Featured News

AI Drug Discovery in China: How Technology is Accelerating Development Timelines

2026-07-29 by AICC
Insilico Medicine AI Drug Development

Insilico Medicine has dramatically accelerated drug development timelines, reducing candidate nomination to approximately one year by integrating artificial intelligence with laboratory research in China, according to CEO Alex Zhavoronkov.

The Hong Kong-listed biotechnology company achieved its fastest programme milestone in just nine months, with typical timelines averaging 13 months. This represents a significant improvement over conventional pharmaceutical development approaches, which typically require approximately four-and-a-half years to reach the same stage.

The accelerated timeline specifically covers early discovery and candidate selection phases, distinct from the complete drug-to-market process which still requires clinical trials, manufacturing scale-up, and regulatory approval.

🎯 AI-Driven Candidate Selection Process

Insilico leverages generative artificial intelligence to identify biological targets, design potential drug molecules, and evaluate which compounds merit advancement to laboratory testing stages.

The company reports that its programmes typically reach preclinical-candidate nomination within 12 to 18 months after researchers synthesize and evaluate between 60 and 200 molecules. This integrated workflow combines AI-generated molecular designs with expert researcher review and rigorous experimental validation.

Laboratory experiments remain essential to confirm biological activity and pharmaceutical properties of AI-selected compounds. Insilico's AI-supported methodology enables research teams to reach candidate nomination after testing a more focused set of synthesized molecules, though direct comparative data with non-AI programmes has not been disclosed.

Since 2021, Insilico has generated 31 preclinical candidates. Thirteen programmes have received investigational new drug (IND) clearances, permitting advancement toward human clinical studies, according to the company's pipeline disclosures.

🌏 China's Strategic Role in Drug Development Infrastructure

The company conducts AI research operations in Montreal and Abu Dhabi, while significant experimental validation and laboratory scale-up activities occur in China. Insilico's Shanghai facility has implemented automation for biological sampling and compound screening processes.

International teams develop and evaluate the company's AI models, while Shanghai-based researchers manage biological testing, screening protocols, and manufacturing scale-up operations.

Zhavoronkov attributed portions of the shortened development cycle to China's research infrastructure, competitive operating costs, and regulatory environment. He noted that pharmaceutical companies with research laboratories in China can potentially reduce traditional candidate-development timelines by approximately two years.

China has evolved beyond manufacturing generic pharmaceutical ingredients and now plays an increasingly substantial role in novel medicine development. International pharmaceutical companies collaborate with Chinese laboratories, contract research organizations, clinical-trial centers, and biotechnology firms.

A Pfizer executive indicated that clinical development in China could be conducted three times faster and at approximately half the cost of equivalent European operations. Drug candidates typically require five to seven years to reach the Chinese market, compared with at least eight to 10 years in Western markets, according to Reuters.

China introduced a 30-working-day review pathway in 2025 for eligible Class I innovative-drug clinical-trial applications. Applications requiring expert consultation or involving complex technical considerations can be extended to a 60-working-day review period.

"We now compete with Chinese pharmaceutical companies on timelines, and with traditional biotechnology companies in the West on novelty," Zhavoronkov stated.

🤝 Strategic Partnerships and Revenue Distribution

Insilico has established research and development agreements with major pharmaceutical companies including Eli Lilly and Japan's Takeda.

The company and Taiwan-based Bora Pharmaceuticals announced a proposed strategic alliance potentially exceeding $2.5 billion if definitive agreements are executed and the collaboration reaches full implementation.

Despite operating research facilities in China, Zhavoronkov disclosed that more than 90% of Insilico's revenue originates from Western pharmaceutical companies. Specific revenue figures generated within China were not disclosed.

Western licensing agreements prove more financially favorable for Insilico because China's national insurance system provides lower reimbursement rates for highly novel therapeutics, according to Zhavoronkov.

The company also restricts sales of most software products within China due to geopolitical considerations, Zhavoronkov said. Expansion of research operations in Shanghai remains planned.

💊 Rentosertib Advances to Phase III Clinical Trials

Insilico announced and registered a Phase III clinical trial of Rentosertib in July 2026. The oral therapeutic candidate is being evaluated for idiopathic pulmonary fibrosis, a progressive disease characterized by lung tissue scarring.

The company utilized artificial intelligence to identify the drug's biological target and generate and optimize its molecular structure.

The Phase III study is designed to enroll 320 participants across 47 centers in China. The trial will compare Rentosertib with placebo over 52 weeks, with the primary endpoint measuring annual rate of decline in forced vital capacity—a standard pulmonary function assessment.

The trial was listed as not yet recruiting when its ClinicalTrials.gov record was updated on July 7. Enrollment was anticipated to commence in August 2026, with primary completion estimated for October 2029.

Rentosertib previously completed a smaller Phase IIa study. The Phase III trial will evaluate the treatment in a larger patient population over an extended duration.

⚠️ Candidate nomination represents an early development milestone. Drugs must complete preclinical testing, human trials, manufacturing validation, and regulatory review before receiving market approval.

📊 Clinical Success Rates and Industry Benchmarks

Industry data have not definitively established whether AI-designed drugs demonstrate higher success rates in later-stage clinical trials.

A 2024 analysis of AI-native biotechnology pipelines reported Phase I success rates between 80% and 90%. The same study identified a Phase II success rate of approximately 40%, broadly consistent with historical industry benchmarks used by researchers.

Researchers noted that the number of Phase II programmes remained too limited to determine whether artificial intelligence improves later-stage clinical success. The analysis relied on publicly reported pipelines and did not compare otherwise identical AI-supported and conventional drug development programmes.

Insilico has produced 31 preclinical candidates and secured 13 investigational new drug clearances. Rentosertib represents its first programme to reach Phase III stage, while none of the company's experimental medicines has received commercial regulatory approval.

🤖 Automation Reshaping Biotechnology Workforce

Artificial intelligence and laboratory robotics are transforming staffing requirements within Insilico's operations.

Zhavoronkov estimated that the company could automate or displace approximately 40% of its software-side workforce. He did not characterize this figure as an announced staff reduction or apply it broadly to the biotechnology industry.

Insilico currently employs approximately 400 people. Laboratory scientists and software engineers are undergoing retraining to manage AI evaluation systems, automated equipment, and robotic platforms, according to Zhavoronkov.

The retraining initiatives focus on AI benchmarking and robotic systems as the company automates additional research and software functions.

(Photo by Julia Koblitz)

300+ AI Models for
OpenClaw & AI Agents

Save 20% on Costs