Identifying essential genes across eukaryotes by machine learning

Abstract

Identifying essential genes on a genome scale is resource intensive and has been performed for only a few eukaryotes. For less studied organisms essentiality might be predicted by gene homology. However, this approach cannot be applied to non-conserved genes. Additionally, divergent essentiality information is obtained from studying single cells or whole, multi-cellular organisms, and particularly when derived from human cell line screens and human population studies. We employed machine learning across six model eukaryotes and 60,381 genes, using 41,635 features derived from sequence, gene functions and network topology. Within a leave-one-organism-out cross-validation, the classifiers showed a high generalizability with an average accuracy close to 80% in the left-out species. As a case study, we applied the method to Tribolium castaneum and validated predictions experimentally yielding similar performance. Finally, using the classifier based on the studied model organisms enabled linking the essentiality information of human cell line screens and population studies.