MLACP(machine learning anticancer peptides prediction) is a method to predict the anti-cancer peptides from the given peptides. In this method, the support vector machine and random-forest were used for the predictions. Here, the anticancer peptides (ACPs) are peptides capable of use as therapeutic agents to treat various cancers. The ACPs are selective toward cancer cells without affecting normal physiological functions, making them a potentially valuable therapeutic strategy. ACPs contain between 5-30 amino acids and exhibit cationic amphipathic structures capable of interacting with the anionic lipid membrane of cancer cells, thereby enabling selective targeting. In the previous decade, multiple peptide-based therapies against various tumor types have been evaluated and are currently undergoing evaluation in various phases of preclinical and clinical trials, confirming the importance of developing novel ACPs for cancer treatment. Identification of anticancer peptides (ACPs) through wet-lab experimentation is expensive and often time consuming; therefore, development of an efficient computational method like MLACP is essential to identify potential ACP candidates prior to in vitro experimentation.
1) Amino Acid Composition (AAC) 2) Di-peptide composition (DPC) 3) Atomic composition (ATC) 4) Physio-chemical properties (PCP)
1) Support Vector machine 2) Random Forest
Execution Steps: #
Step 1: submit the peptide to the webserver (www.thegleelab.org/AIPpred) Step 2: Results
- Manavalan, B.; Basith, S.; Shin, T. H.; Choi, S.; Kim, M. O.; Lee, G., MLACP: machine-learning-based prediction of anticancer peptides. Oncotarget 2017, 8, (44), 77121-77136.