from:"Jennifer Wei"

[Rdkit-discuss] NeurIPS 2020 Workshop on Machine Learning for Molecules: Call for Papers

2020-09-03 Thread Jennifer Wei via Rdkit-discuss

Hello RDKit community,

The call for proposals to the NeurIPS 2020 workshop is now open. Please see
below for details.

Best,
Jennifer

=

 NeurIPS 2020 Workshop on Machine Learning for Molecules.

11 or 12 December 2020

https://ml4molecules.github.io/

Please direct questions to  ml4moleculesworkshop2...@gmail.com

IMPORTANT DATES:

* Submission Deadline: 5. October 2020 25:59 AOE

* Author notification: 23. October 2020

* Workshop: 11 or 12 December 2020



CALL FOR PAPERS



The 2020 NeurIPS Workshop on Machine Learning for Molecules calls for
high-quality contributions on the following topics:



* Applications of ML for molecules (i.e. chemistry, material science,
quantum mechanics, biochemistry, biophysics, structural biology, and
related areas)

* Graph neural networks

* Representation learning for molecules

* Prediction of molecular properties or bioactivities

* ML for quantum chemistry and molecular dynamics

* Generative models of molecules and de novo design

* ML for protein structures

* ML for reaction data, reaction prediction, and synthesis planning

* Active Learning & Uncertainty Quantification

* Interpretable models

* Benchmarks and analysis of state of the art papers

* Any other topic related to the workshop theme



We call for the submission of breaking edge, high-quality work in progress
in the form of extended abstracts or short communication papers, however,
finalized projects will also be considered. Work that is presented at the
main NeurIPS conference or has been published at other peer-reviewed venues
or journals will not be accepted in the workshop. Submissions will be
accepted as contributed talks or poster presentations. Accepted final
versions will be posted on the workshop website (and are archival but do
not constitute a proceedings).



SUBMISSION INSTRUCTIONS



Submissions should be no longer than 4 pages in NeurIPS style. References
do not count towards the page limit. Appendices are discouraged and
reviewers will not be required to read beyond the 4 page limit. Papers have
to be submitted as anonymised PDF.



We will provide a link to an electronic submission system in due course at
https://ml4molecules.github.io/



PEER REVIEW AND ACCEPTANCE CRITERIA



All submissions will undergo anonymized peer review.



Accepted papers will be chosen based on technical merit and suitability to
the workshop's goals. All accepted papers will be included in the poster
sessions on the day of the workshop.



COPYRIGHT FOR ACCEPTED PAPERS



This workshop will be informally published online but not officially
archived. This means:



* Authors will retain full copyright of their papers.

* Acceptance to this workshop does not preclude publication of the same
material in another journal or conference.



We will post links to accepted papers on our workshop website.



Authors should clearly state any overlapping published work at time of
submission.





ORGANIZING COMMITTEE



Brooks Paige

Jennifer Wei

José Miguel Hernández-Lobato

Marwin Segler

Matt Kusner
___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

Re: [Rdkit-discuss] Converting csv/xls file containing SMILES to .sdf

2020-05-28 Thread Jennifer Wei via Rdkit-discuss

Hi Joanna,

If you load the molecules from SMILES with RDKit, you can write them out
using AllChem.SDWriter.

Best,
Jennifer

On Thu, May 28, 2020 at 9:51 AM Gustavo Seabra 
wrote:

> You can open the csv file directly into Schrodinger's Maestro. The free
> version can open CSV files.
>
> --
> Gustavo Seabra
>
> --
> *From:* ITS RDC 
> *Sent:* Thursday, May 28, 2020 9:11:42 AM
> *To:* RDKit Discuss 
> *Subject:* [Rdkit-discuss] Converting csv/xls file containing SMILES to
> .sdf
>
> Hi all,
>
> I have a list of compounds that I want to know their topological and
> molecular properties to be able to generate a model for QSAR. I have over a
> hundred compounds contained in an MS Excel file in csv format since we only
> downloaded these compounds from existing chemical databases that do not
> offer the sdf format. I think it is not convenient to manually open each
> compound in ChemDraw to pool all compounds. I am looking into PandasTools
> but the documentation only indicated that sdf can be converted to csv and
> not vice versa. Has anyone worked with similar task before? Your response
> is very much appreciated. Thank you.
>
> Joanna
> ___
> 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] Are any of the UGM talks recorded?

2020-03-05 Thread Jennifer Wei via Rdkit-discuss

OK Thanks, I'll just have to try and come next time then.

On Thu, Mar 5, 2020 at 3:50 AM Greg Landrum  wrote:

> Hi Jennifer,
>
> We don't have recordings of any of the UGM presentations. Sorry.
>
> -greg
>
>
> On Wed, Mar 4, 2020 at 6:57 PM Jennifer Wei via Rdkit-discuss <
> rdkit-discuss@lists.sourceforge.net> wrote:
>
>> Hi All,
>>
>> I was wondering if any of the UGM talks are recorded. I'm particularly
>> interested in this talk
>> <https://github.com/rdkit/UGM_2019/blob/master/Presentations/Sayle_Clustering.pdf>
>> by Robert Sayle from the 2019 UGM.
>>
>> Thanks!
>> Jennifer
>> ___
>> 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] Are any of the UGM talks recorded?

2020-03-04 Thread Jennifer Wei via Rdkit-discuss

Hi All,

I was wondering if any of the UGM talks are recorded. I'm particularly
interested in this talk

by Robert Sayle from the 2019 UGM.

Thanks!
Jennifer
___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

Re: [Rdkit-discuss] Molecules not rendere in Dataframe

2019-11-04 Thread Jennifer Wei via Rdkit-discuss

Jan, I think this is the same issue you ran into in your example colab?

On Mon, Nov 4, 2019 at 2:03 PM Markus Heller  wrote:

> Hi,
>
>
>
> In a Jupyter notebook, the following code does not show renderings of the
> molecules in a Pandas dataframe:
>
>
>
> 
>
> from rdkit import Chem
>
> from rdkit.Chem import PandasTools
>
> from rdkit.Chem.Draw import MolsToGridImage
>
> from rdkit.Chem.Draw import IPythonConsole
>
> from rdkit.Chem import rdDepictor
>
>
>
> rdDepictor.SetPreferCoordGen(True)
>
> IPythonConsole.ipython_useSVG = True
>
>
>
> test_df = pd.read_csv(‘test.smi’, delim_whitespace=True, header=None,
> names=[‘smiles’, ‘id’])
>
>
>
> PandasTools.RenderImagesInAllDataFrames(images=True)
>
>
>
> PandasTools.AddMoleculeColumnToFrame(test_df, ‘smiles’, ‘mol’,
> includeFingerprints=False)
>
>
>
> test_df
>
> 
>
>
>
> Instead, string representations are shown (I think), i.e. every field in
> the mol column starts with
>
>
>
> 
>
>
> As far as I understand the documentation,
> PandasTools.RenderImagesInAllDataFrames(images=True) should show the
> rendered molecules.  What am I doing wrong?
>
>
>
> I’m using RDkit version 2019.03.4.0 via Anaconda.
>
>
>
> Thanks
>
> Markus
>
>
>
> --
>
> *Markus Heller, PhD*
>
> Senior Scientist
>
> Direct: 604.827.1122 <(604)%20827-1122>   Main: 604.827.1147
> <(604)%20827-1147>
>
>
>
>  [image: A027228F]
>
> 2405 Wesbrook Mall, 4th Floor, Vancouver, BC V6T 1Z3
>
>
>
> This email and any attachments thereto may contain confidential material
> for the sole use of the intended recipient. Any review, copying, or
> distribution of this email (or any attachments thereto) by others is strictly
> prohibited. If you are not the intended recipient, please contact the
> sender immediately and permanently delete the original and any copies of
> this email and any attachments thereto.
>
>
> ___
> 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] RunReactants atom mapping

2017-12-21 Thread Jennifer Wei

Hi Ruben,

I ran into this issue a few months ago. Take a look at this thread :
https://www.mail-archive.com/rdkit-discuss@lists.sourceforge.net/msg07311.html

And also Connor Coley's fork of rdkit:


https://github.com/connorcoley/Rdkit


Example of use:

https://github.com/connorcoley/ochem_predict_nn/blob/master/data/generate_candidates_edits_fullgrants.py



Cheers,
Jennifer


On Thu, Dec 21, 2017 at 10:02 AM Ruben Van de Vijver <
ruben.vandevij...@ugent.be> wrote:

> Dear all,
>
>
>
> I have the following lines to create the products of a hydrogen
> abstraction reaction by a radical atom. The length of the product tuple is
> 6 as expected from the 6 hydrogen atoms of ethane that can be abstracted. A
> first question that I have is, is there a way to know for each set of
> products which hydrogen got abstracted from which carbon atom? I would need
> some sort of mapping of the atom indices of the reactants to the indices
> given by the reaction smarts.
>
> Secondly, if there is a reaction with two reactants, and both reactants
> match the two reactant templates, is it possible to know which reactant
> template was used on which reactant?
>
>
>
> rxn =
> AllChem.ReactionFromSmarts("[C;v4:0][H:1].[C;v3:2]>>[C;v3:0].[H:1][C;v4:2]")
>
> react1 = Chem.AddHs(Chem.MolFromSmiles('CC'))
>
> react2 = Chem.AddHs(Chem.MolFromSmiles('[CH3]'))
>
> prods = rxn.RunReactants((react1,react2))
>
> print len(prods)
>
>
>
> Thanks,
>
> Ruben
>
>
>
>
>
> [image:
> https://styleguide.ugent.be/files/uploads/logo_UGent_EN_RGB_2400_kleur_witbg.png]
>
> *Ruben Van de Vijver*
>
> *Postdoctoral Researcher*
>
> *Laboratory for Chemical Technology (LCT) *
>
> Department of Materials, Textiles and Chemical Engineering
>
> Technologiepark 914, 9052 Ghent, Belgium
>
> T: +32 9 264 56 75 <+32%209%20264%2056%2075>
>
> http://www.lct.ugent.be/
> 
> http://helpdesk.UGent.be/e-maildisclaimer.php
> 
>
>
>
>
>
> --
> Check out the vibrant tech community on one of the world's most
> engaging tech sites, Slashdot.org! http://sdm.link/slashdot
> ___
> Rdkit-discuss mailing list
> Rdkit-discuss@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
>
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

[Rdkit-discuss] Conda-rdkit custom build

2017-10-03 Thread Jennifer Wei

Hi Greg,

I would be using it for myself, and maybe a few other labmates who are
interested.

After reading more about conda build, I have tried editing the meta.yaml
file to point to my fork of rdkit/rdkit with the necessary changes. This
works mostly, except now the build fails the tests. This is the case even
when I use conda-build to build the 2016-09 branch of the main rdkit/rdkit.

Connor, I'll try using your rdkit fork next.

Thank you!
Jennifer


On Tue, Oct 3, 2017 at 7:56 AM Greg Landrum <greg.land...@gmail.com> wrote:

> Hi Jennifer,
>
> On Mon, Oct 2, 2017 at 12:59 AM, Jennifer Wei <jennifer...@fas.harvard.edu
> > wrote:
>
>>
>> I have one more question: I am a bit stuck as to how to rebuild my rdkit.
>> Ideally I would like to create a separate conda environment with the
>> modified rdkit. I have mostly followed the instructions from here:
>> https://github.com/rdkit/conda-rdkit
>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_rdkit_conda-2Drdkit=DwMFaQ=WO-RGvefibhHBZq3fL85hQ=UPzYrSHLXjnX3tYn90C8Ljjzb-yfrb1UtMOxOFh-tKk=Jxt6IBdFyOTxpWpL1loxQmTva2ZDxkrrTQMIu7FeIxE=xaXbSzmdXt3uvMO1TchpchjTLzdy712wzpfENOqUuJg=>
>>
>> How do I modify the instructions to make a package from my customized
>> rdkit source code? The instructions seem to be for getting the general
>> conda build rather than making your own conda environment from customized
>> source code in rdkit/rdkit.
>>
>
> Are you looking to build a copy just for you to run or do you want to
> distribute it to others?
>
> -greg
>
>
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

Re: [Rdkit-discuss] How to number the outputs of a reaction?

2017-10-01 Thread Jennifer Wei

Hi Kovas and Connor,

Thank you for the helpful pointers to the modifications in the rdkit code
to help me number reactions.

I have one more question: I am a bit stuck as to how to rebuild my rdkit.
Ideally I would like to create a separate conda environment with the
modified rdkit. I have mostly followed the instructions from here:
https://github.com/rdkit/conda-rdkit

How do I modify the instructions to make a package from my customized rdkit
source code? The instructions seem to be for getting the general conda
build rather than making your own conda environment from customized source
code in rdkit/rdkit.

Thank you again!
Jennifer

On Fri, Sep 29, 2017 at 3:50 PM Connor Coley <cco...@mit.edu> wrote:

> Hi Jennifer,
>
> I have a fork of RDKit that is slightly out of date, but preserves atom
> mapping using RunReactions (which was needed for the prediction paper).
> You'll need to build from source, but then the atom map number is kept as a
> new attribute of the product atoms. You can iterate through the product
> atoms and re-set the molAtomMapNumber from this new attribute.
>
> https://github.com/connorcoley/Rdkit
> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_connorcoley_Rdkit=DwMFaQ=WO-RGvefibhHBZq3fL85hQ=UPzYrSHLXjnX3tYn90C8Ljjzb-yfrb1UtMOxOFh-tKk=84fKplcxw5Qax5fYEDsUlzLtw3JZn_wawz-VmLyJl7c=hRPMSu46pUw2GC3cj95hZINhb3t2HcQm3b7wFHqQ6qg=>
>
>
> An example of recovering the map number is here:
>
>
>
> https://github.com/connorcoley/ochem_predict_nn/blob/master/data/generate_candidates_edits_fullgrants.py
> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_connorcoley_ochem-5Fpredict-5Fnn_blob_master_data_generate-5Fcandidates-5Fedits-5Ffullgrants.py=DwMFaQ=WO-RGvefibhHBZq3fL85hQ=UPzYrSHLXjnX3tYn90C8Ljjzb-yfrb1UtMOxOFh-tKk=84fKplcxw5Qax5fYEDsUlzLtw3JZn_wawz-VmLyJl7c=XXN9Jsptw1Z3CQbZSTmp_QoIv04C1lAKujRMc7iYS8Q=>
>
>
> Best of luck!
> Connor Coley
>
> On Fri, Sep 29, 2017 at 10:51 AM Jennifer Wei <jennifer...@fas.harvard.edu>
> wrote:
>
>> Hi Kovas,
>>
>> Thank you so much for pointing me to this github issues page and for
>> sharing your code! It is very helpful.
>>
>> I'm having a bit of trouble with the 'react_atom_idx' property. Where did
>> this get set initially? If I try to run your code as written on the github
>> page, it does not recognize this key.
>>
>> Thank you!
>>
>> Best,
>> Jennifer
>>
>> On Thu, Sep 28, 2017 at 5:06 PM Kovas Palunas <kovas.palu...@arzeda.com>
>> wrote:
>>
>>> Hi Jennifer,
>>>
>>> I had this same issue a while back.  Here is an issue I posted about it
>>> on the github: https://github.com/rdkit/rdkit/issues/1269
>>> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_rdkit_rdkit_issues_1269=DwMFAg=WO-RGvefibhHBZq3fL85hQ=UPzYrSHLXjnX3tYn90C8Ljjzb-yfrb1UtMOxOFh-tKk=hXZ3O7Hw9kEXazs6L_WExNyi7ezPgiZXuii8kvqDRA8=eJJg7q8uOJQMmNIHUCyRODhdtFsi_ZXhch3Dn74wk08=>
>>>
>>> I never did make the pull request mentioned in the issue, but all the
>>> code that does what you want should be in there.  Let me know if you have
>>> any other questions, I've spent a good amount of time on this problem.
>>>
>>>  - Kovas
>>>
>>> --
>>> *From:* Jennifer Wei <jennifer...@fas.harvard.edu>
>>> *Sent:* Thursday, September 28, 2017 11:47:53 AM
>>> *To:* rdkit-discuss@lists.sourceforge.net
>>> *Subject:* [Rdkit-discuss] How to number the outputs of a reaction?
>>>
>>>
>> Hi All,
>>>
>>> I am working with atom mapping for reactions. How do I get the correct
>>> atom mapping for my products?
>>>
>>> I have tried the following:
>>> >> rxn =
>>> rdChemReactions.ReactionFromSmarts('[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]')
>>> >> rcts_lab = (Chem.MolFromSmiles('[C:1](=[O:2])[O:3]'),
>>> Chem.MolFromSmiles('[C:4][N:5][C:6]'))
>>> >> pcts_lab = rxn.RunReactants(rcts_lab)
>>> >> Chem.MolToSmiles(pcts_lab[0][0])
>>>   *'O=CN([C:4])[C:6]'*
>>>
>>> I would like the product to be fully labeled, so I get this on the last
>>> line instead.
>>>   *'[O:2]=[C:1][N:5]([C:4])[C:6]'*
>>>
>>> Thank you in advance for any help you can provide me.
>>>
>>> Best,
>>> Jennifer
>>>
>>>
>> --
>> Check out the vibrant tech community on one of the world's most
>> engaging tech sites, Slashdot.org! http://sdm.link/sl

Re: [Rdkit-discuss] How to number the outputs of a reaction?

2017-09-29 Thread Jennifer Wei

Hi Kovas,

Thank you so much for pointing me to this github issues page and for
sharing your code! It is very helpful.

I'm having a bit of trouble with the 'react_atom_idx' property. Where did
this get set initially? If I try to run your code as written on the github
page, it does not recognize this key.

Thank you!

Best,
Jennifer

On Thu, Sep 28, 2017 at 5:06 PM Kovas Palunas <kovas.palu...@arzeda.com>
wrote:

> Hi Jennifer,
>
> I had this same issue a while back.  Here is an issue I posted about it on
> the github: https://github.com/rdkit/rdkit/issues/1269
> <https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_rdkit_rdkit_issues_1269=DwMFAg=WO-RGvefibhHBZq3fL85hQ=UPzYrSHLXjnX3tYn90C8Ljjzb-yfrb1UtMOxOFh-tKk=hXZ3O7Hw9kEXazs6L_WExNyi7ezPgiZXuii8kvqDRA8=eJJg7q8uOJQMmNIHUCyRODhdtFsi_ZXhch3Dn74wk08=>
>
> I never did make the pull request mentioned in the issue, but all the code
> that does what you want should be in there.  Let me know if you have any
> other questions, I've spent a good amount of time on this problem.
>
>  - Kovas
>
> --
> *From:* Jennifer Wei <jennifer...@fas.harvard.edu>
> *Sent:* Thursday, September 28, 2017 11:47:53 AM
> *To:* rdkit-discuss@lists.sourceforge.net
> *Subject:* [Rdkit-discuss] How to number the outputs of a reaction?
>
> Hi All,
>
> I am working with atom mapping for reactions. How do I get the correct
> atom mapping for my products?
>
> I have tried the following:
> >> rxn =
> rdChemReactions.ReactionFromSmarts('[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]')
> >> rcts_lab = (Chem.MolFromSmiles('[C:1](=[O:2])[O:3]'),
> Chem.MolFromSmiles('[C:4][N:5][C:6]'))
> >> pcts_lab = rxn.RunReactants(rcts_lab)
> >> Chem.MolToSmiles(pcts_lab[0][0])
>   *'O=CN([C:4])[C:6]'*
>
> I would like the product to be fully labeled, so I get this on the last
> line instead.
>   *'[O:2]=[C:1][N:5]([C:4])[C:6]'*
>
> Thank you in advance for any help you can provide me.
>
> Best,
> Jennifer
>
>
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

[Rdkit-discuss] How to number the outputs of a reaction?

2017-09-28 Thread Jennifer Wei

Hi All,

I am working with atom mapping for reactions. How do I get the correct atom
mapping for my products?

I have tried the following:
>> rxn =
rdChemReactions.ReactionFromSmarts('[C:1](=[O:2])O.[N:3]>>[C:1](=[O:2])[N:3]')
>> rcts_lab = (Chem.MolFromSmiles('[C:1](=[O:2])[O:3]'),
Chem.MolFromSmiles('[C:4][N:5][C:6]'))
>> pcts_lab = rxn.RunReactants(rcts_lab)
>> Chem.MolToSmiles(pcts_lab[0][0])
  *'O=CN([C:4])[C:6]'*

I would like the product to be fully labeled, so I get this on the last
line instead.
  *'[O:2]=[C:1][N:5]([C:4])[C:6]'*

Thank you in advance for any help you can provide me.

Best,
Jennifer
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Rdkit-discuss mailing list
Rdkit-discuss@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss

[Rdkit-discuss] NeurIPS 2020 Workshop on Machine Learning for Molecules: Call for Papers

Re: [Rdkit-discuss] Converting csv/xls file containing SMILES to .sdf

Re: [Rdkit-discuss] Are any of the UGM talks recorded?

[Rdkit-discuss] Are any of the UGM talks recorded?

Re: [Rdkit-discuss] Molecules not rendere in Dataframe

Re: [Rdkit-discuss] RunReactants atom mapping

[Rdkit-discuss] Conda-rdkit custom build

Re: [Rdkit-discuss] How to number the outputs of a reaction?

Re: [Rdkit-discuss] How to number the outputs of a reaction?

[Rdkit-discuss] How to number the outputs of a reaction?

10 matches

Site Navigation

Mail list logo

Footer information