Optimizing Scorpion Toxin Processing through Artificial Intelligence

Abstract

Scorpion toxins are relatively short cyclic peptides (<150 amino acids) that can disrupt theopening/closing mechanisms in cell ion channels. These peptides are widely studied for severalreasons including their use in drug discovery. Although improvements in RNAseq have greatlyexpedited the discovery of new scorpion toxins, their annotation remains challenging, mainly due totheir small size. Here, we present a new pipeline to annotate toxins from scorpion transcriptomesusing a neural network approach. This pipeline implements basic neural networks to sort amino acidsequences to find those that are likely toxins and thereafter predict the type of toxin represented bythe sequence. We anticipate that this pipeline will accelerate the classification of scorpion toxins inforthcoming scorpion genome sequencing projects and potentially serve a useful role in identifyingtargets for drug development.