Re: [Rdkit-discuss] can't kekulize smiles generated by Chem.MolToSmiles
Hi Greg, 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. TJ On Sun, Jan 9, 2011 at 10:51 PM, Greg Landrum wrote: > Hi TJ, > > On Mon, Jan 10, 2011 at 2:37 AM, TJ O'Donnell wrote: >> Thanks Greg. I compiled in the changes and that molfile works fine >> now, but. >> Here are four new examples of molfiles that convert to mol and smiles just >> fine, but the resulting smiles won't parse properly back to a mol. >> >> Can you take a look? > > Thanks for finding another good bug. The problem here is caused, as > you probably guessed, by the size of the molecules (specifically by > the fact that more than 50 rings were open at one point during the > generation of the SMILES). I will get it fixed for the release. > > Best Regards, > -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
Re: [Rdkit-discuss] can't kekulize smiles generated by Chem.MolToSmiles
Dear TJ, On Mon, Jan 10, 2011 at 5:49 PM, TJ O'Donnell 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. Best Regards, -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
Re: [Rdkit-discuss] can't kekulize smiles generated by Chem.MolToSmiles
On Tue, Jan 11, 2011 at 5:09 AM, Greg Landrum wrote: > Dear TJ, > > On Mon, Jan 10, 2011 at 5:49 PM, TJ O'Donnell 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
