Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2011 Jun;25(6):533-54.
doi: 10.1007/s10822-011-9440-2. Epub 2011 Jun 10.

Online Chemical Modeling Environment (OCHEM): Web Platform for Data Storage, Model Development and Publishing of Chemical Information

Affiliations
Free PMC article

Online Chemical Modeling Environment (OCHEM): Web Platform for Data Storage, Model Development and Publishing of Chemical Information

Iurii Sushko et al. J Comput Aided Mol Des. .
Free PMC article

Abstract

The Online Chemical Modeling Environment is a web-based platform that aims to automate and simplify the typical steps required for QSAR modeling. The platform consists of two major subsystems: the database of experimental measurements and the modeling framework. A user-contributed database contains a set of tools for easy input, search and modification of thousands of records. The OCHEM database is based on the wiki principle and focuses primarily on the quality and verifiability of the data. The database is tightly integrated with the modeling framework, which supports all the steps required to create a predictive model: data search, calculation and selection of a vast variety of molecular descriptors, application of machine learning methods, validation, analysis of the model and assessment of the applicability domain. As compared to other similar systems, OCHEM is not intended to re-implement the existing tools or models but rather to invite the original authors to contribute their results, make them publicly available, share them with other users and to become members of the growing research community. Our intention is to make OCHEM a widely used platform to perform the QSPR/QSAR studies online and share it with other users on the Web. The ultimate goal of OCHEM is collecting all possible chemoinformatics tools within one simple, reliable and user-friendly resource. The OCHEM is free for web users and it is available online at http://www.ochem.eu.

Figures

Fig. 1
Fig. 1
A schematic overview of an individual record in the OCHEM database
Fig. 2
Fig. 2
A screenshot of the second step of the batch upload process
Fig. 3
Fig. 3
A screenshot of data preview, the third step of the batch upload
Fig. 4
Fig. 4
An overview of different user levels in the OCHEM. User’s rights decrease with level. Users can edit/delete entities of the same or lower user levels
Fig. 5
Fig. 5
The workflow of a typical QSAR research in the OCHEM system
Fig. 6
Fig. 6
The first step of model creation: selection of a training and validation set, a machine learning method and a validation protocol
Fig. 7
Fig. 7
A screenshot of the descriptor selection and configuration panel
Fig. 8
Fig. 8
The list of pending models. The models being calculated and the completed models waiting for an inspection by the user are listed here
Fig. 9
Fig. 9
Basic statistics for a predictive model. The training set has a link that opens a browser of experimental records where a user can examine properties of all compounds used in the model. A click on a dot in the observed versus predicted chart opens a similar browser information window for the corresponding compound
Fig. 10
Fig. 10
Statistics of a classification model. Summarized are the prediction accuracies for the training and test sets as well as confusion matrices
Fig. 11
Fig. 11
The plot shows residuals of the predictions for the training set, mapped against the selected “distance to model”, in this case ASNN-STDEV, the standard deviation of ensemble prediction vector. This information is used to estimate accuracy of predictions, when the model is applied to new compounds
Fig. 12
Fig. 12
Selection of models to predict properties for new compounds

Similar articles

See all similar articles

Cited by 62 articles

See all "Cited by" articles

References

    1. Patani GA, LaVoie EJ. Bioisosterism: a rational approach in drug design. Chem Rev. 1996;96:3147–3176. doi: 10.1021/cr950066q. - DOI - PubMed
    1. Cronin MTD, Schultz TW. Pitfalls in QSAR. J Mol Struct Theochem. 2003;622:39–51. doi: 10.1016/S0166-1280(02)00616-4. - DOI
    1. Balakin KV, Savchuk NP, Tetko IV. In silico approaches to prediction of aqueous and DMSO solubility of drug-like compounds: trends, problems and solutions. Curr Med Chem. 2006;13:223–241. doi: 10.2174/092986706775197917. - DOI - PubMed
    1. Tetko IV, Livingstone DJ. Rule-based systems to predict lipophilicity. Oxford: comprehensive medicinal chemistry II. Elsevier; 2007. pp. 649–668.
    1. Moriguchi I, Hironon S, Liu Q, Nakagome I, Matsushita Y. Simple method of calculating octanol/water partition coefficient. Chem Pharm Bull. 1992;40:127–130.

Publication types

LinkOut - more resources

Feedback