Incubated by Tsinghua AIR, AI4S enterprise AIPhi Therapeutics has secured a 100-million-yuan angel round of financing | 36Kr Exclusive

Text by Hu Xiangyun

Edited by Hai Ruojing

36Kr has learned that "Aipharma", an AI Native new drug R&D enterprise, has recently completed a 100 million RMB angel round of financing. This round of financing is led by Xianghe Capital, followed by institutions including Xinglian Capital under Zhipu AI and a well-known industrial fund.

It is reported that the raised funds will be mainly used for the R&D and iteration of the company's self-developed fundamental drug models such as DrugCLIP and the AI drug R&D agent engine PharmAgents, continue to explore next-generation AI drug R&D technologies, and promote independent and cooperative innovative drug pipelines. At present, the company's fastest-progressing self-developed pipeline has entered the Pre-PCC stage.

In addition, in terms of commercialization, Aipharma mainly adopts the Co-development mode instead of simple AI technical services. According to the introduction, the company has carried out co-development with more than five pharmaceutical enterprises and biotech firms in innovative drug discovery projects covering metabolism, CNS, autoimmunity, drug delivery and other directions, with cooperation covering different drug modalities such as small molecules and peptides.

Aipharma was officially established in July 2026, incubated by the research group of Professor Lan Yanyan and Academician Zhang Yaqin from the Institute for Intelligent Industry Research (AIR) of Tsinghua University. Gao Bowen, a core member of the team, previously focused on interdisciplinary research of AI and basic science, worked on recommendation algorithms at ByteDance, returned to Tsinghua AIR to pursue his doctorate in 2022, published multiple papers in top academic conferences, and published a paper in the journal *Science* as a co-first author.

Gao Bowen introduced that although Aipharma has a "very AI" foundation, the team also attaches great importance to integrating with real new drug R&D scenarios to avoid AI technologies being disconnected from experimental implementation. At present, the team has R&D leaders with backgrounds in medicinal chemistry and structural biology, and the head of business cooperation has nearly 20 years of experience in the pharmaceutical industry, who has promoted multiple drugs to enter Phase II and Phase III clinical stages.

"The reason why we have completed such a team configuration in the early stage is that we hope to abandon the traditional relay working mode of 'AI completes calculation, delivers to medicinal chemistry, and medicinal chemistry then delivers to biology', so that R&D personnel in different links can enter a closed loop of collaborative work and decision-making from the first day, and build a real AI Native new drug R&D system with AI as the core productivity," Gao Bowen explained.

In the traditional pharmaceutical model, AI is mainly embedded in the R&D chain as a tool plugin. This is because enterprises usually split their business lines by molecular modality and disease track from the organizational structure level. If necessary, each business line will independently build its own AI capabilities. For example, when encountering molecular design problems, they will develop molecular generation models, and when they need to predict druggability, they will develop corresponding prediction models. It is difficult for AI technologies between different business lines to interoperate.

But "the logic of AI Native is the opposite". Gao Bowen believes that to truly make AI the underlying core capability of an enterprise, it is necessary to "make all businesses radiate outward with AI as the core", redesign the organizational structure, R&D process and human-machine collaboration mode, and let AI participate in answering fundamental questions such as which experiments to carry out, what experimental data to produce, and how to connect calculation and wet experiments.

At Aipharma, this system operates relying on three layers of AI capabilities: "exploration", "decision-making" and "learning and evolution":

First, the exploration layer allows AI to break through the existing cognitive and computational boundaries of human beings, and tap into the huge drug R&D space that is difficult for traditional methods to reach; the decision-making layer requires AI to continuously judge the next action in the face of a large number of uncertainties in drug R&D, and screen the experiments worthy of implementation and the data that needs to be produced; the learning and evolution layer needs to continuously receive feedback from real wet experiments and experts, to push the whole system to iterate and optimize continuously. The three layers of capabilities are closely linked, so that AI can jump out of the tool positioning and deeply participate in the whole process of new drug discovery.

Around this system, the Aipharma team first built a number of fundamental models represented by the high-throughput virtual screening model DrugCLIP as the technical base, to support the team's capabilities at the "exploration" level.

Gao Bowen introduced that the core of DrugCLIP is to use AI to build a high-dimensional representation space where proteins and molecules coexist, just like a "chemical universe". Traditional virtual screening requires the alignment operation of proteins and candidate molecules one by one. When facing compound libraries of the order of billions or trillions, the computational cost will expand sharply; therefore, DrugCLIP does not follow this path, but uses a two-tower contrastive learning architecture to map protein pockets and small molecules to this high-dimensional representation space. In this way, when facing a new target, scientists only need to output the coordinates of the protein pocket in the space, and retrieve molecules with adjacent spatial distances to complete the screening, without the need to operate on massive molecules one by one.

"Relying on this model, we can realize virtual screening at the scale of the human genome. A single server can complete 10 trillion protein-molecule pairing calculations in one day, supporting second-level retrieval of compound libraries of the order of trillions. According to our practice, the hit rate of some optimized targets reaches 60%-80%, and high-activity molecules of nanomolar or even picomolar level can be directly screened at one time without subsequent modification."

Based on the spatial exploration capability of DrugCLIP, the Aipharma team further built the PharmAgents drug discovery agent engine to help improve the capabilities of the "decision-making" layer.

Not only the early-stage molecular screening, the whole process of new drug R&D is full of a large number of complex decisions, for example, after a batch of molecules are screened, which ones should be prioritized for verification? When the experimental results conflict with expectations, which part of the evidence should be adopted? How to balance activity, selectivity and pharmacokinetics... These decision-making processes need to integrate multi-source information such as literature and patents, model outputs, experimental data, and expert experience, and such information is often incomplete or even contradictory.

Different from some agents on the market that can only replicate human scientific research processes, the core capability of PharmAgents is to comprehensively process conflicting and incomplete multi-source evidence, then independently call various professional tools to propose scientific hypotheses, and iterate and update the R&D plan after obtaining new information.

"However, we do not aim to let agents completely replace human experts, but to make the two cooperate. Because the experience of human experts itself is an important source of evidence in the decision-making process, the decisions output by agents will be evaluated and revised by human experts, and these feedbacks can help agents continue to learn and evolve. In other words, our 'learning and evolution' layer capability is reflected in the continuous iteration of the whole system, and the success or failure of execution will be precipitated into system knowledge, making the system stronger as it is used more," Gao Bowen said.

This system has been implemented in actual drug R&D scenarios. At present, Aipharma's fastest-progressing self-developed pipeline focuses on ADHD (Attention Deficit Hyperactivity Disorder), and explores new mechanisms of action with differentiated potential through the newly discovered allosteric pocket; at the same time, the company has carried out cooperation with different types of scientific research institutions such as the School of Life Sciences and School of Pharmaceutical Sciences of Tsinghua University, Chinese Academy of Agricultural Sciences, and Shanghai Jiao Tong University Institute of Translational Medicine to carry out extensive experimental verification.

Since the beginning of this year, the AI4S track has continued to heat up, a large number of start-ups focusing on the pharmaceutical direction have emerged, and the industry's evaluation criteria have become increasingly pragmatic. In addition to papers and demonstration demos, real and reproducible experimental verification has become one of the hard criteria for testing technical value.

Gao Bowen believes that domestic AI pharmaceutical enterprises have gone through two generations of evolution: the first generation of enterprises mainly used AI to solve single-point tasks in drug R&D; subsequently, the industry began to pursue the use of AI to empower the whole R&D process and the construction of automated laboratories. "Now, the core work of the new generation of AI Native pharmaceutical companies such as Aipharma is to let AI take responsibility for R&D decision-making. Traditional pharmaceutical companies are burdened with historical business baggage, making it difficult to completely restructure their organizations and processes, while we build the system from scratch, which makes us more flexible in this regard."