ACPNet: A Deep Learning Network to Identify Anticancer Peptides by Hybrid Sequence Information

Abstract

Cancer is one of the most dangerous threats to human health. One of the issues is drug resistance action, which leads to side effects after drug treatment. Numerous therapies have endeavored to relieve the drug resistance action. Recently, anticancer peptides could be a novel and promising anticancer candidate, which can inhibit tumor cell proliferation, migration, and suppress the formation of tumor blood vessels, with fewer side effects. However, it is costly, laborious and time consuming to identify anticancer peptides by biological experiments with a high throughput. Therefore, accurately identifying anti-cancer peptides becomes a key and indispensable step for anticancer peptides therapy. Although some existing computer methods have been developed to predict anticancer peptides, the accuracy still needs to be improved. Thus, in this study, we propose a deep learning-based model, called ACPNet, to distinguish anticancer peptides from non-anticancer peptides (non-ACPs). ACPNet employs three different types of peptide sequence information, peptide physicochemical properties and auto-encoding features linking the training process. ACPNet is a hybrid deep learning network, which fuses fully connected networks and recurrent neural networks. The comparison with other existing methods on ACPs82 datasets shows that ACPNet not only achieves the improvement of 1.2% Accuracy, 2.0% F1-score, and 7.2% Recall, but also gets balanced performance on the Matthews correlation coefficient. Meanwhile, ACPNet is verified on an independent dataset, with 20 proven anticancer peptides, and only one anticancer peptide is predicted as non-ACPs. The comparison and independent validation experiment indicate that ACPNet can accurately distinguish anticancer peptides from non-ACPs.

An efficient consolidation of word embedding and deep learning techniques for classifying anticancer peptides: FastText+BiLSTM

“…Additionally, to enhance the reliability and performance of the models, a combination of techniques such as Dropout, pooling layer, and batch normalization are utilized. The experimental results demonstrate the effectiveness of the proposed approach, surpassing the success rate (89.6%) of state-of-the-art study ( Sun et al, 2022 ) on the ACPs250 dataset and achieving a remarkable accuracy of 92.50%. Moreover, on the Independent dataset, the proposed model outperforms the leading study’s ( Akbar et al, 2022 ) accuracy rate of 94.02% and achieves an impressive success rate of 96.15%.…”

“…In Sun et al (2022) , ACPNet is introduced as a novel deep learning-based model specifically crafted for discriminating between anticancer peptides and non-anticancer peptides (non-ACPs). ACPNet incorporates three distinct sources of peptide sequence information, including peptide physicochemical properties and auto-encoding features, integrated into the model’s training process.…”

Anti-Cancer Peptides: Status and Future Prospects

“…Upon testing ACP-red LAF on a balanced ACP-mixed-80 dataset, an accuracy of 81.15% and MCC of 0.633 was obtained compared to 74.32% and 0.519 as obtained for accuracy and MCC, respectively, by the AntiCP-DPC model. Several additional DL models are reported such as CL-ACP and more recently ACPNet [ 267 , 268 ].…”

ACP-BC: A Model for Accurate Identification of Anticancer Peptides Based on Fusion Features of Bidirectional Long Short-Term Memory and Chemically Derived Information

“…By employing a deep learning approach, the ACP-MHCNN demonstrated promising performance in peptide prediction. Similarly, Sun et al [45] introduced ACPNet, a novel framework for identifying anticancer peptides. ACPNet incorporates peptide sequence information, physicochemical properties, and self-encoding features into its architecture.…”