BioGeometry Completes Pre-A Funding Round to Empower Bio-Manufacturing with Generative AI

Investment Circle (ID: pedaily2012) June 19 News: BioGeometry, a frontier digital biotechnology company, announced the completion of a new round of financing. This round of financing was led byZhimu AI and Shengjing Jicheng Follow-up Invest, Gaorong Venture Capital Continues to Increase Investment Led by Jiangmen Venture CapitalThe funds will be mainly used to accelerate the implementation of generative AI large models in the biomanufacturing field and to advance the development of proprietary products. The long-term vision of BioGeometry is to build a generative AI platform to accelerate China's manufacturing transformation towards digitalization, intelligence, green practices, and sustainable development.

BioGeometry focuses on building a generative AI protein design platform to empower the entire biomanufacturing field. Its core team is a pioneer in applying generative AI to molecular generation, having utilized diffusion models for generating three-dimensional molecular structures as early as 2021, making them one of the first teams to apply diffusion generative models to 3D molecular structure generation. By creating an artificial intelligence-generated content (AIGC) platform, the company is redefining the process of protein molecule discovery and design, developing programmable proteins that can be widely applied across various sectors including biopharmaceuticals, food, chemicals, medical aesthetics, and materials within the broader biomanufacturing industry. Founded in 2022 by Dr. Jian Tang, a top scientist in AI-driven drug discovery, with AI pioneer and Turing Award recipient Yoshua Bengio serving as the chief scientific advisor. Currently, the company has established two foundational platforms: generative AI for protein design and high-throughput wet lab validation, achieving a closed-loop integration of dry and wet experiments. These platforms are empowering partners to achieve precise and efficient macromolecule design and optimization while advancing the development of proprietary products. The company’s long-term vision is to build a generative AI platform to help China’s manufacturing sector achieve intelligent, green, and sustainable transformation.

Recently, BioGeometry released the latest large generative AI model for protein design, GeoFlow, which can be used for two key tasks: antigen-antibody complex structure prediction and antibody design. Unlike existing Transformer architectures, GeoFlow adopts a geometric deep learning foundation model, which is better at modeling atom-to-atom relationships in three-dimensional space. In terms of generative model selection, GeoFlow uses the latest flow matching model. Compared with diffusion generative models, flow matching generative models are more efficient and robust in both training and inference. In the task of antigen-antibody complex structure prediction, GeoFlow's performance has reached the same level as AlphaFold3, making it the first generative AI macromolecule design model in the industry to approach the level of AlphaFold3.

Figure 1: GeoFlow Model Architecture Diagram

Figure 2: Evaluation results of antigen-antibody complex predictions, GeoFlow is close to the performance of AF3.The accuracy rate is twice as high as that of AF2.

Based on its self-developed generative AI large model, BioGeometry has developed the GeoBiologics one-stop protein design platform. It has already reached licensing cooperation agreements with multiple pharmaceutical companies in China and abroad regarding this platform. Additionally, BioGeometry has also established strategic partnerships with various upstream and downstream enterprises to jointly promote the application of generative artificial intelligence in the field of biomanufacturing. These include co-building intelligent AI solutions for biomanufacturing with Alibaba Cloud, developing generative AI large models for antibody design with Sanyou Biopharmaceuticals and Baijun Biotechnology, and advancing the joint development of protein and antibody drug products with Xiangyao Biotech and Yinka Biotechnology.

Figure 3: GeoBiologics Protein Design Platform

In the future, BioGeometry will continue to optimize its generative artificial intelligence protein design platform, empower the biomanufacturing industry, and rapidly advance the implementation of its proprietary products.

BioGeometry CEO Dr. Jian Tang"Thanks to the trust from Zijiang Capital, Zhipu AI, Shengjing Jia Cheng, and our existing shareholder Gao Rong Venture Capital! After a year and a half of development, BioGeometry has completed the construction of two fundamental platforms: a generative AI large model for proteins and a high-throughput wet-lab validation platform for proteins. These have been successfully validated in multiple projects, including antibodies, peptides, vaccines, and enzyme design. In the future, BioGeometry will continue to optimize these platforms and accelerate the implementation of its proprietary products."

Gao Xinxin, Founding Partner of Zhen Fund"In Dr. Tang Jian's leadership, the core team of BioGeometry has demonstrated world-class technical strength based on more than a decade of research and accumulation in the field of AI-driven protein design. The team also brings together a group of professionals with extensive experience in the biopharmaceutical and synthetic biology industries. Their developed protein design platform has been successfully applied to numerous projects and established cooperative relationships with several leading domestic and international enterprises. Under the guidance of Dr. Tang Jian, we remain optimistic about BioGeometry’s development into a high-tech enterprise with world-class standards in the field of AI-powered biomanufacturing!"

Zhipu AISince the release of the Z Plan last year, the company has been providing investment and technical support to enterprises in the upstream and downstream of the large model ecosystem. The BioGeometry team has profound professional expertise in the field of protein molecule discovery and design, which is also an excellent industrial application point for large models to create significant value! Looking forward to continuing in-depth cooperation.