Sure... it's currently intended to be Toolkit agnostic, Rdf (the CTfile
kind not the triple kind) is kind of a meta-format.
John
On Thu, 20 Oct 2022 at 12:30, Uli Fechner wrote:
> I have to check what our priorities are at the moment but if I find the
> time would you be okay with me merging th
I have to check what our priorities are at the moment but if I find the
time would you be okay with me merging this in CDK?
On Thu, Oct 20, 2022 at 7:30 PM John Mayfield
wrote:
> Correct, my plan was to add it when I rewrote the MDL/CTfile stack which
> is needed. This is a v. large effort thoug
Depends on the data, journal reactions are more esoteric. People like to
try and eval/test atom mapping with hard/rare reactions. Common reaction
mechanisms used day-to-day are common because they're useful building
blocks :-).
Something I always thought it (IBM RxnMapper) would benefit from is so
Okay, thank you.
We do use RXNMapper and in our experience the numbers they state in their
publication are a bit optimistic...
On Thu, Oct 20, 2022 at 7:25 PM John Mayfield
wrote:
> It does not, personally today I would use the IBM AI based one.
>
> On Thu, 20 Oct 2022 at 07:05, Uli Fechner w
Correct, my plan was to add it when I rewrote the MDL/CTfile stack which is
needed. This is a v. large effort though and the danger in add the RDF
support is I would just redo it in future. However since the format is
quite trival it's possible to have some local code to do this (I did the
same wit
It does not, personally today I would use the IBM AI based one.
On Thu, 20 Oct 2022 at 07:05, Uli Fechner wrote:
> Hi,
>
> I vaguely remember that there is/was code in the CDK for atom-to-atom
> mapping of reactions (wasn't that RDTool?). However, I cannot find that now.
>
> RDTool by Asad uses
6 matches
Mail list logo
