ML Researcher @cradlebio GenAI for proteins with a touch of uncertainty quantification. Views are my own. (he/him)
Zurich, Switzerland
Joined November 2007
- Tweets533
- Following477
- Followers238
- Likes645
Pinned Tweet
Our paper got accepted at #AAAI24! 🎉
We propose two new
sequence generation algorithms with "error bars", by adapting beam search to conformal predictions.
If you use LLMs for science, like predicting molecules or proteins that verify some conditions, check it out!
Here's our preprint on conformal sequence generation!
w/ @malberts99 @MariaRoCompBio
arxiv.org/abs/2309.03797
Two new algorithms for sequence prediction sets with guarantees:
- Conformal sub-beams: pruning standard beams
- Conformal dynamic beams: step-by-step conformal decoding.
Nicolas Deutschmann retweeted
Today we’re launching Proteinbase, a single hub for experimental protein design data. Over 1,000 novel proteins are already live, each with computational predictions, experimental validation, and the method used to design them.
Everything comes from one lab under standardized protocols, which means the results are reproducible, comparable, and include negative data that usually never gets shared.
Nicolas Deutschmann retweeted
Zurich AI meetup speakers and friends for 4 Mar!
- Peter Kontschieder, Research Director at Meta. We met back in Mapillary (acq. Meta) days!
- Philippe Schwaller, Asst. Prof at EPFL, AI for chemistry. I love his papers.
- Stef van Grieken, CEO at @cradlebio, AI for proteins. We met back in his Google days!
This'll be a blast :)
zurich has always been a city where ai thrives
on 4 march, @airstreet is coming to zurich to host our ai meetup! join us :-)
- 3 talks on research and applied topics with a focus on best practices
- 100 people building ai for real
- good vibes
airstreet(dot)com/zurichai
Nicolas Deutschmann retweeted
Nice write up by Kyle!
I’ll add on - answering questions like "why do we exist" needs no industrial application! It is the *endgame*, sitting atop Maslow's hierarchy. I prefer asking: "how can technology help us understand ourselves and our universe?"
My first draft of a reaction to @beenwrekt's blog post on the Higgs discovery. TL;DR, yes it did.
theoryandpractice.org/2024/1…
Nicolas Deutschmann retweeted
⚡️ New blog post... whilst wearing my Cradle hat!! 🧬
"State-of-the-art enzyme engineering with fully-automated GenAI"
cradle.bio/blog/align-to-inn…
TL;DR: Dataset goes in, SOTA protein function models come out. *Zero human intervention required.*
1/3
Nicolas Deutschmann retweeted
Lovely measurement of W-boson mass from @CMSExperiment; slides at indico.cern.ch/event/1441575…
Nicolas Deutschmann retweeted
✨Aaaand it's time for ICML!
DM me or @constance_frg if you'd like to chat about 🧬ML-for-proteins or 🚀startups! :D
Nicolas Deutschmann retweeted
Si nous étions en Grande-Bretagne ou aux USA, une telle information ne se serait pas enfouie dans un live mais ferait le gros titre de Une du journal, et une équipe de journalistes serait sur la brèche pour savoir si d’autres candidats ont reçu le même message du Président.
Nicolas Deutschmann retweeted
📢 We are hiring! 📢
Are you a MSc/PhD👩🎓👨🎓 passionate about #AI #ML in #cancer, looking for your next career step?
Join our newly-founded AI/ML for Biomedicine group part of the Biomedical Data Science Center at @unil and @CHUVLausanne in beautiful Lausanne!🇨🇭🏔🌈
👇
Nicolas Deutschmann retweeted
Join our Track on #AI for #drugdiscovery at #AMLD2024 March 25 in Lausanne 🇨🇭!
🔥 Sessions on #AI for #molecules, #singlecell #omics
🔊 Stellar invited talks from @mo_lotfollahi @fra_grisoni and @DRoqueiro
🗒️ Submit your abstract and get selected for a short talk or a poster 👇
The call for Posters is now open for AMLD EPFL 2024! Passionate about AI and machine learning? Join a track at AMLD EPFL 2024!
Find out more here. go.epfl.ch/AMLDTracks Early Bird rates until 25 January. Register now! go.epfl.ch/AMLD
#AMLDEPFL2024 #AI #MachineLearning
Nicolas Deutschmann retweeted
Interested in Uncertainty Quantification for Sequence Prediction?
Come check out our poster at @RealAAAI today. We add rigorous uncertainty quantification to Beam Search using Conformal Predictions!
@nickgermann @IBMResearch
Nicolas Deutschmann retweeted
We have a new preprint on DFT and eigenvalue algorithms:
"Hermitian Pseudospectral Shattering, Cholesky, Hermitian Eigenvalues, and Density Functional Theory in Nearly Matrix Multiplication Time". Link to Arxiv:
arxiv.org/abs/2311.10459
This is so cool! I keep pushing back using JAX thinking “so much of my current work is in PyTorch”. Can’t wait to try it out!
Nicolas Deutschmann retweeted
Excited our Preprint on Conformal Beam Search with @nickgermann and @MariaRoCompBio is out on @Arxiv. We add rigorous uncertainty quantifications to Beam Search using Conformal Predictions. Applicable to any model without changes in the architecture!!
🔗ibm.biz/conformal_beams
One of the cool surprises from this work is how well calibrated the set sizes turned out to be in our experiments with dynamic beam sizes:
Great correlation between how wide the beams need to be vs how they actually are.
Excited to see how well this holds in other exps!
Here's our preprint on conformal sequence generation!
w/ @malberts99 @MariaRoCompBio
arxiv.org/abs/2309.03797
Two new algorithms for sequence prediction sets with guarantees:
- Conformal sub-beams: pruning standard beams
- Conformal dynamic beams: step-by-step conformal decoding.
Nicolas Deutschmann retweeted
Great to see our work @IBMResearch on prompt driven retrosynthesis in @ACSCentSci highlighted by @OPRD_ACS alongside several former colleagues and collaborators!
🌟Highlight: pubs.acs.org/doi/10.1021/acs…
📰Paper: pubs.acs.org/doi/10.1021/acs…
#NLP #MachineLearning #Chemistry #AI
Nicolas Deutschmann retweeted
Are you dealing with geometric data, be it from molecules or robots? Would you like inductive biases *and* scalability?
Our Geometric Algebra Transformer (GATr 🐊) may be for you.
New work w/ @pimdehaan, Sönke Behrends, and @TacoCohen:
arxiv.org/abs/2305.18415
1/9
Nicolas Deutschmann retweeted
Can’t wait to meet new and old connections at #ACSFall2023. If you are around, pass and say 👋🏻 by the @IBMResearch booth 249. We are here at ACS with 42 contributions, 6 of which from the team. We will also unveil the concept of a “Lab that Learns”. Curious ? Come and visit us!
Nicolas Deutschmann retweeted
On Wednesday, @malberts99 will present at 08:45am:
Automatic structure elucidation from IR spectra
and at 04:15pm:
Automatic structure elucidation from NMR spectra
Both contributions exploring the use of foundation models for molecular structure elucidation.