Tetsuya Yamada

Beeswarm plot of the prediction error across different methods of double perturbations showing that all methods (scGPT, scFoundation, UCE, scBERT, Geneformer, GEARS, and CPA) perform worse than the additive baseline.

Line plot of the true positive rate against the false discovery proportion showing that none of the methods is better at finding non additive interactions than simply predicting no change.

Our paper benchmarking foundation models for perturbation effect prediction is finally published 🎉🥳🎉

www.nature.com/articles/s41...

We show that none of the available* models outperform simple linear baselines. Since the original preprint, we added more methods, metrics, and prettier figures!

🧵

You link #phenotype 🦜 to #genotype 🧬 with #comparative #genomics 💻?

This #review is for you 📜: authors.elsevier.com/sd/article/S...

We review new #methods, remaining #challenges and #future directions and highlight recent key studies.

Thanks @hillermich.bsky.social!

Please share! 🙂

Under which circumstances do genomic neural networks learn motifs and their interactions? The use of neural networks to model genomic data in sequence-to-function scenarios has soared over the last decade. There remains much debate about whether these models are interpretable, either inher...

Under which circumstances do genomic neural networks learn motifs and their interactions?https://www.biorxiv.org/content/10.1101/2025.07.25.666754v1

Marsupial single-cell transcriptomics identifies temporal diversity in mammalian developmental programs Menchero et al. generate a single-cell transcriptomic atlas in the opossum and show rapid progression of transcriptional programs in specific tissues relative to morphological landmarks. This shift in...

Thrilled to share that our latest work on marsupial heterochrony is now online at @cp-devcell.bsky.social @cellpress.bsky.social @lab-turner.bsky.social @crick.ac.uk We used scRNAseq to understand the asynchronous progression of developmental programmes in marsupials www.cell.com/developmenta...

Diet/microbes place the gut epithelium as a nexus for evolutionary change. With Jason Spence and Craig Lowe labs we use #organoids to explore how evolution prepared the developing human intestine for exposure to the environment. @science.org #evodevo www.science.org/doi/10.1126/... 1/11

Borzoi-informed fine mapping improves causal variant prioritization in complex trait GWAS Genome-wide association studies (GWAS) have identified thousands of trait-associated loci. Prioritizing causal variants within these loci is critical for characterizing trait biology. Statistical fine...

I'm excited to share work on a research direction my team has been advancing: connecting machine learning derived genetic variant embeddings to downstream tasks in human genetics. This work was led by the amazing Divyanshi Srivastava! www.biorxiv.org/content/10.1...

A phylogenetic approach uncovers cryptic endogenous retrovirus subfamilies in the primate lineage A phylogenetic approach reveals cryptic LTR subfamilies and functional insights at nucleotide resolution in primates.

Is the annotation of viruses in the human genome accurate? We think not. Take a look at our new paper and let us know if you agree! www.science.org/doi/10.1126/...

Check out our latest work co-led by @dcsoto.bsky.social and @jmuribescr.bsky.social identifying hundreds of human duplicated gene families using the new T2T-CHM13 assembly, with a focus on those potentially contributing to brain evolution 🧪: authors.elsevier.com/a/1lTQtL7PXu...

Thrilled to see our revised preprint now published in Nature Ecology & Evolution!
If you’re curious about how to build a bat wing by re-using existing gene programs, check out the link or the tutorial below. Big congratulations to all co-authors!! Thanks to reviewers!

www.nature.com/articles/s41...

A male-essential miRNA is key for avian sex chromosome dosage compensation - Nature Birds have evolved a unique sex chromosome dosage compensation mechanism involving the male-biased microRNA (miR-2954), which is essential for male survival by regulating the expression of dosage-sens...

Our study on a male-essential microRNA and the evolution of other dosage compensation mechanisms in birds is now out in Nature! www.nature.com/articles/s41...

My postdoc work at Treutlein lab and @graycamplab.bsky.social with @jasperjanssens.bsky.social is out in @science.org ! We screen for neuron subtypes using pro-neural TFs + morphogen combinations + scRNA-seq and profiled over 700,000 cells in 480 conditions. www.science.org/doi/10.1126/...

Enhancer adoption by an LTR retrotransposon generates viral-like particles, causing developmental limb phenotypes - Nature Genetics Activation of an LTR retrotransposon inserted upstream of the Fgf8 gene produces viral-like particles in the mouse developing limb, triggering apoptosis and causing limb malformation. This phenotype c...

Finally out! 🥳 Our paper showing how a transposable element (TE) insertion can cause developmental phenotypes is now published @natgenet.nature.com 🧬🦠🐁
Below is a brief description of the major findings. Check the full version of the paper for more details: www.nature.com/articles/s41588-025-02248-5

I am very happy to have posted my first bioRxiv preprint. A long time in the making - and still adding a few final touches to it - but we're excited to finally have it out there in the wild:
www.biorxiv.org/content/10.1...
Read below for a few highlights...

Range extender mediates long-distance enhancer activity - Nature The REX element is associated with long-range enhancer–promoter interactions.

Our paper describing the Range Extender element which is required and sufficient for long-range enhancer activation at the Shh locus is now available at @nature.com. Congrats to @gracebower.bsky.social who led the study. Below is a brief summary of the main findings www.nature.com/articles/s41... 1/

Conference Report: Cerebellar Development and Disease at Single-Cell Resolution - The Cerebellum The Cerebellum -

Did the miss the Cerebellum Development and Disease conference last year? Never fear, as we wrote up a conference report! link.springer.com/article/10.1...

Excited to share the first 2(!) preprints from the Kebschull Lab. The amazing @hyopilkim.bsky.social developed MAPseq2 & POINTseq and used them to map the dopaminergic cells of VTA and SNc. tl;dr MAPseq2=10x cheaper, 4x better; POINTseq=easy cell type specific barcoding; DA neurons=very cool.

Postdoctoral Researcher in Computational Genetics The research group of Oliver Stegle looks for a postdoctoral researcher to join a collaborative project with GSK with the goal to apply computational methods to investigate the effects of rare variant...

Job alert: Join us for a postdoc in AI in genetics at @EMBL Heidelberg! Great collaboration with @Adrian Cortes @GSK, aiming to develop new tools to elucidate genetic effects using population-scale cohorts and single-cell readouts. Please share!

embl.wd103.myworkdayjobs.com/de-DE/EMBL/d...

New preprint alert!

Corgi imitates cellular gene regulation and integrates DNA sequence and trans-regulator information.

This allows Corgi to make accurate predictions in unseen cell types. Also, it can simulate trans-regulator perturbations in silico.

Excited to launch our AlphaGenome API goo.gle/3ZPUeFX along with the preprint goo.gle/45AkUyc describing and evaluating our latest DNA sequence model powering the API. Looking forward to seeing how scientists use it! @googledeepmind

I'm very excited to finally share the main work of my PhD!
We explored the evolutionary dynamics of gene regulation and expression during gonad development in primates. We cover among others: X chromosome dynamics (incl. in a developing XXY testis), gene regulatory networks and cell type evolution.

We are delighted to share our new preprint “The evolution of gene regulatory programs controlling gonadal development in primates” www.biorxiv.org/content/10.1...

🧠 Excited to share my main PhD project! We mapped the regulatory rules governing Glioblastoma plasticity using single-cell multi-omics and deep learning. This work is part of a two-paper series with @bayraktarlab.bsky.social @oliverstegle.bsky.social and @moritzmall.bsky.social, Preprint at end🧵👇

Today in @nature.com , we report a spatial single-cell atlas of human cortical development, revealing surprisingly early specification of human cortical layers and areas.
We built an interactive browser to explore the spatial data: walshlab.org/research/cor...
Paper link below 👇

A human-specific enhancer fine-tunes radial glia potency and corticogenesis - Nature HARE5, a human accelerated region enhancer, modulates cortical development by influencing neural progenitor cell behaviour, leading to an enlarged neocortex with increased functional independence betw...

Thrilled to share our latest study out in @natureportfolio.nature.com led by the fantastically talented Jing Liu. Our study provides insight into a long standing question in biology: What molecular features make us uniquely human and how do these function? www.nature.com/articles/s41...

Predicting gene expression from DNA sequence using deep learning models Nature Reviews Genetics, Published online: 13 May 2025; doi:10.1038/s41576-025-00841-2Barbadilla-Martínez et al. review recent progress in deep-learning-based sequence-to-expression models, which predict gene expression levels solely from DNA sequence. These models are providing new insights into the complex combinatorial logic underlying cis-regulatory control of gene expression.

New online! Predicting gene expression from DNA sequence using deep learning models

Bonsai: Tree representations for distortion-free visualization and exploratory analysis of single-cell omics data Single-cell omics methods promise to revolutionize our understanding of gene regulatory processes during cell differentiation, but analysis of such data continues to pose a major challenge. Apart from...

Here it is! Bonsai. Now there is really no more excuse for using t-SNE/UMAP. Bonsai not only makes cool pictures of your data. It actually rigorously preserves its structure. No tunable parameters. Incredible work by @dhdegroot.bsky.social.
I'm so excited about this!
www.biorxiv.org/content/10.1...

Check out our latest work on the evolution of animal genome regulation out today in @nature.com. Nicely summarized below by @ianakim.bsky.social.
www.nature.com/articles/s41...

This is a major output from our ERC-StG project Evocellmap @erc.europa.eu at @crg.eu

Why does the forebrain expand dramatically while other neural regions grow less? Our new publication reveals progenitor metabolism critically shapes region-specific brain growth. Thread below. authors.elsevier.com/a/1k-udL7PXu...

Very cool study from Ikuo Suzuki lab, comparing temporal patterning in mouse and rat cerebral cortex.

Non-uniform temporal scaling of neurogenesis for species-specific dosing of cortical excitatory subtypes.

www.biorxiv.org/content/bior...

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...