Inhibitor Prediction

  KiDoQ (Mtb target)

  GDoQ (Mtb target)

  ABMpred (Mtb target)

  eBooster (Mtb target)

  MDRIpred (Mtb cell)

  CancerIN (Cancer)

  ntEGFR (Cancer EGFR)

  EGFRpred (Cancer EGFR)

  DiPCell (Pancreatic Cancer)

  DMKPred (Human Kinases)

  TLR4HI (Human TLR4)

  HIVFin (HIV)

Antigenic Properties

ADMET Properties

  MetaPred (Cytochrome P450)

  ToxiPred (Aqueous toxicity)

  DrugMint (Drug-like)

  QED (Oral drug-like)

  Format Conversion



Welcome to DrugMint server

If you are using this webserver please cite Dhanda et. al 2013: DrugMint: A webserver for predicting and designing of drug-like molecules. Biology Direct 2013

DrugMint is a web server developed for predicting drug-likelihood of a compound. All models were trained, tested and evaluated on a dataset contain 1347 approved drugs obtained from DrugBank 2.5 and 3206 experimental drugs. All QSAR models were developed using open source software packages like PaDEL, WEKA, SVM_Light. Overall objective of this server is to provide service to drug development community in predicting, screening and designing drug-like molecules.
DrugMint is also available in following platform:
1. Mirror Site at http://osddlinux.osdd.net/oscadd/drugmint
2. Standalone version at http://osddlinux.osdd.net>
3. Galaxy version at http://osddlinux.osdd.net:8001

Major Modules

Module Description
Draw_Structure This module allows users to generate structure of their molecules using Marvin applet and to predict its drug-like potential.
Virtual_Screening This module is designed for virtually screeing of chemcial library or set of chemicals. This module allows users to predict drug-like potential of each molecule submitted by a user
Analog_Designing This module is important for lead optimization and analogs based drug designing. It generate a virtual chemical library using user-specified scaffold, blocks and linkers; drug-likeness of each molecule of library is also predicted.
Search_Database Drug-like potentail of each molecule in CheEMBL and ZINC datbases has been computed and maintained. User can search drug-like property of their molecule by providing ChEMBL or ZINC IDs.