Information Department, Shijiazhuang Vocational College of Finance & Economics, Shijiazhuang 050061, China.
Global Media Communication, The University of Melbourne, Melbourne 3006, Australia.
Cell Mol Biol (Noisy-le-grand). 2020 Oct 31;66(7):103-110.
In view of the shortcomings of the current abnormal data detection system of the protein gene library, such as low detection rate and high error detection rate, the abnormal data detection system of the protein gene library based on data mining technology is designed. The protein gene enters the firewall module of the system, and enters the immune module when it does not match the firewall rules; the memory detector in the immune module presents the protein gene, if the memory detector does not match the protein gene, the mature detector presents the protein gene, if the mature detector does not match the protein gene, it is determined as the normal protein gene data package, if it matches, it is considered that The abnormal data of protein gene was processed by the collaborative stimulation module, and the control module controlled by C8051F060 chip to detect the abnormal data of protein gene library. The immune module generates new protein gene sequences through an immature detector, simulates the immune mechanism of protein gene through a mature detector module, and simulates the secondary response in the abnormal data detection system of protein gene library through memory detector. The system introduces data mining technology into the detection and uses a two-level dynamic optimization algorithm to calculate the ASG similarity value of protein gene secondary structure arrangement. According to this value, the abnormal data detection of the protein gene library is realized by randomly generating protein genes, negative selection, clone selection and copying memory cells through gene expression. The experimental results show that the system can quickly detect abnormal data of the protein gene library, ensure the detection efficiency, and the detection accuracy reaches 97.1%. The system can reduce the error rate of normal protein gene detection as an abnormal protein gene.
针对当前蛋白质基因库异常数据检测系统检测率低、误检率高的缺点，设计了基于数据挖掘技术的蛋白质基因库异常数据检测系统。蛋白质基因进入系统的防火墙模块，不匹配防火墙规则时进入免疫模块；免疫模块中的记忆探测器呈现蛋白质基因，如果记忆探测器不匹配蛋白质基因，则成熟探测器呈现蛋白质基因，如果成熟探测器不匹配蛋白质基因，则确定为正常蛋白质基因数据包，如果匹配，则认为蛋白质基因的异常数据已被协同刺激模块处理，并由 C8051F060 芯片控制模块检测蛋白质基因库的异常数据。免疫模块通过不成熟探测器生成新的蛋白质基因序列，通过成熟探测器模块模拟蛋白质基因的免疫机制，通过记忆探测器模拟蛋白质基因库异常数据检测系统中的二次反应。该系统将数据挖掘技术引入检测中，并使用两级动态优化算法计算蛋白质基因二级结构排列的 ASG 相似值。根据该值，通过基因表达随机生成蛋白质基因、负选择、克隆选择和复制记忆细胞来实现蛋白质基因库的异常数据检测。实验结果表明，该系统能够快速检测蛋白质基因库的异常数据，保证检测效率，检测准确率达到 97.1%。该系统可以将正常蛋白质基因检测的错误率降低为异常蛋白质基因。
