🚨 Workshop Alert 🚨 Dive into Gen AI and its applications, from physics to drug design, with a top-notch line-up of speakers! 🚀 Join us in Bonn this fall! 🇩🇪 Register now: indico.hiskp.uni-bonn.de/event/443/page… #AI4Science #Workshop #UniBonn #GenerativeModels

Congrats to all on this great resource! For sure, this will enable progress in protein-ligand and protein-protein docking.

How can we efficiently (approximately) solve an RL problem with non-additive trajectory rewards? In our #ICML2024 paper (session: Tue 23rd, 1.30pm), we propose a meta-algorithm that solves this problem by reducing it to a specific sequence of standard MDPs.

🧵1/3 Excited to be presenting our paper, CLIPZyme, at ICML Conference this week with Peter G Mikhael. In our paper we introduce a new method to rank enzymes based on their catalytic activity for a given reaction of interest. Paper: arxiv.org/pdf/2402.06748 Code: github.com/pgmikhael/clip…

🧵1/3 Excited to be presenting our paper, CLIPZyme, at ICML Conference this week with itamar. In our paper we introduce a new method to rank enzymes based on their catalytic activity given the reaction of interest. Paper: arxiv.org/pdf/2402.06748 Code: github.com/pgmikhael/clip…

Exciting work addressing the biggest blocker in protein-ligand interaction prediction.

The lack of datasets and proper evaluation approaches is a massive problem for AI-driven drug discovery, as even available data sometimes comes with restrictions (see PDBBind). This work on Protein-Ligand/Protein Complex prediction is a big step forward in the right direction.

I will be at #ICML in Vienna from tomorrow! I'm looking forward to meeting a lot of amazing people! I'll also be presenting DisCo-Diff tomorrow and a glimpse to new work on flexible docking on Friday! 🔥

📢 We are excited to announce that the next #MoML Conference @ MIT will be taking place on Nov. 5! Join us @ MIT for the 5th #MoML Conference! 🌟 Registrations and paper submissions are now open: moml.mit.edu

The #MoML conference at MIT is coming back this year!

The MLSB 2024 call for papers is live at mlsb.io ! New this year: we're excited to use MLSB to highlight importance of benchmarks. We'll have 2 tracks for models evaluated on pinder.sh / plinder.sh from VantAI NVIDIA MIT CSAIL !

We have a few spots left! Register now at indico.hiskp.uni-bonn.de/event/443/ 14 technical talks 3 keynotes 3 panel discussions 1 poster session and much more... Including speakers like (in random order) pan tom, Jonas Köhler, Michael Albergo, Lei Wang, Lorenz Richter, and many more!

Each week, we want to highlight Learning on Graphs Conference 2024 papers! ✨ Check out "Learning Graph Search Heuristics" by Michal Pándy, Weikang Qiu, Gabriele Corso, Petar Veličković, Zhitao Ying, Jure Leskovec, Pietro Lio openreview.net/pdf?id=-xjStp_…

My seminar on ML in Structure-Based Drug Discovery at the MoML Summer School is now on YouTube youtube.com/watch?v=0EmYfN… Giving this class had a particular significance for me as MoML is dedicated to the memory of Octavian Ganea an amazing friend who introduced me to this topic 🙏

📢 Missed the last lecture? Here's the key takeaways for the upcoming MLSB @ NeurIPS challenge: 🧵 📅 The PINDER + PLINDER + MLSB teams are organizing a training workshop Sep 24th - plinder.sh/blog/training 🎯 Tasks: flexible protein-protein & protein-ligand docking/co-folding

II/III 🧵

III/III 🧵

The expert has made his diagnosis: Europe is sleepwalking. Will European leaders now show leadership & take the medicine? I wouldn't bet on it. on.ft.com/3XcM4Fw