Cancer miRNA biomarker classification based on syntax-guided hierarchical attention network optimized with Golden Jackal optimization algorithm

Abstract

MicroRNAs (miRNAs) are integral components of genomic data, offering valuable insights into genome sequences. Existing studies have faced challenges in achieving desired classification accuracy. To address this issue, Syntax-Guided Hierarchical Attention Network optimized with Golden Jackal Optimization (SGHAN-GJOA-MiRNA-BC) is proposed to classify cancer miRNA biomarkers. Input data is amassed from Cancer Genome dataset. Data pre-processing uses the Z-score normalization method for standardizing the data. The stochastic gradient enhancement-based recursive feature elimination (SGB-RFE) method selects relevant features. Then the Syntax-Guided-Hierarchical Attention Network (SGHAN) classifies cancer miRNA biomarkers for diagnosis, therapy, and prognosis. The Golden Jackal Optimization (GJO) algorithm optimizes SGHAN ensuring precise classification. The efficiency of proposed SGHAN-GJOA-MiRNA-BC technique is evaluated. For cancer genome atlas dataset, it achieves increase in accuracy of 10.95 %, 24.45 %, 11.85 %, 12.87 %, 16.58 %, 10.99 % and 11.54 %, sensitivity of 15.92 %, 23.43 %, 12.62 %, 10.87 %, 15.58 %, 13.91 % and 10.74 %, F-Measure of 11.78 %, 21.45 %, 12.77 %, 13.82 %, 15.23 %, 12.69 % and 11.54 %, precision of 9.84 %, 20.42 %, 11.88 %, 12.17 %, 17.53 %, 10.29 % and 12.54 %, lower in computation time of 43.45 %, 48.21 %, 48.98 %, 49.15 %, 47.42 %, 45.46 % and 46.54 %, mean square error (MSE) of 9.03 %, 12.27 %, 13.72 %, 11.12 %, 14.29 %, 13.78 %, 15.45 %,and error rate of 3.72 %, 9.57 %, 6.75 %, 13.13 %, 16.09 %, 13.73 % and 15.83 %,compared to the existing techniques Cancer MiRNA biomarker categorization using generative adversarial network (GAN-MFOA-MiRNA-BC), lung cancer detection utilizing hybrid deep neural network (ML-ABCOA-MiRNA-BC), convolution neural network for breast cancer categorization under RNA-Seq-data (CNN-EOSA-MiRNA-BC), Parallel Bayesian model for breast cancer prediction(DNN-ASCCS-MiRNA-BC), Biomarker identification and cancer survival prediction using Bayesian optimized-DNN (BODNN-CSOA-MiRNA-BC), identifying ovarian cancer’s potential biomarkers (SVM-ICA-MiRNA-BC), a machine learning method for pancreatic cancer diagnosis (ANN-PSO-MiRNA-BC) respectively.