We are thrilled to share our new single-cell foundation model, Tabula (preprint: package: —a privacy-preserving predictive foundation model for single-cell transcriptomics, leveraging federated learning and tabular modeling. Over the past year, we’ve seen a surge in foundation models for single-cell genomics, where genes are often arbitrarily ordered to mimic NLP paradigms. Furthermore, as we start to train on large datasets comprising thousands of individuals, the ethical and privacy concerns arise as well. To address these challenges, we introduce Tabula: a federated-learning-based, privacy-preserving foundation model that explicitly represents single-cell data using tabular modeling. Tabula demonstrates excellent performance across diverse tasks, including cell type annotation, multi-omics and multi-batch integration, gene imputation, denoising, and both gene perturbation and reverse perturbation predictions. Very excitingly, as one of the first examples of a truly predictive foundation model, Tabula accurately uncovers pairwise and even combinatorial regulatory logic across diverse biological systems, including hematopoiesis, pancreatic endogenesis, neurogenesis, and cardiogenesis, all of which have very well validated regulatory networks. For more details, please see @JiayuanDing 's excellent post here: This is really an amazing collaboration with three brilliant young trainees, including @JiayuanDing Jianhui (@JilinJJ) and Shiyu (@shiyu_jiang23) and two other labs Jiliang (@tangjiliang), and Min Li.. Kudos to @JiayuanDing , the incredibly talented PhD student in my lab who led this project! Jianyuan is currently on the faculty job market and would be an outstanding addition to any institution. Please consider him and feel free to reach out to Jianyuan or me for more information. Additionally, Shiyun @shiyu_jiang23 , who contributed to innovative approaches for pairwise and combinatorial perturbation prediction, is applying to PhD programs. Please consider this rising star to join your PhD program as well! This work represents another important advance in my lab’s long time vision to establish a predictive “virtual embryo” model for human health. We are currently extending this approach to 3D Spatial Transcriptomics data as we previously reported in Spateo ( . If you are a developmental biologist, technology developer, or a machine learning expert, please consider joining us on this exciting journey, please reach out regarding potential positions at all levels in my lab ( Email: xiaojie@stanford.edu). We also highly welcome graduate students from Stanford @StanfordEng @DevBioStanford @ChemSysBio @StanfordData @StanfordAILab for rotations in my new lab. I am excited about many collaboration opportunities within Stanford and the broader Bay Area as well.

RT @naturemethods: Research Highlight by @madhuramukho: Spateo developed by @Xiaojie_Qiu @YifanLu2024 and colleagues is a 3D reconstruction…

We are thrilled to join the FutureHouse community, @SGRodriques @FutureHouseSF! We are seeking exceptional machine learning experts to help create predictive virtual 3D mammalian embryos and virtual scientists for advancing human health. As part of the FutureHouse community, we offer an exciting opportunity for co-mentorship between my lab and FutureHouse. The annual salary for this position is $125,000. If you’re interested, please attend the info session tomorrow and email me xiaojie at stanford dot edu. For more details, check out Sam’s post:

@meSuper8 project is now online. please let us know how it goes

RT @BiologyAIDaily: Toward a privacy-preserving predictive foundation model of single-cell transcriptomics with federated learning and tabu…

@meSuper8 There was some miscommunications. We will release the code in about 1 day, please check back tomorrow

We are hiring! Join us in building virtual embryo models — an ambitious and exciting mission that goes beyond the widely acclaimed “virtual cell” initiative! 🚨 Are you a technology developer, developmental biologist, or machine learning expert interested in creating predictive, virtual 3D mammalian embryos to advance human health, particularly for congenital heart diseases? We’re looking for applicants with expertise in genomics, developmental biology, generative AI, or related fields to join our visionary project. The selected candidate will work within a multidisciplinary team of biologists, engineers, machine learning experts, mathematicians, and physicists. We offer an enriching, collaborative environment where post-docs, students, and team members can develop into leaders in both academia and industry. Join us on this exciting journey to shape the future of human health! ! 🚀 Nature career link below: Email: xiaojie at stanford dot edu

RT @junyue_cao: Finally out in @ScienceMagazine! Utilizing the cost-effective EasySci to profile 21 million single-cell transcriptomes acro…

RT @Nanguage: 🚀 Discover Executor Engine: A powerful, lightweight job management & parallel computing library for Python! ✨ Features: - Mu…

@Nanguage welcome Weize! We are honored to have you here!

RT @jengreitz: Introducing scE2G: a new model to link enhancers to target genes using single-cell data. Excited that scE2G will enable bui…

RT @weallen1: In collaboration with Reuben Saunders, @JswLab, and Xiaowei Zhuang, we are very excited to release Perturb-Multi: a platform…

RT @JswLab: Our wonderful collaborators on the Perturb-Multi work ( are now here and on the other app, at @ZhuangLab

schedule of the conference:

@xiongfz thanks Fengzhu! love your biomechanics work too. I have contacted Cell for an update. Hope they will get it fixed soon. Thank you so much for your insights

@QiQiu8788 @samuelhking @YifanLu2024 thanks Qi ~ glad to hear that

@XinTang288269 thanks Xin

@gc_shan thanks Guancun