iiinova — where your digital self keeps evolving

Reposted by Hannah Dickmänken

Nature Portfolio @natureportfolio.nature.com · 08/08/2026

Struggling to stay focused in the lab? Nature’s careers team asked six attention researchers and educators for tips on how to mitigate disruptions and improve concentration. #Academicsky 🧪

go.nature.com

Science-backed tips on how to avoid distractions

Struggling to stay focused in the lab? Attention researchers offer some advice.

0197 19

Reposted by Hannah Dickmänken

European Commission @ec.europa.eu · 02/08/2026

🔹 AI-generated media, ‘deepfakes’ must be clearly labelled as such 🔸Chatbots and virtual agents must explicitly state they aren't human 🔹You must be told when AI is actively analysing you, like biometrics, emotion tracking → link.europa.eu/gTvhRX

15349113 349

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/07/2026

Just saw this at the Entomology conference presented by Konstantina, super cool work 😍

110 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 03/07/2026

Big thanks to @ece2026tours.bsky.social for letting me present my PhD work this week. It was truly the best conference organization ever! Plus I learned so much about the coolest insects, biodiversity, agriculture and science communication & made new friends as well ♥️🪲

PhD student presenting her work at a conference, standing in front of a screen taking.

040 4

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/06/2026

Looking forward to 5 days of insect science #ECE2026Tours ! Join my talk tomorrow in the insects & society AI session at 18h15 on what genomics and Deep Learning can teach us about fly development 🧬

Photo of title slide at the start of the ECE conference in the main auditorium.

131 3

Reposted by Hannah Dickmänken

Science Magazine @science.org · 14/06/2026

A new Science study shows that bumble bees can position a ball underneath a fake “flower” to reach a reward, suggesting they can exhibit spontaneous problem-solving and challenging the notion that such advanced cognitive abilities are exclusive to large-brained vertebrates. scim.ag/4vs08dC

362100608 2.1K

Reposted by Hannah Dickmänken

Alexandra P @alexanrna.bsky.social · 12/06/2026

I will be presenting this work at #eshg2026 on Monday during "From Population to Pertubation" session (C31, room F1-F3 @ 10:30)!

142 4

Hannah Dickmänken @hannahdckmnkn.bsky.social · 30/03/2026

Happy to see my paper re-posted by the VSC! Without their high-performance computing resources, this research would not have been possible.

020 2

Reposted by Hannah Dickmänken

VIB.AI @vibai.bsky.social · 13/02/2026

The @steinaerts.bsky.social lab is looking for a postdoctoral researcher to develop next-generation sequence-to-function models for glioblastoma, one of the most aggressive brain cancers. More info & how to apply 👉 vib.ai/en/opportunities#/job-descri…

0611 11

Reposted by Hannah Dickmänken

Seppe De Winter @seppedewinter.bsky.social · 15/01/2026

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.

14521 45

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

With more deep learning tools becoming available & easy to use to decode enhancer logic and cell-type identity, evaluating scATAC platforms of training data generation adds a new pillar to tech development! (10/10)

011 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

Technical consistency matters for integration: We observe highly similar Tn5 insertion bias between HyDrop v2 and commercial droplet-based scATAC-seq platforms, across species. (9/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

f, S2F models in 10-fold cross-validation. g-h, Scanning of ~2kb enhancers with 500 bp sliding window. Predicted accessibility of neuroblast enhancer (VDRC library). Both 10x and Hydrop v2-based models identify the same region as a core enhancer in the 200kb VDRC region. Taken from Figure 4. (8/n)

f, Computational design evaluating scATAC techniques as training data for S2F models in k-fold cross-validation (k=10). g-h, Scanning of ~2kb enhancers (g) with 500 bp sliding window (10bp
shift). Predicted accessibility of 500 bp windows of VT3067 enhancer (VDRC library). The region coordinates are based on Kvon et al. (2014), accessibility as ground truth. Line plots show mean predicted accessibility across n=10 cross-validation folds. Bands represent 95% confidence intervals (1.96 × SD). Both 10x and Hydrop v2-based models identify the same region as a core enhancer in the 200kb VDRC region. Taken from Figure 4.

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

d-e, 10x v1 and v2 datasets combined into the 10x Genomics training dataset compared to the HyDrop v2-based dataset for S2F deep learning models in 10-fold cross-validation. Performance is validated on standard DL metrics and mouse cortex enhancers previously validated in vivo seen in e. (7/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

Models trained on HyDrop v2 data accurately recover in vivo-validated enhancers in mouse and fly. Pretrained models are publicly available and ready for downstream use. (6/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

We identify saturated sequencing depths for model training: • ~12k reads/cell for Drosophila embryo • ~36k reads/cell for mouse cortex Beyond these points, deeper sequencing provides little added value. (5/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

A central result: Lower per-cell coverage can be offset by increasing dataset size, without loss of predictive performance. Even with ~60% more cells than 10x, HyDrop v2 datasets remain ~8× cheaper to generate. (4/n)

110 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

a, b, study design in mouse and Drosophila embryo. c, Estimation of generation costs of 67k cells in euros, excluding sequencing costs. HyDrop v1: 851.53 euro, HyDrop v2: 668.18 euro, 10x v2: 9,337.79 euro. Taken from Figure 1. (3/n)

110 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

With our new mouse motor cortex and Drosophila embryo data (600k cells!), we trained 220 sequence-to-function models, systematically varying read depth and cell number, and evaluated performance, robustness, and interpretability via cross-validation. (2/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

We benchmarked custom vs commercial droplet-based scATAC-seq platforms for ML model training and introduce an optimized HyDrop v2 protocol with improved sensitivity and scalability. The full protocol is openly available. (1/n)

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 29/01/2026

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)

nature.com

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...

24118 41

Reposted by Hannah Dickmänken

VIB-KU Leuven Center for Neuroscience @vibneuroleuven.bsky.social · 27/01/2026

🚀 Proudly introducing the VIB-KU Leuven Center For Neuroscience, a merger of the two former VIB research centers VIB-KU Leuven Center for Brain & Disease Research and Neuro-Electronics Research Flanders (NERF)! Our new motto: Bold Science, Real Impact. www.youtube.com/watch?v=uhaq...

youtube.com

VIB-KU Leuven Center for Neuroscience

YouTube video by VIB-KU Leuven Center for Neuroscience

0157 15

Reposted by Hannah Dickmänken

Arnau Sebé-Pedrós @arnausebe.bsky.social · 24/09/2025

Happy to share the Biodiversity Cell Atlas white paper, out today in @nature.com. We look at the possibilities, challenges, and potential impacts of molecularly mapping cells across the tree of life. www.nature.com/articles/s41...

4229107 229

Hannah Dickmänken @hannahdckmnkn.bsky.social · 18/09/2025

Ending my two weeks conference marathon: last week Single Cell Spatial Omics #SCSO 600 year #KULeuven edition & now #SCG2025 - learned so much & am now already searching for the next one! Any recommendations for biodiversity, non-model organisms & genetics in 2026? 🪰🦋🐛🐌

040 4

Reposted by Hannah Dickmänken

Alexandra P @alexanrna.bsky.social · 10/09/2025

1/ First preprint from @jdemeul.bsky.social lab 🥳! We present our new multi-modal single-cell long-read method SPLONGGET (Single-cell Profiling of LONG-read Genome, Epigenome, and Transcriptome)! www.biorxiv.org/content/10.1...

14917 49

Reposted by Hannah Dickmänken

Stein Aerts @steinaerts.bsky.social · 04/04/2025

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...

biorxiv.org

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...

510939 109

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

Make sure to also check out the preprint on the new CREsted package: many more sequence-to-function models across different species! … and it works with HyDrop v2 data as well. Congrats to @niklaskemp.bsky.social & @seppedewinter.bsky.social & all the others working on this super cool project!

0122 12

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

The data is out at GEO, resources.aertslab.org/papers/hydro..., and the models at crested.readthedocs.io/en/stable/mo... - we are looking forward to your feedback!

010 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

Thanks a lot to the whole lab for the great teamwork and especially to @s-poovathingal.bsky.social and @steinaerts.bsky.social for the support, Marta for the bead optimization, and @lukasmahieu.bsky.social for the help with all Deep Learning questions!

141 4

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

With HyDrop v2, we offer an accessible, scalable, and low-cost method to generate scATAC-seq datasets suitable for training ready-to-use deep learning tools. HyDrop v2 data reliably captures biologically relevant regulatory features and achieves predictive performance comparable to commercial tools.

120 2

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

Just as in fly, the mouse model trained on HyDrop v2 mouse cortex data also correctly identifies and matches predictions of in vivo validated enhancers.

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

We also compared our multi-class embryo model to the embryo models by Alexander Stark's lab @impvienna.bsky.social (sciATAC). With both 10x and HyDrop data-based sequence-to-function models, we were able to replicate and refine their motif predictions without the need for fine-tuning our models.

110 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

In the Drosophila embryo, we scored the in vivo validated enhancers from the VDRC lines and were able to track down the most predictive 500 bp region within the 2kb enhancers using our sequence-to-function models with 10-fold cross-validation.

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

We trained sequence-to-function models with the new CREsted package on both species and used the Seq2PRINT for footprinting in HyDrop and 10x data. Both are comparable as well in terms of enhancer predictions, sequence explainability, and transcription factor footprinting.

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

Differentially accessible regions & motif enrichment are equivalent between HyDrop v2 & 10x. Due to the bead optimization@s-poovathingal.bsky.social, HyDrop v2 experiments are very robust, and the data integrates seamlessly with commercially available chromatin accessibility methods (10x Genomics).

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

The costs of generating the library of, e.g., the mouse cortex across 35 experimental “runs” accumulate to merely 1,080.60 euros compared to an equivalent of 10x v2-based library preparation for 15,330.70 euros, excluding the sequencing cost. 35 experiments can be performed in just 1.5 days!

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

To demonstrate the cost-effective generation of large scATAC-seq atlases with HyDrop with increased sensitivity and scale, we evaluated the data quality in the mouse cortex (110k cells) and our new Drosophila embryo atlas and compared them to atlases generated on commercial platforms.

100 1

Hannah Dickmänken @hannahdckmnkn.bsky.social · 04/04/2025

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...

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.

25525 55