Re: [Rdkit-discuss] Source of the solubility data?
That's a great idea. A pull request with that change would be very welcome. :-) On Wed, Feb 26, 2020 at 3:19 AM Gao Zhenting wrote: > Hi Greg, > > Thanks for the details. > Would you like to add this note to the GitHub( > https://github.com/rdkit/rdkit/tree/master/Docs/Book/data)? Other > visitors will get the message then. > > Best regards > Zhenting > > Greg Landrum 于2020年2月26日周三 下午2:48写道： > >> Hi Zhenting, >> >> That's the Huuskonen dataset. The reference is here: >> https://pubs.acs.org/doi/10.1021/ci9901338 >> The origins of the SDF itself are unfortunately lost in antiquity. I >> originally got them here: >> http://cheminformatics.org/datasets/huuskonen/index.html >> but cheminformatics.org no longer exists. archive.org isn't working at >> the moment, but when it's back someone could check there to try and figure >> out who curated the SDF >> >> -greg >> >> >> On Mon, Feb 24, 2020 at 11:53 PM Gao Zhenting >> wrote: >> >>> Hi Greg, >>> >>> I am trying to reproduce some machine learning scripts using >>> >>> https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.test.sdf >>> >>> >>> https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.train.sdf >>> >>> >>> What is the source of these data? How are they organized? Any citation? >>> >>> Best regards >>> Zhenting >>> ___ >>> Rdkit-discuss mailing list >>> Rdkit-discuss@lists.sourceforge.net >>> https://lists.sourceforge.net/lists/listinfo/rdkit-discuss >>> >> ___ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
Re: [Rdkit-discuss] Source of the solubility data?
Hi Greg, Thanks for the details. Would you like to add this note to the GitHub( https://github.com/rdkit/rdkit/tree/master/Docs/Book/data)? Other visitors will get the message then. Best regards Zhenting Greg Landrum 于2020年2月26日周三 下午2:48写道： > Hi Zhenting, > > That's the Huuskonen dataset. The reference is here: > https://pubs.acs.org/doi/10.1021/ci9901338 > The origins of the SDF itself are unfortunately lost in antiquity. I > originally got them here: > http://cheminformatics.org/datasets/huuskonen/index.html > but cheminformatics.org no longer exists. archive.org isn't working at > the moment, but when it's back someone could check there to try and figure > out who curated the SDF > > -greg > > > On Mon, Feb 24, 2020 at 11:53 PM Gao Zhenting > wrote: > >> Hi Greg, >> >> I am trying to reproduce some machine learning scripts using >> >> https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.test.sdf >> >> >> https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.train.sdf >> >> >> What is the source of these data? How are they organized? Any citation? >> >> Best regards >> Zhenting >> ___ >> Rdkit-discuss mailing list >> Rdkit-discuss@lists.sourceforge.net >> https://lists.sourceforge.net/lists/listinfo/rdkit-discuss >> > ___ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
Re: [Rdkit-discuss] Source of the solubility data?
Hi Zhenting, That's the Huuskonen dataset. The reference is here: https://pubs.acs.org/doi/10.1021/ci9901338 The origins of the SDF itself are unfortunately lost in antiquity. I originally got them here: http://cheminformatics.org/datasets/huuskonen/index.html but cheminformatics.org no longer exists. archive.org isn't working at the moment, but when it's back someone could check there to try and figure out who curated the SDF -greg On Mon, Feb 24, 2020 at 11:53 PM Gao Zhenting wrote: > Hi Greg, > > I am trying to reproduce some machine learning scripts using > > https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.test.sdf > > > https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.train.sdf > > > What is the source of these data? How are they organized? Any citation? > > Best regards > Zhenting > ___ > Rdkit-discuss mailing list > Rdkit-discuss@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/rdkit-discuss > ___ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
[Rdkit-discuss] Source of the solubility data?
Hi Greg, I am trying to reproduce some machine learning scripts using https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.test.sdf https://github.com/rdkit/rdkit/blob/master/Docs/Book/data/solubility.train.sdf What is the source of these data? How are they organized? Any citation? Best regards Zhenting ___ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
