MindRank's AI-Assisted Drug Enters Phase 3 Trial, Slashes R&D Costs

Hangzhou-based biotech start-up MindRank has progressed to Phase 3 clinical trials for MDR-001, a weight-loss drug. This makes it China’s first artificial intelligence-assisted Category 1 new drug to reach this advanced stage.

MindRank announced last month that it had initiated the Phase 3 clinical trial in China for MDR-001, a small molecule GLP-1 receptor agonist. The drug was designed with the help of AI, mimicking natural hormones to regulate blood sugar and appetite.

MindRank’s founder and Chief Executive Officer, Niu Zhangming, stated the drug was the first AI-assisted, Category 1 new drug to reach this stage in China. The company aims for approval in the second half of 2028, with a market launch projected for 2029.

The new drug development process has taken about four and a half years to date, significantly less than the typical seven to 10 years to reach this stage. Niu noted that efficiency gains from AI had effectively reduced overall research and development costs by at least 60%.

Human specialists specify a target, typically a protein molecule linked to a disease. MindRank then leverages its proprietary AI tools to rapidly generate potential drugs, allowing researchers to select promising candidates from an AI-generated pool. Niu described this as “overseeing an automated assembly line.”

MindRank also developed a specialised biomedical system. This system uses open-source large language models integrated with Retrieval-Augmented Generation (RAG) technology, which allows the LLM to access real-time external information.

This technology improved target research accuracy from an industry average of approximately 85% to over 97%. Target research accuracy measures how effectively viable targets for treating a disease are identified.

AI can also assess a drug’s safety and efficacy through advanced predictive models. It tackles complex calculations that were previously beyond human capability.

Despite AI’s advancements, humans remain an indispensable part of the process. Many intermediate steps still necessitate manual software operations, and Niu commented, “It still takes a human to tie the entire process together.”

Experts continue to steer high-level strategic planning, making critical decisions. These include which targets to prioritise, and whether to optimise existing compounds or engineer entirely new ones from scratch.

Artificial Intelligence for Science (AI4S) is revolutionising life sciences. Demis Hassabis and John Jumper of Google DeepMind were awarded the 2024 Nobel Prize for chemistry for AlphaFold, which uses AI to predict protein structures.

The global landscape also sees significant AI4S advancements. Last December, US-based Generate:Biomedicines announced plans to launch two global Phase 3 clinical trials for an AI-engineered antibody to treat asthma.

Chinese AI4S companies are gaining traction as well. Baidu-backed BioMap stated it had surpassed Alphabet subsidiary Google DeepMind’s AlphaFold in the commercialisation of AI foundation models for drug discovery.

Beijing-based start-up DP Technology recently completed a Series C funding round, raising USD 114 million. AI-powered drug discovery firm Insilico Medicine, which has a business model similar to MindRank, listed in Hong Kong last December.

MindRank planned to file for an initial public offering in Hong Kong this year, with the aim of listing in 2027, according to Niu.

Niu cautioned that at the current stage, AI may not disrupt the life sciences in the same way it has other fields. Niu warned that the core issue is that the trial-and-error cycle is far too long, lamenting a problem that plagued biopharmaceutical behemoths and start-ups alike. He added, “For AI4S to deliver meaningful impact in life sciences, we still need to go through a longer cycle of testing and evaluation.”

• MindRank's MDR-001, an AI-assisted weight-loss drug, has entered Phase 3 clinical trials in China.

• This is China’s first AI-assisted Category 1 new drug to reach Phase 3, developed in four and a half years with a 60% reduction in R&D costs.

• MindRank plans to file for a Hong Kong initial public offering this year, aiming for a 2027 listing.

Source: SCMP