BioGeometry Secures Hundreds of Millions in RMB Strategic Funding to Build Next-Gen AI-Native Biotech Company

BioGeometry is a cutting-edge digital biology company, focusing onApplying Generative AI to Protein Design.By leveraging data- and AI-driven approaches to bridge protein sequences, structures, and functions, we are dedicated to the de novo design of programmable proteins for applications in biomedicine and synthetic biology.

The company was founded in 2022 by Dr. Tang Jian, a leading scientist in AI-driven drug discovery, with Yoshua Bengio, the “Father of Deep Learning” and Turing Award laureate, serving as Chief Scientific Advisor. Currently,The company has established two foundational platforms: the GeoBiologics AI-powered macromolecular drug design platform and the high-throughput wet-lab validation platform for macromolecular drugs.Achieving a closed-loop integration of dry and wet labs, empowering...partners to achieve precise and efficient design and optimization of macromolecular drugs.

BioGeometry has chosen a more challenging, long-cycle path since its inception:Reconstructing the R&D paradigm of life sciences from the ground up,Building the Next-Generation AI-Native Biotechnology Company。This confidence in “building the foundational engine from scratch” stems from its powerful research team: founded by renowned AI4S scientist Professor Tang Jian, with Turing Award laureate and “father of deep learning” Yoshua Bengio serving as Chief Scientific Advisor, while other team members have achieved multiple international milestone accomplishments in fields such as graph machine learning and diffusion generative models.Recently, the team, as a core contributor, participated in the development of NVIDIA’s open-source large protein model, La Proteina. Its independently developed AI virtual cell model, PerturbDiff has garnered widespread attention in the international scientific research community, possessing the research capability to define the next generation of life science infrastructure.

BioGeometry, driven by the dual engines of “collaborative development and proprietary pipelines,” has delivered multiple industry-shattering cases in high-difficulty fields such as biopharmaceuticals and synthetic biology.

Biopharmaceuticals: Reshaping Antibody Drug and Vaccine Development

Tumor Immunology—De Novo Design of High-Specificity Antibodies:Faced with highly similar proteins within the same family that are indistinguishable by traditional methods, GeoFlow directly incorporates “specificity” as a prior constraint into the generation phase. By designing no more than 100 sequences, it successfully identified two antibodies exhibiting both high selectivity and high affinity, thereby pushing the boundaries of existing AI tools.

International Pharmaceutical Collaboration—Lead Antibody Multi-Parameter Synchronous Optimization:For a multi-objective optimization project that an internal team at a renowned foreign pharmaceutical company had failed to resolve after more than a year, GeoFlow delivered perfect molecules with affinity improved by tens of fold, expression levels increased 8-fold, and humanization optimized to over 90%—all in a zero-shot setting (without fine-tuning on target-specific data) and through just one round of design. The project delivery timeline was shortened by more than 80% compared to the client’s expectations.

Vaccine Development—From “Naturally Impossible” to “Engineerably Feasible”:Addressing the long-standing industry challenge that the native antigenic protein of a certain virus cannot stably form dimers, GeoFlow has increased the dimer proportion of this protein from less than 10% to over 90%.Expression levels increased synchronously by tens of fold, fundamentally overcoming the limitations of natural structures.

Synthetic Biology: Redesigning Industrial Enzymes, with Multiple Pipelines Completing Pilot-Scale Trials

Natural Borneol:Global First Achievement in Biosynthesis: Chiral Purity as High as 99.9%, with an 80% Significant Reduction in Cost Compared to Traditional Plant Extraction

α-Ketoglutaric Acid:Targeted optimization of key enzyme activities reduces costs by more than 60% compared to existing biosynthesis technologies on the market

From Molecules to Cells, from Understanding Life to Designing Life—BioGeometry is Building the Foundation for Engineering LifeInfrastructure.

Guo Qiushan, President of the Shanghai Biomedical Innovation and Transformation Fund, stated:"The development of macromolecular drugs has long been hindered by the lengthy traditional screening processes and the cumulative error amplification in past stepwise AI toolchains. BioGeometry"Achieved atomic-level precision modeling of biomolecular interactions, integrating structure prediction, sequence generation, druggability assessment, and wet-lab feedback into a closed loop, representing an AI-native pathway that aligns more closely with fundamental scientific logic and real-world industrial needs.This all-atom de novo design paradigm has enabled the company to demonstrate unparalleled generational advantages in high-difficulty pipelines, including traditionally undruggable targets, complex antibodies, and multispecific macromolecules, while successfully delivering preclinical candidate (PCC)-level molecules. We look forward to BioGeometry leveraging its rapidly iterative, fully proprietary GeoFlow algorithm foundation to accelerate the clinical development of its in-house pipeline and foster global collaborations.

Zhang Kun, Head of the Smart Healthcare Group at Guoke Investment, stated:“AI-driven drug discovery is poised to break the ‘anti-Moore’s Law’ R&D bottleneck in the biopharmaceutical industry, promoting the gradual establishment of a new paradigm for macromolecular drug development characterized by ‘structural understanding, targeted design, and closed-loop validation through integrated computational and experimental approaches.’ We highly recognize the technical capabilities and global influence of the team led by Professor Tang Jian in the field of AI for Science (AI4S),”Its independently developed GeoFlow model has demonstrated differentiated technological advantages in the de novo design of antibody drugs and industrial enzymes."We believe that in the era where AI is reshaping drug development, BioGeometry will deeply empower innovative pharmaceutical companies and the biomanufacturing industry, accelerating pipeline translation and commercialization, continuously delivering industrial value and realizing industrial dividends."

Dr. Wang Dakui, Managing Director of Fortune Capital, stated:“The ‘emergent intelligence’ moment of AI in the biopharmaceutical sector has arrived faster than anticipated by the industry. AI can design and screen candidate molecules at a nearly infinite scale, shifting drug discovery innovation from traditional trial-and-error experimentation to computation-driven approaches. BioGeometry is a top-tier AI for Science (AI4S) team led by Professor Tang Jian, with deep-rooted expertise in biological computing. The team combines solid academic foundations with the capability to translate cutting-edge algorithms into practical engineering solutions.”The team’s self-developed GeoFlow microscopic world model can accurately predict the structures and interactions of biological macromolecules such as proteins. Its technical capabilities rank among the top tier globally, representing a key breakthrough in breaking the monopoly held by overseas closed-source models in this field.“Coupled with the advantages of low costs and rapid iteration in wet-lab experiments in China, AI-driven pharmaceutical companies represented by BioGeometry are fully capable of achieving late-mover catch-up.”

Li Wenjue, Partner at Xinglian Capital, stated: “Life sciences are entering a new era: moving from reliance on experience and serendipitous discoveries to precision innovation driven by computation and design. BioGeometryPowered by generative AI, we explore the programmable design of proteins—the fundamental language of life—and continuously accelerate model iteration and experimental validation through a closed-loop integration of computational and wet-lab experiments, thereby enhancing the efficiency and success rate of novel molecule discovery and functional design.“We are optimistic about BioGeometry’s systematic accumulation in AI foundation models, protein design capabilities, and experimental validation systems, as well as the long-term innovation potential demonstrated by its global, interdisciplinary team. We look forward to BioGeometry continuing to drive the deep integration of AI and life sciences, opening up a new paradigm for biopharmaceuticals and synthetic biology that is more efficient, more predictable, and more engineered.”