Deep learning provides new insights into the molecular mechanisms of insect metamorphosis

Metamorphosis is one of the major innovations in the evolutionary history of insect, playing an important role in environmental adaptation and biodiversity formation. However, it is still a challenge to recognize the underlying mechanisms of insect metamorphosis in traditional molecular biology. In this study, based on 138 insect genomes across 10 orders, we present a gene network classification model (GNCM) utilizes deep learning (DL) and attention mechanism (AM) to mine some key genes of metamorphosis. The GNCM identified a total of 97 sets of orthologous genes (OGs) with high weights in insect metamorphosis, and the subsequent annotations suggested that these genes were involved in hormone regulation, immune, detoxification, metabolism and developmental functions. Notably, 38 genes with high weights showed specific expression lever of their transcripts during the pupal stage. This study not only developed a new method of artificial intelligence for evolutionary biology, but also provides a new insight to understand the macroevolutionary of insect metamorphosis.