Ovary transcriptome profiling via application of artificial intelligence predicts egg quality in striped bass. Morone saxatilis

We modeled profiles of ovary gene expression and their relationship to egg quality, evaluated as production of viable mid-blastula stage embryos, in striped bass (Morone saxatilis) using artificial neural networks and supervised machine learning. Collective changes in expression of a limited suite of genes (233) representing only 2% of the queried ovary transcriptome explained >90% of the eventual variance in embryo survival. Egg quality related to minor changes in expression (≤0.2-fold), with most gene transcripts making minor contribution (50% of eggs producing 4 h embryos were considered to be of high quality and spawns with <30% of eggs producing 4 h embryos were considered to be of low quality.