MolClass version 1.5 (November 2013 beta release)

Rapid Molecule Classification Based on Structure and Activity

Update November 19th 2013
The new release has undergone some major improvements including a much faster structure search, new fingerprints, new machine learning algorithms, an 85% similarity match and likelihood score distribution display. For more information please go to Details.
In addition to the publication release we added models to cover the metabolikeness of molecules, compound aggregation effects, liver toxcicity (DILI) and interference with drug pumps as well as a model to predict the interference with mitochondrial fusion an evolutionary conserved process.
Those and future models can help to guide compound selection for follow up screens and library design. Most computer-aided ventures overlook promiscuous binding to off-target proteins that results in side effect of a drug. Those compounds will be visible in the approach we have taken. We hope that our portlet will help to guide scientists in the systems- and chemical biology community. The current dataset contains more than 78000 molecules with predictions for 18 experimental datasets.

MolClass generates computational models from small molecule datasets using structural features identified in hit and non-hit molecules. In contrast to existing experimental resources like PubChem and Chembank, MolClass aims to present the user with a likelihood value for each molecule entry. This creates an activity fingerprint that currently includes models for Ames mutagenicity, blood brain barrier penetration, CaCo2 penetration (derived from Hou et al.), stem cell neurosphere proliferation (derived from Diamandis et al.), Autofluorescence Model (derived from ChemBank data), Flucanozole synergy predictive model (derived from Spitzer et al.) and a toxcicity benchmark.
In addition we uploaded some example datasets build on experimental data from Pubchem to build a P. falicarum Sensitivity data model (derived from Yuan et al.) and a Hsp90 co-chaperone disrupter screen. The second source is the NCI funded database ChemBank, here we incorporated from a Cell Cycle Inhibitor Screen, a Beta Cell Transdifferentiation model, Xenopus Actin Polymerization dataset and a Thrombin Acitivity Predictive Model (derived from ChEMBL data).