How cooperation events in different omics can help to infer molecular mechanisms ? Read our new pre-print ! "Molecular mechanisms reconstruction from single-cell multi-omics data with HuMMuS" biorxiv.org/content/10.110… @LauCan88 InaMaria Deutschmann - explainer thread 1/6

Next Tuesday at 2023-06-27 18:00 CEST will be another community meeting! Geert-Jan Huizing will talk about Mowgli, a method for the integration of paired multi-omics data! Looking forward to seeing everyone there!

New paper out : a simple way to have optimal transport with sparse displacements🎆 "Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps" arxiv.org/abs/2302.04065 w. @CuturiMarco and Michal Klein A small thread👇

Geert-Jan Huizing from my team Institut Pasteur, since 1887 presenting Mowgli MLCSB #ISMBECCB2023 If you want to know more about it check the preprint biorxiv.org/content/10.110…

I have written a very short mathematical summary of the main ingredients of denoising diffusion models. mathematical-tours.github.io/book-sources/o… Most of this is directly borrowed from the amazingly clear slides of Valentin De Bortoli vdeborto.github.io/project/genera…

Ah, we forgot to tweet this. Geert-Jan Huizing from Institut Pasteur, since 1887 (@LauCan88 lab) has won the MLCSB best poster award with their work titled "Paired single-cell multi-omics data integration with Mowgli". #ISMBECCB2023

🥳🥳 New work: arxiv.org/abs/2309.01213 Implicit Regularization of ResNets towards Neural ODEs w. Pierre Marion, Yu-Han Wu and Gérard Biau We show: ResNet initialized as discretization of a neural ODE -> such a discretization holds throughout training.

Stay tuned for the next live coding session on twitch 👨‍💻 coming soon @ twitch.tv/zaccharier

🔬Pleased to share our latest preprint, "G-PLIP: Knowledge graph neural network for structure-free protein-ligand bioactivity prediction" 📖: doi.org/10.1101/2023.0… 🤝 Collaborated between Roche and EPFL #Research #DrugDiscovery #GeometricDeepLearning

How does optimal transport allow us to study dynamical systems? How does it connect to control theory, flow matching, & diffusion models? How is it advancing molecular biology research? Find the answers in our tutorial! Recording, slides, & script under bunne.ch/ot_tutorial/.

Happy to be at NeurIPS! I'll present my work on conservation laws for gradient flows (openreview.net/forum?id=kMueE…) tomorrow at 10:15am during the DL theory oral session (Room R06-R09) and during the follow-up poster session (Poster #900). Joint work w. Gabriel Peyré & Rémi Gribonval

🥳 I’m very happy to announce our preprint biorxiv.org/content/10.110… ! scConfluence combines uncoupled autoencoders with Inverse Optimal Transport to integrate unpaired multimodal single-cell data in shared low dimensional latent space. @LauCan88 Gabriel Peyré

Come check @VCastin_ ´s work on the smoothness of attention 🔥🔥🔥 Happening now, poster 510 !

🚨🚨 AI in Bio release 🧬  Very happy to share my work on a Large Cell Model for Gene Network Inference. It is for now just a preprint and more is to come. We are asking the question: “What can 50M cells tell us about gene networks?” ❓Behind it, other questions arose like:

"Transformers are Universal In-context Learners": in this paper, we show that deep transformers with a fixed embedding dimension are universal approximators for an arbitrarily large number of tokens. arxiv.org/abs/2408.01367

🥳Bravo Sibylle Marcotte, membre de l'équipe Ockham de notre centre, doctorante à École normale supérieure | PSL, lauréate 🏆du Prix Jeunes Talents France 2024 Fondation L'Oréal-UNESCO 🏛️ #Education #Sciences #Culture 🇺🇳 #ForWomenInScience Académie des sciences For Women in Science Toutes nos félicitations !!! ©Richard Pak et Clémence Losfeld

New preprint! 🚨 Clustering is a powerful tool in genomics & neurosci, but is contingent on the distance /cost chosen between data features. With Samo Hromadka & myamada0 we used optimal transport on trees 🌳 to learn underlying distances – fast! arxiv.org/abs/2411.07432 1/8