Hi all,
I started writing a RDKIT-python-script including Andrew Dalke's MCS
implementation (thanks by the way) for a ligand-based (MCS) alignment and
noticed some
odd things - which might also be due to my implementation. The idea of the
program is that given a template molecule and a library
Dear RDKitters,
anyone worked with RDKit (data processing descriptor calculation)
scikit-learn (train Random Forests) and could share some experiences with
setting up a domain of application?
Cheers Thanks so far,
Paul
This message and any attachment are confidential and may be privileged
Dear RDKitters,
anyone worked with RDKit (data processing descriptor calculation)
scikit-learn (train Random Forests) and could share some experiences with
setting up/defining a domain of applicability?
Cheers Thanks so far,
Paul
P.S.: Just resent this mail, since the last mail contained
Hi Paul,
We are using RDKit along with R, instead of scikit-learn, though the
general idea is the same.
Using a good dataset of compounds with known biological property you can
train a model using an algorithm such as Random Forests.
This model, can later be used on a new dataset to predict the
Hi Fabian,
On Mar 19, 2013, at 2:05 PM, Fabian Dey wrote:
- in order to get a 1-1 correspondence of atom ids (to get the coordinate
map) I had to search the MCS-SMARTS match again against the original files to
get the atom-ids - is there a more direct way to do this?
There is no more direct
Hi RDKitters,
I'm sure this must of been covered somewhere else but I can't find it in the
forum or the source.
I am manipulating SMILES strings and wonder whether I can use RDKit as a
shortcut, so my question is does the order of occurrence in a SMILES string of
an atom match the atom index
I agree with Christian. I have been using fraction of trees voting for the
prediction as an indicator of model confidence (and thus some kind of measure
of applicability domain) for many years.
This is, by the way, how the confidence values produced by the rdkit's models
are calculated
-greg
Hi Nick,
On Mar 19, 2013, at 5:00 PM, Nicholas Firth nicholas.fi...@icr.ac.uk wrote:
Hi RDKitters,
I'm sure this must of been covered somewhere else but I can't find it in the
forum or the source.
I am manipulating SMILES strings and wonder whether I can use RDKit as a
shortcut, so my
On Mon, Mar 18, 2013 at 2:36 PM, Syeda Sabrina sus364...@gmail.com wrote:
Hi Greg,
If this is working as it is supposed to be then I don't understand why even
if I add only explicit Hydrogens to a molecule and check the number the of
explicit Hydrogens attached to it later why it returns
Hello Greg,
Thanks for your input. Well, basically the current version of
RunReactants() deals with the implicit Hs in some cases, so I was trying to
make some new function for my code that will replace the implicit Hs by
some other similar atom (e.g. At) and then once I am done with the
I meant to say probably current version of the RunReactants messes up with
the implicit Hs in some cases.
I am not sure though. This is a guess and trying to see how it deals with
the problematic cases if I replace those implicit Hs with some other
similar atom.
Sorry for the confusion!
Thanks
Fabian,
On Tue, Mar 19, 2013 at 2:05 PM, Fabian Dey fabian...@gmail.com wrote:
I started writing a RDKIT-python-script including Andrew Dalke's MCS
implementation (thanks by the way) for a ligand-based (MCS) alignment and
noticed some
odd things - which might also be due to my
12 matches
Mail list logo
