No abstract

Motivation Insects possess a vast phenotypic diversity and key ecological roles. Several insect species also have medical, agricultural and veterinary importance as parasites and disease vectors. Therefore, strategies to identify potential essential genes in insects may reduce the resources needed to find molecular players in central processes of insect biology. However, most predictors of essential genes in multicellular eukaryotes using machine learning rely on expensive and laborious experimental data to be used as gene features, such as gene expression profiles or protein-protein interactions, even though some of this information may not be available for the majority of insect species with genomic sequences available. Results Here we present and validate a machine learning strategy to predict essential genes in insects using sequence-based intrinsic attributes (statistical and physicochemical data) together with the predictions of subcellular location and transcriptomic data, if available. We gathered information available in public databases describing essential and non-essential genes for Drosophila melanogaster (fruit fly, Diptera) and Tribolium castaneum (red flour beetle, Coleoptera). We proceeded by computing intrinsic and extrinsic attributes that were used to train statistical models in one species and tested by their capability of predicting essential genes in the other. Even models trained using only intrinsic attributes are capable of predicting genes in the other insect species, including the prediction of lineage-specific essential genes. Furthermore, the inclusion of RNA-Seq data is a major factor to increase classifier performance. Availability and implementation The code, data and final models produced in this study are freely available at https://github.com/g1o/GeneEssentiality/. Supplementary information Supplementary data are available at Bioinformatics online.

Background: Insects are organisms with a vast phenotypic diversity and key ecological roles. Several insect species also have medical, agricultural and veterinary importance as parasites and vectors of diseases. Therefore, strategies to identify potential essential genes in insects may reduce the resources needed to find molecular players in central processes of insect biology. Furthermore, the detection of essential genes that occur only in specific groups within insects, such as lineages containing insect pests and vectors, may provide a more rational approach to select essential genes for the development of insecticides with fewer off-target effects. However, most predictors of essential genes in multicellular eukaryotes using machine learning rely on expensive and laborious experimental data to be used as gene features, such as gene expression profiles or protein-protein interactions. This information is not available for the vast majority of insect species, which prevents this strategy to be effectively used to survey genomic data from non-model insect species for candidate essential genes. Here we present a general machine learning strategy to predict essential genes in insects using only sequence-based attributes (statistical and physicochemical data). We validate our strategy using genomic data for the two insect species where large-scale gene essentiality data is available: Drosophila melanogaster (fruit fly, Diptera) and Tribolium castaneum (red flour beetle, Coleoptera). Results: We used publicly available databases plus a thorough literature review to obtain databases of essential and non-essential genes for D. melanogaster and T. castaneum, and proceeded by computing sequence-based attributes that were used to train statistical models (Random Forest and Gradient Boosting Trees) to predict essential genes for each species. We demonstrated that both models are capable of distinguishing essential from non-essential genes significantly better than zero rule classifiers. Furthermore, models trained in one insect species are also capable of predicting essential genes in the other species significantly better than expected by chance. Finally, we demonstrated that the D. melanogaster model can distinguish between essential and non-essential T. castaneum genes with no known homologs in the fly significantly better than a zero-rule model, demonstrating that it is possible to use models trained using fly genes to predict lineage-specific essential genes in a phylogenetically distant insect order. Conclusions: Here we report, to the best of our knowledge, the development and validation of the first general predictor of essential genes in insects using sequence-based attributes that can, in principle, be computed for any insect species where genomic information is available. The code and data used to predict essential genes in insects are freely available at https://github.com/g1o/GeneEssentiality/.