MetaPred:A webserver for the Prediction of Cytochrome P450 Isoform responsible for Metabolizing a Drug Molecule

    Toxipred |KiDoQ | GDoQ | NPTOPE |KetoDrug |CRDD |OSDD |IMTECH | Raghava

** If you are using this server, please cite:: Prediction of cytochrome P450 isoform responsible for metabolizing a drug molecule BMC Pharmacology 2010, 10:8 **


» Home | » Submit| » Algorithm| » Developers| » Contact Us| » Help| » Dataset


Home OSCADD
Inhibitor Prediction

  KiDoQ
  GDoQ
  KetoDrug
  DMKPred
  TLR4HI
  ABMpred
  eBooster
  MDRIpred
  HIVFin
  MetaServer (Comming Soon)

Antigenic Properties

  Carbotope
ADMET Properties

  MetaPred
  ToxiPred
  DrugMint
  QED
  MetaServer (Comming Soon)
Descriptors

  Format Conversion
  WebCDK
  MetaServer
      Metapred

Advantage of Server:

One of the major challenges for researchers working in the field of drug discovery is to predict the metabolizing isoform of a drug molecule. Best of authors knowledge there is no free software or web server for predicting metabolizing isoforms of a substrate, though number of methods have been developed in past to predict substrate specificity. Most of the powerful software packages commonly used for computing molecular descriptors are commercial and license for limited use. Thus it is not possible to use them for developing web server. One of the major aims of our group is to promote open source software. In this study, we also developed model using molecular descriptors calculated using following software packages; i) Chemistry Development Kit (CDK) a open source java library and ii) a descriptors calculation software from Vlife.
The major advantage of MetaPred server is that, we also provide the list of calculated descriptors which we have used for model development.

Performance of MetaPred Server :

The performance achieved using CDK descriptors is nearly the same as we achieved using descriptors calculates using commercial software.Although Vlife is a commercial package but we buys right to use its descriptors in our web server. Firstly we compute 178 descriptors using CDK on our main dataset. Secondly, 26 best molecular descriptors were selected using WEKA based GreedyStepWise and genetic search approach. These 26 descriptors were used to develop SVM models based on 1-v-r approach. We achieved overall accuracy 81.42% on main dataset; single label was predicted for each substrate as described in above (single label prediction) section. The performance was evaluated using fivefold cross-validation technique. Similar approach was adopted for models based of Vlife descriptors and achieved maximum overall accuracy 80.58%. As our models based on CDK descriptors perform better than models based on Vlife so we develop and evaluate performance of rest of models on CDK descriptors.

Chemical Molecule information :

MetaPred is a user friendly web server, allows user to submit their molecule in mol2/sdf/smile format or by online drawing of molecule in JME editor. It also allows user to predict single or multiple label/isoform for a molecule.


Metapred