With Zhuoqi Zheng, Bo Zhang, @kdidi.bsky.social @jasonyim.bsky.social @josephwatson.bsky.social Hai-Feng Chen, @briantrippe.bsky.social
19.02.2025 22:10 — 👍 2 🔁 1 💬 0 📌 0
And thanks as well to ChatGPT for turning my first banal attempt at a tweet-thread into emoji-packed click-bait for real work! 😂
19.02.2025 20:49 — 👍 2 🔁 0 💬 0 📌 0
This has been a big team effort – with contributions across 5 timezones 🌍. Many thanks to my fantastic coauthors on our whitepaper: arxiv.org/abs/2502.12479
19.02.2025 20:49 — 👍 2 🔁 0 💬 1 📌 0
This is a V0 pilot—we need your input for V1!
🧩 Know of an important motif? Add it to the benchmark!
🏗️ Help improve the pipeline & metrics (sequence-based? Side-chain-level?)
Let’s shape the future of motif scaffolding together!
19.02.2025 20:49 — 👍 0 🔁 0 💬 1 📌 0
Surprise: A modern baseline (RFdiffusion) fails on motifs scaffolded into de novo enzymes 15 years ago 🤯
This suggests modern deep learning methods aren’t always better than past methods!
19.02.2025 20:49 — 👍 2 🔁 1 💬 1 📌 0
MotifBench fixes this by providing:
🧪 A standardized evaluation pipeline
🏆 30 challenging motifs as test cases
📊Easy-to-use eval scripts and a leaderboard for method comparison
Now, results can be easily and consistently measured.
19.02.2025 20:49 — 👍 0 🔁 0 💬 1 📌 0
Recent progress in motif scaffolding has been exciting! But…
❌ Current evaluation are inconsistent, and results incomparable
❌ Widely used test cases are too easy
❌ Reproducibility is difficult
That’s where MotifBench comes in.
19.02.2025 20:49 — 👍 0 🔁 0 💬 1 📌 0
Motif scaffolding is a core challenge in protein design:
✅ Input: a motif (small functional substructure)
🎯 Goal: find a scaffolds (full proteins) that preserves the motif’s geometry.
But what's the state of methods for this problem?
19.02.2025 20:49 — 👍 1 🔁 0 💬 1 📌 0
🔥 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
Group Leader @ Institut Curie. Working on geometric deep learning for protein and RNA structures representation. Interested in drug design applications.
Principal Research Scientist at NVIDIA | Former Physicist | Deep Generative Learning | https://karstenkreis.github.io/
Opinions are my own.
Assistant Professor at UMich with a focus on computational pharmacology (he/him)
Senior Applied Scientist @ MSR // AI, molecular dynamics, protein design, and some sillyness 🧬
(she/her)
PhD student at CTU Prague. Working on machine learning for molecule discovery 🤖🧪
Protein engineering & synthetic biochemistry at GSK
Opinions my own
https://linktr.ee/ddelalamo
ML Scientist @prescientdesign.bsky.social developing LLM agents for biological discovery. Previously at Stanford and UChicago
Stanford Linguistics and Computer Science. Director, Stanford AI Lab. Founder of @stanfordnlp.bsky.social . #NLP https://nlp.stanford.edu/~manning/
Professor a NYU; Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.
http://yann.lecun.com
Genomics, Machine Learning, Statistics, Big Data and Football (Soccer, GGMU)
Professor of Machine Learning, University of Cambridge, academic lead of ai@cam, Accelerate Science, author of The Atomic Human, proceedings editor for PMLR.
Associate Professor of Machine Learning, University of Oxford;
OATML Group Leader;
Director of Research at the UK government's AI Safety Institute (formerly UK Taskforce on Frontier AI)
AI, sociotechnical systems, social purpose. Research director at Google DeepMind. Cofounder and Chair at Deep Learning Indaba. FAccT2025 co-program chair. shakirm.com
Machine learning prof at U Toronto. Working on evals and AGI governance.
Machine learning lab at Columbia University. Probabilistic modeling and approximate inference, embeddings, Bayesian deep learning, and recommendation systems.
🔗 https://www.cs.columbia.edu/~blei/
🔗 https://github.com/blei-lab
Professor of Machine Learning and Inference, Edinburgh Informatics, Formerly Amazon Scholar. Opinions are my own. Also https://homepages.inf.ed.ac.uk/imurray2/ and https://mastodon.social/@imurray and https://x.com/driainmurray
Google Chief Scientist, Gemini Lead. Opinions stated here are my own, not those of Google. Gemini, TensorFlow, MapReduce, Bigtable, Spanner, ML things, ...
Assistant Professor, UBC school of Biomedical Engineering. Trying to enable personalized medicine by solving gene regulatory code.
Senior Staff Research Scientist @Google DeepMind, previously Stats Prof @Oxford Uni - interested in Computational Statistics, Generative Modeling, Monte Carlo methods, Optimal Transport.
