Pat Walters

New Practical Cheminformatics Post
patwalters.github.io/Three-Papers...

New Practical Cheminformatics Post, "Useful RDKit Utils - A Mötley Collection of Helpful Routines"
patwalters.github.io/Useful-RDKit...

The latest Practical Cheminformatics post, “The Trouble With Tautomers,” emerged from a discussion about the impact of tautomers on machine learning model predictions.

patwalters.github.io/The-Trouble-...

Thanks, Colab can be picky

The latest addition (#33) to the Practical Cheminformatics Tutorials series explores Bayesian optimization of reaction conditions.
github.com/PatWalters/p...

You know how I feel about bar plots for showing distributions, right? 😀

Even More Thoughts on ML Method Comparisons Introduction A few things motivated this post.   Some recent discussions about the virtues of LightGBM vs XGBoost Posts on TabPFN by Jon...

In a new Practical Cheminformatics post titled "Even More Thoughts on ML Method Comparisons," I share several plots that I find valuable for comparing machine learning methods.
practicalcheminformatics.blogspot.com/2025/03/even...

　Determine bond order from XYZ format of molecule #RDKit

As readers know that recent version of RDKit supports XYZ format which is used in quantum chemistry field. The format doesn't have information of bond order. So to re-construct from the information bond order determination step is required.…

All of it! Lots of great new datasets. More new blogs coming online with great content. Open science at its best!

GitHub - PatWalters/resources_2025: Machine Learning in Drug Discovery Resources 2024 Machine Learning in Drug Discovery Resources 2024. Contribute to PatWalters/resources_2025 development by creating an account on GitHub.

Machine Learning in Drug Discovery Resources page updated for 2025. github.com/PatWalters/r...

GitHub - Graylab/DL4Proteins-notebooks: Colab Notebooks covering deep learning tools for biomolecular structure prediction and design Colab Notebooks covering deep learning tools for biomolecular structure prediction and design - Graylab/DL4Proteins-notebooks

Deep learning for proteins tutorial: github.com/Graylab/DL4P...

Super cool!

Here's a nice Christmas gift - ChEMBL 35 is out! Use your well-deserved Christmas holidays to spend time with your loved ones and explore the new release of ChEMBL 35!            This fresh...

ChEMBL 35 is out. Happy Holidays!
chembl.blogspot.com/2024/12/here...

Thank for the invitation @freundlichgroup.bsky.social. I had a blast!

Yes, absolutely! The approach was designed to facilitate interpretation by med chemists.

Ordinal Confidence Level Assignments for Regression Model Predictions We present a simple method for assigning accurate confidence levels to molecular property predictions from regression models. These confidence levels are easy to interpret and useful for making decisi...

Excellent new paper (with code) by my former colleagues Steven Kearnes and Patrick Riley describing a procedure for associating confidence levels with regression model predictions in drug discovery. pubs.acs.org/doi/10.1021/...

Well said, thank you Rommie!

I'm not happy with the way this all went down. I have tremendous respect for Gabriele and the rest of the DiffDock authors. Their work has broken new ground and helped advance machine learning in drug discovery. If I had to do it over again, I'd do things differently.

@prof-ajay-jain.bsky.social's response is here. www.linkedin.com/pulse/more-r...

My "response to the response" is here. www.linkedin.com/pulse/my-res...

Many of you have seen Gabriele Corso's response to our recent preprint. If you haven't, it's here. www.linkedin.com/pulse/respon...

I don't know. All the DiffDock results we report are from the original DiffDock paper.

This is great, thanks for sharing

Point taken

For AutoDock-Vina, we directly compared with what was in the DiffDock paper.

Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows The diffusion learning method, DiffDock, for docking small-molecule ligands into protein binding sites was recently introduced. Results included comparisons to more conventional docking approaches, wi...

I'm thrilled to announce a new preprint describing collaborative work with Ajay Jain and Ann Cleves Jain, "Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows".

arxiv.org/abs/2412.02889

These have different uses. The one liner gets the SMILES for a particular ligand. My script uses that SMILES to assign bond orders, which are missing in PDB files.

I prefer to think of myself as a realistic enthusiast 😆

Hey Polaris!