In June, MDR-001 successfully completed phase 1 clinical trials, affirming its superior efficacy and safety. In early September, it began its phase 2 clinical trials, with participants receiving the drug in multiple doses.
Typically, drug development commences with the identification of proteins on cell surfaces that possess specific functions. Researchers then search for drug molecules capable of binding to these receptors, subsequently testing their effectiveness and safety before proceeding to clinical trials.
This remarkable achievement was made possible by MindRank’s self-developed AI computing platform Molecule Pro and data centre, which contribute at every stage of drug development.
The team also collaborated with researchers from Westlake University and published an article explaining the inner logic of the model at the International Conference on Machine Learning (ICML) 2023, in February.
To start, a data-digging assistant constructs disease databases and automatically filters out potential targets for drug molecules to bind and take effect. Subsequently, a protein structure prediction calculator decodes the dynamic structure of target proteins, enabling the precision drug design module to create tailored drugs from scratch, providing multiple possible solutions.

This AI-driven drug development process not only shows significant advantages in terms of speed but also yields drugs of superior quality. In experiments involving monkeys, MDR-001 helped obese monkeys achieve a healthy weight without experiencing any rebound effects upon discontinuation.
“In comparison to other GLP-1 related drugs currently on the market, such as semaglutide and liraglutide, MDR-001 can be taken orally, resulting in better patient compliance and ease of storage,” Jin said.
MDR-001 is MindRank’s first drug developed with the help of AI technology. The company currently also has five other self-developed drugs in progress.
The use of AI is helping to shorten development time and reduce costs while ensuring the effectiveness and safety of drugs, thereby increasing pharmaceutical companies’ competitiveness in the international market.
Niu Zhangming, CEO of MindRank, said AI could also help find solutions to problems that traditional methods could not.
“AI has the potential to enable domestic pharmaceutical companies and projects to quickly catch up and develop drugs with greater international influence and competitiveness. For challenges that traditional methods cannot solve, machine learning can provide systematic solutions.”
AI unlikely to destroy most jobs, but clerical workers at risk, ILO says
AI unlikely to destroy most jobs, but clerical workers at risk, ILO says
While the US pharmaceutical industry currently dominates the field, Niu said Chinese companies possess certain advantages in specific segments.
“Presently, more than half of the global AI pharmaceutical companies are concentrated in the United States, including pioneering companies such as Schrödinger and Relay. However, foreign companies only hold a slight advantage in AI drug development,” Niu said.
“In this competitive landscape, different countries may possess their respective advantages, but the ultimate goal remains the same – to address real-world problems and improve human health.”
“But when AI is involved in the pharmaceutical process, it greatly reduces the cost of developing new drugs, allowing patients with some rare diseases to be treated.”