Predicting bacterial essential genes using only sequence composition information

Abstract

ABSTRACT. Essential genes are those genes that are needed by organisms at any time and under any conditions. It is very important for us to identify essential genes from bacterial genomes because of their vital role in synthetic biology and biomedical practices. In this paper, we developed a support vector machine (SVM)-based method to predict essential genes of bacterial genomes using only compositional features. These features are all derived from the primary sequences, i.e., nucleotide sequences and protein sequences. After training on the multiple samplings of the labeled (essential or not essential) features using a library for SVM, we obtained an average area under the ROC curve (AUC) of about 0.82 in a 5-fold cross-validation for Escherichia coli and about 0.74 for Mycoplasma pulmonis. We further evaluated the performance of the method proposed using the dataset consisting of 16 bacterial genomes, and an average AUC of 0.76 was achieved. Based on this training dataset, a model for essential gene prediction was established. Another two independent genomes, Shewanella oneidensis RW1 and Salmonella enterica serovar Typhimurium SL1344 were used to evalutate the model. Results showed that the AUC sores were 0.77 and 0.81, respectively. For the convenience of the vast majority Predicting bacterial essential genes by sequence composition of experimental scientists, a web server has been constructed, which is freely available at http://cefg.uestc.edu.cn:9999/egp.

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

“…In [28], the authors used the Kullback-Leibler 251 divergence (KLD) to measure the distance between k-mer distribution (for k = 1, 2, 3) 252 obtained from sequences. In [29], the authors used CD-HIT to remove redundancy in 253 the training data and improve the generalization ability of their model. As explained in 254 the previous section, DeeplyEssential uses OrthoMCL to cluster homologous genes 255 to prevent similar genes to appear in both training and testing dataset.…”

“…As explained in 254 the previous section, DeeplyEssential uses OrthoMCL to cluster homologous genes 255 to prevent similar genes to appear in both training and testing dataset. Table 7 and 256 Table 8 shows the performance comparison of DeeplyEssential with [29] and [28] on 257 their respective datasets. Observe that in both cases DeeplyEssential achieves the 258 best predictive performance.…”

“…In their work, the authors dealt with the redundancy in the 40 dataset (i.e., homologous genes shared by multiple bacterial genomes) by clustering 41 genes based on their sequence similarity. In [29], nucleotide, di-nucleotide, codon, and 42 amino acid frequencies and codon usage analysis were used for predicting essentiality in 43 sixteen bacterial species. The authors used CD-HIT [20] for homology detection in both 44 essential and non-essential genes.…”

“…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.…”

Efficient Adaptive Exon Prediction for DNA study using Proportionate LMS Variants

“…An essential step to attain this goal is tracing the protein coding areas in a gene sequence [1]. Identification of exon sections is an mammoth space of exploration in bio-informatics.…”