Abstract World widely, cancer is considered a fatal disease and remains the major cause of death. Conventional medication approaches using therapies and anticancer drugs are deemed ineffective due to its high cost and harmful impacts on the normal cells. However, the innovation of anticancer peptides (ACPs) provides an effective way how to deals with cancer affected cells. Due to the rapid increases in peptide sequences, truly characterization of ACPs has become a challenging task for investigators. In this paper, an effort has been carried out to develop a reliable and intelligent computational method for the accurate discrimination of anticancer peptides. Three statistical feature representation schemes namely: Quasi-sequence order (QSO), conjoint triad feature, and Geary autocorrelation descriptor are applied to express motif of the target class. In order to eradicate irrelevant and noisy features, while select salient, profound and high variated features, principal component analysis is employed. Furthermore, the diverse nature of learning algorithms is utilized in order to select the best operational engine for the proposed model. After examining the empirical outcomes, support vector machine obtained quite encouraging results in combination with QSO feature space. It has achieved an accuracy of 96.91% and 89.54% using the main dataset and alternative dataset, respectively. It is observed that our proposed model shows an outstanding improvement compared to literature methods. It is expected that the developed model may be played a useful role in research academia as well as proteomics and drug development.

中文翻译：

---

cACP：通过周氏 5 步规则和一般伪成分使用判别智能模型对抗癌肽进行分类

摘要 在世界范围内，癌症被认为是一种致命疾病，并且仍然是导致死亡的主要原因。由于其高成本和对正常细胞的有害影响，使用疗法和抗癌药物的常规药物治疗方法被认为是无效的。然而，抗癌肽（ACPs）的创新提供了一种有效的方法来处理受癌症影响的细胞。由于肽序列的快速增加，真正表征 ACP 已成为研究人员的一项具有挑战性的任务。本文致力于开发一种可靠且智能的计算方法，用于准确区分抗癌肽。三种统计特征表示方案，即：准序列顺序（QSO）、联合三元组特征、和 Geary 自相关描述符用于表达目标类的motif。为了消除无关和嘈杂的特征，同时选择显着、深刻和高变异的特征，采用主成分分析。此外，利用学习算法的多样性来为所提出的模型选择最佳操作引擎。在检验经验结果后，支持向量机结合 QSO 特征空间获得了相当令人鼓舞的结果。它分别使用主数据集和替代数据集实现了 96.91% 和 89.54% 的准确率。观察到，与文献方法相比，我们提出的模型显示出显着的改进。