Alotaibi Fahad M, Khan Yaser Daanial
Department of Information System, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia.
Department of Computer Science, University of Management and Technology, Lahore 54770, Pakistan.
Diagnostics (Basel). 2023 Jul 6;13(13):2291. doi: 10.3390/diagnostics13132291.
Mutations in genes can alter their DNA patterns, and by recognizing these mutations, many carcinomas can be diagnosed in the progression stages. The human body contains many hidden and enigmatic features that humankind has not yet fully understood. A total of 7539 neoplasm cases were reported from 1 January 2021 to 31 December 2021. Of these, 3156 were seen in males (41.9%) and 4383 (58.1%) in female patients. Several machine learning and deep learning frameworks are already implemented to detect mutations, but these techniques lack generalized datasets and need to be optimized for better results. Deep learning-based neural networks provide the computational power to calculate the complex structures of gastric carcinoma-driven gene mutations. This study proposes deep learning approaches such as long and short-term memory, gated recurrent units and bi-LSTM to help in identifying the progression of gastric carcinoma in an optimized manner. This study includes 61 carcinogenic driver genes whose mutations can cause gastric cancer. The mutation information was downloaded from intOGen.org and normal gene sequences were downloaded from asia.ensembl.org, as explained in the data collection section. The proposed deep learning models are validated using the self-consistency test (SCT), 10-fold cross-validation test (FCVT), and independent set test (IST); the IST prediction metrics of accuracy, sensitivity, specificity, MCC and AUC of LSTM, Bi-LSTM, and GRU are 97.18%, 98.35%, 96.01%, 0.94, 0.98; 99.46%, 98.93%, 100%, 0.989, 1.00; 99.46%, 98.93%, 100%, 0.989 and 1.00, respectively.
基因中的突变会改变其DNA模式，通过识别这些突变，许多癌症在进展阶段就能被诊断出来。人体包含许多人类尚未完全理解的隐藏且神秘的特征。2021年1月1日至2021年12月31日共报告了7539例肿瘤病例。其中，男性患者有3156例（41.9%），女性患者有4383例（58.1%）。已经实施了几种机器学习和深度学习框架来检测突变，但这些技术缺乏通用数据集，需要进行优化以获得更好的结果。基于深度学习的神经网络提供了计算能力，以计算胃癌驱动基因突变的复杂结构。本研究提出了长短期记忆、门控循环单元和双向长短期记忆等深度学习方法，以帮助以优化方式识别胃癌的进展。本研究包括61个致癌驱动基因，其突变可导致胃癌。如数据收集部分所述，突变信息从intOGen.org下载，正常基因序列从asia.ensembl.org下载。所提出的深度学习模型使用自一致性测试（SCT）、10折交叉验证测试（FCVT）和独立集测试（IST）进行验证；LSTM、Bi-LSTM和GRU的IST预测指标准确率、灵敏度、特异性、MCC和AUC分别为97.18%、98.35%、96.01%、0.94、0.98；99.46%、98.93%、100%、0.989、1.00；99.46%、98.93%、100%、0.989和1.00。
