hERGBoost

hERG-mediated cardiotoxicity predictor

Human Ether-a-go-go Related Gene (hERG) channel is one of the most prominent proteins in the drug discovery process, due to its susceptibility to small molecule blockade, which can lead to potentially critical cardiotoxic symptoms. Filtering out the potential hERG channel blockers from drug candidates is therefore crucial for successful drug development. To address the need for reliable quantitative prediction of the hERG channel blocking ability of small molecules, we developed a machine learning model hERGBoost for prediction of hERG channel blockade in small molecules. This web server works on Chrome, Firefox, and Opera.

hERG-mediated cardiotoxicity predictor

Human Ether-a-go-go Related Gene (hERG) channel is one of the most prominent proteins in the drug discovery process, due to its susceptibility to small molecule blockade, which can lead to potentially critical cardiotoxic symptoms. Filtering out the potential hERG channel blockers from drug candidates is therefore crucial for successful drug development. To address the need for reliable quantitative prediction of the hERG channel blocking ability of small molecules, we developed a machine learning model hERGBoost for prediction of hERG channel blockade in small molecules. This web server works on Chrome, Firefox, and Opera.

Server Submission
hERGBoost accepts compounds in SMILES format (Simplified Molecular-Input Line-Entry System). Please submit a single compound in SMILES or multiple compounds in SMILES. The input format should exclusively contain SMILES strings, with each line representing the SMILES notation for a single molecule. File extension should be '.smi' or '.txt'.
Input SMILES or Submit File:

Citation: Under submission

Bug reports: blisszen [at] cau.ac.kr

Swagger API for streamlined batch prediction is also available.

Training and test datasets used for development of hERGBoost are available at: http://ssbio.cau.ac.kr/software/hergboost/dataset.zip

The 2D structure of molecule is generated using SmileDrawer tool. https://doi.org/10.1021/acs.jcim.7b00425

School of integrative engineering
Chung-Ang University, Korea