AUTHOR=Wu Xiujin , Zeng Wenhua , Lin Fan , Xu Peng , Li Xinzhu 

TITLE=Anticancer Peptide Prediction via Multi-Kernel CNN and Attention Model

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.887894

DOI=10.3389/fgene.2022.887894

ISSN=1664-8021

ABSTRACT=Background: With today's way of life, people are more likely to suffer from some forms of cancer. The anticancer peptides can effectively kill cancer cells, which play an important role of fighting cancer. The anticancer peptides has aroused extensive more and more researcher’s interest.
Methods: In this study, we present a useful tool to identify the anticancer peptides based on multi-CNN and attention model, called ACP-MCAM. It can automatically learn adaptive embedding and the context sequence features of ACP. In addition, in order to obtain better interpretability and integrity, we visualized the model.
Results: Benchmarking comparison shows that ACP-MCAM significantly outperforms several state-of-the-art model. Different encoding schemes have different impact on the performance of the model. We also have studied the method parameter optimization.
Conclusion: The ACP-MCAM can integrate multi-CNN and self-attention mechanism, which outperforms previous model in identifying the anticancer peptides. It is expected that the work will provide new research ideas for anticancer peptides prediction in the future. In addition, this work will provide theoretical basis for the development of the biomedical field.