I like this so much!

Excited to share a new publication in European Journal of Nuclear Medicine and Molecular Imaging highlighting clinical experiences with Bicycle Imaging Agents and their potential as a diagnostic tool for EphA2-positive malignancies. Read the publication: bit.ly/43e7kxZ

A major epigenetics study using UK Biobank samples will unlock new insights into the biological basis for human health & disease ✅ Led by @UniofExeter, the research will transform how we understand, predict & treat health outcomes including heart conditions, dementia & cancer.

Our stream for Single Cell Genomics Day goes live tomorrow morning at satijalab.org/scgd , look forward to seeing you there for our 10th year!

I enjoy using IGV, but I need a more efficient tool for analyzing diploid genomes. So, I developed one for myself. It provides exceptional GPU acceleration, allowing me to uncover all essential information spanning six orders of magnitude. #bioinformatics #genomics #visualization

🧬💥 Beyond gene editing to total destruction! First author Jingkun Zeng & Nobel Laureate Jennifer Doudna (@doudnalab) at @igiberkeley, @GladstoneInst, @UCBerkeley & @UCSF just published a jaw-dropping paper in @Nature — and it rewrites what we thought CRISPR could do. 📄 "Targeting Cancer-Specific Mutations with RNA-Triggered Chromatin Shredding" Forget fixing mutations one by one. This CRISPR-Cas12a2 system doesn't edit cancer cells — it SHREDS them. 🔬 🎯 The target? Mutant p53 — the "guardian of the genome" gone rogue in ~40–50% of ALL cancers, and 70–90% of ovarian, pancreatic & non-small cell lung cancers. Previously UNDRUGGABLE. Not anymore. ⚙️ Here's the elegant mechanism: Cas12a2 scans for cancer-specific RNA transcripts. The moment it detects a mutant signal, it activates — then unleashes total chromatin shredding inside that cell, triggering complete cell death. 💀 Healthy cells? Left completely untouched. ✅ 🤯 The precision? The system distinguished cancer from healthy cells differing by just ONE nucleotide. 🔄 And it's fully adaptable — easily reprogrammed to target new mutations as they emerge. "Not only can this approach target the 'undruggable' cancers that we know, we can also easily and quickly adapt this to new mutations." — Jennifer Doudna 📎 nature.com/articles/s41586-0… #CRISPR #CancerResearch #Cas12a2 #Undruggable #Genomics #ScienceBreakthrough @OncoAlert @oncodaily

Absolutely thrilled to see more and more tools bridging knowledge graphs and models! arxiv.org/pdf/2605.21994 ^^ Ex-GraphRAG: Interpretable Evidence Routing for Graph- Augmented LLMs @NVIDIAHealth @TPlasterer @QIAGEN @AWSOpenData

No scaling laws for single-cell foundation models: when bigger atlases stop teaching the model anything In language and vision, the recipe has been simple: more data, bigger models, better performance. Single-cell biology borrowed that playbook. Foundation models for transcriptomics jumped from 1 million cells to atlases of over 100 million, on the assumption that scale would unlock the same gains. Alan DenAdel and coauthors put that assumption to the test, and the result is sobering. Working from a 22.2-million-cell corpus, they pretrained 400 models across five architectures (from PCA and a variational autoencoder up to the Geneformer transformer) and ran 6,400 evaluation experiments. They varied not just dataset size (1% to 75%) but also diversity, using cell-type re-weighting and geometric sketching to deliberately enrich rare cell types and transcriptional states. The finding: performance saturates almost immediately. On cell-type classification, batch integration, and perturbation prediction, most models hit their ceiling at roughly 1% of the corpus, about 200,000 cells. Beyond that, adding millions more cells changed essentially nothing. More diversity didn't help. Even spiking in genome-scale Perturb-seq data, to give the models perturbed phenotypes rather than just healthy ones, failed to move the needle. Larger models did score better overall, but they too plateaued early on data. Two points stood out. Simple baselines (PCA, logistic regression) often matched or beat the transformers. And the strongest model, SCimilarity, won not because of size but because its contrastive training objective is aligned with the downstream task. For single-cell data, what you train on and how you frame the objective matters far more than how much you collect. This reframes a quiet but expensive habit. In drug discovery, biotech, and any pipeline leaning on cell atlases, the instinct to keep scaling pretraining corpora may be burning compute for no return. The real leverage sits elsewhere: curating high-quality, task-relevant data and matching the training objective to the actual question you're trying to answer. Paper: DenAdel et al., journal license | doi.org/10.1038/s41592-026-0…

We're heading to HLTH Europe next week to showcase our new solutions powering the AI transformation in precision health. Meet with us to see how our new product innovations provide faster insight, stronger governance, and supercharge user productivity. hubs.ly/Q04kQjwP0

Nature Protocols: Structural variant calling using Sniffles2 nature.com/articles/s41596-0…

📢 Hiring several postdocs in AI for RNA therapeutics! Projects span: - Explainable RNA language models - Optimising coding & non-coding parts of mRNA sequences - RNA 3D structure prediction - RNA–small molecule binding - Agentic AI In RNA biology Strong AI track record needed; biology background a plus, not a must. Please RT 🔁

Come join our #bioinformatics hackathon event @BCM_HGSC August 25-28, 2026. Details: lnkd.in/gvpj-a6P Topics include: long-read methylation, SV annotation, pangenomes, benchmarking, visualization, rare disease, mosaic/somatic variants, mobile elements and more.

We’re excited to connect with leaders next week at the Multi-Omics Technology Trade Gateway Event. Schedule time to connect with us to learn how our platform turns multiomics data into an evidence engine for AI-driven scientific breakthroughs: hubs.ly/Q04jSkKy0

Last night, Jennifer Perry joined esteemed clinical and industry experts at the Women Leaders in Oncology and Allies Event, hosted in collaboration with @ConquerCancerFd. We're proud of JP and grateful for her work helping elevate women across our field.

Our study led by @Yunfeng_Ruan describes a method of interpolated polygenic risk scoring (DiscoDivas) for more accurate scoring across ancestries, particularly in settings of admixture sciencedirect.com/science/ar… @AJHGNews @AniruddhPatelMD @skoyamamd @buutrg @somijemmacho @HornsbyWhitney @AndrewHaoyu @nilanjan10c

Become a Nextflow Ambassador in 2026!🌍 The ambassador program recognizes dedicated volunteers who contribute their time and expertise to foster collaboration & knowledge sharing across the Nextflow community. Applications close June 14. Apply now: hubs.la/Q04jlhmx0

I'm very excited to share that I will be joining @Amgen, overseeing cardiometabolic research and human genetics, starting Aug 3! I am excited to shape target identification, biology, and drug discovery as the therapeutic area head for cardiovascular disease, obesity, and general medicine. And I will lead the human genetics efforts, spanning Amgen deCODE genetics (a subsidiary of Amgen), that drive target discovery and biology across all therapeutic areas. I have been incredibly fortunate to interface with truly remarkable individuals and culture across @MassGenBrigham, @broadinstitute, and @harvardmed, where I could not have asked for a more meaningful and enjoyable academic career. Being able to build on my prior work, discover and clarify therapeutic hypotheses, and now carry them through to medicines that reach millions is an opportunity I'm grateful for. I'm very excited for what comes next.

Cancer type-specific variation in patterns of driver alterations across 50,000 tumors cell.com/cancer-cell/fulltex…

This blog shares some thoughts on protein and genome foundation models. The first part explains some of the concepts by training models for example tasks. The second part is opinion on the state of the field. andrewcarroll.github.io/2026…

Join us this week at #ASCO26 to learn how our solutions provide an evidence engine for AI-driven oncology breakthroughs! Setup time to meet with us and see how our recently announced solutions are powering the next era of precision health: hubs.ly/Q04hGtw40

Excited to be at the 90th Cold Spring Harbor Symposium on AI in Biology 🧬🤖 Amazing speakers & discussions amongst others on how AI moves from analyzing biology to actively helping shape next experiments. 🚀 Will talk about closing the loop in single-cell perturbation bio. 🧫