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
