in RDKit using proximityBonding=False.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
pon., 27 wrz 2021 o 12:25 Lewis Martin
napisał(a):
> Very interesting - thank you Francois! PDB re-do does the trick:
>
>
>
>
>
>
>
>
>
> *import
Hi Michał,
Conda-forge is your solution - you probably checked legacy rdkit channel.
Best,
Maciek
czw., 24 cze 2021, 19:59 użytkownik Michal Krompiec <
michal.kromp...@gmail.com> napisał:
> Hello,
> Is it possible to install RDKit on MacOSX in a Python 3.8 environment?
> There is no conda
Hi Pat,
What I found useful in the past is to make the imports inside of the
functions for dask. Not very elegant, but works.
Best,
Maciek
pon., 22 mar 2021, 14:30 użytkownik Patrick Walters
napisał:
> 2020.09.5
>
> On Mon, Mar 22, 2021 at 9:24 AM Guillaume GODIN <
>
, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
wt., 9 mar 2021 o 13:14 Jean-Marc Nuzillard
napisał(a):
> Hi Maciek,
>
> I would find your example rather readable even without explicit H atoms.
>
>
>
> I drew it like that because I do not have the wavy wedge at hand
,
Maciek Wójcikowski
mac...@wojcikowski.pl
wt., 9 mar 2021 o 10:47 Paul Emsley napisał(a):
> On 09/03/2021 09:01, Jean-Marc Nuzillard wrote:
> > Sure, testosterone may be drawn as
> > [snip]
>
> OK :-)
>
> That's a top quality rendering by the way. Ho
()
> params.removeDegreeZero = True
> mol_nohs = Chem.RemoveHs(mol, params)
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
czw., 21 sty 2021 o 16:58 Paolo Tosco
napisał(a):
> Hi Navid,
>
> if I interpret correctly your question, either of these should do
(),
but we have no such option unfortunately.
Best,
Maciek
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
czw., 23 lip 2020 o 16:41 Tim Dudgeon napisał(a):
> RDKit can read PDB files but is there any functionality to work with the
> resulting molecule at the
bond orders.
In ODDT it is also possible to run a docking "pipeline" with Vina using
RDKit exclusively, and use SDFs as a input/output.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
sob., 11 kwi 2020 o 15:57 Zhenting Gao <183310...@qq.com> napisał(a):
Hi,
I'm happy to help with Python projects.
śr., 1 kwi 2020, 21:31 użytkownik Geoffrey Hutchison <
geoff.hutchi...@gmail.com> napisał:
> Wearing my "admin for Open Chemistry" hat for the moment.. As a community,
> we've been very lucky to get a lot of good open source chemistry
> development
Thank Nils for pointing both algorithms to the list. Interestingly Greg is
putting together scaffold tree algorithm in this PR
https://github.com/rdkit/rdkit/pull/2911 so anyone could try it in the
nearest future, hopefully 2020 release.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac
make a lot of
assumptions about the molecule, so things like filling your valences on
atoms and defining bonds explicitly as single will help a lot. For very
small SMARTS the screen out rate might be small anyhow, unfortunately.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac
,
Maciek
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
pon., 10 lut 2020 o 16:10 Alexis Parenty
napisał(a):
> Dear Rdkiters,
>
> I am interested in doing substructure searches between many thousands
> structures and many thousands of fragments, as quickly
/index.jsp?topic=%2Fcom.vmware.vsphere.vcenterhost.doc_50%2FGUID-8B226625-4923-410C-B7AF-51BCD2806A3B.html
Best,
Maciek
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
czw., 23 sty 2020 o 08:15 Thomas Strunz napisał(a):
> Hi Greg,
>
> reopening this old questi
.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
wt., 17 gru 2019 o 18:38 Maciek Wójcikowski
napisał(a):
> Hi Peter,
>
> You can index any binary fingerprint (both sparse and explicit). Also, you
> can create any custom fp in python and pass it over to postgresql. Th
Hi Peter,
You can index any binary fingerprint (both sparse and explicit). Also, you
can create any custom fp in python and pass it over to postgresql. That
said, I have not managed to transfer a sparse one from python to postgres,
only the explicit.
Best,
Maciek
wt., 17 gru 2019, 13:00
Hi Thomas,
You could also use SetBitsFromList() method:
> bv.SetBitsFromList(np.where(ar)[0].tolist())
>
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
czw., 14 lis 2019 o 16:28 Greg Landrum napisał(a):
> Hi Thomas,
>
> There may be more effic
Mike,
On top of what Greg said what might be particularly useful is an options
parameter where you can pass some non default params to InChI call.
śr., 9 paź 2019, 07:22 użytkownik Greg Landrum
napisał:
> Hi Mike,
>
> The InChI API itself is not exposed. The contents of the module are in the
>
If you turn off the sanitization the splitting should be super fast too. If
that is the only thing you would like to do.
pon., 7 paź 2019, 10:31 użytkownik Téletchéa Stéphane <
stephane.teletc...@univ-nantes.fr> napisał:
> Le 05/10/2019 à 12:46, Chris Swain via Rdkit-discuss a écrit :
> > Hi,
>
Paolo and Chris,
There actually is Rdkit function to do this very task: SplitMolByPDBChainId
http://rdkit.org/docs/source/rdkit.Chem.rdmolops.html#rdkit.Chem.rdmolops.SplitMolByPDBChainId
sob., 5 paź 2019, 14:42 użytkownik Paolo Tosco
napisał:
> Hi Chris,
>
> The following, though quite
f you wish to be safe it is best to
save the two atom indices instead the bond idx itself.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
wt., 2 paź 2018 o 22:57 Nils Weskamp napisał(a):
> Hi Peter,
>
> to the best of my knowledge: for a given SMILES string, you sho
I would suggest that all coordination bonds to metal that exceed the
accepted valence of an atom could be mark as zero-ordered. This is what
happens in recent PDB reader changes and fixed a lot of problems with
sanitization.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac
Hi
As Nils has mentioned this is fingerprint dependent. ECFP4 have the
significant cutoff ~0.4, see https://pubs.acs.org/doi/10.1021/ci7004498
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-07-04 8:44 GMT+02:00 Nils Weskamp :
> Dear Phuong,
>
> unfo
,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-05-10 11:39 GMT+02:00 carlo del moro <delmoro.ca...@gmail.com>:
> Thanks to all for the replies,
>
> I put an example for better explain my problem.
> starting from a PDB representing HPE, I use RDKIT/obabel for calculate the
>
the release
on the docs.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-05-02 11:17 GMT+02:00 David Cosgrove <davidacosgrov...@gmail.com>:
> Hi Greg,
> After a quick poke about, I think the new documentation looks great in
> general. If a change is forced
ng the hash, you just need to look it up. Without salting such
lookup tables would not be that big i suppose. If you had such lookup
table, then you'd only need an algorithm (or GA) that builds a molecule
from a set of environments not randomly build it.
----
Pozdrawiam, | Best regards,
Maciek
,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-04-04 5:39 GMT+02:00 Greg Landrum <greg.land...@gmail.com>:
> Dear all,
>
> As you may have noticed, the new release (2018.03) is late.
>
> This is not, as you might expect, connected to my previous email about the
> backend
Hi Maria,
This is one of many routines molecule undergoes when reading from a "Corina
Mol2", which is implemented in RDKit. Unfortunately there is no way to turn
it off, due to the (gu)estimation of formal charges.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowsk
above example is
taken from RDKit's Lipinski module.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-03-09 13:56 GMT+01:00 Mariana Assmann <mariana.assm...@gmx.net>:
> Hi everyone,
>
> is it possible to check for a single bond if it is rotatable? I only
, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2018-01-11 16:30 GMT+01:00 Michał Nowotka <mmm...@gmail.com>:
> Hi,
>
> Imagine I have two numpy arrays containing zeros and ones (or bools)
> effectively being fingerprints:
>
> np_1, np_2 = some_fingerprints_a
ly.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-11-28 0:50 GMT+01:00 Francois BERENGER <beren...@bioreg.kyushu-u.ac.jp>
:
> On 11/28/2017 12:42 AM, Tim Dudgeon wrote:
> > I see exactly the same when I build with those cmake args.
>
> Maybe
Hi,
Wrap the reader into a list() function:
> mols = list(SDMolSupplier('in.sdf'))
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-11-21 15:39 GMT+01:00 abhik <ab...@ebi.ac.uk>:
> Hi,
>
> I am running a similarity search process using rd
Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Hi Lionel,
There is PropertyMol class which does what you want, see
http://www.rdkit.org/Python_Docs/rdkit.Chem.PropertyMol.PropertyMol-class.html
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-10-26 15:17 GMT+02:00 Lionel Colliandre <lio...@beckerdata.
of 1 to
each sides and it worked.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-09-14 20:53 GMT+02:00 Maciek Wójcikowski <mac...@wojcikowski.pl>:
> I've tried that, but ended up with molecules out of picture. I'll try
> again tomorrow and ping back
I've tried that, but ended up with molecules out of picture. I'll try again
tomorrow and ping back here should I succeed. The real problem were two
atom molecules, which have delta x or y = 0, such as C=0 or CN.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-09
Hi RDKitters!
Quick question: is there a way to force drawing to output molecules on a
grid image or separate in fixed scale (i.e. constant/matching bond length)?
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
Hi Noel,
sio.seek(0) before assert or sio.getvalue() instead read().
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-09-08 15:51 GMT+02:00 Noel O'Boyle <baoille...@gmail.com>:
> Hi all,
>
> I'd like to capture error messages during SMILES parsing
/rdkit/Chem/AllChem.py#L370
Then you can use Chem.RenumberAtoms to set the new order.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-07-18 14:31 GMT+02:00 Max Pillong <max.pill...@gmx.net>:
> Hi everyone,
>
> I am stuck on the following issue: I
Hi,
There is a method GetPropsAsDict() or GetPropNames() for RDKit molecule.
http://www.rdkit.org/Python_Docs/rdkit.Chem.rdchem.Mol-class.html#GetPropsAsDict
which should do what you want.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-27 11:26 GMT+02:00
versions of Ubuntu: Zetsy already
has the 2016.3 version https://packages.ubuntu.com/zesty/python-rdkit
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-22 5:00 GMT+02:00 Greg Landrum <greg.land...@gmail.com>:
> I'm not aware of any such repository.
>
&g
remember correctly the order may differ
from the canonical smiles, although that might have changed.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-15 9:03 GMT+02:00 Brian Kelley <fustiga...@gmail.com>:
> Yes, atoms are always added in file order. It w
I must correct myself, pandas was not installed, so the only test that
failed was "test3D".
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-04 15:07 GMT+02:00 Maciek Wójcikowski <mac...@wojcikowski.pl>:
> I tried compiling Git master on arm
Is there a big difference in the quality of the final dataset between
K-means and random under-sampling of big database (~20M)?
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-04 12:24 GMT+02:00 Samo Turk <samo.t...@gmail.com>:
> Hi Chris,
>
>
atoms not associated with molecules
> 116: Violation occurred on line 267 in file
> /root/rdkit/Code/GraphMol/Atom.cpp
> 116: Failed Expression: dp_mol
> 116:
> 116:
And few others, like Pandas fail to import etc. If you want full tracestack
I can upload it in separate file.
--
Has anyone try the Arm64 (aarch64)? Is it the same?
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-06-03 8:46 GMT+02:00 Gianluca Sforna <gia...@gmail.com>:
> On Thu, Jun 1, 2017 at 12:03 AM, Samo Turk <samo.t...@gmail.com> wrote:
> > Tha
Hi Greg,
Just FYI rdkit for Python 3.6 requires boost 1.56 which has no Python 3.6
version in your repo. I just tested Linux packages, but it should be the
same for other platforms.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-04-21 6:36 GMT+02:00 Greg
Hi Francois,
There are no Python 3.6 packages of rdkit right now.
I guess we can ask Greg or Riccardo to build them with the next release of
RDKit.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-04-12 10:27 GMT+02:00 François-Régis Chalaoux <chal
I find installing RDKit using Conda the easiest and the most
straightforward across all platforms.
First install miniconda [http://conda.pydata.org/miniconda.html] and then
in terminal: "conda install -c rdkit rdkit"
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojc
Which RDKit version do you have?
"print rdkit.__version__"
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-01-21 21:38 GMT+01:00 Janusz Petkowski <jjpet...@mit.edu>:
> Czesc again,
>
> Many thanks for the code snippet. I thought
t; Out[5]: '[H]c1([H])c1[H]'
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-01-21 15:54 GMT+01:00 Janusz Petkowski <jjpet...@mit.edu>:
> Czesc Maciek,
>
> Thanks a lot for suggesting "onlyOnAtoms" option out. It looks like it
Hi Janusz,
AddHs has a parameter "onlyOnAtoms" which takes a list of indices of atoms
to include. [http://www.rdkit.org/Python_Docs/rdkit.Chem.rdmolops-
module.html#AddHs]
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2017-01-20 23:21 GMT+01:00 Janusz
Hi Jean-Marc and others,
There is also CanonicalRankAtoms [
http://www.rdkit.org/Python_Docs/rdkit.Chem.rdmolfiles-module.html#CanonicalRankAtoms]
which seams to be forgotten.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-12-18 23:14 GMT+01:00 Jean-Marc
nefficient, so I'd parse all
strings passing above filter. Although there will be some false positives
like "CC" which may occur in text (emails especially).
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-12-02 10:11 GMT+01:00 Alexis Parenty <alexis
Hi Michał,
Have you tried using AdjustQueryProperties(). I think Greg mentioned it in
his presentation at UGM
http://www.rdkit.org/Python_Docs/rdkit.Chem.rdmolops-module.html#AdjustQueryProperties
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-11-01 19:20 GMT
ol(ParentMol, bonds, atomMap=atommap)
atommap is a dictionary populated with atom indicies mapping from ParentMol
to the new one.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-11-01 11:00 GMT+01:00 Juuso Lehtivarjo <juuso.lehtiva...@gmail.
Hi,
If you really desperately need it, there is a mockup of MolToMol2Block()
and MolToMol2File() by Jan and myself [see
https://github.com/rdkit/rdkit/pull/415], but it's still rough around the
eadges at best.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-10
I could only imagine the errors when using threading/multiprocessing +
reusing SDMolSupplier object... So if I understand correctly the official
line of RDKit is: "a multimol file => supplier => file(-like) objects".
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac..
Thank you Andrew! Indeed it's working and it's a tiny bit faster too.
Best,
M
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-10-03 13:08 GMT+02:00 Andrew Dalke <da...@dalkescientific.com>:
> On Oct 2, 2016, at 10:48 PM, Maciek Wójcikowski wrote:
>
,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-10-02 22:20 GMT+02:00 Brian Kelley <fustiga...@gmail.com>:
> It's neither a bug nor a feature in this case, simply the specification of
> the mdl format.
>
> The SD in an sd file stands for "structured data" which are the
I've noticed that GMail might have mess up spaces in the text, so I
included the example as an attachment.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-10-02 21:46 GMT+02:00 Maciek Wójcikowski <mac...@wojcikowski.pl>:
> Hi RDKitters,
>
&
irs which fall
within cutoff, and a bool array saying if they match the angle criteria.
Note, that it looks at D-A distance and not at H-A distance.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-09-14 12:16 GMT+02:00 Greg Landrum <greg.land...@gmail.com>:
, nonBondedThresh=10.,
ignoreInterfragInteractions=False)
where comp is complex Mol, ff_mp are force-field molecular properties.
PS. There is no C++ API to my knowledge, although Greg/Paolo might have
something in his undocumented wizard hat ;)
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac
in
residues by "residue number + residue chain".
Implementing such grouping in similar way as SplitMolByPDBResidues/Chains
would also loose the atom mapping if I understand the RDKit code correctly.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-03-22 11
I correct myself, all residue types are available
from Chem.SplitMolByPDBResidues().
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-03-22 9:50 GMT+01:00 Maciek Wójcikowski <mac...@wojcikowski.pl>:
> Hi Greg,
> 2016-03-22 6:28 GMT+01:00 Greg Landru
Hi Greg,
2016-03-22 6:28 GMT+01:00 Greg Landrum <greg.land...@gmail.com>:
>
> Hi Maciek,
>
>
> On Mon, Mar 21, 2016 at 8:33 PM, Maciek Wójcikowski <mac...@wojcikowski.pl>
wrote:
>>
>>
>> I came across one problem with RDKit today, namely Chem.PathT
cid) in separate mol. It
would be much easier if we could use "Molecule -> Residues -> Atoms"
instead of "Molecule -> Atoms -> (grouping of monomers) -> Residues".
Pozdrawiam, |
= pickle.loads(pickle.dumps(mol))
print list(mol2.GetPropNames()) # ['']
In [19]: rdkit.__version__
Out[19]: '2015.09.2'
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
--
Transform Data
x.replace('>', '')})
http://pandas.pydata.org/pandas-docs/stable/generated/pandas.read_csv.html
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-03-11 11:12 GMT+01:00 Paul Czodrowski <paul.czodrow...@merckgroup.com>:
> Dear RDKitter & Pandas-Dataframes h
Hi,
Few months back Greg has added CanonicalRankAtoms to rdkit.Chem after my
similar question.
http://www.rdkit.org/Python_Docs/rdkit.Chem.rdmolfiles-module.html#CanonicalRankAtoms
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-03-10 13:18 GMT+01:00 Michal
Hello,
I'd guess they mean a graph = 2D representation of molecule.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-02-03 14:24 GMT+01:00 Guillaume GODIN <guillaume.go...@firmenich.com>:
> Dear All,
>
>
>
> Can you explain me a li
So my initial guess was wrong. They also include a github repo, where you
can exactly see how the graph is formed:
https://github.com/HIPS/neural-fingerprint/blob/master/neuralfingerprint/mol_graph.py#L75
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2016-02-03 14
Hi David,
I think that SF was abandoned in favor of GitHub, so for new releases go to
https://github.com/rdkit/rdkit/releases
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-12-10 11:12 GMT+01:00 David Cosgrove <davidacosgrov...@gmail.com>:
> Hi All
Hi Gaetano,
There is property called "_TriposPartialCharge" for each atom. To get
partial charges read from mol2 just execute:
[float(a.GetProp("_TriposPartialCharge")) if "_TriposPartialCharge" in
a.GetPropNames() else 0.0) for a in mol.GetAtoms()]
Pozdra
e activate test_rdkit
conda install -c rdkit rdkit
conda install -c rdkit rdkit=2015
I hope we manage to get it fixed for 2015.09 :)
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojc
Hi Christopher,
Since you're mentioning Rajarshi's SMARTS, I guess that you haven't seen
Greg's latest revision of PAINS filters (see
http://rdkit.blogspot.com.es/2015/08/curating-pains-filters.html). On the
other hand, during RDKit UGM I remember Greg saying that some of the
filters would
).
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-08-28 17:17 GMT+02:00 Jing Lu ajin...@gmail.com:
Thanks, Greg,
Yes, sciket learn will automatically promote to arrays of float with
check_array()
function. What I am currently doing is
fpa = numpy.zeros((len(fp
Hi Jing,
Most fingerprints are binary, thus can be stored as np.bool_, which
compared to double should be 64 times more memory efficient.
Best,
Maciej
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-08-27 16:15 GMT+02:00 Jing Lu ajin...@gmail.com:
Hi Greg
Hi Greg,
This is super feature, but are there any downsides? Why not to enable it by
default (provided the dependencies are met)?
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-07-03 16:54 GMT+02:00 Greg Landrum greg.land...@gmail.com:
Hi Adam,
Sorry I
I vote for setting up readthedocs.org automatic documentation generation,
plus some sphinx API docs. All we need to do then is to keep track of
changes and create solid docstrings.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-03-13 15:43 GMT+01:00 David Hall
My bad. I knew it's Sphinx generated, although had no idea it's in sync
with Github :) There is also no mention of it on github (a badge would be
nice) - Pull Request coming.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-03-13 16:10 GMT+01:00 Greg Landrum
Hello,
If interested in clustering in python I can recommend, as usual, sklearn:
http://scikit-learn.org/stable/modules/clustering.html
It's pretty much all you should need. Have fun!
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-02-23 11:43 GMT+01:00 Anthony
output values for one feature vector.
PS.
I could also recommend my Open Drug Discovery Toolkit for playing around
with RDKit and scikit-learn.
https://github.com/oddt/oddt
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-02-20 7:29 GMT+01:00 Greg Landrum greg.land
/oddt/jcheminf/blob/master/Snippet_3.ipynb]
- train RF using many fingerprints (OpenBabel's and RDKit's)
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-02-20 13:52 GMT+01:00 Igor Filippov igor.v.filip...@gmail.com:
Oops, sorry, got into a wrong branch! I am
That's true. it's been a while since last release of OB and I'm currently
working on git master branch, since it has less bugs and more features.
Have fun and feel free to mail me if you'd have trouble with ODDT.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2015-02
Hi,
Actually there are some slides on github: https://github.com/rdkit/UGM_2014
I can't wait to see them all since I couldn't be there myself.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2014-10-24 13:29 GMT+02:00 Nicholas Firth nicholas.fi...@icr.ac.uk:
Hi
Just as Christos said: you're missing boost path in LD_LIBRARY_PATH
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2014-07-28 15:53 GMT+02:00 Enrico Perspicace
e.perspic...@mx.uni-saarland.de:
Dear Greg,
Thanks for your help.
I have this:
[root@Pc-Eric-linux
/PandasTools.py#L284)
and warks really well.
Pozdrawiam, | Best regards,
Maciek Wójcikowski
mac...@wojcikowski.pl
2014-07-02 14:19 GMT+02:00 Adrian Jasiński jasinski.adr...@gmail.com:
If I can start a list of wishes for new function it will be nice to add a
possibility for drawing the series
87 matches
Mail list logo
