Table 2 Benchmark models for comparison
Models | Model details | References |
|---|---|---|
DeepLOF | Evolution-based deep learning model, DeepLOF, a novel deep learning framework to integrate both population and functional genomic data | [27] |
PreEGSRF | Machine learning method termed Prediction of Essential Genes in Comparison States, PreEGS. PreEGS extracts topological and gene expression features of each gene in a five-dimensional vector | [24] |
DeepHE | A deep learning-based network embedding method is utilized to automatically learn features from protein–protein interaction network | [14] |
DeeplyEssential | Deep neural network for predicting essential genes in microbes. DeeplyEssential makes minimal assumptions about the input data to carry out the prediction, thus maximizing its application | [45] |
NLP-SL | A natural language processing (NLP) model in learning biological sequences by treating them as natural language words employed by an ensemble deep neural network | [46] |
iEsGene-ZCPseKNC | A computational predictor called iEsGene-ZCPseKNC. Z curve pseudo k-tuple nucleotide composition was proposed and SMOTE algorithm was employed to further improve the predictive | [47] |
iEsGene-CSMOTE | Clustering-based Synthetic Minority Oversampling Technique with over-sampling strategy, Z curve, global features, and SVM | [48] |
GCNN-SFM | A method integrates gradient descent algorithm, a graph convolutional layer, a convolutional layer, and a fully connected layer with a multi-layer GCN capturing both local and global features | [49] |
Bingo | A large language model and graph neural network under two “zero-shot” scenarios with transfer learning | [50] |