EuroMLSB at EurIPS is confirmed and the submission deadline is set to Oct 1st. This is **earlier than the EurIPS-suggested workshop deadline** for a reason: we have a shared submission process with MLSB in SanDiego for which the deadline is now also extended to Oct 1st!
Last chance to register for the 2025 European RosettaCon - we had a blast last year, and @ajasjaljubetic.bsky.social is putting together a great program. With Easter eggs 🥚 in the submission system!
Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫
🧬 I'm looking for a new colleague (machine learning researcher) to work on exciting research projects around protein engineering with our ML team in Zurich. Speaking from experience, this is an amazing gig!
We trained a genomic language model on all observed evolution, which we are calling Evo 2.
The model achieves an unprecedented breadth in capabilities, enabling prediction and design tasks from molecular to genome scale and across all three domains of life.
Still at AMLD in Lausanne today. If you’re around, let’s have a coffee! Also, we (Cradle) and our collaborators from Adaptyv are hosting a little conference after party. Stop by!
Interestingly, our submission initially ranked between 300-600 on the competition leaderboard due to in-silico scoring mechanics that didn't normalize for sequence length. This highlights a crucial point: in-silico scores don't always tell the whole story when evaluating generative methods!
Agreed that the full solution is a challenge! Adding variable length CDR edits expands the search space quite dramatically! Current experiments look quite promising, though!
I‘d be curious to see the results! We’ve been playing around with CDR manipulation (including indels) and some of the ML models actually produce some pretty reasonable results! For diversification this is absolutely the way to go in my opinion. Most of the time binding got worse for us, though.
Real-world example on how targeted protein sequence engineering can significantly outperform structurally informed de novo design. I strongly believe both methods have their place. This challenge by #AdaptyvBio was a good example of optimization>design.
Also, we will be talking about how our zero shot approach landed first in the #AdaptyvBio protein design competition. See you there @patrickkidger.bsky.social :)
Agreed! That being said, the models are trained to capture higher-order epistasis, and we generally try to avoid single-mutation datasets during training if possible.
Thank you @klausenhauser.bsky.social ! We are currently working on some experiments for jointly optimizing Kon and Koff separately vs Kd as a singular metric. The former should give more fine-grained control of the trade offs of binding behavior without losing any signal for optimization.
Adaptyv Bio hosted an antibody engineering competition to design/engineer binders to EGFR. Super stoked that we came in first place with the Cradle team! We’ll be talking about the methods used at #NeurIPS this coming week! Here are the full results
