An experimental drug empowered by artificial intelligence to identify a novel therapeutic target for a severe lung disease has demonstrated promising safety and efficacy results in its phase two clinical trial, according to a research paper released this week.

The outcome marks the world's most advanced clinical trial progress for an AI-driven drug discovery and has boosted confidence in tapping into AI's potential in expediting drug development, according to Insilico Medicine, a global biotech company, and a Chinese researcher involved in the experiment.

The novel drug, named Rentosertib, features a newly discovered protein target known as TNIK, which was identified and optimized through the assistance of the company's generative AI platforms.

The drug aims at treating idiopathic pulmonary fibrosis, a chronic lung disease that can cause irreversible decline in lung function. The disease affects about 5 million people worldwide. There is no drug that can stop or reverse the progression of the disease.

According to the company, it took about 18 months from identifying the target to selecting preclinical candidates, compared to a typical duration of about 2.5 to four years required in traditional drug development.

During a phase two clinical trial that was carried out across 22 sites in China and involved 71 patients, the drug candidate proved safe and demonstrated promising effects in improving lung function, as well as curbing fibrosis and inflammation.

Results of the clinical trial were released in the journal Nature Medicine on Tuesday.

"These results not only suggest that Rentosertib has a manageable safety and tolerability profile, but also warrant further investigation in larger-scale clinical trials of longer duration," said Alex Zhavoronkov, founder and CEO of Insilico Medicine.

He added that clinical results have showcased the "transformative potential" of AI in drug discovery and paved the way for faster and more innovative therapeutic advancements.

Xu Zuojun, a professor at the Peking Union Medical College Hospital and a lead researcher of the clinical trial, said that idiopathic pulmonary fibrosis is a highly complicated disease with profound, unmet medical needs.

He said the target identification and molecular design of the novel drug were enabled by AI, which represented a pioneering approach in the pharmaceutical industry.

"However, the sample size in each patient group was relatively limited, and these findings will need to be validated in larger cohort studies," he added.

AI has become a powerful tool to make drug development faster and cheaper in recent years.

Chen Kaixian, an academician with the Chinese Academy of Sciences and a researcher at Shanghai Institute of Materia Medica of the CAS, said that application of AI technologies can reduce drug design time by 70 percent and increase success rate tenfold, citing data from overseas.

During an interview with Science and Technology Daily, he said that AI can play an important role in detecting new protein targets, such as through vast amounts of literature.

The robust and efficient learning and analytical capabilities of AI can help uncover correlations scattered throughout extensive literature, thereby facilitating the identification of new mechanisms and novel targets, he said.

Liu Zhihua contributed to this story.