AI Drug Discovery Company Shuimu Molecule Proposes ChatDD Paradigm: Enabling Expert Experience to Enter the Full AI Workflow Through Dialogue
Incubated by Tsinghua University's Artificial Intelligence for Science (AIR) institute, Shuimu Molecule is the only AI drug discovery company among CCTV’s selected Top Ten Chinese AI Startups. Its core argument is that the key bottleneck in past AI drug discovery was not model predictive capability, but the lack of a continuous collaboration channel between expert experience and algorithms. ChatDD aims to allow pharmaceutical research experts to participate in task planning, execution, and correction through natural language dialogue, while validating platform capabilities via its self-developed pipeline, forming a dual-wheel drive strategy.
Drug development is governed by a widely circulated 'three-ten rule': it takes an average of ten years and over one billion US dollars to develop a new drug, yet the success rate remains below ten percent. When Xing Jie, COO of Shuimu Molecule, cited this figure on a CCTV program, the issue he intended to highlight was more specific than cost alone—how can the decades of experience accumulated by a pharmaceutical research expert be truly utilized by AI?
Nie Zaiqing, Chief Scientist at Shuimu Molecule, believes that the critical barrier in past AI drug discovery projects appeared precisely here. Models can predict structures, generate molecules, and rank candidate results, but researchers may not fully understand the basis for the ranking, nor can they easily feed their concerns back into the model. While computational results can be handed over for experimental validation, there is a lack of a continuous collaboration channel between experts and algorithms. This means that the bottleneck in AI drug discovery is not merely single-point prediction accuracy, but the organizational structure of the entire scientific research workflow.
Consequently, Shuimu Molecule proposed a four-stage division of drug development: TMDD (relying on experimental accumulation and expert judgment), CADD (computer-aided calculation and simulation), AIDD (using AI for property prediction and molecule generation), and ChatDD (where experts participate in task planning, execution, and result correction through natural language dialogue). In the first three generations, expert experience and intuition were difficult to effectively interact with and organically integrate into AI models; ChatDD attempts to let experts pose questions and task objectives, have large models break them down and call tools, and then return the results to the experts. Through multiple rounds of interaction, expert experience can efficiently participate in every step of AI drug discovery.
The implementation of this framework relies on several specific technical layers. Shuimu Molecule, jointly advancing BioMedGPT with Tsinghua AIR, explores the alignment of natural language with biological data such as molecules and proteins. Among these, BioMedGPT-10B is the world's first open-source, commercially usable multi-modal biomedical large model with tens of billions of parameters. MutaPLM, selected for NeurIPS 2024, correlates textual descriptions of mutation impacts with protein mutations, both explaining what changes a single mutation might bring and proposing candidate mutations based on researcher-described goals. CodeFP, accepted by ICML 2026, focuses on the collaborative design of sequences and structures for functional proteins, while AbGaze explores end-to-end de novo design of antibodies at the all-atom level.
Above the model foundation, Shuimu Molecule organizes research methods described by experts through dialogue into skill packages that AI agents can call at any time. The first batch of OpenBioMed skill packages released this year encompasses 45 professional skills, covering five categories: biochemistry and drug discovery, protein analysis and design, single-cell omics analysis, data retrieval, and tool invocation. The Skill Creator feature allows researchers to explain task intent, inputs, outputs, and constraints through dialogue; the system assists in organizing the workflow, which is then verified and modified using actual data to form a reusable method. In this way, a single piece of guidance from an expert has the potential to leave behind a continuously usable workflow.
Shuimu Molecule's commercial strategy is a dual-wheel drive of platform and pipeline. On the platform side, ChatDD offers three modules for enterprises: Insight (target assessment before project initiation), Discovery (molecule design and virtual screening), and Trial (clinical development support); Shuimu Zhile, aimed at individual researchers, promotes adoption from the bottom up. On the pipeline side, the company personally advances innovative drug R&D for autoimmune diseases and tumors, integrating the platform into its own R&D decision-making, molecule design, and project operations. According to Chief Scientist Pan Qi, the company's first self-developed pipeline—a bispecific antibody in the autoimmune field—took only seven months from target-based initiation grounded in biology and clinical evidence, through molecule design and virtual screening, to wet-lab validation and confirmation of the preclinical candidate (PCC), whereas traditional methods typically require twelve to twenty-four months.
This model shares structural similarities with Isomorphic Labs under Alphabet: both are AI-native companies with closed wet-dry loops, employing parallel strategies of platform services and proprietary pipelines, and both incubated by top-tier AI institutions. However, Shuimu Molecule leans more towards macromolecule pipelines and technology open-sourcing. The complementarity of platform and pipeline lies in this: self-developed projects enable pharmaceutical experts to continuously use the platform, while giving algorithm teams the opportunity to long-term track the subsequent results of a task to continuously improve tools and processes; project data provides direct feedback for ChatDD, such as whether computational suggestions hold up in experiments and how to adjust where they do not.
Regarding external cooperation, ChatDD has already been implemented among multiple external clients, including large Chinese pharmaceutical companies (such as Fosun PharmAID participating in co-creating the R&D agent platform), biotechnology companies, CROs (entering process transformations in CMC operations, clinical trial protocols, etc.), and leading multinational pharmaceutical companies (involving clinical operations and post-market clinical work). Xing Jie expects revenue in 2026 to be three to four times that of last year, with pipelines entering the development phase and business expansion expected next year. These figures are company-reported expectations and have not yet been independently verified.
The Shuimu Molecule team spans two fields: AI and pharmaceuticals. Zhang Yaqin, Nie Zaiqing, and Ma Weiying bring AI research and technology industrialization experience; CEO Wang Zhuozhi previously served as Vice President of WuXi Biologics, deeply participating in over 300 innovative drug projects; Pan Qi accumulated years of drug R&D and AI application experience at companies such as Genentech, Boehringer Ingelheim, Legend Biotech, and Pathos AI; Xing Jie previously served as Vice President and CIO of WuXi AppTec. This combination does not prove product efficacy per se, but explains why this company chose to enter AI drug discovery via conversational interaction rather than pure model prediction—it needs to simultaneously understand the real working methods of pharmaceutical research experts and the capability boundaries of AI agents.