Human-supervised Agentic AI for Hypothesis Generation and Experimental Assistance in Drug Repurposing https://www.biorxiv.org/content/10.64898/2026.04.20.719538v1

The main project of my PhD 🧬🔬 is out: we developed single-cell lentiMPRA, a lentivirus-based method to measure enhancer activity and transcriptomes at single-cell resolution. We then applied sc-lentiMPRA to fully synthetic enhancers 🧩... 🔗 doi.org/10.64898/202...

We wrote a perspective "How to build the regulatory genome: a constructionist guide to the cis-regulatory code", out in Development yesterday. Title says it all. Find it here: journals.biologists.com/dev/article/...

it is worrying to see how easy it is to make your way into a LLM. In these papers, there are obvious clues that the results are fake. What about fake papers where there are fewer obvious clues? How can these be detected.

Beyond the mean: genetic control of gene expression fidelity and dispersion www.biorxiv.org/content/10.6...

Epstein-Barr Virus #EBV was linked to #MultipleSclerosis - now a plausible cause has been found, misidentification by longterm memory T-cells that pick on the wrong protein, ANO2, instead of the EBV-antigen. Massive inflection towards the elimination of MS!!! 🧪🧠Cell www.cell.com/cell/fulltex...

There's a really good essay by Ronald Purser in Current Affairs making the rounds: AI is Destroying the University and Learning Itself www.currentaffairs.org/news/ai-is-d...

In a new work with Joseph Rich and Conrad Oakes we tackle the problem of how to best organize alluvial plots. We formalize two optimization problems and develop a solution for them based on the neighbornet algorithm, implemented in the program wompwomp: github.com/pachterlab/w...

🚀 Two exciting days of Computational Biology at the Cardio-Pulmonary Institute in Bad Nauheim @cpi-exstra.bsky.social ! 🔬 Workshop on single-cell analysis + the CPI repository data ressource; 💡 Hackathon together with the Schulz Lab @themarcelschulz.bsky.social Collaboration, coding & discovery

🎉 To mark the fourth extension of the CPI, we celebrated our success at the @mpi-hlr.bsky.social 🥳 We are delighted about the renewed funding and would like to thank everyone who made this step possible! Read more in the latest issue of "Synapse": www.unimedizin-ffm.de/fileadmin/re...

we asked a simple question: What does it take to learn the rules of RNA base pairing? using standard deep-learning technics, got a simple answer: don't need structures, nor alignments or many parameters only a few RNA sequences and 21 parameters; doi.org/10.1101/2025...

A resource of RNA-binding protein motifs across eukaryotes reveals evolutionary dynamics and gene-regulatory function go.nature.com/4mc1SmQ

Multi-omics with A.I. analytics demonstrates critical role of the gut microbiome and immune response and enables accurate diagnosis of ME/CFS, may also be applicable to Long Covid. www.nature.com/articles/s41... www.ft.com/content/9cdf...

Our collaboration with Tony Mustoe's lab us out today. MPRA libraries and possible cryptic splicing in MPRA reporters, or reporters in general. The additional novelty here is that such events are controlled or influenced by AU-rich sequences. www.nature.com/articles/s41...

Very excited that our most significant work, a collaboration w/ Dr. Can Cenik at UT Austin on translational gene regulation, was finally published in Nature Biotechnology in a dual set of studies: Paper 1 -- an AI model trained to predict translation rates from mRNA sequences: rdcu.be/exN1l

And BIG thanks to #RegSys track organizers @abardet.bsky.social A. Emad J. Welch R. Gordan @xiuweizhang.bsky.social R. Beekman @martamele.bsky.social @anniquec.bsky.social @shaunmahony.bsky.social @ferhatay.bsky.social and co-chairs @alemedinarivera.bsky.social and @themarcelschulz.bsky.social

What a fantastic #ISMBECCB2025 conference it has been, with an outstanding #RegSys @iscb-regsys.bsky.social COSI track! Thanks, everyone, for submitting, attending, presenting, and organizing @iscb.bsky.social @eccb-europe.bsky.social

🧬 New @emblebi.bsky.social service beta launched: Perturbation Catalogue 🔎 Browse genetic perturbation datasets 🧠 Train models 🧬 Interpret variant function 🧭 Explore gene dependencies Search, test APIs, suggest datasets, send feedback! 🔗 www.ebi.ac.uk/perturbation... Funded by @opentargets.org

Last talk at #regsys today is a keynote by Mafalda Dias about modelling sequence variation in Evolution with insights into diseases #ismbeccb2025

First talk of the last session of RegSys day 1 at #ismb2025 is from Jacob Schreiber on how we read the book of DNA Spoiler: regulation is key

Laura Gunsalus talks about design of small native regulatory elements using #ML #ismbeccb2015 #regsys

Last talk in this #regsys session is Jishnu Das who talks about regulatory programs that determine B-cell fates #ismbeccb2025

Tatevik Jalatyan will talk about a new pipeline for estimating cell cycle phase from single cell data #ismbeccb2025 #regsys

Surag Nair talks about a general framework to combine different paradigms of DL genome models #ismbeccb2025 #regsys

Vitalii Kleshchenikow about a biophysical model for learning gene regulation from single cell data #ismbeccb2025 #regsys @oliverstegle.bsky.social

#regsys session is overflowing at #ismbeccb2025 consider to go to rooms 6 and 7 for video broadcast if full

Laura Rumpf talks about the MetaFR pipeline to learn gene regulation models from unpaired and paired scATAC and scRNA data #ismbeccb2025 #regsys #schulzlab @dzhk.de @sfb1531.bsky.social

Refreshed after lunch we start with Oluwatosin Oluwadare to introduce a new approach for single cell HiC analysis #ismbeccb2025 #regsys

Last speaker before lunch is Christophe Vroland to talk about confounders in Rna-Dna interaction data analysis #regsys #ismbeccb2025

Laura Hinojosa talks about TFs that regulate replication timing #RegSys #ismbeccb2025 @ferhatay.bsky.social

Next is @damlaob to talk about putting new Deep learning models of TFs into #Jaspardb #RegSys #ismbeccb2025 @amathelier.bsky.social

First flash talk session starts with @aryankamal.bsky.social who represents his analysis about understanding transcriptional regulation in blood generation #regsys #ismbeccb2025

Second proceedings talk by an Panagiotis Alexiou about benchmarking methods for miRNA-target prediction #regsys #ismbeccb2025

First proceedings talk in #RegSys by Yijie Wang about GRN inference from single cell data

#RegSys is starting with the keynote from @verapancaldi.bsky.social who talks about the changes of chromatin structure and the epigenome in cancer patients #ismbeccb2025

Today marks the start of the #RegSys @iscb-regsys.bsky.social track at ##ISMBECCB2025! Very much looking forward to listening to the exciting science that will be presented. Join us in room 11BC today and tomorrow.

Join 4 #Schulzlab related talks at #ismbeccb2025 : Wed #RegSys 14:20 , Laura Rumpf: Single-cell ATAC&RNA analysis, Thu #iRNACOSI 8:40, Christina Kalk – Prediction of Split-ORFs 9:40 , Tim Warwick – Pipeline for DNA-RNA analysis 12:10 , Giulia Cantini – Transformer for miRNA-mRNA prediction

For example ismb-schedule.luispedro.org?speaker=Luis...

The #RegSys @iscb-regsys.bsky.social track is gonna be outstanding again this year with a great selection of talks and keynotes @verapancaldi.bsky.social, Mafalda Dias, Roser Vento-Tormo, and @lucapinello.bsky.social ! www.iscb.org/ismbeccb2025...

Epilogos: information-theoretic navigation of multi-tissue functional genomic annotations https://www.biorxiv.org/content/10.1101/2025.06.18.660301v1

Our latest work: The immunoproteasome disturbs neuronal metabolism and drives neurodegeneration in multiple sclerosis: Cell www.cell.com/cell/fulltex...

Second new preprint ‼️ Work led by brilliant postdoc @alinaemelianova.bsky.social (in collab with Pablo Garcia and Daniel Tan) where we leverage multiscale simulations to predict small-molecule partitioning into condensates 💦💊🙌🏽 www.biorxiv.org/content/10.1...

In the new issue of @cp-trendsgenetics.bsky.social, @wiringthebrain.bsky.social & Nick Cheney seek out a better metaphor. They propose a generative model concept to capture the indirect, distributed, & non-linear relationship between info in the genome & form of the organism. Worth a read: 🧬👇🧪 11/11

Current genomic deep learning models display decreased performance in cell type-specific accessible regions

I am super happy to join this year's nightofscience.de. I'll represent the @cpi-exstra.bsky.social speaking on "Small vessels, big impact: How your heart's microcirculation affects ageing and disease". I am looking forward to meeting y'all! @instcardregffm.bsky.social @goetheuni.bsky.social

🧬🖥️Drug response prediction is a machine learning challenge with immense potential for precision medicine. Our latest preprint introduces DrEval, a comprehensive benchmarking framework to evaluate state-of-the-art methods, uncover widespread issues, and guide the development of more robust models.

Annique Claringbould @anniquec.bsky.social is talking about CRISPR interference in primary CD4 T cells for ~1000 GWAS-implicated enhancers, reading out ~2000 genes. Interfering with some key enhancers (CD28, IL2RA) impact basically every CD4-expressed gene. #eshg2025

SUM-seq is now out 🤩 See Mikael's thread below for paper highlights

Awesome paper. Simple post-hoc trick (averaging over homologs) with elegant evolution theory dramatically improves zero shot coding variant effect prediction in pLMs & actually delivers better results from the larger models (inverting the trend with raw likelihoods). 1/