Tina Šubic

Thanks! Happy to hear any feedback 🙂

Mechanistic Genome Folding at Scale through the Differentiable Loop Extrusion Model The spatial folding of the genome shapes gene regulation by controlling which loci interact, yet inferring the mechanisms behind these 3D structures from contact maps remains difficult. Cohesin-mediat...

I had the best time working on dLEM! Huge thanks to my amazing co-authors: Maria Chikina, Ali Tugrul Balci, Kristina Perevoshchikova, and @gfudenberg.bsky.social!

check the preprint: 🔗 www.biorxiv.org/content/10.1...

Bottom line: dLEM shows we don't have to choose between mechanistic insight and predictive power.
By reformulating loop extrusion as a differentiable process, we get:
✅ Interpretability
✅ Scalability
✅ Perturbation prediction
✅ Integration with ML

10/10

The parameter reduction compared to other deep learning models in deep dLEM is wild 🤯:
- 280× fewer than C.Origami
- 750× fewer than Orca
Yet we achieve competitive accuracy!

Why? Because we hard-coded the biophysics instead of making the model learn it.

9/10

We took dLEM to the next level: deep dLEM 🧠
We embedded dLEM as a biophysical layer in a neural network that learns from:

- DNA sequence
- Chromatin accessibility (DNase/ATAC)

Result: Sequence → structure prediction that stays mechanistically grounded

8/10

Example 2: CTCF depletion
→ We systematically reduced CTCF coefficients in our linear model
→ Optimal prediction at α=0.33, matching the 33% of CTCF peaks that remain after auxin treatment
The model reveals residual CTCF is still functionally active!

7/10

Because dLEM parameters are physically interpretable, we can do something deep learning can't: predict perturbation effects!

Example: WAPL depletion
→ We modified just the detachment rate
→ Successfully predicted emergence of new loops & extended stripes

What do we learn from these velocity profiles?
😌 CTCF shows expected directional asymmetry (blocks L or R depending on orientation)
😲 BUT: Transcription machinery (H3K4me3, H3K36me3, H3K4me1,...) ALSO modulates cohesin dynamics!
CTCF isn't the whole story 👀

5/10

dLEM acts as an encoder-decoder.
📥 ENCODER: Compress complex 2D Hi-C maps into simple 1D velocity profiles
📤 DECODER: Reconstruct contact maps from these profiles

It's dimensionality reduction, but with built-in biophysics!

4/10

💡The key insight: While contact maps are 2D, loop extrusion is inherently 1D—cohesin walks along chromatin!
dLEM captures this with two velocity profiles:
→ L: leftward cohesin speed
→ R: rightward cohesin speed
Obstacles (like CTCF) = dips in velocity 📉

3/10

The challenge: Current methods face an impossible tradeoff.
❌ Polymer simulations = mechanistic, but not scalable
❌ Deep learning = predictive, but black-box
❌ Summary metrics = compressed, but mechanism-agnostic
We needed something that's mechanistic, interpretable, AND scalable.
✅ Enter dLEM!
2/10

✨New preprint!✨

We built dLEM - a differentiable Loop Extrusion Model that bridges biophysics and machine learning for 3D genome folding.

dLEM makes loop extrusion learnable and interpretable—predicting how genomes fold and how they respond to perturbations.

🧵

Learning locally dominant force balances in active particle systems | Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences We use a combination of unsupervised clustering and sparsity-promoting inference algorithms to learn locally dominant force balances that explain macroscopic pattern formation in self-organized active...

Learning interpretable mathematical models from data is transforming science. But what if different models apply in different areas or at differnt times? After all, living systems are plastic and self-organized. Now you can learn *local* model clusters! doi.org/10.1098/rspa...

8/8 I had so much fun working on this paper with Ivo @mosaicgroup.bsky.social group at @mpicbg.bsky.social! Thanks for all the support, patience, and freedom to explore! # CompBio #Biophysics #PhDLife #Science #Research

7/8 There's more to explore, especially for 2D systems (like membranes), but this changes how we use these models to study cellular processes!

6/8 When these models "lose" reactions, they're actually capturing a real physical transition to the diffusion-limited regime. This opens new possibilities for studying complex molecular systems.

5/8 On top of that, we find that different diffusion models (like GRDME vs traditional RDME) correspond to different molecular sizes on the same grid. So even with this interpretation of RDME, we can model systems with molecules of different sizes!

4/8 Our key finding is that grid size sets molecular size! Smaller boxes —> smaller molecules —> need to get closer to react—> fewer reactions. This perfectly matches the theory for diffusion-limited systems.

3/8 But what if the grid size itself represents the reaction radius - the distance at which molecules can react? Then fewer reactions when boxes are smaller would be exactly what should happen physically! 💡

2/8 In grid-based models (RDME/GRDME), molecules jump between boxes and react when in the same box. As we make boxes smaller, reactions become less frequent - for years, this was seen as a flaw! 🤔

Loss of bimolecular reactions in reaction–diffusion master equations is consistent with diffusion limited reaction kinetics in the mean field limit We show that the resolution-dependent loss of bimolecular reactions in spatiotemporal Reaction–Diffusion Master Equations (RDMEs) is in agreement with the mean-

🧵 We @mosaicgroup.bsky.social just published in @aip-publishing.bsky.social JChemPhys (doi.org/10.1063/5.02...): Turns out that grid resolution in stochastic reaction-diffusion models represents molecule size! This completely changes how we understand "reaction loss" in these models:

7/7 This work led to some surprising insights about how these models actually represent physical reality, particularly the 'reaction loss' phenomenon... and that's a story of the just published paper! 😉 #CompBio #Biophysics #PhDLife #Science #Research

6/7 Here's where it gets interesting: RDME "loses" bimolecular reactions at very fine grid resolutions. Well, so does GRDME! We derived a rule of thumb to predict this limit - turns out GRDME's limit is higher by the same factor as its speedup.

5/7 Both RDME and GRDME show second-order convergence of the diffusion error with grid resolution. While GRDME has a slightly larger error, it runs up to 6x faster in 3D (or even more if you increase the smoothing length)! There's no free lunch in computing, but this is a pretty good deal!

4/7 PSE naturally comes with a 'smoothing length' parameter (the spread of the Gaussian). By repurposing it for GRDME, we get a built-in way to tune the trade-off between speed and accuracy!

3/7 Our new method, GRDME, lets molecules make "Gaussian jumps" - like confetti 🎊, they can land in boxes further away, with closer boxes being more likely! The math comes from Particle Strength Exchange (PSE), a discretization technique from the particle methods community.

2/7 I worked with RDME (Reaction-Diffusion Master Equation) - a method that divides space into a grid of boxes and tracks molecules moving between them. Molecules can only jump to adjacent boxes —> it approximates diffusion with finite differences - simple and accurate, but oh so slow! 🐌

A Gaussian jump process formulation of the reaction–diffusion master equation enables faster exact stochastic simulations We propose a Gaussian jump process model on a regular Cartesian lattice for the diffusion part of the Reaction–Diffusion Master Equation (RDME). We derive the r

GRDME (Gaussian Reaction Diffusion Master Equation) is a method that makes exact stochastic simulations of molecular interactions more efficient! It was also the subject of my first PhD paper (doi.org/10.1063/5.01...) with @mosaicgroup.bsky.social from my time at @mpicbg.bsky.social 🧵

My second PhD paper just got published! 🎉 So, it’s good time to introduce my PhD work to Blue Sky.

Great to be here! I guess I should introduce myself: I’m a postdoc (Chikina lab), using physical modeling and machine learning to study transcription and genome organization. But, I’d really like to get into plant science and tackling climate change!