Portfolio Insight： Hong Kong start-up IntelliGen AI aims to challenge Google DeepMind in drug discovery 【Published】

Source： Xinmei Shen， South China Morning Post

IntelliGen AI, an artificial intelligence (AI) start-up founded in Hong Kong, is positioning itself as a competitor to Google DeepMind in the field of drug discovery, as the city increasingly seeks to bolster its AI capabilities.

In an interview with the Post, founder and president Ronald Sun expressed confidence that IntelliGen AI could soon compete globally with Isomorphic Labs, a spin-off of DeepMind, in leveraging AI for drug screening and design.

“For generative science, new breakthroughs and application opportunities are global in nature,” Sun said. “Within 12 to 18 months, we aim to land major, high-value clients on a par with Isomorphic.”

The term “generative science”, although not widely recognised yet, refers to the use of AI to model the natural world and facilitate scientific discovery.

The company’s ambitious plan follows the launch of its IntFold foundational model, which is designed to predict the three-dimensional structures of biomolecules, including proteins. The model’s accuracy levels were comparable to DeepMind’s AlphaFold 3, according to IntelliGen AI.

DeepMind, based in London and acquired by Google in 2014, launched AlphaFold in 2018. AlphaFold 2, released in 2020, was said to have significantly advanced protein-structure prediction accuracy, while AlphaFold 3, announced last year, further improved predictions of interactions among proteins, nucleic acids and small molecules.

Isomorphic Labs, established in 2021, announced partnerships with pharmaceutical giants Eli Lilly and Novartis earlier this year. The company said last week it was “getting very close” to starting human clinical trials for its AI-designed drugs.

IntelliGen AI was co-founded in October 2024 by Sun, who previously worked at venture firm Future Capital and consultancy Accenture, alongside chief scientist Sun Siqi, an associate professor at Fudan University’s Research Institute of Intelligent Complex Systems.

The IntFold model had shown prediction capabilities comparable to AlphaFold 3 in areas such as protein monomers and protein-protein interfaces, the team said in a technical paper.

While there was a gap with AlphaFold 3 in areas like antibody-antigen interfaces, IntFold outperformed other competitors, including the Massachusetts Institute of Technology’s Boltz-1, ByteDance’s Protenix, and Baidu’s HelixFold 3, according to IntelliGen AI researchers.

Baidu, one of China’s leading AI companies, launched HelixFold 3 in August 2024 and said its model also achieved accuracy comparable to AlphaFold 3.

According to Sun, the gap between China and the US in foundational models for science was relatively smaller than that in large language models (LLMs), partly because the field was still in its early stages and China benefited from an abundance of talent.

The computing power required to train biological foundation models was “less staggering” compared with that needed for LLMs, he added.

However, Chinese start-ups face greater challenges in securing funding, with their US counterparts typically raising over 10 times more capital and commanding significantly higher valuations, he said.

IntelliGen AI is in the process of raising tens of millions of US dollars in an angel funding round, according to Sun.

Despite having team members in Shanghai, the company chose to establish itself in Hong Kong due to the city’s robust capital market and government support for innovation and technology, he said.

While China presented ample opportunities as a major market for drug consumption and research, Sun said, IntelliGen AI was eager to pursue global collaborations.

“Can one single company serve all of the few dozen major global pharmaceutical corporations? We don’t think so,” he said.