Scaffold growing with RNN #RDKit #Pytorch #Chemoinformatics

My favorite molecular generator is REINVENT which is SMILES RNN based generator. Because it is very flexible and easy to modify. And recently same group in Astrazeneca published new version of REINVENT, its title is ‘SMILES-Based Deep Generative Scaffold Decorator for De-Novo Drug Design‘ It seems very exciting for me! Because there are many molecular

Cut molecule to ring and linker with RDKit #RDKit #chemoinformatics #memo

Sometime chemists analyze molecule as small parts such as core, linker and substituents. RDKit has functions for molecular decomposition RECAP, BRICS and rdMMPA. It’s useful functions but these functions can’t extract directly extract core and linker from molecule. I had interested how to do it and tried it. Following code, Core is defined Rings in

Make report with rdkit and matplotlib #RDKit #memo #chemoinformatics

Recently jupyternotebook is being very powerful and useful tool for chemoinformatitian. It can be able to not only analysis but also visualize data. Of course I love it. However sometime it is not so friendly tool to medchem I think. So I think that it is nice to having reporting function for medchem. I found

Draw RDKit mol/reaction object on HTML without static png image #RDKit #memo

I think this post might not useful for many people. Just for my memorandum. When I make web app, I use draw SVG function for rdkit object rendering. But from last my post and Greg’s gist, I could learn draw png image without writing static png files. So I wonder that can I draw PNG

Edit reaction image and draw it #RDKit #memo

I often use rdkit on jupyter notebook because notebook can render molecules very conveniently. However I couldn’t find way to edit font size of reaction some days ago. Following code is an example. Changing atom font size of MolToImage is easy but reaction image can’t apply same manner. OK, next tried to change font size.

Partial charge visualization with RDKit #RDKit #QuantumChemistry #psikit

Last post, I showed how to visualize each fingerprint contribution for predictive model results with RDKit. The function also can visualize atomic properties such as a partial charge of atoms. Dr. Thomas Evangelidis shared me an example of visualization of quantum chemistry based atom property. He showed an example of conformation effect to the QM

Model interporation with new drawing code of RDKit #RDKit #Machine learning #chemoinformatics

Following code does not use new drawing code but it revised one of my old post. :) I think, everyone who visits my blog has already read Gregs nice blog post about the drawing similarity map with new code. If you don’t read it I recommend to read it soon. URL is below. ;)http://rdkit.blogspot.com/2020/01/similarity-maps-with-new-drawing-code.html Now

Handling solid-containing photochemical reactions #memo #organic_chemistry

Happy new year! This is the first post of 2020. ;-)End of the last year I found some interesting articles and this is one of them. The URL is below.https://pubs.acs.org/doi/abs/10.1021/acs.oprd.9b00378 This research describes new reaction device of photohemical reactions. As you know, photochemical reaction is useful for not only organic chemistry but also medicinal chemistry.