stacked convolutional and LSTM architecture. This model leverages SNP position information to capture correlations within genomic regions and introduces a specialized metric to evaluate the quality of augmented data. The effectiveness of the proposed phenotype prediction model is demonstrated through real-world testing on a collection of 192 tomato varieties, highlighting its potential to revolutionize breeding processes and improve agricultural outcomes.