Darina Abaffy
@darinaabaffy.bsky.social
PhD student @ Stein Aerts Lab of Computational Biology.
Reposted by Darina Abaffy
What a great day at the Night Science Workshop in Leuven! A huge thank you to @itaiyanai.bsky.social and @martinlercher.bsky.social for sharing your inspiring take on the creative process with us, to all participants who made it so fun and dynamic, and to all who supported and made this possible!
May 17, 2026 at 9:01 AM
What a great day at the Night Science Workshop in Leuven! A huge thank you to @itaiyanai.bsky.social and @martinlercher.bsky.social for sharing your inspiring take on the creative process with us, to all participants who made it so fun and dynamic, and to all who supported and made this possible!
Reposted by Darina Abaffy
CREsted is finally out! You can find the article, together with a summarizing Research Briefing, in thread. 🦎
CREsted: an efficient and user-friendly toolbox for analysis, modeling and design of cell-type-specific enhancers.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
CREsted: modeling genomic and synthetic cell-type-specific enhancers across tissues and species - Nature Methods
CREsted is an efficient and user-friendly toolbox for analysis, modeling and design of cell-type-specific enhancers across diverse species.
www.nature.com
April 8, 2026 at 7:10 AM
CREsted is finally out! You can find the article, together with a summarizing Research Briefing, in thread. 🦎
Reposted by Darina Abaffy
Paper alert! 💻 How many cells do you need to train reliable deep learning models in regulatory genomics? We asked how data quality, sequencing depth, and dataset size affect training of sequence-to-function models from scATAC-seq. Out now www.nature.com/articles/s41...
(details below)
(details below)
Evaluating single-cell ATAC-seq atlasing technologies using sequence-to-function modeling - Nature Communications
Generating high-quality training data for machine learning is costly. Here, authors include sequence-to-function modeling in benchmarking of custom and commercial droplet-based scATAC platforms, and r...
www.nature.com
January 29, 2026 at 2:08 PM
Paper alert! 💻 How many cells do you need to train reliable deep learning models in regulatory genomics? We asked how data quality, sequencing depth, and dataset size affect training of sequence-to-function models from scATAC-seq. Out now www.nature.com/articles/s41...
(details below)
(details below)
Reposted by Darina Abaffy
We are thrilled to share our new pre-print: “System-wide extraction of cis-regulatory rules from sequence-to-function models in human neural development”. S2F-deeplearning models can accurately encode enhancers, yet decoding these models into human-interpretable rules remains a major challenge.
January 15, 2026 at 11:57 AM
We are thrilled to share our new pre-print: “System-wide extraction of cis-regulatory rules from sequence-to-function models in human neural development”. S2F-deeplearning models can accurately encode enhancers, yet decoding these models into human-interpretable rules remains a major challenge.
Reposted by Darina Abaffy
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...
www.biorxiv.org/content/10.1...
April 4, 2025 at 8:52 AM
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...
www.biorxiv.org/content/10.1...
Reposted by Darina Abaffy
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...
April 3, 2025 at 2:30 PM
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...
Reposted by Darina Abaffy
Most proteins fold co-translationally, but what if key residues aren’t available in time? Our new study introduces Native Fold Delay, a metric that links protein topology and translation rates to quantify folding delays. ⏳
Read more here www.nature.com/articles/s41...
Read more here www.nature.com/articles/s41...
Native Fold Delay and its implications for co-translational chaperone binding and protein aggregation - Nature Communications
During vectorial protein translation, native interactions are temporarily unsatisfied. Here, authors introduce “Native Fold Delay”, integrating protein topology with translation kinetics to quantify t...
www.nature.com
February 17, 2025 at 12:22 PM
Most proteins fold co-translationally, but what if key residues aren’t available in time? Our new study introduces Native Fold Delay, a metric that links protein topology and translation rates to quantify folding delays. ⏳
Read more here www.nature.com/articles/s41...
Read more here www.nature.com/articles/s41...
Reposted by Darina Abaffy
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... 🙂
In a new study, Nikolai Hecker, Niklas Kempynck et al. in the team of @steinaerts.bsky.social explore 300 million years of brain evolution through the lens of enhancer codes.
www.science.org/doi/10.1126/...
www.science.org/doi/10.1126/...
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...
www.science.org
February 14, 2025 at 10:08 AM
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... 🙂