Published: 12:33, October 8, 2025 | Updated: 12:57, October 8, 2025
Chinese scientists uncover mystery of life evolution with AI protein language model
By Xinhua
This screenshot taken from the official website of the academic journal Proceedings of the National Academy of Sciences shows the overview of a research article about a key mechanism explaining why different organisms independently evolve similar functions when adapting to similar environments, using an artificial intelligence (AI) protein language model.

BEIJING - Bats and toothed whales are distant groups, yet both have independently developed the ability to perceive their environment through echolocation.

A Chinese research team has uncovered a key mechanism explaining why different organisms independently evolve similar functions when adapting to similar environments, using an artificial intelligence (AI) protein language model.

Convergent evolution, or convergence, refers to repeated, independent emergence of the same trait in two or more lineages of species during evolution, often indicating functional adaptation to specific environmental factors.

The research team from the Institute of Zoology of the Chinese Academy of Sciences uncovered the critical role of high-order protein features in adaptive convergence.

The team with Zou Zhengting as the leader proposed a computational analysis framework named "ACEP". The core innovation of this framework lies in its use of a pre-trained protein language model.

"A protein language model can understand the deeper structural and functional characteristics and patterns behind amino acid sequences," Zou explained.

The findings were recently published in the international academic journal Proceedings of the National Academy of Sciences.

READ MORE: Chinese scientists develop 'NeuroWorm' fiber for neural monitoring

"This work not only deepens the understanding of the laws of evolution of life but also demonstrates the strong potential of AI technology in resolving complex biological issues," Zou said. "We hope to achieve broader and more effective application of AI technology in evolutionary biology in the future."