DeepHE: Accurately predicting human essential genes based on deep learning

Accurately predicting essential genes using computational methods can greatly reduce the effort in finding them via wet experiments at both time and resource scales, and further accelerate the process of drug discovery. Several computational methods have been proposed for predicting essential genes in model organisms by integrating multiple biological data sources either via centrality measures or machine learning based methods. However, the methods aiming to predict human essential genes are still limited and the performance still need improve. In addition, most of the machine learning based essential gene prediction methods are lack of skills to handle the imbalanced learning issue inherent in the essential gene prediction problem, which might be one factor affecting their performance. We propose a deep learning based method, DeepHE, to predict human essential genes by integrating features derived from sequence data and protein-protein interaction (PPI) network. A deep learning based network embedding method is utilized to automatically learn features from PPI network. In addition, 89 sequence features were derived from DNA sequence and protein sequence for each gene. These two types of features are integrated to train a multilayer neural network. A cost-sensitive technique is used to address the imbalanced learning problem when training the deep neural network. The experimental results for predicting human essential genes show that our proposed method, DeepHE, can accurately predict human gene essentiality with an average performance of AUC higher than 94%, the area under precision-recall curve (AP) higher than 90%, and the accuracy higher than 90%. We also compare DeepHE with several widely used traditional machine learning models (SVM, Naïve Bayes, Random Forest, and Adaboost) using the same features and utilizing the same cost-sensitive technique to against the imbalanced learning issue. The experimental results show that DeepHE significantly outperforms the compared machine learning models. We have demonstrated that human essential genes can be accurately predicted by designing effective machine learning algorithm and integrating representative features captured from available biological data. The proposed deep learning framework is effective for such task.Author summary: Essential genes are a subset of genes. They are indispensable to the survival or reproduction of a living organism and thus play a very important role in maintaining cellular life. The identification of gene essentiality is very important for understanding the minimal requirements of an organism, identifying disease genes, and finding new drug targets. Essential genes can be identified via several wet-lab experimental methods, but these methods are often time-consuming, laborious, and costly. As a complement to the experimental methods, some centrality measures and traditional machine learning based computational methods have been proposed which mainly focused on predicting essential genes on model organisms. Here, we show that human essential genes can be accurately predicted by exploring sequence data and protein interaction network based on deep learning techniques. The ability to accurately and efficiently predict essential genes by utilizing existing biological omics data accelerates the annotation and analysis of essential genes, advance our understanding of the mechanism of basic life, and boosts the drug development.