Join Franciszek Job at EuroSciPy as he presents a scalable framework to unify chemical datasets from sources like PubChem, UniChem & COCONUT.
Canonicalize with RDKit
Scale via Dask
Deduplicate with InChI keys
Ideal for ML pretraining, benchmarking, and chemical data analysis.
Schedule: https://lnkd.in/eaAxwUN2
Tickets: https://lnkd.in/end9aYzE
Today's #RDKit blog post shows a way to store partial charges in SD files. We really should stop using mol2 files.
https://greglandrum.github.io/rdkit-blog/posts/2025-07-24-writing-partial-charges-to-sd-files.html
Today's #RDKit blog post is a heartfelt plea for clearer communication.
https://greglandrum.github.io/rdkit-blog/posts/2025-07-17-naming-similarity-metrics.html
The new #RDKit blog post, inspired by a question from Kjell Jorner, looks at the impact of molecular size on similarity thresholds.
https://greglandrum.github.io/rdkit-blog/posts/2025-06-20-size-and-similarity-1.html
This week's #RDKit blog post shows how to use some of the information added to molecules that come from the chemical reactions code.
https://greglandrum.github.io/rdkit-blog/posts/2025-06-12-using-reaction-info.html
The new #RDKit blog post is a guest post from @jemonat with a tutorial on using Bemis-Murcko scaffolds.
https://greglandrum.github.io/rdkit-blog/posts/2025-06-06-murcko-scaffolds.html
This week I have updated and revised an old blog post showing how to perform extended Hueckel calculations with the #RDKit. This is a fun one for me because it involves work I did back in grad school. :-)
https://greglandrum.github.io/rdkit-blog/posts/2025-05-30-eHT-in-RDKit.html
This #RDKit blog post builds on the earlier one about chemical words; this time I'm using Morgan fingerprint bits as the "words".
https://greglandrum.github.io/rdkit-blog/posts/2025-05-22-common-chemical-words-2.html
The new #RDKit blog posts demonstrates how to work with your own fingerprints in the PostgreSQL cartridge.
https://greglandrum.github.io/rdkit-blog/posts/2025-05-17-custom-fingerprints-in-postgresql.html
This week's #RDKit blog post revisits and updates a really old post looking at the most common chemical "words".
https://greglandrum.github.io/rdkit-blog/posts/2025-05-09-common-chemical-words-1.html
Hi. I'm a scientist and programmer based in Basel, Switzerland. I'm a long-time advocate of #OpenSource and #OpenScience and am the primary developer of the #RDKit.
The 2025_03_1 release of #RDKit release includes my contribution to speed up part of getting 2D fingerprints for a molecule by ~75x! So if you generate #chemical fingerprints, now is a good time to upgrade.
Reminder that I'm #OpenToWork so if you're hiring for #cheminformatics or #scientificSoftware development, let's talk.
#chemistry #DrugDiscovery #pharma #PythonForChemists
https://github.com/rdkit/rdkit/releases/tag/Release_2025_03_1
I'm excited to present "Finding Tautomers" at the first North American #RDKit User Group Meeting in the #Boston #MA area on Friday April 11!
Reminder that I'm #OpenToWork so if you're in the area and hiring for #cheminformatics or #scientificSoftware development, let me know and we can meet to discuss your needs.
Here's a new post on my first encounter with building a simple deep learning model on manually-compiled adverse drug reactions data (thanks to @baoilleach for feedback) - https://jhylin.github.io/Data_in_life_blog/posts/22_Simple_dnn_adrs/2_ADR_regressor.html
Notes re. data - https://jhylin.github.io/Data_in_life_blog/posts/22_Simple_dnn_adrs/1_ADR_data.html
There's a new #RDKit blog post introducing some new functionality that I'm really excited about: doing efficient substructure and similarity searches in very large chemical libraries:
https://greglandrum.github.io/rdkit-blog/posts/2024-12-03-introducing-synthon-search.html
As the YouTubers would say, “A lot of you have been asking me about how to write #cheminformatics blog posts.” Well, not a lot, but at least a couple! Here's my process. https://bertiewooster.github.io/2024/11/21/Cheminformatics-Blogging-How-To.html
#Python #RDKit #chemistry
A really interesting preprint caught my attention from Connor Coley’s group at MIT. ShEPhERD diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design https://macinchem.org/2024/11/23/shepherd-shape-electrostatics-and-pharmacophore-explicit-representation-diffusion/ #cheminformatics #RDKit
Just announced "talus - tools to make SMARTS-based #cheminformatics fingerprints" to the #RDKit mailing list.
I'm able to process SMILES file -> Klekota-Roth SMARTS-based fingerprints at about 12.5x baseline speed.
RDMol -> fingerprints performance is 13.2x baseline.
It includes some SMARTS analysis methods to tell if a SMARTS atom pattern X is a subset of a SMARTS atom pattern Y.
@dr_greg_landrum I'm sure I'm doing something either quite naive or unoriginal here (I'm a #RDKit newbie). @cthoyt says you have likely looked into this.
