Related Experiment Video
Updated: Mar 22, 2026
A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
Published on: April 6, 2016
Self-Organizing Map (SOM) and Support Vector Machine (SVM) Models for the Prediction of Human Epidermal Growth Factor
Yue Kong, Dan Qu, Xiaoyan Chen
1State Key Laboratory of Chemical Resource Engineering, Department of Pharmaceutical Engineering, P.O. Box 53, Beijing University of Chemical Technology, 15 BeiSanHuan East Road, Beijing 100029, P.R. China. yanax@mail.buct.edu.cn.
Abstract:
EGFR (ErbB-1/HER1) kinase plays an important role in cancer therapy. Two classification models were established to predict whether a compound is an inhibitor or a decoy of human EGFR (ErbR-1) by using Kohonen's self-organizing map (SOM) and support vector machine (SVM). A dataset containing 1248 ATP binding site inhibitors and 3090 decoys was collected and randomly divided into a training set (831 inhibitors and 2064 decoys) and a test set (417 inhibitors and 1029 decoys). The descriptors that represent molecular structures were calculated by software ADRIANA.Code. Thirteen significant descriptors including five global descriptors and eight 2D property autocorrelation descriptors were selected by Pearson correlation analysis and stepwise analysis. The prediction accuracies on training set and test set are 98.5% and 96.3% for SOM model, 99.0% and 97.0% for SVM model, respectively. Both of these two classification models have good performance on distinguishing EGFR inhibitors from decoys.
Insights
This study developed two computational models, Kohonen
Area of Science:
- Computational Chemistry
- Drug Discovery
- Bioinformatics
Background:
- Epidermal Growth Factor Receptor (EGFR) kinase is a crucial target in cancer therapy.
- Distinguishing EGFR inhibitors from decoys is vital for efficient drug development.
- Predictive models can accelerate the identification of potential therapeutic compounds.
Purpose of the Study:
- To establish and evaluate two classification models for predicting EGFR inhibitors.
- To differentiate between compounds that inhibit EGFR and those that do not (decoys).
- To identify key molecular descriptors for accurate EGFR inhibitor prediction.
Main Methods:
- Utilized Kohonen's Self-Organizing Map (SOM) and Support Vector Machine (SVM) for classification.
- A dataset of 1248 EGFR ATP binding site inhibitors and 3090 decoys was curated.
- Thirteen significant molecular descriptors were selected using statistical analyses (Pearson correlation, stepwise analysis) from ADRIANA.Code software.
Main Results:
- The SOM model achieved prediction accuracies of 98.5% (training) and 96.3% (test).
- The SVM model demonstrated higher prediction accuracies of 99.0% (training) and 97.0% (test).
- Both models exhibited robust performance in distinguishing EGFR inhibitors from decoys.
Conclusions:
- Both SOM and SVM models are effective for classifying EGFR inhibitors and decoys.
- The developed models show high accuracy and can aid in the early stages of drug discovery.
- This computational approach facilitates the identification of novel EGFR-targeted cancer therapeutics.
More Related Videos
08:28Validated Immunochemical Assay for Comprehensive Determination of the Human Epidermal Growth Factor Receptor 2 Released from and Bound to Cells
Published on: May 9, 2025
09:53Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
