...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Theoretical and Applied Information Technology >MACHINE LEARNING CONFIGURATIONS FOR HUMAN PROTEIN CLASSIFICATION USING SDFES
【24h】

MACHINE LEARNING CONFIGURATIONS FOR HUMAN PROTEIN CLASSIFICATION USING SDFES

机译：使用SDFES进行人类蛋白质分类的机器学习配置

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The identification of target proteins for diseased condition yields the development of the disease detection recommender system and drug discovery processes whose reticence can demolish the pathogen. The testing of this drug discovery is done through clinical and in addition through pre-clinical observations first on the creatures then on people. Thereafter the discovered drug is ready for public use. But if the drug discovery testing phase does not show the suitable consequences, then the entire task must be repeated. This repetitive clinical as well as the preclinical experimentation task is very cumbersome. But keeping in view the importance of the disease detection and drug discovery phase in protein identification as well as in the protein classification process this task must be done by researchers. The advancements in computational biology reveal the importance of computational prediction of protein function or to identify the target on the basis of protein sequence extracted features. To accurately predict the human protein functionalities, lots of approaches are incorporated but this is a very cumbersome task due to the large and versatile nature of the domain. The present work will help to do this job through computational prediction. This paper involves the development of a model which use associative rule mining to extract the sequence derived features at a single platform (SDFES-Sequence derived feature extraction server) from the given human protein sequence and then critically analyzed with machine learning (ML) approaches under the aegis of data analysis tool WEKA. The new sequence derived features are identified and incorporated in the data set, and the scopes of ML approaches were examined for effective prediction. The important configuration incorporation and their configured comparison of approaches are completed to accomplish higher accuracy. In addition to comparative analysis, the limitation of ML approach is discussed along with its remedies by changing the configurations. The proposed work will assist to derive the sequence extracted feature together at a single place and further predict the class or function of the protein which leads to the innovation in drug discovery and disease detection recommender systems.
机译：疾病条件靶蛋白的鉴定产生了疾病检测推荐系统和药物发现过程的发展，其沉默可以消灭病原体。该药物发现​​的测试是通过临床以及先对生物然后对人进行临床前观察来完成的。此后，发现的药物准备好供公众使用。但是，如果药物发现测试阶段未显示适当的结果，则必须重复整个任务。这种重复的临床以及临床前的实验任务非常繁琐。但是要考虑到疾病检测和药物发现阶段在蛋白质鉴定以及蛋白质分类过程中的重要性，这项任务必须由研究人员来完成。计算生物学的进步揭示了蛋白质功能的计算预测或基于蛋白质序列提取特征识别目标的重要性。为了准确地预测人类蛋白质的功能，已结合了许多方法，但是由于该域的广泛性和通用性，这是一项非常繁琐的任务。目前的工作将有助于通过计算预测来完成这项工作。本文涉及一个模型的开发，该模型使用关联规则挖掘从给定的人类蛋白质序列中在单个平台（SDFES-序列派生特征提取服务器）上提取序列派生特征，然后使用机器学习（ML）方法对其进行严格分析数据分析工具WEKA的守护神。识别新的序列衍生特征并将其纳入数据集，并检查ML方法的范围以进行有效预测。完成重要的配置合并及其配置的方法比较，以实现更高的准确性。除了比较分析之外，还通过更改配置讨论了ML方法的局限性及其补救措施。拟议的工作将有助于在单个位置一起获得序列提取的特征，并进一步预测蛋白质的类别或功能，从而导致药物发现和疾病检测推荐系统的创新。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号