On Thu, Aug 22, 2013 at 5:08 PM, Martin Guetlein <
[email protected]> wrote:
>
> IMHO it should be a built in functionality for each descriptor, but I
> dont know if that is easy to decide for each descriptor (e.g. for
> molecular weight it may for many applications be correct to sum up the
> weights of the single compounds, but for a QSAR model, the mean
> molecular weight sounds more appropriate to me).
>
I'd argue that even for a QSAR model one needs to make a call on how
descriptors are calculated. You might be provided with an SD file where
some structures have salts. But in the assay itself, the activity may not
be related at all to the salt component. In that case a descriptor derived
from all components would be misleading
--
Rajarshi Guha | http://blog.rguha.net
NIH Center for Advancing Translational Science
------------------------------------------------------------------------------
Introducing Performance Central, a new site from SourceForge and
AppDynamics. Performance Central is your source for news, insights,
analysis and resources for efficient Application Performance Management.
Visit us today!
http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
_______________________________________________
Cdk-user mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/cdk-user
