Adam He

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/

Rachel Thomas, PhD - Deep learning gets the glory, deep fact checking gets ignored an AI researcher going back to school for immunology

A case study on the challenges of evaluating AI predictions in biology and the implications for published results.

1/2
rachel.fast.ai/posts/2025-0...

Figure 1

Figure 2

Figure 3

Figure 4

Frustratingly easy domain adaptation for cross-speciestranscription factor binding prediction [new]
Predicts TF binding in target species via aligned sequence data distribution moments for cross-species generalization.

breaking news, white steam emerges from the Autoclave

Design principles of cell-state-specific enhancers in hematopoiesis Screen of minimalistic enhancers in blood progenitor cells demonstrates widespread dual activator-repressor function of transcription factors (TFs) and enables the model-guided design of cell-state-sp...

Out in Cell @cp-cell.bsky.social: Design principles of cell-state-specific enhancers in hematopoiesis
🧬🩸 screen of fully synthetic enhancers in blood progenitors
🤖 AI that creates new cell state specific enhancers
🔍 negative synergies between TFs lead to specificity!
www.cell.com/cell/fulltex...
🧵

If they behave anything like the introverts I know, we won't have to worry about robo spam callers anymore because the LLMs will have to psyche themselves up for hours before they can make the call.

Many of you enjoy our sequence-based model of single-cell RNA and ATAC data scooby... Don't miss Laura Marten's talk at the upcoming Kipoi seminar about it this Wed!
@lauradmartens.bsky.social @johahi.bsky.social @kipoizoo.bsky.social
Last preprint version:
www.biorxiv.org/content/10.1...

Disease-associated loci share properties with response eQTLs under common environmental exposures Many of the genetic loci associated with disease are expected to have context-dependent regulatory effects that are underrepresented in the transcriptomes of healthy, steady-state adult tissues. To un...

www.biorxiv.org/content/10.1...

Hopefully this'll make our models a bit more accessible/usable for all the PyTorch folks out there (including me now 😂).

(1) small tweaks to bpnetlite's BPNet class to reduce memory footprint & enable training on large, multi-individual datasets and (2) a full reimplementation of CLIPNET in PT using BPNet as its backbone and w/ 2114 bp context length (instead of the original's 1 kb).

GitHub - adamyhe/PersonalBPNet: A small modification to bpnetlite's BPNet to accomodate large validation datasets. A small modification to bpnetlite's BPNet to accomodate large validation datasets. - adamyhe/PersonalBPNet

Finally finished porting our CLIPNET models to PyTorch. I've released the code for loading the TF models into PT as part our PersonalBPNet package, which also contains ...

Read the prompt again. I guess some of those papers aren't directly related for gene expression specifically, but successes in epigenomic VEP should be part of the discussion of gene expression VEP IMO.

It's missing a bunch of important papers too. Fine-tuning work from Ioannidis & Pollard labs, DeepAllele, BigRNA, ChromBPNet, my stuff (obvious COI but it's relevant). Not a cutoff date issue since it's got the pretty recent review from Ioannidis lab.

New preprint from the @arnausebe.bsky.social lab! 💐

Here @crisnava.bsky.social, @seanamontgomery.bsky.social & collaborators develop a novel ChIPseq protocol, and demonstrate its huge potential to study the evolution of chromatin function and regulation across the eukaryotic tree of life.

Positively transformative *raises pinky*

I guess that's true, but using language models to learn a cell state autoencoder feels a bit overkill to me.

It's also not clear to me why we should expect MLM to work for gene expression vectors? Like at least for PLMs and DNALMs I can see the language analogy (and PLMs actually work) and how we might learn something from MLM training. What's being learned from ordered gene expression vectors?

🎉🎉🎉

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...

High-resolution reconstruction of cell-type specific transcriptional regulatory processes from bulk sequencing samples Biological systems exhibit remarkable heterogeneity, characterized by intricate interplay among diverse cell types. Resolving the regulatory processes of specific cell types is crucial for delineating developmental mechanisms and disease etiologies. While single-cell sequencing methods such as scRNA-seq and scATAC-seq have revolutionized our understanding of individual cellular functions, adapting bulk genome-wide assays to achieve single-cell resolution of other genomic features remains a significant technical challenge. Here, we introduce Deep-learning-based DEconvolution of Tissue profiles with Accurate Interpretation of Locus-specific Signals (DeepDETAILS), a novel quasi-supervised framework to reconstruct cell-type-specific genomic signals with base-pair precision. DeepDETAILS’ core innovation lies in its ability to perform cross-modality deconvolution using scATAC-seq reference libraries for other bulk datasets, benefiting from the affordability and availability of scATAC-seq data. DeepDETAILS enables high-resolution mapping of genomic signals across diverse cell types, with great versatility for various omics datasets, including nascent transcript sequencing (such as PRO-cap and PRO-seq) and ChIP-seq for chromatin modifications. Our results demonstrate that DeepDETAILS significantly outperformed traditional statistical deconvolution methods. Using DeepDETAILS, we developed a comprehensive compendium of high-resolution nascent transcription and histone modification signals across 39 diverse human tissues and 86 distinct cell types. Furthermore, we applied our compendium to fine-map risk variants associated with Primary Sclerosing Cholangitis (PSC), a progressive cholestatic liver disorder, and revealed a potential etiology of the disease. Our tool and compendium provide invaluable insights into cellular complexity, opening new avenues for studying biological processes in various contexts. ### Competing Interest Statement The authors have declared no competing interest.

www.biorxiv.org/content/10.1...

Genome-wide dynamic nascent transcript profiles reveal that most paused RNA polymerases terminate We present a simple model for analyzing and interpreting data from kinetic experiments that measure engaged RNA polymerase occupancy. The framework represents the densities of nascent transcripts with...

Our latest work indicates that termination of paused RNA polymerase is its most likely fate, while attempting to reconcile disparate estimates of relative rates and pause residency times from previous studies: www.biorxiv.org/content/10.1...

Does anyone know if the ATAC-seq bam files on ENCODE have had their tags shifted? and if so, by the more common +4/-5 or by +4/-4?

My next pull request will make wingdings the default font for sequence logos.

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...

I think you mean this review? The Stark paper is a cool one, but definitely an example of conflating design method w/ oracle

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

Join us for our next Kipoi Seminar with with Alexander Sasse
@lxsasse.bsky.social
@zmbh.uni-heidelberg.de

👉Advanced training strategies for genomic sequence-to-function models
📅 Wed March 5, 5:30pm CET
🧬 kipoi.org/seminar/
🦋 @kipoizoo.bsky.social

Accurate de novo transcription unit annotation from run-on and sequencing data Functional element annotations are critical tools used to provide insight into the molecular processes governing cell development, differentiation, and disease. Run-on and sequencing assays measure th...

Accurate de novo transcription unit annotation from run-on and sequencing data

@charlesdanko.bsky.social

www.biorxiv.org/content/10.1...

ralphi: a deep reinforcement learning framework for haplotype assembly

Figure 1

Figure 2

Figure 3

ralphi: a deep reinforcement learning framework for haplotype assembly [new]
Deep reinforcement learning accurately partitions reads into haplotype sets. It uses fragment graphs and the max-cut problem for the reward objective.

A scalable approach to investigating sequence-to-expression prediction from personal genomes

Figure 1

Figure 2

Figure S1

A scalable approach to investigating sequence-to-expression prediction from personal genomes [new]
Models fail to gen. w/ individual var., personal genome training helps some individuals only.

Mapping the regulatory effects of common and rare non-coding variants across cellular and developmental contexts in the brain and heart Whole genome sequencing has identified over a billion non-coding variants in humans, while GWAS has revealed the non-coding genome as a significant contributor to disease. However, prioritizing causal...

New preprint w/ @soumyakundu.bsky.social @sbmontgom.bsky.social @anshulkundaje.bsky.social !

Using deep learning & scATAC-seq, we studied context-specific variants in disease & evolution, and introduce FLARE for de novo mutations—w/ application to autism-affected families.

doi.org/10.1101/2025...

YouTube video by Bethesda Softworks Skyrim: Very Special Edition – Official Trailer

The same people who want to play Skyrim on their smart fridge

www.youtube.com/watch?v=FnEW...