🚨thingsvision (github.com/ViCCo-Group/th…) has a few new gems for you: - 🔥efficient mini-batch feature extraction for using your custom data pipeline 👇 - 🤖more vision models including OpenCLIP, DINOv2, and MAEs - 🧠optional alignment of model representations with gLocal 👇

First publication of my postdoc in Berlin is out on arXiv today! 🎉 ~~> We use diffusion probabilistic models to relax distorted molecules. No out-of-equilibrium data needed! A little 6-thread🧵

Big thanks to my collaborators and mentors, first and foremost Mina Jamshidi Idaji, as well as Oliver Eberle @eberleoliver.bsky.social, Thomas Schnake, Jonas Dippel, Laure Ciernik, Oliver Buchstab, Andreas Mock, Frederick Klauschen, Klaus-Robert Müller, and all the supporters from BIFOLD and ML Group, TU Berlin.

New Preprint 🚨: Our lab finds that high mitochondrial RNA (pctMT) levels, typically flagged as cell death in single-cell RNA-seq, may actually mark viable, critical cancer cell populations. doi.org/10.1101/2024.1… Here’s what we uncovered 👇 (1/n)

❓ Do histopathological foundation models eliminate batch effects? ❓ The surprisingly clear answer is: they do not! Find out more in our new paper that we will present at the AIM-FM Workshop at NeurIPS Conference. Link: arxiv.org/abs/2411.05489

1/ 🧬 Single-cell genomics reveals biological variations beyond cell types. Unveiling these in separate latent dimensions is known as disentanglement. Led by Amir Ali Moinfar, we introduce DRVI to learn nonlinear, disentangled & interpretable latent spaces. biorxiv.org/content/10.110…

🚀 New preprint from our lab, Ekaterina Krymova and Fabian Theis : UniversalEPI, an attention-based method to predict enhancer-promoter interactions from DNA sequence and ATAC-seq🌟 🔬 Key Highlights: - Predicts chromatin interactions across unseen cell types with no retraining. -

1/🚀 Excited to share RegVelo, our new computational model combining RNA velocity with gene regulatory network (GRN) dynamics to model cellular changes and predict in silico perturbations. Here's how it works and why it matters! 🧵👇 biorxiv.org/content/10.110…