Hi Andrew and others,

>
> I don't have the mad skills of most people on this list, so I'll be
> exploring all your suggestions over the next semester. The advice is
> invaluable.
>

Your message was great inspiration to me to 1) release more of our
group's QsarDB-related Java source code to Google Code and 2) develop
new end-user oriented GUI and command-line applications.

Now it's possible to convert chemical datasets from various source
formats (CSV, XLS, SDF, QMRF etc.), curate them against NCI/CADD
resolver service, perform quantum-chemical computations and descriptor
calculations, and more. The latest addition to the toolkit was
command-line property prediction application that you originally asked
for.

So, if you have your statistical models in PMML format (most modern
statistical software packages should be able to export in that format)
and descriptors in the YAML serialization format that I described
earlier today (should be easy to compose in text editor), then you can
have executable QsarDB archives without doing any Java programming.
The structure input is either via SMILES (one structure) or SDFile
(multiple structures).

The QsarDB project is sorely lacking proper documentation, but I
expect to have some really nice Prezis available in a few weeks time.


Best regards,
VR

------------------------------------------------------------------------------
Ridiculously easy VDI. With Citrix VDI-in-a-Box, you don't need a complex
infrastructure or vast IT resources to deliver seamless, secure access to
virtual desktops. With this all-in-one solution, easily deploy virtual 
desktops for less than the cost of PCs and save 60% on VDI infrastructure 
costs. Try it free! http://p.sf.net/sfu/Citrix-VDIinabox
_______________________________________________
Blueobelisk-discuss mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/blueobelisk-discuss

Reply via email to