Biomedical Engineering Reference
In-Depth Information
with ADME data provided by a large pharmaceutical company to show that
such models can be equivalent to those generated with commercial tools [64].
This sets the stage for using CDD as a selective ADME model building and
sharing platform on the cloud. The rationale for this is that the existing com-
putational ADME/Tox programs are limited in using the same very small data
sets from the literature or combining data sets from different groups, which is
suboptimal. These data sets also only cover a small region of chemical space,
focused on druglike molecules that tend to be compliant with the Rule of Five
[74]. Thus, there is a need for building models using data from various phar-
maceutical and biotechnology companies and then securely sharing the models
with collaborators or groups designated by the user. The advantage of using
such data from pharmaceutical and biotech companies is that they have gener-
ally screened orders-of-magnitude more data (e.g., tens to hundreds of thou-
sands of compounds under standardized conditions) than is in the public
domain and thus have far better coverage of chemistry space. This could result
in powerful models that will improve predictions for groups with compounds
of interest but no idea of their ADME properties, for example, assisting
neglected disease researchers.
New informatics tools that incorporate biology and chemistry with social
networking technologies should enable a better, faster, and ultimately cheaper
mechanism to discover and advance drug candidates in a collaborative manner,
regardless of whether they are for neglected, orphan, or potential “block-
buster” diseases. We have found that many biotechs use CDD as their corpo-
rate database as it is cost effective, provides compound registration functions,
and can handle their high-throughput screening data while having many other
features. Though it is hard to predict the direction this or similar technologies
could go, we have presented some ideas which we think are realistic. Challenges
to a tool like CDD, which has a foot in the commercial sector while at the
same time making data searchable to the community for free, come not only
from other cheminformatics or database companies [e.g., Heos from Scynexis
( http://www.scynexis.com/research_capabilities/heos_software.asp ), which cur-
rently does not have both private and public sharing capabilities, and Ensemble
from Artus Labs (www.artuslabs.com)] but also from the public-private part-
nership sector [e.g., the Innovative Medicines Initiative (http://imi.europa.eu/
index_en.html), which recently had a call for development of Open
Pharmacological Space]. It will be critical to continue to expand the CDD user
community and integrate with other open and proprietary tools such as work-
fl ow software while at the same time showing demonstrable success in improv-
ing drug discovery by assisting in collaborations, speeding up the process, and
fi nding new hits and leads. A pure database alone will only facilitate such
results and ultimately it may come down to how it is used and how well it is
exploited by the user. This will require integration of tools that can enhance
the user experience and build on their own expertise. These requirements
ultimately take away from the relatively elegant, yet straightforward and
simple-to-use experience, so it will be important not to lose sight of this.
Search WWH ::




Custom Search