Our scientists
use a combination of externally licensed and internally
developed computational and modeling tools to achieve their
goals. Internal development at BioPredict focuses on problems
for which commercial software is unavailable, inadequate, or
inappropriate in scale for modern high-throughput drug
discovery. A key focus at BioPredict is the development of
methods that allow the full spectrum of available information
to be brought to bear on a problem. Utilizing multiple
structures on related targets within a protein family is the
motivation behind
Comparing Active Sites within Protein Families. Merging
structural information with medicinal-chemical information is
the motivation behind Hypothesis-Driven
Docking and Enhancing
Results of Virtual Screens Using Data Mining Techniques
(links below). Using all information from a high-throughput
screen - both positive and negative - is a motivation behind
QSAR Analysis and High
Throughput Screening Interpretation. Imprecise and/or
incomplete data is a hallmark of typical problems encountered in
drug discovery. To be meaningful models should embrace these
aspects of their input and phrase their output appropriately -
i.e. statistically. This is the motivation behind our current
development of statistical ensemble-based approaches to
docking, ab initio design, pharmacophore derivation and
search, and 3D peptide-library profiling that uses the
mathematical framework of Markov Random Fields. The methods
embrace uncertainty in input, by for example enabling
simultaneous statistical docking against ensembles of protein
conformations. The methods frame their output statistically, by
providing ensembles of solutions enriched for the likelihood of
activity. The incremental cost of success when testing a
small ensemble of compounds far outweighs the potential cost of
failure when testing a single compound. |