|
BioInfoBank Institute is a non-for-profit research
and development organization. The general objective
of the Institute is to generate, incubate and inspire
innovative ideas and to facilitate and promote
unrestricted and productive research conducted by
highly motivated excellent young scientists in
Poland. The Institute generates innovative
technological solutions. Some of them are converted
into commercial project ideas that can be
disseminated across the BioInfoBank network. The
institute not only educates experts in biotechnology
and information technology but also promotes
commercial exploitation of scientific discoveries by
their own authors through a spin-off program. The
main scientific focus of the institute is
Bioinformatics, an inter-disciplinary field of
science driven by achievements in biotechnology and
information technology. The institute is mainly funded by
Framework Grants from the European Commission and by
grants from the Foundation for Polish Science
and from the Polish Ministry of Science.
Main services:
Latest paper:
We present here the random forest supervised machine learning algorithm applied to flexible docking results from five typical virtual high throughput screening (HTS) studies. Our approach is aimed at: i) reducing the number of compounds to be tested experimentally against the given protein target and ii) extending results of flexible docking experiments performed only on a subset of a chemical library in order to select promising inhibitors from the whole dataset. The random forest (RF) method is applied and tested here on compounds from the MDL drug data report (MDDR). The recall values for selected five diverse protein targets are over 90% and the performance reaches 100%. This machine learning method combined with flexible docking is capable to find 60% of the active compounds for most protein targets by docking only 10% of screened ligands. Therefore our in silico approach is able to scan very large databases rapidly in order to predict biological activity of small molecule inhibitors and provides an effective alternative for more computationally demanding methods in virtual HTS.
Comb Chem High Throughput Screen. 2009 Jun;12 (5):484-9
|
