Skip to content

MLCPP #

Find similar titles

1회 업데이트 됨.

Edit
  • 작성자

You are seeing an old version of the page. Go to latest version

MLCPP #

Introduction #

MLCPP is a two-layer machine learning method to predict the cell-penetrating peptides (CPPs) from the given peptides. In first layer, it predicts CPPs and in second layer, it predict the uptake efficiency of peptides. In first layer, the extremely randomized tree (ERT) performing well, and in second layer, the random forest performing well. CPPs are typically 5 to 30 amino acids in length and can pass through cell membranes via energy-dependent and -independent mechanisms without specific receptor interaction. CPPs can transport to the inside of cells while carrying a wide variety of covalently or non-covalently linked cargo, including nanoparticles, peptides, proteins, antisense oligonucleotides, small-interfering RNA, double-stranded DNA, and liposomes. Interestingly, pre-clinical evaluations of CPP-derived therapeutics showed promising results in various disease models, which subsequently translated into clinical trials. Therefore, CPPs represent an effective approach for delivering bioactive molecules into cells for various biomedical applications.

Features: #

1)  Amino Acid Composition 
2)  Di-peptide composition (DPC)
3)  Amino acid index (AAI)
4)  Composition-Transition-Distribution (CTD)
5)  Physio-Chemical Properties (PCP)

Machines: #

1)  Random Forest (RF)
2)  Extremely Randomized Tree (ERT)
3)  Support Vector Machine (SVM)
4)  K-nearest neighbor (k-NN)

Steps to execute: #

Step 1: Submit to the webserver (http://www.thegleelab.org/MLCPP/)
Step 2: Results from the webpage

Reference: #

  1. Manavalan, B.; Subramaniyam, S.; Shin, T. H.; Kim, M. O.; Lee, G., Machine-Learning-Based Prediction of Cell-Penetrating Peptides and Their Uptake Efficiency with Improved Accuracy. Journal of Proteome Research 2018.
0.0.1_20240318_1_v95