On the Relation of Gene Essentiality to Intron Structure: A Computational and Deep Learning Approach

Identification and study of human-essential genes has become of practical importance with the realization that disruption or loss of nearby essential genes can introduce latent-vulnerabilities to cancer cells. Essential genes have been studied by copy-number-variants and deletion events, which are associated with introns. The premise of our work is that introns of essential genes have characteristic properties that are distinct from the introns of nonessential genes. We provide support for the existence of characteristic properties by training a deep learning model on introns of essential and nonessential genes and demonstrated that introns alone can be used to classify essential and nonessential genes with high accuracy (AUC of 0.846). We further demonstrated that the accuracy of the same deep-learning model limited to first introns will perform at an increased level, thereby demonstrating the critical importance of introns and particularly first introns in gene essentiality. Using a computational approach, we identified several novel properties of introns of essential genes, finding that their structure protects against deletion and intron-loss events, and that these traits are especially centered on the first intron. We showed that GC density is increased in the first introns of essential genes, allowing for increased enhancer activity, protection against deletions, and improved splice-site recognition. Furthermore, we found that first introns of essential genes are of remarkably smaller size than their nonessential counterparts, and to protect against common 3 end deletion events, essential genes carry an increased number of (smaller) introns. To demonstrate the importance of the seven features we identified, we trained a feature-based model using only information from these features and achieved high accuracy (AUC of 0.787).