Related Experiment Video
Updated: Dec 30, 2025
Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
Comprehensive Review and Comparison for Anticancer Peptides Identification Models
Xiao Song1, Yuanying Zhuang2, Yihua Lan1
1Nanyang Normal University. China.
Abstract:
Anticancer peptides (ACPs) eliminate pathogenic bacteria and kill tumor cells, showing no hemolysis and no damages to normal human cells. This unique ability explores the possibility of ACPs as therapeutic delivery and its potential applications in clinical therapy. Identifying ACPs is one of the most fundamental and central problems in new antitumor drug research. During the past decades, a number of machine learning-based prediction tools have been developed to solve this important task. However, the predictions produced by various tools are difficult to quantify and compare. Therefore, in this article, we provide a comprehensive review of existing machine learning methods for ACPs prediction and fair comparison of the predictors. To evaluate current prediction tools, we conducted a comparative study and analyzed the existing ACPs predictor from 10 public literatures. The comparative results obtained suggest that Support Vector Machine-based model with features combination provided significant improvement in the overall performance, when compared to the other machine learning method-based prediction models.
Insights
Anticancer peptides (ACPs) show promise for cancer therapy by killing tumor cells without harming normal cells. A review found Support Vector Machine models with combined features best predict these crucial anticancer peptides.
Area of Science:
- Biochemistry and Molecular Biology
- Computational Biology and Cheminformatics
- Pharmacology and Drug Discovery
Background:
- Anticancer peptides (ACPs) possess a dual function: eliminating pathogenic bacteria and selectively destroying tumor cells.
- Their unique properties, including lack of hemolysis and minimal damage to normal human cells, highlight their potential in cancer therapy and drug delivery systems.
- Accurate identification of ACPs is a critical bottleneck in developing novel antitumor drugs.
Purpose of the Study:
- To provide a comprehensive review of existing machine learning (ML) methods for predicting anticancer peptides (ACPs).
- To conduct a fair comparison of various ML-based ACP prediction tools.
- To identify the most effective ML approach for ACP prediction based on performance evaluation.
Main Methods:
- A systematic review and comparative analysis of 10 public literature-based ACP prediction tools.
- Evaluation of existing machine learning methods applied to ACP identification.
- Performance assessment of different ML models, focusing on feature combinations and prediction accuracy.
Main Results:
- Existing machine learning prediction tools for ACPs often yield results that are difficult to quantify and compare.
- A comparative study analyzing 10 public literature sources was conducted to evaluate current prediction tools.
- Support Vector Machine (SVM)-based models, particularly those utilizing feature combinations, demonstrated significantly improved overall performance compared to other ML methods.
Conclusions:
- Machine learning plays a vital role in accelerating the discovery of anticancer peptides (ACPs).
- The performance of ACP prediction tools varies, necessitating standardized evaluation methods.
- Support Vector Machine models incorporating combined features represent a highly effective strategy for accurate ACP prediction, offering a promising direction for future drug discovery efforts.
