Patrick Kidger

Patrick Kidger

@patrickkidger.bsky.social

πŸš€ Doing something new. Curing uncured diseases. πŸ§ͺ antibodies+AI, neural ODEs, open-source JAX ecosystem. πŸ‘¨β€πŸ’» ex-{Cradle, Google, Oxford}. πŸ“ ZΓΌrich, Switzerland

4.8K followers645 following80 posts

You: please act normal, you need these people to like you Me: ok! People: hi Me: there is a parasite on salmon called Henneguya zschokkei which started as a jellyfish cancer before *budding off into its own species*.

parafilm is cool dot com@parafilmm.bsky.social

You: please act normal, you need these people to like you Me: ok! People: hi Me: Parafilm is a semi-transparent, flexible film composed of a blend of waxes and polyolefins. It is a non-toxic, tasteless, odorless, and self-sealing thermoplastic, which can be stretched up to 200%

Alright chaps, I am in Boston for PEGS, here to chat all things AI + antibody engineering. Send me a message if you're around! 🧬 (PS I'm hiring! Pharma x AI startup, come make drugs with us.)

A reminder that there is now *1 week* left until the MLSB deadline on October 1st! Send in your πŸ§ͺbio+πŸ€–ML papers, for either πŸ‡ΊπŸ‡ΈSan Diego, πŸ‡©πŸ‡°Copenhagen, or ✨both✨!

MLSB (in San Diego + Copenhagen)@workshopmlsb.bsky.social

🚨To accommodate the addition of EuroMLSB, we have extended the submission deadline to October 1, 2025 11:59pm AoE. Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.

πŸ’₯ We are *also* organizing Machine Learning for Structural Biology @ EurIPS, Copenhagen!! Topics include anything in the ML+bio intersection. Submit your ML+bio short papers! Authors can even present in both locations if they have people in both locations πŸš€

MLSB (in San Diego + Copenhagen)@workshopmlsb.bsky.social

You asked and we listened... @workshopmlsb.bsky.social is excited to be expanding to Copenhagen, DK at @euripsconf.bsky.social πŸŽ‰ Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portalπŸ’«

πŸš€ So `tinyio` hit the front page of Hacker News. Now we're at 487 GitHub stars :D I've also just done a ✨v0.2 release✨. Now comes batteries-included with common operations (locks, yield-as-available, etc.) and with a major performance improvement. GitHub: github.com/patrick-kidg...

github.comGitHub - patrick-kidger/tinyio: Ever used asyncio and wished you hadn't? A tiny (~300 lines) event loop for Python.Ever used asyncio and wished you hadn't? A tiny (~300 lines) event loop for Python. - patrick-kidger/tinyio
Patrick Kidger@patrickkidger.bsky.social

✨Announcing: tinyio! A tiny barebones event loop library for Python. Born out of my frustration with asyncio... GitHub: github.com/patrick-kidg... It's nothing too fancy, just a little library that does one thing well. πŸ”₯

✨v0.1 release of typst_pyimage!✨ Do you: - write scientific papers in Typst (boo hiss LaTeX)? - have many matplotlib figures? Would you like the code for those images inlined directly into your Typst file, and autogenerated when you compile it?πŸ”₯ github.com/patrick-kidg...

github.comGitHub - patrick-kidger/typst_pyimage: Typst extension, adding support for generating figures using inline Python codeTypst extension, adding support for generating figures using inline Python code - patrick-kidger/typst_pyimage

✨Announcing: tinyio! A tiny barebones event loop library for Python. Born out of my frustration with asyncio... GitHub: github.com/patrick-kidg... It's nothing too fancy, just a little library that does one thing well. πŸ”₯

github.comGitHub - patrick-kidger/tinyio: Ever used asyncio and wished you hadn't? A tiny (~200 lines) event loop for Python.Ever used asyncio and wished you hadn't? A tiny (~200 lines) event loop for Python. - patrick-kidger/tinyio

✨Cradle is hiring protein+ML researchers!✨ We operate ML for lab-in-the-loop lead optimization across all industries (pharma, synbio, ...), modalities (antibodies, enzymes, ...), properties (binding, activity, ...) We're a scaleup and already relied upon by 4 of the top 20 big pharma. Apply here!

jobs.ashbyhq.comMachine Learning Researcher in Protein Design (f/m/*)Join a scaleup researching and operating ML-guided lead optimization of proteins. This means developing a combination of protein language models, and multi-property prediction and generation.

This library brought to you originally by my need to debug re-raised exceptions in some of the libraries I'm using. Then in my usual fashion I kept adding features, and now we have a whole library πŸ˜„ If like me your debugging experience has been a lot of `pdb`, then this library is for you... 2/3

...like `pdb`, but with a snappier interface, fewer commands overall, with a focus on a clean REPL/TUI experience to navigate the stack. Now used by me... and adopted by a host of my coworkers at Cradle! 3/3

I also went back and took at look at one of the very early READMEs. I think we've stayed true to these goals! (Also included: Equinox started out as a 'tech demo'. I had to procrastinate from real work somehow, after all. πŸ˜„)

✨ We previously took 1st place on the Adaptyv protein binding competition. πŸš€ In this update, we now take all of *top 12*! Just one of our entries into the competion was tested at the time. Our prize for winning was to have our other designs be tested... Post: www.cradle.bio/blog/adaptyv2 [1/2]

cradle.bioCradle – Optimizing CetuximabNews, updates, tutorials, and more from the makers of Cradle
Patrick Kidger@patrickkidger.bsky.social

πŸ”₯ How we won the Adaptyv Bio competition, designing a 1.21nM binder to EGFR using generative AI :) www.cradle.bio/blog/adaptyv... 🌟 This was a super fun project from four of us at Cradle Bio ! ✨

Patrick Kidger reposted

🌟 We have a proteinML PhD internship at Cradle! jobs.ashbyhq.com/cradlebio/d8... Come see what it's like to work at a frontier bioML lab. This is a unique opportunity to work across the entire stack: πŸ”¬ Automated wet lab data; πŸ€– Train your own ~1B parameter ML models; πŸ“š Publish end result! πŸš€

jobs.ashbyhq.comSoftware Engineering/Machine Learning Intern (f/m/*)Machine Learning Eningeer - Internship

πŸš€ It's time for a new JAX ecosystem library! This time quite a small one: ESM2quinox. A #JAX + Equinox implementation of the ESM2 protein language model. GitHub: github.com/patrick-kidg... SciML is obviously my whole jam. My open source has largely focused on the differential equations ... [1/2]

github.comGitHub - patrick-kidger/esm2quinox: An implementation of ESM2 in Equinox+JAXAn implementation of ESM2 in Equinox+JAX. Contribute to patrick-kidger/esm2quinox development by creating an account on GitHub.

... whilst my professional work has largely focused on things like protein language models! So I'm very happy to doing a better job bridging these two halves of my work. 🌟 I hope this will be a useful starting point for the JAX users of bioML :) [2/2]

✨We're hiring for bio roles at Cradle! You can expect to work on a huge variety of problems (antibodies, enzymes, peptides, ...) across all modalities (therapeutics, agtech, biosynthesis, ...), as at this point (post series B) we work with pretty much the whole industry. [1/2]

jobs.ashbyhq.comBioinformatician - Protein ScienceTHIS IS CRADLE Proteins are the molecular machines of life, used for many therapeutic, diagnostic, chemical, agricultural and food applications. Designing and optimizing proteins takes a lot of exper...

Basically, we want quantitative bio PhDs who care about translational/applied research: bridging the details of real-world protein design projects and the capabilities of ML. DMs open for any questions and link below! πŸ’₯⭐️ jobs.ashbyhq.com/cradlebio/45... [2/2]

jobs.ashbyhq.comBioinformatician - Protein ScienceTHIS IS CRADLE Proteins are the molecular machines of life, used for many therapeutic, diagnostic, chemical, agricultural and food applications. Designing and optimizing proteins takes a lot of exper...

Patrick Kidger reposted

In school, you probably learned that human cells have 46 chromosomes, which is 2 copies of 23 chromosomes, sometimes called 'diploid' or '2n'. But there are other 'ploidies' in your cells. To start with, 80+% of your cells have NO chromosomes: red blood cells or 'erythrocytes'...

Patrick Kidger reposted

FutureHouse is launching an independent postdoctoral fellowship program for exceptional researchers who want to apply our automated science tools to specific problems in biology and biochemistry, in collaboration with world-leading academic labs. 1/

πŸŽ‰ Okay folks it's that time of year! Who's at NeurIPS?? Come find me and the rest of the Cradle Bio crew πŸ§ͺ Always happy to chat sciML, protein design, open source, and everything in between 🌟

Good software is an enabler for good science! πŸ’₯πŸ§ͺ Inspired by the below post, I like to point people at libraries like github.com/patrick-kidg... as a template for what a modern Python library looks like: `pre-commit`, ruff, pyright, pyproject.toml, an open-source license, etc. πŸ€“

github.comGitHub - patrick-kidger/equinox: Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/ - patrick-kidger/equinox
Ashley Ringer McDonald@aringermcdonald.bsky.social

If you want to help your students move from just writing code and scripts to actually developing scientific software that is useable and maintainable in the long-term, check out our latest paper in JCE. pubs.acs.org/doi/10.1021/...

pubs.acs.orgCookiecutter for Computational Molecular Sciences: A Best Practices Ready Python Project GeneratorScientific software development takes far more than good programming abilities and scientific reasoning. Concepts such as version control, continuous integration, packaging, deployment, automatic documentation compiling, licensing, and even file structure are not traditionally taught to scientific programmers. The skill gap leads to inconsistent code quality and difficulty deploying products to the broader audience. Most of the implementation of these skills however can be constructed at project inception. The Cookiecutter for Computational Molecular Sciences generates ready-to-go Python projects that incorporate all of the concepts above from a single command. The final product is then a software project which lets developers focus on the science and minimizes worries about nonscientific and nonprogramming concepts because the best practices, as established by the Molecular Sciences Software Institute, have already been incorporated for them. This is a community driven project with widespread adoption across the computational molecular sciences. The Molecular Sciences Software Institute and Computational Molecular Sciences community also continually contribute and update the Cookiecutter for Computational Molecular Science, ensuring that the project is responsive to community needs and tool updates. All are welcome to suggest changes and contribute to making this the best starting point for Python-based scientific code.

Now this is awesome! I love the way that ML, with its open-source-everything approach, is taking on biology.

Gabriele Corso@gcorso.bsky.social

Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with Jeremy, Saro, and an amazing team at MIT and Genesis Therapeutics. A thread!

We have an AI-designed antibodies challenge! πŸ”₯ Nature: www.nature.com/articles/s41... Website: www.aintibody.org (Co-authored with approximately everyone, haha. 🌟) The challenge is primarily around CDR design, with the submitted sequences tested in vitro. πŸ§ͺ Come give it a go :)

nature.comAIntibody: an experimentally validated in silico antibody discovery design challenge - Nature BiotechnologyNature Biotechnology - AIntibody: an experimentally validated in silico antibody discovery design challenge

You are up to date.