Selection of key sequence-based features for prediction of essential genes in 31 diverse bacterial species

Abstract

Genes that are indispensable for survival are essential genes. Many features have been proposed for computational prediction of essential genes. In this paper, the least absolute shrinkage and selection operator method was used to screen key sequence-based features related to gene essentiality. To assess the effects, the selected features were used to predict the essential genes from 31 bacterial species based on a support vector machine classifier. For all 31 bacterial objects (21 Gram-negative objects and ten Gram-positive objects), the features in the three datasets were reduced from 57, 59, and 58, to 40, 37, and 38, respectively, without loss of prediction accuracy. Results showed that some features were redundant for gene essentiality, so could be eliminated from future analyses. The selected features contained more complex (or key) biological information for gene essentiality, and could be of use in related research projects, such as gene prediction, synthetic biology, and drug design.

DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

“…We extracted features from gene nucleotide sequences and protein sequences. Several features derived from sequence data have been validated their usefulness in predicting gene essentiality in model organisms [10,16]. In this paper, we used the following sequence derived features: codon frequency, maximum relative synonymous codon usage (RSCUmax), codon adaptation index (CAI), gene length, GC content, amino acid frequency, and protein sequence length.…”

DeeplyEssential: A Deep Neural Network for Predicting Essential Genes in Microbes

“…Our experiments showed that DeeplyEssential has better predictive performance 291 both on down-sampled and clustered datasets. On the down-sampled dataset used 292 in [23], DeeplyEssential showed an improvement of 12.8% in AUC compared to [23] 293 and achieved a slightly better AUC on the network-based feature model [2]. In addition, 294 DeeplyEssential produced significantly better sensitivity and precision than the 295 three methods in Table 5, achieving 6.2% improved sensitivity and 137.4% improved 296 precision compare to [2].…”

“…With the 14 introduction of large gene database such as DEG, CEG and OGEE [4, 25, 40], researchers 15 designed more complex prediction models using a wider set of features. These features 16 can be broadly categorized into (i) sequence features, i.e., codon frequency, GC content, 17 gene length [29, 35, 42], (ii) topological features, i.e., degree centrality, cluster 18 coefficient [1, 6, 24, 31], and (iii) functional features, i.e., homology, gene expression 19cellular localization, functional domain and molecular properties [5,9,23,30,39].Sequence based features can be directly obtained from the primary DNA sequence of 21 a gene and its corresponding protein sequence. Functional features such as network 22 topology requires knowledge of protein-protein interaction network, e.g., STRING and 23 HumanNET [15,37].…”

“…In order to improve the performance of our classifier, we balanced the dataset by 89 downsampling non-essential genes. Codon frequency has been recognized an important feature for gene essentiality 99 prediction [23,30]. Given the primary DNA sequence of a gene, its codon frequency is 100 computed by sliding a window of three nucleotides along the gene.…”

“…The random selection was repeated ten times, 177 i.e., a ten-fold cross-validation was performed to complete the inference. The tools described in [23], [30], [29] and [28] are currently unavailable. We ran 180 DeeplyEssential on the datasets used in the corresponding papers, and compared 181 DeeplyEssential's classification metrics to the published metrics.…”