Pat Walters

4 Sept

M6 Mac Mini as the prize for the Marimo Cheminformatics notebook competition!

marimo@marimo.io

For our cheminformatics competition, you can now win an @Apple Mac Mini M6. You have 1 month left to take a dataset and build a marimo notebook that brings cheminformatics to life. Competition details below.

2 Sept

A great opportunity to showcase your marimo skills and compete for some solid prizes. Looking forward to seeing what the community builds.

marimo@marimo.io

33 days to win a mac mini. the challenge: pick a cheminformatics dataset and build a marimo notebook that answers a question you want the answer to. we're judging based on creativity, not on model accuracy. co-hosted with @wpwalters.bsky.social. we'll see you in our submissions 👀

24 Aug

Excited to team up with @marimo to explore new relationships between chemical structures and biological data. Bring your creativity, push the boundaries of reactive notebooks, and compete for prizes! Details below 👇

marimo@marimo.io

We're running a cheminformatics notebook competition with @wpwalters.bsky.social and OpenADMET. Take a dataset & bring cheminformatics to life. Mac Mini + $2.5K in prizes, deadline Oct 4 👀

22 July 2025

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

13 May 2025

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

patwalters.github.ioThe Trouble With TautomersIntroductionOne factor often overlooked when applying machine learning (ML) in small-molecule drug discovery is the influence of tautomers on model predictions. Drug-like molecules, especially those c...

6 May 2025

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-...

24 Mar 2025

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

practicalcheminformatics.blogspot.comEven More Thoughts on ML Method ComparisonsIntroduction A few things motivated this post. Some recent discussions about the virtues of LightGBM vs XGBoost Posts on TabPFN by Jon...

10 Mar 2025

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...

Pat Walters reposted

pen(Taka)

@iwatobipen.bsky.social

7 Feb 2025

　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.…

iwatobipen.wordpress.com　Determine bond order from XYZ format of molecule #RDKitAs 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. Recently I found useful function for determining the order in rdkit and Greg wrote useful post almost two years ago I think it's worth to read.

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

23 Jan 2025

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

Pat Walters reposted

Bird account

@dialecticbio.bsky.social

28 Dec 2024

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

github.comGitHub - Graylab/DL4Proteins-notebooks: Colab Notebooks covering deep learning tools for biomolecular structure prediction and designColab Notebooks covering deep learning tools for biomolecular structure prediction and design - Graylab/DL4Proteins-notebooks

chembl.blogspot.comHere'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...

12 Dec 2024

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

pubs.acs.orgOrdinal Confidence Level Assignments for Regression Model PredictionsWe 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...

10 Dec 2024

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/...

linkedin.comResponse to Jain et al.You may have seen a recent pre-print [1] from Jain et al. with strongly worded claims against the experimental results in our DiffDock paper [2].

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...

View full thread

linkedin.comMore response to the response (DiffDock/DiffDock-L)To amplify on what Pat Walters said (quotes from Gabriel Corso's post in italics): It only took a few days (in August 2023) for Ann Cleves, Pat, and me to figure out that the original DiffDock work ha...

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

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.

linkedin.comResponse to Jain et al.You may have seen a recent pre-print [1] from Jain et al. with strongly worded claims against the experimental results in our DiffDock paper [2].

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...

linkedin.comMy Response to the ResponseResponding to our analysis, the DiffDock authors contend they were not responsible for developing the benchmark dataset or its data splits. Instead, they relied on previously published datasets and sp...

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

arxiv.orgDeep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking WorkflowsThe 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...

5 Dec 2024

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