Karthik Guruvayurappan

Happy to share that the paper on enhancer interactions led by @zrcjessica and I from my time in the @GrahamMcVicker lab is now published in Cell Genomics! cell.com/cell-genomics/… A thread on some of the new analyses below: (1/n)

Thrilled to announce that our paper on Orthrus, a state-of-the-art mRNA foundation model, was published in Nature Methods! 🎉 Huge congrats to my co-first authors @phil_fradkin and @ianshi3 - this has been a long time coming! Paper: nature.com/articles/s4159… A thread 👇🏼

We’re unwrapping a new method today @MSKCancerCenter! Led by @SydneyBlattman, @NabihMaslah, @AustinAVarela, Ronan Chaligne and @dana_peer, plus colleagues at @10xGenomics, we’re delighted to share Genotyping In Fixed Transcriptomes (GIFT): biorxiv.org/content/10.648… 1/n

Excited to share our preprint on "tagging" effects in enhancer-gene links from single-cell multiome data!🧬 We show that correlated ATAC peaks can induce non-causal peak-gene links (similar to LD in GWAS), affecting regulatory architecture interpretation. medrxiv.org/content/10.648…

My lab at MSKCC in New York is hiring for two positions. Join us at the frontier of functional genomics, studying fibroblast state transitions, combinatorial genetics, and ECM in disease. Please share with anyone who might be a good fit! (Mustache not required.)

New preprint on technologies to scale up CRISPR screens. We use them to map 665,856 pairwise genetic perturbations and outline a path to comprehensive interaction mapping in human cells. We also introduce an approach for cloning lentiviral libraries with billions of elements.

Scaling perturbations: beyond genome-scale CRISPR screens biorxiv.org/content/10.648… #biorxiv_sysbio

Very excited to share this preprint with @arthurwchow and @CalebLareau where we asked whether we could use advances in protein generative models to rationally design and optimize CAR-T cells! The short answer is Yes but there are much more to unpack in this awesome tweetorial!

Which mutations rewire function of regulatory DNA? Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models. Led by @EESetiz 1/N 🧵👇

Can AI develop methods like a seasoned statistical geneticist? 🤔 In 8 hrs, our new method TusoAI improve two popular tools in genetics: scDRS (+40% power) & pgBoost (+11% enrichment). Preprint: arxiv.org/abs/2509.23986 Great work by @AlistairTurcan with @KexinHuang5 @lileics

Introducing Spacelink, a unified framework for identifying and prioritizing spatially variable gene programs at tissue and cell type resolution and linking them to disease GWAS studies. Led by Hanbyul Lee & Haochen Sun biorxiv.org/content/10.110…

Latest genomic AI models report near-perfect prediction of pathogenic variants (e.g. AUROC>0.97 for Evo2). We ran extensive independent evals and found these figures are true, but very misleading. A breakdown of our new preprint: 🧵

Our paper is now out in final form at Nature Genetics! For those who missed the preprint, we used large-scale Perturb-seq targeting transcription factors to push primary fibroblasts into diverse transcriptional states, including those observed in cell atlas studies.

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10.11…

I am excited to introduce mRNABench, a comprehensive benchmarking suite that we used to evaluate the representational capabilities of 18 families of nucleotide foundation models on mature mRNA specific tasks. Paper: doi.org/10.1101/2025.0… Code: github.com/morrislab/mRNA… A 🧵

We're excited to release 𝐦𝐑𝐍𝐀𝐁𝐞𝐧𝐜𝐡, a new benchmark suite for mRNA biology containing 10 diverse datasets with 59 prediction tasks, evaluating 18 foundation model families. Paper: biorxiv.org/content/10.110… GitHub: github.com/morrislab/mRNA… Blog: blank.bio/post/mrnabench

🧬 Excited to open-source Biomni! With just a few lines of code, you can now automate biomedical research with AI agent! We are releasing Biomni A1 (agent) + E1 (env) with 150 specialized tools, 59 databases, and 105 software. E1 is our first attempt at curating the bio-agent environment, but it only scratches the surface: Call to help build Biomni-E2 - an open environment for bio-agent, built with and for the community! We welcome new tools, benchmarks, datasets, agents, and beyond to build the environment together. Significant contributors will be invited as co-authors on our upcoming E2 manuscript. More to come! 💻 github.com/snap-stanford/… 🌐 biomni.stanford.edu @ProjectBiomni

want to learn about #PerturbSeq data but not sure where to start? working on the #VirtualCellChallenge? we're pleased to share differential expression summary statistic tables from five perturb-seq atlases collected by @josephmreplogle! (link below)

1/6 Excited to share our latest preprint: "MORPH Predicts the Single-Cell Outcome of Genetic Perturbations Across Conditions and Data Modalities". 🔗 biorxiv.org/content/10.110… 🧵 👇 Here is what MORPH is in a nutshell!

🤝Excited to announce @ProjectBiomni × @AnthropicAI! AI agents are set to transform how biologists do everyday research. Thanks to this partnership, the platform is now free for scientists worldwide: biomni.stanford.edu Learn more: anthropic.com/customers/biom…

The cells in our bodies constantly acquire mutations. But what are the patterns of mutations across tissues? How do mutations in normal cells lead to disease? These and other questions we will tackle within the SMaHT Network, now described in @Nature nature.com/articles/s4158…