Richard Michael

The most important aspect when facing data shift is the type of shift present in the data. I will give below a few examples of shifts and some existing methods to compensate for it.🧵1/6

01.07.2025 09:38 — 👍 30    🔁 16    💬 2    📌 1

End-to-end differentiable homology search for protein fitness prediction.

@yaringal.bsky.social @deboramarks.bsky.social @pascalnotin.bsky.social

arxiv.org/abs/2506.089...

11.06.2025 19:00 — 👍 32    🔁 9    💬 0    📌 0

Spotted Oosterkade in Utrecht

11.03.2025 13:35 — 👍 0    🔁 0    💬 0    📌 0

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

🚀 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]

11.02.2025 14:40 — 👍 32    🔁 8    💬 2    📌 1

🔥 Benchmark Alert! MotifBench sets a new standard for evaluating protein design methods in motif scaffolding.
Why does this matter? Reproducibility & fair comparison have been lacking—until now.
Paper: arxiv.org/abs/2502.12479 | Repo: github.com/blt2114/Moti...
A thread ⬇️

19.02.2025 20:49 — 👍 40    🔁 17    💬 1    📌 5

The BioEmu-1 model and inference code are now public under MIT license!!!

Please go ahead, play with it and let us know if there are issues.

github.com/microsoft/bi...

19.02.2025 20:17 — 👍 103    🔁 39    💬 2    📌 2

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now 🥳 They cover quite a bit from basic information theory to some recent papers:

blackhc.github.io/balitu/

and I'll try to add proper course notes over time 🤗

17.12.2024 06:50 — 👍 179    🔁 28    💬 3    📌 0

I'm very grateful for the work w/ Simon Bartels and @miguelgondu.bsky.social, who did the heavy lifting on the libraries, CI/CD, testing, PR reviews, up-to-date docs, and much more.

Thanks to the generous support and funding by the MLLS center and the #DDSA!

12.12.2024 16:15 — 👍 0    🔁 0    💬 0    📌 0

GitHub - MachineLearningLifeScience/poli-baselines: A collection of objective functions and black box optimization algorithms related to proteins and small molecules A collection of objective functions and black box optimization algorithms related to proteins and small molecules - MachineLearningLifeScience/poli-baselines

With the tasks in place, we can run and assess different optimizers.

A range of solvers is available in the `poli-baselines` package,
here: github.com/MachineLearn....

The docs on how to get set up and contribute, are here: machinelearninglifescience.github.io/poli-docs/

12.12.2024 15:56 — 👍 2    🔁 0    💬 0    📌 0

GitHub - MachineLearningLifeScience/poli: A library of discrete objectives A library of discrete objectives. Contribute to MachineLearningLifeScience/poli development by creating an account on GitHub.

We developed the `poli` package for easy access to (bio-chemical) black-box functions (cf. TDC, protein stability, ...) and synthetic tasks, with under-the-hood isolation.

Repo: github.com/MachineLearn...
License: MIT (unless a blackbox says otherwise)
A quick install away: `pip install poli-core`

12.12.2024 15:50 — 👍 2    🔁 0    💬 0    📌 0

NeurIPS Poster A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencesNeurIPS 2024

Working on (high-dimensional) Bayesian optimization and care about reproducible, robust comparisons?

Check out our poster presented by @miguelgondu.bsky.social : neurips.cc/virtual/2024... at #NeurIPS2024

Paper: arxiv.org/abs/2406.04739
Site: machinelearninglifescience.github.io/hdbo_benchma...
🧵

12.12.2024 15:44 — 👍 5    🔁 0    💬 3    📌 2

Traveling to Copenhagen. Tomorrow, I will give a talk at the DeLTA lab seminar sites.google.com/diku.edu/del...

I will talk about our joint work with Geoffrey Wolfer on the estimation of the average mixing time for Markov chains + consequences for machine learning. Link:
arxiv.org/abs/2402.10506

01.12.2024 12:57 — 👍 17    🔁 5    💬 1    📌 0