How outcomes in relapsed/refractory multiple myeloma changed, from 1986 to 2026

📢 New preprint out! We are thrilled to introduce our framework to track #ongoingCIN by leveraging single-cell genomics and CIN signatures: biorxiv.org/content/10.1101/…

Knowledge-informed multimodal #cfDNA analysis improves sensitivity and generalization in #cancerdetection biorxiv.org/content/10.1101/…

#TransposableElements and Homotypic Niches Drive Immune Dynamics and Resistance in #Melanoma #Epigenetic-based #immunotherapy biorxiv.org/content/10.1101/…

Excited to share a milestone published in @NatureMedicine from our decade-long effort to build The Human Phenotype Project, a unique longitudinal cohort with unmatched depth of clinical and multi-omic profiling, enabling truly predictive, personalized medicine. Led together with @ericxing, it is a global collaboration between @WeizmannScience, @MBZUAI, and Japanese partners, spanning 30,000+ participants and continuing to grow internationally By devising AI models trained on individuals deeply profiled with genetics, microbiome, glucose, sleep, bone density, and more, we can now forecast diseases before symptoms appear and simulate treatment or lifestyle outcomes. Key findings: • Re-defined metabolic risk thresholds • Predicted menopause impact via biological aging • Mapped organ-specific aging trajectories • Developed models for early detection of diabetes & heart disease This dataset is a blueprint for digital health twins, AI-driven tools grounded in real-world, longitudinal data Data access: humanphenotypeproject.org Full paper: tinyurl.com/4kftyndh Thanks to all the people who led this work: Lee Reicher, Smadar Shilo, Anastasia Godneva, Guy Lutsker, Liron Zahavi, Saar Shoer, David Krongauz, Michal Rein, Sarah Kohn, Tomer Segev, Yishay Schlesinger, Daniel Barak, Zachary Levine, Ayya Keshet, Rotem Shaulitch, Maya Lotan-Pompan, Matan Elkan, Yeela Talmor-Barkan, Yaron Aviv, Maya Dadiani, Yonatan Tsodyks, Einav Nili Gal-Yam, Haim Leibovitzh, Lael Werner, Roie Tzadok, Nitsan Maharshak, Shin Koga, Yulia Glick-Gorman, Chani Stossel, Maria Raitses-Gurevich, Talia Golan, Raja Dhir, Yotam Reisner, Adina Weinberger, Hagai Rossman, and Le Song And special thanks to all participants of the Human Phenotype Project

1/11 Our study on subclonal immune evasion in non-small cell lung cancer has just been published in @Cancer_Cell cell.com/cancer-cell/fulltex…

Detecting and quantifying clonal selection in somatic stem cells | Nature Genetics. So pleased to share this work. It is one of the most important pieces of work we have done. Huge thanks to all. More improvements on SCIFER to come! nature.com/articles/s41588-0…

How does tumour heterogeneity arise? How can we predict cancer cell plasticity? In 2 studies, we trace #glioblastoma heterogeneity to a spatial cancer cell trajectory w. atlassing bit.ly/4mkrWgs & predict plasticity w. snRNA/ATAC+deep learning bit.ly/3FbI6Ic 🧵

14/ Want to learn more? Read our regulatory paper biorxiv.org/content/10.1101/… and companion spatial multi-omics study biorxiv.org/content/10.1101/… Watch out for a separate 🧵from @bayraktar_lab on conserved spatiotemporal trajectories in GB

Online Now: Brain metastasis: From etiology to ecotypes dlvr.it/TKjkbd

Our Single Cell Genomics Day - highlighting our favorite new sc/spatial methods - starts Friday at 10AM ET! The most common question we get: is this open to anyone? Yes! Talks are free and live-streamed (no registration required) on Youtube and satijalab.org/scgd

Topography Aware Optimal Transport for Alignment of Spatial Omics Data biorxiv.org/content/10.1101/…

Navigating established and emerging biomarkers for immune checkpoint inhibitor therapy dlvr.it/TKC1Nr

scMultiSim is a comprehensive single-cell and spatial data simulator generating realistic multi-omics data based on modeling gene regulatory networks, cell-cell interactions, and other biological and technical factors nature.com/articles/s41592-0…

"Mathematics for Computer Science" from MIT. The entire book of 1048 pages is now FREE.

What if LLMs could “read” & “write” biology? 🤔 Introducing C2S‑Scale—a @Yale + @GoogleAI @GoogleDeepMind collab: we scaled LLMs (up to 27 B!) to analyze & generate single‑cell insights by turning transcriptomes into text 🧬➡️📝 🔗 Blog: research.google/blog/teachin… 🔗 Preprint: biorxiv.org/content/10.1101/… #SingleCell #AI #LLM

🚀 Our perspective is out in @Nature! We present a roadmap for Multimodal Foundation Models (MFMs) — large AI models pretrained across multi-omics and multi-timepoint data — to serve as the computational backbone for building virtual cells. Read the full paper in Nature: nature.com/articles/s41586-0… 🔍 Why MFMs? Biology is inherently multimodal, and molecular layers are deeply interconnected and context-specific. MFMs aims to integrate these layers to uncover shared biological principles that govern diverse cell states, offering a unified substrate for downstream inference. 🧠 What’s new? 💡 From hypothesis-driven to data-centric workflows: MFMs shift biology’s paradigm. Instead of crafting bespoke models for narrow tasks, we can now pretrain over massive datasets, distill foundational knowledge, and refine insights through lab-in-the-loop experimentation—where models guide experiments, and experiments update models. 🧬 Conditional gene regulation: MFMs go beyond static models. By training across multiple omics layers (e.g., chromatin accessibility, transcriptomics), they can learn context-specific gene functions and regulatory programs—key to understanding development and disease. 🧪 In silico perturbation: Biology’s combinatorial complexity is immense—thousands of genes, millions of interactions. MFMs provide a framework to simulate perturbations before wet-lab execution. Trained on CRISPR perturb-seq data, they can predict molecular responses across cell types, tissues, and time—enabling programmable biology at scale. ⚙️ What makes MFMs possible? Envisioned techniques include: - Unified tokenization from nucleotides to pathways - Hybrid attention across intra- and inter-modal interactions - Prompt-driven multitasking for temporal prediction, conditional generation, and modality translation - Human knowledge integration from curated databases and biomedical literature These design principles translate the architecture of foundation models into the molecular domain. ⚠️ What are the challenges? MFMs aren’t just about scale—they demand accessibility, reliability, and transparency. - Low-resource learning techniques (e.g., LoRA, adapters) are vital for democratizing training - Human-agnostic benchmarks are needed, as conventional labels may punish models that uncover novel biology - Uncertainty modeling is essential to mitigate hallucinations and increase scientific trust Interpretability and ethical stewardship must be foundational in this emerging ecosystem. Kudos to all co-authors for the collective effort and vision: @HOATIANCUI1, @Alejandro__TL, @mariabrbic, @JulioSaezRod, @simocristea, @genophoria, @mo_lotfollahi, @fabian_theis. Let’s build the future of virtual cells together.

Delighted to share a step-by-step protocol for spatially resolved epigenome-transcriptome co-sequencing to map tissue development, aging & disease. Fully committed to open science!! ⁦@sennetresearch⁩ ⁦@_hubmap⁩ ⁦@NIH_CommonFund⁩ @NCIHTAN nature.com/articles/s41596-0…

Happy to share our recent take on #Tcell #exhaustion in #cancer and #infection, now out at @NatRevImmunol. Kudos to @AbhishekDGarg for taking the lead here, and to our co-authors offtwitter(?)!! Available at rdcu.be/ehm67 @FoxChaseCancer

Excited to share our exploration @naturemethods into new horizons opening up in the era of low cost sequencing! 🔥 Deeper sequencing at WGS scale for PPM sensitivity of tumor informed MRD 🔥Duplex sequencing at WGS scale for plasma only exploration of ctDNA Check out thread 👇