Jackson Burns

Purple graphic with pyOpenSci logo at the top. Large white text reads: From Zero to Python Package. Subheading: A 2-hour packaging workshop with pyOpenSci! A checklist underneath says: Build your first Python package, Publish securely to PyPI, Automate releases with GitHub Actions, Write docs that help users & contributors. Below, text reads: Thursday, 6 November 2025, 10:00 AM MST – 12:15 PM MST. At the bottom: bit.ly/PythonPackaging with a button that says Register Now. A simple robot illustration is on the right side.

🐍 Want to publish your own Python package?

Join pyOpenSci’s 2-hour online workshop Nov 6:

✔️ Build your first package fast
✔️ Learn the core files (pyproject.toml, docs, metadata)
✔️ Publish to PyPI with confidence

📅 Nov 6, 2025 | Online
🎟️ bit.ly/PythonPackaging

The emperor has no clothes

This is the golden age of science informatics!

The new #RDKit blog post is an update of an older tutorial on displaying fingerprint bits.
greglandrum.github.io/rdkit-blog/p...

Just started using Zarr - literally unbelievably good.

Are you interested in getting involved in peer review of software? We need more editors!

We are looking for folks with a background in #physics and also people with more stats / analytics background.

Join our team. support the #opensource tools that drive #science
📢 Apply here: buff.ly/PKSpJ47

Currently making a slide deck in markdown and I've never felt so powerful

Cool application of a foundation model to drug design

polaris is an amazing tool with a similarly amazing development team! Try it out today if you work in Computer Aided Drug Discovery world

🚨 Extension Alert: The intermediate leaderboard submission deadline for the antiviral challenge has been extended to midnight on February 7th!

Don't miss this chance to see how you stack up against other participants! Submit your results today: polarishub.io/competitions

This is obviously how scientific articles should be, and if we had an open ecosystem designed for users rather than profit, we would have had this years ago. Time to dump commercial publishers and their paywalls.

I highly suggest all my followers working with Python to follow @pyopensci.org - great resources for packaging your code for improved reproducibility

Thank you to everyone who read and cited my papers last year - proud to say that I received 10 citations in 2024! Double digits for the first time🎉

It is roughly 10 lines of code to go from 1 GPU to N GPUs with pytorch DDP. Pointing this out so that everyone is aware and doesn't shy away from scaling their code

That C-C and C-N coupling are now viewed as boring (comparable to amide bond formation!!) is a testament to the work that Buchwald, Hartwig, and many others have done in the past 20 years.

An interesting read for all scientists publishing papers

LLMs aren't reasoning, and I tire of seeing articles acting like they are

📢 Calling all ML practitioners!

Have you been waiting for an opportunity to prove how well your model performs on a blind, newly generated and consistent test set? You now have the unique opportunity to!

Super excited to launch a first competition on @polarishub.io!

I want to learn fortran - any recommendations on projects to try, toolchains to use, etc.?

GitHub - JacksonBurns/astartes: Better Data Splits for Machine Learning Better Data Splits for Machine Learning. Contribute to JacksonBurns/astartes development by creating an account on GitHub.

My machine learning data splitting library astartes has just hit 64 stars on GitHub! ⭐

We built this to help rigorously quantify how well our models actually work - if you want to quantify how well you models extrapolates into new feature or target space, give it a look:

github.com/JacksonBurns...

Graduate school is revising a paragraph seven times knowing full well that people will skim it just to get to the figures...