Skip to content

Cambridge Cheminformatics Newsletter, January/February 2024 Edition

Dear All,

I would like to circulate some current Cheminformatics- (and related) news to everyone as follows.

In particular, I would like to point out the first EFMC2 Tandem Talk this year, which will take place on 15 February virtually, and the first Cambridge Cheminformatics Meeting, which will take place on 21 February in hybrid mode; for further information please see below.

The dates for the Cambridge Cheminformatics Meetings in 2024 are now also fixed – after 21 February this will be 8 May, 4 September and 13 November. Please mark your calendar, more information will be circulated before each meeting via this newsletter.

So here we go…


15 February 2024
EFMC2 Tandem Talk
Virtual Event
“BAY-069, a Novel (Trifluoromethyl)pyrimidinedione-Based BCAT1/2 Inhibitor and Chemical Probe”

21 February 2024
Cambridge Cheminformatics Meeting
Hybrid – at CCDC, Cambridge and on Zoom
More Information (and all 2024 dates):
Zoom registration:


MolFlux: A Python Ecosystem for Molecular Machine Learning
Ward Haddadin, ExScientia

Ten Years of Extracting Reactions: Where Did We Come From, Where Do We Go?
John Mayfield, NextMove

Practical Machine Learning for Synthetic Chemistry
Emma King-Smith, University of Cambridge

Please join us and circulate further!

26 February 2024
NFDI4 Chem Community Workshop
Mainz, Germany

1 March 2024
NextGen Basel 1 – Next Generation Product Design and Risk Assessment
Basel, Switzerland and Virtual (Hybrid)

3-5 March 2024
9th Fragment-based Drug Discovery Meeting
Hinxton Hall/near Cambridge, UK

4-6 March 2024
International Leopoldina Symposium on Molecular Machine Learning
Halle, Germany

11 April 2024
UK QSAR Meeting
Babraham Research Campus, Cambridge, UK

13-17 May 2024
Bolzano, Italy
International Workshop on Open Molecular Informatics (IWOMI)

19-23 May 2024
European Workshop in Drug Design
Siena, Italy

24-28 June 2024
Strasbourg Summer School in Chemoinformatics 2024
Strasbourg, France

2 July 2024
Milner Therapeutics Symposium 2024
Cambridge, UK

8-11 September 2024
Copenhagen, Denmark


Assistant Professor in Computational Chemistry / Data Science
Durham University
Durham, UK

Principal Scientist – CADD
Emeryville, CA

Chemoinformatics Data Scientist
Frankfurt, Germany

Postdoc – Virtual screening and molecular dynamics simulations in early stage drug development
University of Oslo
Oslo, Norway

Postdoctoral Scientist – Structural Studies
MRC Laboratory of Molecular Biology
Cambridge, UK

PhD Studentships – AI in Drug Discovery
Queen Mary University of London
London, UK

Internship on Cheminformatics
Leverkusen, Germany

AI/Cheminformatics Intern
Pangea Bio
Berlin, Germany


Scipion-Chem: An Open Platform for Virtual Drug Screening
Plug-in based and with GUI, see also

AI-driven molecular generation of not-patented pharmaceutical compounds using world open patent data
… not everything the computer comes up with is what you really want to make

“MolFlux is a foundational package for molecular predictive modelling. From data to features to models, MolFlux provides you with a complete ecosystem for building and handling machine learning models!”
Also see

httk: High-Throughput Toxicokinetics
… it’s not all about fancy AI, always make sure you consider PK!

Some Thoughts on Biotech vs Pharma for Computational Chemists
Excellent blog post by Dean Brown

“Create an easy to comprehend visualization for your SMARTS expression. While our Compare, Search and Create functionality is limited to SMARTS, the viewer is handling Reaction SMILES, Reaction SMARTS and SMIRKS as well.”

“Build predictive models for CompChem with hyper-parameters optimized by Optuna.”

Scikit-Mol – Easy Embedding of RDKit into Scikit-Learn
On the integration of two toolkits many of us use

GUIDEMOL: A Python graphical user interface for molecular descriptors based on RDKit
… making RDKit more accessible via GUI

Cambridge Cheminformatics Meeting Recording from 6 December 2023 now Online
… on assessing conformations against the CSD, guided diffusion for molecular generation, and handling drug discovery data

Digidrug Recording from 29 November 2023 now Online
… on ML for drug discovery with low data, and fast QM quality strain energy with neural network potentials

DataWarrior… probably widely known, but circulated again due to lots of new features in recent versions
… such as docking, patent search, retrosynthesis, building block search, etc.

Vina-GPU 2.1: towards further optimizing docking speed and precision of AutoDock Vina and its derivatives
First there was AutoDock, then AutoDock Vina, then Vina-GPU…

ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries

PKSmart: An Open-Source Computational Model to Predict in vivo Pharmacokinetics of Small Molecules
“PKSmart is an open-source app framework built specifically for predicting human and animal PK parameters.”

RSC CICAG Newsletter – Winter 2023/24
Lots of news from RSC CICAG

… beyond Cheminformatics …

“PostgresML is a complete MLOps platform in a PostgreSQL extension. Build simpler, faster and more scalable models right inside your database.”

“Friends Don’t Let Friends Make Bad Graphs”

“The pharma industry from Paul Janssen to today: why drugs got harder to develop and what we can do about it”
Beautifully written, also with interesting facts and historic pictures

“The rise and fall of the industrial R&D lab”
Once it was Bell and AT&T, now Google and Microsoft… but why do they actually do it?

Atlas Venture 2023 Year in Review
by Bruce Booth

“Who´s to blame for octanol”
Sometimes it’s an event deep down in history that influences what is still being done today

“New analysis raises doubts over autonomous lab’s materials ‘discoveries’”
Damn… but wasn’t it published in … Nature?!

Yep, here we go again

“More Is Different”
Broken symmetry and the nature of the hierarchical structure of science

… and clearly beyond cheminformatics

Reminiscences from the End of the Horse Era in New York City

A truly unique city in the good ol’ times

Possibly of current interest
“The relationship between Trump and his supporters is an abusive one, as an author of the 2017 book I edited, The Dangerous Case of Donald Trump, presciently pointed out. When the mind is hijacked for the benefit of the abuser, it becomes no longer a matter of presenting facts or appealing to logic.”

A crucial algorithmic breakthrough I missed until now! Also check out ‘related algorithms’ section

View from inside Google
“My hot take: Google does not have one single visionary leader. Not a one. From the C-suite to the SVPs to the VPs, they are all profoundly boring and glassy-eyed.”

I believe this is all from my side for now – if you have any information for me to circulate, or wish to present at one of our next Cambridge Cheminformatics or Digital Science for Drug Discovery Meetings, please just let me know, cheers!

Best wishes,


Leave a Reply

Your email address will not be published.