ChEMBL 36 is out! chembl.blogspot.com/2025/09/chem...

Check out our new paper available as preprint: chemrxiv.org/engage/chemr...

This looks nice.

Want to work with me on cool stuff? #ukchemjobs #chembl #chemjobs

ellmer (for #RStats) and chatlas (for #Python) integrate LLMs directly into your code. They also support local LLMs (like #Ollama) so you can run models on your own machine, in case you have sensitive data, a lack of API access, or cost restrictions. Check out how here! posit.co/blog/setting...

In support of @egonw.mastodon.social.ap.brid.gy 's 'One Million IUPAC Names' project, we have just released more than 4 million IUPAC names text-mined from patents. Read more at: chembl.blogspot.com/2025/08/unle...

#cheminformatics #chembl #surechembl #chemjobs #chempostdocs

Always verify the domain is pypi.org before logging in. Read more: blog.pypi.org/posts/2025-0...

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

Announcing Orbital for Python! For Scikit-learn users, this tool transforms your ML pipelines into SQL queries, letting predictions run directly in your database without a #Python environment. Learn more: posit.co/blog/introdu...

We would very much appreciate people taking the time to fill our impact survey. This helps makes the case for support for our resources. Survey closes on July 16th.

The ChEMBL-og: Support ChEMBL - EMBL-EBI user survey! chembl.blogspot.com/2025/06/supp...

You can now use marimo with quarto from Posit! With the marimo-quarto plugin you get reactive execution as well as our suite of widget are all available from blogs that want to use it. For a demo, check our latest YT video: youtu.be/scuGmtv81S0

But most importantly you can build this yourself using open source tools. A notebook with full end-to-end code is here: gist.github.com/lmcinnes/951... You can use the same tools and techniques to build a map for your own data.

In collaboration with Dr Daniel Lowe, we are delighted to announce that the new home of the OPSIN web service is at EMBL-EBI. This well-known service converts systematic IUPAC names to structure. Read more on our post: chembl.blogspot.com/2025/05/opsi...

New release of my "Hands-on Introduction to Data Science with Python" textbook! Contains many text edits and figure updates. For instance, in the sections on Clustering and Machine Learning. All fully #opensource and #openaccess. Figures are #CCBY. --> florian-huber.github.io/data_science...

the og drug discovery, inside an 1800s monastery pharmacy in Zurich. Complete with an upside down alligator hanging from the ceiling

Here's the expanded CYP-ADRs dataset on adverse drug reactions for cytochrome P450 substrates (drugs) with ideas behind this work. Dataset: github.com/jhylin/Adver... Ideas: jhylin.github.io/Data_in_life... #prescription_drugs #cytochromep450 #adverse_reactions #cheminformatics

🎉 Yeah, uv 0.6.15 supports PEP751, pylock.toml with • uv export -o pylock.toml • uv pip compile -o pylock.toml -r requirements.in • uv pip sync pylock.toml • uv pip install -r pylock.toml github.com/astral-sh/uv... #Python

Over on LinkedIn, I am polling people on whether they are interested in attending a ChEMBL UGM in person or remote. Leave a message here or follow the link if interested. (Stupid LI, you need to view desktop version of this site if on phone): www.linkedin.com/posts/noel-o...

Don't use the method `replace` to remove punctuation from a Python string. Instead, use the method `translate`. This is much more efficient and more general. The method `translate` expects a “translation table” in a specific format, but `maketrans` builds it for us.

A short note (for me or others if interested) about strategies used to prevent model overfitting in deep neural networks jhylin.github.io/Data_in_life...

For Quarto blog users, if wanting to add bsky icon to navbar, try this (as I've just figured it out): - ensure your Quarto version is 1.2.198 or above - download font awesome extension from this repo (github.com/quarto-ext/f...) - add: text: "{{< fa brands bluesky >}}" to _quarto.yml under navbar

1/6 🚀 Scikit-Mol 0.4.6 is Here! 🚀 We’re excited to announce the release of Scikit-Mol 0.4.6. A huge thank you to @Anton Sionchem for contributing to this update! #Scikit-Mol #OpenSource #Python #RDKit #Scikit-Learn

#cheminformatics #compchem #medchem

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

Comparison operators in #Python can be chained together, but using them that way could be controversial. I wrote this this other day:

Here's a new post on my 1st encounter with building a simple deep learning model on manually-compiled ADRs data (thanks to @baoilleach.bsky.social for feedback) - jhylin.github.io/Data_in_life... Notes re. data - jhylin.github.io/Data_in_life... #PyTorch #RDKit #ChEMBL #embeddings #cheminfomatics

Recent invited talk sharing some of my learnings of co-founding an AI drug discovery company. Thank you Dassault Systèmes for inviting me to #ScienceWeek, it was amazing. www.youtube.com/watch?v=5MYT...

Recently I've been working on getting #polars running in #pyodide. This was a fun one, even requiring patches to LLVM's #wasm writer! Everything has now been upstreamed and earlier this week Pyodide v0.27.0 released, including a Wasm build of Polars usable in Pyodide, Shinylive and Quarto Live 🎉

Curated list of #Python resources for data science 🧪🧬🖥️ github.com/r0f1/datasci...

Blogpost comparing engagement on X vs Mastodon vs BlueSky baoilleach.blogspot.com/2024/12/enga...

New post: I think the debate around whether LLMs can replace developers is lacking some nuance because, if we're lucky, we as developers don't work without context. I work with my Alphabet Radio on, streaming the greatest hits of the best devs I've worked with. vickiboykis.com/2024/12/16/w...

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: greglandrum.github.io/rdkit-blog/p... #ChemSky

I didn’t know I could REPL Python in a notebookesque way like this. TIL!

@wpwalters.bsky.social is here! practicalcheminformatics.blogspot.com?m=1

“Eureka” moments in discovery, as described by chemists who’ve experienced them:

Today we celebrate the life of Warren DeLano. Warren is best known for his development of PyMOL, the tool we use almost every day to depict 3D molecular structure of small molecules and proteins. Please post your favourite PyMOL illustration. Tag with #PyMOL #WarrenDeLano #PyMOL #Chemsky 🧪

If anyone from the #pyladies or #rladies community has a blog or YouTube channel, feel free to add them here so that the @pyladies-bot.bsky.social and @rladies-bot.bsky.social can post about your content 🫶

Here are the last two updated posts that will complete the story from earlier: 3rd post - building a logistic regression model using scikit-learn and Polars dataframe library jhylin.github.io/Data_in_life... 4th post - evaluations of the model using scikit-learn jhylin.github.io/Data_in_life...

This is the second updated post (that follows on from the first Parquet file post) re. preprocessing data using Polars dataframe library - to be followed by two more posts about using Scikit-learn alongside Polars later. jhylin.github.io/Data_in_life... #Python #Polars #cheminformatics

An update on an older post looking at saving a relatively large csv file (although may not be considered large by some) as a Parquet file (to be followed by 3 other posts later re. using Polars with scikit-learn) jhylin.github.io/Data_in_life... #sklearn #Polars #Parquet #Python #Cheminformatics

Nice discussion about the Future of AI in Drug Discovery www.collaborativedrug.com/cdd-blog/htt...

I got a Covid booster today (Comirnaty JN.1 for anyone counting) and to do it, I went to the oldest trading pharmacy in England! Look at these bottles and cabinets! 😍 #Chemsky

New post on cytochrome P450 and small molecules (CYP3A4 and 2D6 inhibitors). At one point I thought I might not be able to finish it properly, glad I did, many thanks to @baoilleach jhylin.github.io/Data_in_life... #metabolism #toxicology #structural_alerts #pandas #RDKit #cheminformatics #Python

Our lwreg paper came out last week (I'm behind...). I think the cheminformatics/computational chemistry community isn't generally great at tracking the molecules they've worked on and the results generated for them. lwreg is our attempt to help fix that. #chemsky pubs.acs.org/doi/full/10....

I have finally grown more trees leading to a new post on boosted trees, re. chaining Scikit-mol's transformers along with AdaBoost and XGBoost via Scikit_learn's interface and pipelines jhylin.github.io/Data_in_life... #cheminformatics #chembl #rdkit #python #xgboost #adaboost #sklearn #scikit_mol

A short note (post) to self, but in case any others are also interested - "Using Molstar in Quarto" - embedding Mol* 3D viewer in Quarto docs - jhylin.github.io/Data_in_life... #bioinformatics #cheminformatics #molstar #sbdd

Our most recent paper just appeared in JCIM. The title of this one pretty much tells the story: when you assemble a data set by combining data from different literature assays, there is a very good chance that the resulting data contains a lot of noise. pubs.acs.org/doi/10.1021/...