iACP-MultiCNN: Multi-channel CNN based anticancer peptides identification.

Area of Science:

• Computational biology
• Bioinformatics
• Cancer research

Background:

• Cancer remains a leading cause of death globally, with current therapies causing significant side effects.
• Anticancer peptides (ACPs) offer a promising therapeutic avenue due to their unique properties.
• Accurate identification of novel ACPs is crucial for advancing cancer treatment strategies.

Purpose of the Study:

• To develop and validate a novel computational method for identifying anticancer peptides (ACPs).
• To improve the predictive performance beyond existing machine learning and deep learning models.
• To provide a user-friendly tool for researchers in the field of anticancer peptide discovery.

Main Methods:

• A novel multi-channel convolutional neural network (CNN) architecture was designed for ACP identification.
• Data from state-of-the-art methods were collected and preprocessed using binary encoding.
• Model training was performed using k-fold cross-validation on benchmark datasets, with performance evaluated on independent datasets.

Main Results:

• The proposed multi-channel CNN model demonstrated superior performance compared to existing methods across various evaluation metrics.
• The model achieved high accuracy in identifying anticancer peptides from protein sequences.
• Comparative analysis confirmed the model's effectiveness on independent test datasets.

Conclusions:

• The developed multi-channel CNN is a valuable tool for the discovery of novel anticancer peptides.
• This computational approach can significantly contribute to the fight against cancer by identifying new therapeutic agents.
• A publicly accessible web server has been developed to facilitate research and academic use.