Insilico Medicine has dramatically shortened the time needed to produce drug development candidates to about one year by combining artificial intelligence with laboratory research in China, according to CEO Alex Zhavoronkov.
The Hong Kong-listed company's fastest program reached candidate nomination in just nine months, while its typical timeline is about 13 months, Zhavoronkov said. He noted that conventional approaches usually take about four-and-a-half years to reach the same stage.
How AI speeds up early drug discovery
According to Reuters, Insilico uses generative AI to identify biological targets and design potential drug molecules. The timeline covers early discovery and candidate selection, rather than the full process of bringing a drug to market. Clinical trials, manufacturing, and regulatory review remain separate stages.
The company's approach combines AI-powered target identification with laboratory validation, allowing researchers to quickly move from computational predictions to experimental testing. This integration of digital and physical research is what makes the speed possible.
What this means for drug development
Cutting the early discovery phase from four-and-a-half years to about one year represents a significant shift in pharmaceutical research. The AI system can analyze vast amounts of biological data and propose drug candidates much faster than traditional methods.
According to Artificial Intelligence News, Insilico Medicine has reduced the time needed to produce some drug development candidates to about one year by combining artificial intelligence with laboratory research in China.
However, it is important to note that this accelerated timeline only applies to the early discovery and candidate selection phase. The drug still must go through clinical trials, manufacturing, and regulatory approval, which can take many more years.
Our Take: A practical step forward, not a miracle cure
Insilico's achievement is genuinely impressive. Cutting early drug discovery from years to months could mean faster treatments for patients and lower research costs for companies. But we need to be clear-eyed about what this means.
The hardest and most expensive parts of drug development — clinical trials and regulatory approval — still lie ahead. AI is not replacing those steps. What it is doing is making the starting phase much more efficient. In our view, this is a practical improvement, not a revolution. It shows how AI can be a powerful tool in the right hands, but the full journey from lab to pharmacy shelf remains long and uncertain.
For now, Insilico's results in China offer a glimpse of how AI can reshape pharmaceutical research timelines — one candidate at a time.
