BFT Bio AI - Multi-omics Driven Development and Cancer Modeling

研究成果与卓越性 Research Excellence

在顶级期刊发表论文 (Nature、Nature Genetics、Cell Reports) Published in top-tier journals (Nature, Nature Genetics, and Cell Reports)

研究团队建立了Geo-seq、Auto-seq等单细胞空间组学技术平台 Research team developed Geo-seq, Auto-seq and other single-cell spatial omics platforms

利用单细胞和空间多组学技术研究细胞命运调控，发表 55 篇论文他引 1,705 次 Pioneering single-cell and spatial multi-omics for cell fate regulation, 55 publications with 1,705 citations

胚胎发育 4D 时空模型, 推断时间-空间-细胞命运的耦合调控 4D spatiotemporal embryonic development model, inferring coupled time-space-cell fate regulation

学术发表 Academic Publications

团队亮点 Group Highlights

Guizhong Cui^#, Su Feng^#, Yaping Yan^#, Li Wang, Xiechao He, Xi Li, Yanchao Duan, Jun Chen, Patrick P.L. Tam, Ke Tang, Ping Zheng, Wei Si⁺, Naihe Jing⁺, Guangdun Peng⁺. Spatial molecular anatomy of germ layers in the gastrulating Cynomolgus monkey embryo. Cell Reports, 2022, 40(9): 111285-111285.

Guangdun Peng^#⁺, Shengbao Suo^#, Guizhong Cui^#, Fang Yu^#, Ran Wang, Jun Chen, Shirui Chen, Zhiwen Liu, Guoyu Chen, Yun Qian, Patrick P. L. Tam, Jing-Dong J. Han⁺, Naihe Jing⁺. Molecular architecture of lineage allocation and tissue organization in early mouse embry. Nature, 2019, 572(7770): 528-32.

Qiaozhen Liu^#, Kuo Liu^#, Guizhong Cui^#, Xiuzhen Huang, Shun Yao, Wenke Guo, Zhen Qin, Yan Li, Rui Yang, Wenjuan Pu, Libo Zhang, Lingjuan He, Huan Zhao, Wei Yu, Muxue Tang, Xueying Tian, Dongqing Cai, Yu Nie, Shengshou Hu, Tao Ren, Zengyong Qiao, Hefeng Huang, Yi Arial Zeng, Naihe Jing, Guangdun Peng⁺, Hongbin Ji⁺, Bin Zhou⁺. Lung regeneration by multipotent stem cells residing at the bronchioalveolar-duct junction. Nature Genetics, 2019, 51(4): 728-38.

Jiaxin Yang, Wenjing Sun, Guizhong Cui⁺. Roles of the NR2F Family in the Development, Disease, and Cancer of the Lung. Journal of Developmental Biology, 2024, 12(3): 24.

第一作者/通讯作者 First Author/Corresponding Author

1. Xiaogao Meng^#, Wenjia Li^#, Jian Xu, Yao Yao, An Gong, Yumeng Yang , Fangfang Qu, Chenkai Guo, Hui Zheng, Guizhong Cui⁺, Shengbao Suo⁺, Guangdun Peng⁺. Spatio-temporal transcriptome atlas of developing mouse lung. Science Bulletin, 2025, 70(10): 1641-58.

2. Jiaxin Yang, Wenjing Sun, Guizhong Cui⁺. Roles of the NR2F Family in the Development, Disease, and Cancer of the Lung. Journal of Developmental Biology, 2024, 12(3): 24.

3. Fangfang Qu^#, Wenjia Li^#, Jian Xu^#, Ruifang Zhang, Jincan Ke, Xiaodie Ren, Xiaogao Meng, Lexin Qin, Jingna Zhang, Fangru Lu, Xin Zhou, Xi Luo, Zhen Zhang, Minhan Wang, Guangming Wu, Duanqing Pei, Jiekai Chen, Guizhong Cui⁺, Shengbao Suo⁺, Guangdun Peng⁺. Three-dimensional molecular architecture of mouse organogenesis. Nature Communications, 2023, 14(1): 4599.

4. Xiaogao Meng, Guizhong Cui⁺, Guangdun Peng⁺. Lung development and regeneration: newly defined cell types and progenitor status. Cell Regeneration, 2023, 12(1): 5.

查看完整发表列表 View Full Publications

空间转录组学数据库 Spatial Transcriptomics Database

Spatial Of Primate (SOP)

猕猴胚胎发育空间转录组学数据库 Cynomolgus Monkey Embryogenesis Spatial Transcriptomics

基于Geo-seq技术构建的猕猴胚胎发育高分辨率解剖学图谱，提供3D数字胚胎模板和空间转录组学数据，支持跨物种比较分析。 High-resolution anatomical atlas of Cynomolgus gastrulation embryos based on Geo-seq technology, providing 3D digital embryo templates and spatial transcriptomics data for cross-species comparative analysis.

3D重建 3D Reconstruction

E17-E21发育阶段3D模型 E17-E21 stage 3D models

空间转录组学 Spatial Transcriptomics

胚层特异性基因表达 Germ layer-specific expression

跨物种比较 Cross-species Analysis

小鼠与灵长类对比 Mouse vs Primate comparison

数据下载 Data Download

原始数据和分析结果 Raw data & analysis

访问SOP数据库 Explore SOP Database 相关论文 Related Paper

技术亮点 Technical Highlights

• 基于Geo-seq技术的空间转录组学Geo-seq based spatial transcriptomics
• 1天时间分辨率的发育动态1-day temporal resolution dynamics
• 连续切片重建的3D数字胚胎Serial sections 3D digital embryo
• 交互式可视化平台Interactive visualization platform

科学发现 Scientific Insights

• 胚层形成的进化保守性Conserved germ layer formation
• 物种特异性转录程序Species-specific programs
• 发育坐标系的建立Developmental coordinate system
• 信号通路的空间调控Spatial signaling regulation

核心解决方案 Core Solutions

数字孪生生命建模平台 Digital Twin Life Modeling Platform

基于时间序列深度学习和多组学数据整合，构建胚胎发育与肿瘤发生的数字孪生模型，实现生命过程的动态模拟与预测，为细胞命运调控研究和靶标发现提供计算基础。 Using time-series deep learning and multi-omics data integration, we build digital twin models for embryonic development and tumorigenesis, enabling dynamic simulation and prediction of life processes, providing computational foundations for cell fate regulation research and target discovery.

肿瘤发生机制与靶标发现 Tumorigenesis Mechanism & Target Discovery

整合基因组、转录组和表观基因组数据，解析肿瘤发生的关键调控机制，快速筛选重要的调控因子，推断候选靶标的分子机制，为药物靶标虚拟设计提供科学依据。 Integrating genomic, transcriptomic, and epigenomic data to elucidate key regulatory mechanisms of tumorigenesis, rapidly identify important regulatory factors, infer molecular mechanisms of candidate targets, and provide scientific basis for virtual drug target design.

多组学整合平台 Multi-Omics Integration Platform

基于图神经网络和注意力机制的数据整合方法，实现基因组、表观基因组、转录组和蛋白质组数据的统一分析，支持跨组学关联分析和生物学解释。 Data integration methods based on graph neural networks and attention mechanisms, enabling unified analysis of genomic, epigenomic, transcriptomic, and proteomic data, supporting cross-omics correlation analysis and biological interpretation.

即将推出COMING SOON

药物靶标虚拟设计平台 Virtual Drug Target Design Platform

整合多组学数据和机器学习算法，基于数字孪生模型进行药物靶标的虚拟筛选与设计，支持生物制药企业的靶标发现和药物研发流程。 Integrating multi-omics data and machine learning algorithms, we perform virtual screening and design of drug targets based on digital twin models, supporting target discovery and drug development processes for biopharmaceutical enterprises.

关于 BFT Bio AI About BFT Bio AI

BFT Bio AI 专注于多组学数据整合与机器学习算法在生命科学研究中的应用。我们通过整合基因组、转录组、表观基因组等多维度数据，运用深度学习和可解释机器学习方法，构建数字孪生生命模型，为科研工作者、生物试剂企业和生物制药企业提供解决方案。我们帮助用户快速筛选细胞命运调控过程中的重要调控因子，推断候选靶标的分子机制，并进行药物靶标的虚拟设计。 BFT Bio AI focuses on integrating multi-omics data with machine learning algorithms in life sciences research. By combining genomic, transcriptomic, and epigenomic data, we apply deep learning and interpretable machine learning methods to build digital twin life models, providing solutions for researchers, biotech reagent companies, and biopharmaceutical enterprises. We help users rapidly identify key regulatory factors in cell fate regulation, infer molecular mechanisms of candidate targets, and perform virtual design of drug targets.

先进研究 Advanced Research

深度学习与可解释机器学习方法 Deep learning and interpretable ML methods

多组学整合 Multi-Omics

跨维度的整合数据分析 Cross-dimensional integrated data analysis

产业应用 Industry Applications

服务于科研与生物制药产业 Serving research and biopharmaceutical industries

准备好一起重塑
医疗健康的未来了吗？ Ready to transform
healthcare with us?

联系我们，深入了解我们的技术方案、算法模型以及潜在的合作伙伴关系。让我们共同推进胚胎发育与肿瘤研究领域的科学进展。 Contact us to explore our technical solutions, algorithm models, and partnership opportunities. Let's advance scientific progress in embryonic development and cancer research together.

contact@bftbioai.com

Guangzhou International Bio Island

多组学驱动的发育与癌症建模 Multi-omics Driven Development & Cancer Models