Hi Sereina,
At the moment, for historical reasons, the atom pair and topological
torsion fingerprint is limited to invariants that are at most 9 bits long
(i.e. <512). I think it should be possible to remove the restriction, but
it requires a bit of rethinking of the way the code works.
What you could do is use "the dictionary trick" and assign small integers
to the connectivity invariants that you see in your dataset and just pass
those along. This is a bit of extra book-keeping code that you'd need to
deal with, but should work.
-greg
On Fri, Jun 24, 2016 at 12:10 PM, Sereina <sereina.rini...@gmail.com> wrote:
> Hi RDKitters,
>
> Is there a way to use the Morgan (connectivity) atom invariants in the
> atom pairs fingerprint?
> I tried naively the following:
>
> inv = AllChem.GetConnectivityInvariants(m)
> AllChem.GetHashedAtomPairFingerprintAsBitVect(m, atomInvariants=inv)
>
> but it gives me the error “ValueError: list element larger than allowed
> value"
>
> Any ideas would be greatly appreciated.
>
> Best,
> Sereina
>
>
> ------------------------------------------------------------------------------
> Attend Shape: An AT&T Tech Expo July 15-16. Meet us at AT&T Park in San
> Francisco, CA to explore cutting-edge tech and listen to tech luminaries
> present their vision of the future. This family event has something for
> everyone, including kids. Get more information and register today.
> http://sdm.link/attshape
> _______________________________________________
> Rdkit-discuss mailing list
> Rdkit-discuss@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
>
>
------------------------------------------------------------------------------
Attend Shape: An AT&T Tech Expo July 15-16. Meet us at AT&T Park in San
Francisco, CA to explore cutting-edge tech and listen to tech luminaries
present their vision of the future. This family event has something for
everyone, including kids. Get more information and register today.
http://sdm.link/attshape
_______________________________________________
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
