Fantastic, I was thinking based on the article that was only the neural net
part of the code.
Thanks a lot Maciek
From: Maciek Wójcikowski [mailto:[email protected]]
Sent: mercredi 3 février 2016 14:41
To: Giuseppe Marco Randazzo
Cc: Guillaume GODIN; RDKit Discuss
Subject: Re: [Rdkit-discuss] reproduce this method to obtain graph using RDkit
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
[email protected]<mailto:[email protected]>
2016-02-03 14:35 GMT+01:00 Giuseppe Marco Randazzo
<[email protected]<mailto:[email protected]>>:
The graph it’s a simple adjacency matrix (square matrix) which is able to
represent the connectivity of the molecule.
The element of this matrix are the atoms which can be connected.
If you have a simple smile like c1ccccc1 this means that your molecule is a
ring of six atoms (6*c), and the small letter “c” means that your atom is of
aromatic type. thus you can write
your adjacency matrix in this manner:
Adjacency matrix:
c1 c2 c3 c4 c5 c6
c1 0 1 0 0 0 1
c2 1 0 1 0 0 0
c3 0 1 0 1 0 0
c4 0 0 1 0 1 0
c5 0 0 0 1 0 1
c6 1 0 0 0 1 0
1 means that there is a bond between two atoms.
That’s it.
Marco
On 03 Feb 2016, at 14:24, Guillaume GODIN
<[email protected]<mailto:[email protected]>> wrote:
Dear All,
Can you explain me a little how to reproduce this paper experimental
process:http://www.broadinstitute.org/~jbloom/smrc/neural-fingerprints.pdf page
5 using RDKit.
Look like they tweak RDKit:
From page 5: “Experimental setup:
1 Our pipeline takes as input the SMILES [30] string encoding of each molecule,
which is then converted into a graph using RDKit [20].
2 We also used RDKit to produce the extended circular fingerprints used in the
baseline.
3 Hydrogen atoms were treated implicitly.
In our convolutional networks, the initial atom and bond features were chosen
to be similar to those used by ECFP: Initial atom features concatenated a
one-hot encoding of the atom’s element, its degree, the number of attached
hydrogen atoms, and the implicit valence, and an aromaticity indicator.
The bond features were a concatenation of whether the bond type was single,
double, triple, or aromatic, whether the bond was conjugated, and whether the
bond was part of a ring.”
My question: I don’t see how to obtain the graph from the smile.
Best regards,
Dr. Guillaume GODIN
Project Manager
Innovation
CORPORATE R&D DIVISION
DIRECT LINE +41 (0)22 780 3645<tel:%2B41%20%280%2922%20780%203645>
MOBILE +41 (0)79 536 1039<tel:%2B41%20%280%2979%20536%201039>
Firmenich SA
RUE DES JEUNES 1 | CASE POSTALE 239 | CH-1211 GENEVE 8
**********************************************************************
DISCLAIMER
This email and any files transmitted with it, including replies and forwarded
copies (which may contain alterations) subsequently transmitted from Firmenich,
are confidential and solely for the use of the intended recipient. The contents
do not represent the opinion of Firmenich except to the extent that it relates
to their official business.
**********************************************************************
------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140_______________________________________________
Rdkit-discuss mailing list
[email protected]<mailto:[email protected]>
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140
_______________________________________________
Rdkit-discuss mailing list
[email protected]<mailto:[email protected]>
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140
_______________________________________________
Rdkit-discuss mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
