AI-developed pharmaceutical on the verge of clearing last barrier: could this technology revolutionize drug discovery?
In a significant development, a small molecule named rentosertib, developed by InSilico Medicine, is on the verge of entering phase 3 clinical trials. This drug is intended to treat idiopathic pulmonary fibrosis, a lung-scaring condition for which there currently are limited treatment options.
The 71-patient study in China reported by InSilico in June showed that rentosertib was safe and well-tolerated. The drug targets a chronic lung disease, making it the most advanced investigational drug where both the biological target and therapeutic compound were discovered using AI.
AI has shown substantial advantages over traditional drug discovery methods, particularly in early-stage research and clinical trial processes. It reduces drug discovery timelines by around 25%, shortens clinical trial durations by 50-80%, and cuts trial costs up to 70%. Advanced AI models, such as PATH, improve prediction accuracy for drug-target interactions and run thousands of times faster than prior methods, enabling faster and smarter drug design [1][2].
However, while AI has demonstrated its efficiency in drug discovery, its impact is still emerging in delivering a large volume of fully AI-discovered drugs that have passed phase 3 and received regulatory approval. Much of AI's impact so far is complementary—streamlining the drug pipeline rather than fully replacing traditional methods [3].
Partnerships between AI biotechs and pharma companies have proliferated. In January 2024, Isomorphic Labs (a subsidiary of tech giant Alphabet) entered into deals with drug firms Eli Lilly and Novartis that could be worth billions. Recursion, founded in 2013, runs highly automated in-house labs and generates data covering swathes of biology and chemistry before zeroing in on individual diseases. Last December, Recursion announced it had dosed the first patient with a candidate drug to treat certain solid tumors and lymphoma [4].
In 2023, Benevolent signed a deal with Merck for $594 million (£439 million). Lina Nilsson, the firm's chief platform officer, states that this program went from target initiation to new drug application-enabling studies in about 18 months, while the industry average is around 42 months.
Critics argue that AI relies on data that has been collected, meaning that chemical space has already been explored, and many of the targets are not very novel. Some holdouts argue that AI has yet to make a significant impact during the crucial and costly phases of drug research and development. There is far less data from patients and toxicological predictive models, for now, underperform [5].
Despite these challenges, AI's impact is increasingly profound in accelerating timelines, optimising trial design, and enhancing candidate selection. This is expected to lead to more AI-discovered approved drugs in the near future. InSilico needs to demonstrate that rentosertib effectively treats idiopathic pulmonary fibrosis in large phase 3 trials.
Machine learning, a type of AI, is proficient at identifying which proteins or genes should be targeted based on experimental results. AI is efficient at searching and mining large datasets, summarising information, and detecting patterns in the data. However, much of the in vivo translation is currently missing [6].
The drug industry is closely watching the progress of rentosertib, as its success could pave the way for more AI-discovered drugs to enter clinical trials and potentially receive regulatory approval.
References:
- Accelerating Drug Discovery with AI
- AI in Drug Discovery: Transforming the Pharmaceutical Industry
- The Impact of AI on Drug Discovery and Development
- Recursion Pharmaceuticals Announces First Patient Dosed in Phase 1 Clinical Trial for its Proprietary Small Molecule Program
- The Limits of AI in Drug Discovery
- The Current State of AI in Drug Discovery
The groundbreaking development of rentosertib, a potential treatment for idiopathic pulmonary fibrosis, has sparked interest in the medical-conditions sector, as it represents one of the most advanced investigational drugs where both the biological target and therapeutic compound were discovered using technology, specifically AI. The success of rentosertib, if proven effective in large phase 3 trials, could significantly impact health-and-wellness by providing a novel treatment for a condition with limited options. However, the industry is still grappling with the full potential of AI in drug discovery, as while it has demonstrated efficiency in accelerating timelines, optimizing trial design, and enhancing candidate selection, it still faces challenges in in vivo translation [1][2][3][4][5][6].
