Seppe De Winter's Avatar

Seppe De Winter

@seppedewinter.bsky.social

PhD researcher at aertslab VIB-AI KU Leuven.

64 Followers  |  106 Following  |  5 Posts  |  Joined: 03.04.2024  |  1.5455

Latest posts by seppedewinter.bsky.social on Bluesky

Preview
Evaluating methods for the prediction of cell-type-specific enhancers in the mammalian cortex Johansen et al. report the results of a community challenge to predict functional enhancers targeting specific brain cell types. By comparing multi-omics machine learning approaches using in vivo data...

Check out our work on evaluating methods for predicting in vivo cell enhancer activity in the mouse cortex! Combined, scATAC peak specificity and sequence-based CREsted predictions gave the best predictive performance, aiming to advance genetic tool design for cell targeting in the brain.

21.05.2025 16:45 β€” πŸ‘ 20    πŸ” 10    πŸ’¬ 1    πŸ“Œ 0

One thousand candidate enhancers tested in vivo in the mouse brain! A massive resource and oh so useful as validation set for genome-wide enhancer prediction methods. Super fun to be involved in one of the papers: β€˜the prediction challenge paper’ by Nelson&Niklas et al www.cell.com/cell-genomic...

21.05.2025 16:50 β€” πŸ‘ 40    πŸ” 13    πŸ’¬ 0    πŸ“Œ 0

Great! Thank you so much!

21.05.2025 12:21 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
SharedIt | Springer Nature | For Researchers | Springer Nature__small_youtube

Hi, looks very interesting!
Any chance that you can share the manuscript, for example using www.springernature.com/gp/researche...?

21.05.2025 07:09 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
Modelling and design of transcriptional enhancers Nature Reviews Bioengineering - Enhancers are genomic elements critical for regulating gene expression. In this Review, the authors discuss how sequence-to-function models can be used to unravel...

For those looking to read the article, it's available via this link rdcu.be/egQdA

24.04.2025 18:42 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Programmatic design and editing of cis-regulatory elements The development of modern genome editing tools has enabled researchers to make such edits with high precision but has left unsolved the problem of designing these edits. As a solution, we propose Ledi...

Our preprint on designing and editing cis-regulatory elements using Ledidi is out! Ledidi turns *any* ML model (or set of models) into a designer of edits to DNA sequences that induce desired characteristics.

Preprint: www.biorxiv.org/content/10.1...
GitHub: github.com/jmschrei/led...

24.04.2025 12:59 β€” πŸ‘ 115    πŸ” 37    πŸ’¬ 2    πŸ“Œ 3
Preview
CREsted: modeling genomic and synthetic cell type-specific enhancers across tissues and species Sequence-based deep learning models have become the state of the art for the analysis of the genomic regulatory code. Particularly for transcriptional enhancers, deep learning models excel at decipher...

Very proud of two new preprints from the lab:
1) CREsted: to train sequence-to-function deep learning models on scATAC-seq atlases, and use them to decipher enhancer logic and design synthetic enhancers. This has been a wonderful lab-wide collaborative effort. www.biorxiv.org/content/10.1...

04.04.2025 09:04 β€” πŸ‘ 109    πŸ” 39    πŸ’¬ 5    πŸ“Œ 1
Data collected with the new sequencing platform HyDrop v2 is shown. First, a schematic overview of the bead batches of the microfluidic beads is followed by a tSNE and a barplot showing the costs in comparison to 10x Genomics. 
Then, a track of mouse data (cortex) is shown together with nucleotide contribution scores in the FIRE enhancer in microglia. Here, the HyDrop and 10x based models show the same contributions. 
On the right, the Drosophila embryo collection is explained; in the paper HyDrop v2 and 10x data are compared to sciATAC data. Then, a nucleotide contribution score is also shown, whereas HyDrop v2 and 10x models show the same contribution, just as in mouse.

Data collected with the new sequencing platform HyDrop v2 is shown. First, a schematic overview of the bead batches of the microfluidic beads is followed by a tSNE and a barplot showing the costs in comparison to 10x Genomics. Then, a track of mouse data (cortex) is shown together with nucleotide contribution scores in the FIRE enhancer in microglia. Here, the HyDrop and 10x based models show the same contributions. On the right, the Drosophila embryo collection is explained; in the paper HyDrop v2 and 10x data are compared to sciATAC data. Then, a nucleotide contribution score is also shown, whereas HyDrop v2 and 10x models show the same contribution, just as in mouse.

Our new preprint is out! We optimized our open-source platform, HyDrop (v2), for scATAC sequencing and generated new atlases for the mouse cortex and Drosophila embryo with 607k cells. Now, we can train sequence-to-function models on data generated with HyDrop v2!
www.biorxiv.org/content/10.1...

04.04.2025 08:52 β€” πŸ‘ 54    πŸ” 25    πŸ’¬ 2    πŸ“Œ 2
Post image

We released our preprint on the CREsted package. CREsted allows for complete modeling of cell type-specific enhancer codes from scATAC-seq data. We demonstrate CREsted’s robust functionality in various species and tissues, and in vivo validate our findings: www.biorxiv.org/content/10.1...

03.04.2025 14:30 β€” πŸ‘ 74    πŸ” 38    πŸ’¬ 1    πŸ“Œ 5
Post image

How does gene regulation shape brain evolution? Our new preprint dives into this question in the context of mammalian cerebellum development! rb.gy/dbcxjz
Led by @ioansarr.bsky.social, @marisepp.bsky.social and @tyamadat.bsky.social, in collaboration with @steinaerts.bsky.social

16.03.2025 10:31 β€” πŸ‘ 187    πŸ” 69    πŸ’¬ 4    πŸ“Œ 5

πŸ“„ Update on our preprint about Gene Regulatory Net (GRN) benchmarking πŸ“„
We have included the original and decoupled version of SCENIC+, added a new metric and two more databases. Dictys and SCENIC+ outperformed others, but still performed poorly in causal mechanistic tasks.
doi.org/10.1101/2024... πŸ‘‡

14.03.2025 10:34 β€” πŸ‘ 49    πŸ” 18    πŸ’¬ 2    πŸ“Œ 0

Thank you! I'm glad you liked it :).

12.03.2025 19:59 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Modelling and design of transcriptional enhancers - Nature Reviews Bioengineering Enhancers are genomic elements critical for regulating gene expression. In this Review, the authors discuss how sequence-to-function models can be used to unravel the rules underlying enhancer activit...

We wrote a review article on modelling and design of transcriptional enhancers using sequence-to-function models.

From conventional machine learning methods to CNNs and using models as oracles/generative AI for synthetic enhancer design!

@natrevbioeng.bsky.social

www.nature.com/articles/s44...

28.02.2025 14:45 β€” πŸ‘ 57    πŸ” 32    πŸ’¬ 1    πŸ“Œ 1
Post image

The latest Discover ASAP episode dives into "Cell Type Directed Design of Synthetic Enhancers," a study published in Nature by CRN Team Voet. They discuss how machine learning enables precise enhancer design for targeted gene expression 🧬

Watch: www.youtube.com/watch?v=Qcms...

13.02.2025 16:47 β€” πŸ‘ 6    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0
Preview
Explore cellular diversity with microscopy and AI: registration | KU Leuven

KU Leuven turns 600(!) this year and is celebrating with a public event this weekend! The @steinaerts.bsky.social lab is offering guided lab tours. Want a behind-the-scenes look? All tours on Saturday are full, but you can still register for Sunday!
www.kuleuven.be/600years/exp...

14.02.2025 16:33 β€” πŸ‘ 3    πŸ” 1    πŸ’¬ 0    πŸ“Œ 1
Preview
Enhancer-driven cell type comparison reveals similarities between the mammalian and bird pallium Combinations of transcription factors govern the identity of cell types, which is reflected by genomic enhancer codes. We used deep learning to characterize these enhancer codes and devised three metr...

In a new study, Nikolai Hecker, NiklasΒ Kempynck et al. in the team of @steinaerts.bsky.socialΒ exploreΒ 300 million years of brain evolution through the lens of enhancer codes.
www.science.org/doi/10.1126/...

14.02.2025 08:28 β€” πŸ‘ 27    πŸ” 8    πŸ’¬ 1    πŸ“Œ 1

This has been a fantastic adventure - to capture the genomic regulatory code underlying brain cell types (using deep learning models trained on chromatin accessibility), and then use these models to compare cell types between the bird and mammalian brain

14.02.2025 12:06 β€” πŸ‘ 41    πŸ” 12    πŸ’¬ 4    πŸ“Œ 1

Just very happy to have our paper out today! A big thanks to all our co-authors, and to Nikolai and @steinaerts.bsky.social for the teamwork over the past years. If you are interested in using our models for cross-species enhancer studies, check out crested.readthedocs.io/en/stable/mo... πŸ™‚

14.02.2025 10:07 β€” πŸ‘ 53    πŸ” 25    πŸ’¬ 3    πŸ“Œ 3

@seppedewinter is following 20 prominent accounts