I'm delighted to announce we already have some exciting speakers lined up for the 7th RSC-CICAG / RSC-BMCS Artificial Intelligence in Chemistry Symposium this September 16-18, 2024, including:
• John Jumper, Google DeepMind, UK
• Heather Kulik, MIT, USA
• Pat Walters, Relay Therapeutics, USA
• Andrea Volkamer, University of Saarland, Germany
• and more…
https://www.rscbmcs.org/events/aichem7/
Looking forward to seeing you in Cambridge! :-)
You can also hear Martin speak at the upcoming RSC CICAG and RSC BMRC's 6th "AI in Chemistry" Symposium at Churchill College, Cambridge—and there's still time to register, too!
https://rscbmcs.org/events/aichem23/
4/4
Martin has developed a pip-installable Python package that's easy to use:
https://github.com/maabuu/posebusters
3/4
If you're interested in assessing the structural quality and chemical validity of predicted binding modes (and conformations) of small molecules, you might like to read about one of our DPhil students Martin Buttenschoen's work on PoseBusters:
https://arxiv.org/abs/2308.05777
2/4
The last few years have seen the development of numerous deep learning-based protein-ligand docking methods. They offer huge promise in terms of speed and accuracy. However, despite claims of state-of-the-art performance in terms of crystallographic root-mean-square deviation (RMSD), upon closer inspection, it has become apparent that they often produce physically implausible molecular structures. It is therefore not sufficient to evaluate these methods solely by RMSD to a native binding mode. It is vital, particularly for deep learning-based methods, that they are also evaluated on steric and energetic criteria. We present PoseBusters, a Python package that performs a series of standard quality checks using the well-established cheminformatics toolkit RDKit. Only methods that both pass these checks and predict native-like binding modes should be classed as having "state-of-the-art" performance. We use PoseBusters to compare five deep learning-based docking methods (DeepDock, DiffDock, EquiBind, TankBind, and Uni-Mol) and two well-established standard docking methods (AutoDock Vina and CCDC Gold) with and without an additional post-prediction energy minimisation step using a molecular mechanics force field. We show that both in terms of physical plausibility and the ability to generalise to examples that are distinct from the training data, no deep learning-based method yet outperforms classical docking tools. In addition, we find that molecular mechanics force fields contain docking-relevant physics missing from deep-learning methods. PoseBusters allows practitioners to assess docking and molecular generation methods and may inspire new inductive biases still required to improve deep learning-based methods, which will help drive the development of more accurate and more realistic predictions.
We've been investigating deep learning-based protein-ligand docking methods which often claim to be able to generate ligand binding modes within 2Å RMSD of the experimental one. We found, however, this simple criterion can conceal a multitude of chemical and structural sins.
1/4
Introduction and methodology Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs). It has been hypothesised that QSAR models struggle to predict ACs and that ACs thus form a major source of prediction error. However, the AC-prediction power of modern QSAR methods and its quantitative relationship to general QSAR-prediction performance is still underexplored. We systematically construct nine distinct QSAR models by combining three molecular representation methods (extended-connectivity fingerprints, physicochemical-descriptor vectors and graph isomorphism networks) with three regression techniques (random forests, k-nearest neighbours and multilayer perceptrons); we then use each resulting model to classify pairs of similar compounds as ACs or non-ACs and to predict the activities of individual molecules in three case studies: dopamine receptor D2, factor Xa, and SARS-CoV-2 main protease. Results and conclusions Our results provide strong support for the hypothesis that indeed QSAR models frequently fail to predict ACs. We observe low AC-sensitivity amongst the evaluated models when the activities of both compounds are unknown, but a substantial increase in AC-sensitivity when the actual activity of one of the compounds is given. Graph isomorphism features are found to be competitive with or superior to classical molecular representations for AC-classification and can thus be employed as baseline AC-prediction models or simple compound-optimisation tools. For general QSAR-prediction, however, extended-connectivity fingerprints still consistently deliver the best performance amongs the tested input representations. A potential future pathway to improve QSAR-modelling performance might be the development of techniques to increase AC-sensitivity. Graphical Abstract
I'm delighted to announce that The Ninth Joint Sheffield Conference on Chemoinformatics will take place at the University of Sheffield from the 19-21 June, 2023.
Registration for the conference is now open via the website at https://cisrg.shef.ac.uk/shef2023, with reduced rates for students and for registration prior to 30th April. The website now also lists the planned speakers.
We look forward to welcoming you in Sheffield in June.
6th RSC-BMCS / RSC-CICAG Artificial Intelligence in Chemistry
— Abstract submission is now open: https://hg3.co.uk/ai/
Deadlines:
Oral presentations: Midnight (BST), Fri, 14 April, 2023; &
Poster abstracts: Midnight (BST), Fri, 5 May, 2023.
6th RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry Symposium:
Registration and abstract submissions are now open!
Register or submit an abstract here: https://www.rscbmcs.org/events/aichem23/
Chris Swain