On Tue, Jan 11, 2011 at 5:09 AM, Greg Landrum <greg.land...@gmail.com> wrote: > Dear TJ, > > On Mon, Jan 10, 2011 at 5:49 PM, TJ O'Donnell <t...@acm.org> wrote: >> >> As usual, thanks for your quick response. Yes, these were big molecules. >> Let me know if you'd like me to try out any changes. I can recompile >> changes from subversion easily now. I discovered these four examples >> using 1/10 of the chembl database and can try any new code changes >> on the entire set of 600K molecules. > > I checked some changes in yesterday that allow the RDKit to generate > correct (as far as I can tell) SMILES for those molecules. > Unfortunately at the moment the SMILES generated for these big > molecules are not canonical. I'm going to try and get that cleared up > in the next day or so before doing the release; I'll keep you posted.
Looks like I mis-spoke: the failing canonicalization tests were because I hadn't rebuilt everything. After a clean build everything looks fine. -greg ------------------------------------------------------------------------------ Gaining the trust of online customers is vital for the success of any company that requires sensitive data to be transmitted over the Web. Learn how to best implement a security strategy that keeps consumers' information secure and instills the confidence they need to proceed with transactions. http://p.sf.net/sfu/oracle-sfdevnl _______________________________________________ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
