《生命科学》 2025, 37(10): 1212-1227

人工智能时代跨生境的微生物组研究：环境的约束与生命的记录

赵维殳^1,* , 凌鋆超^2,* , 李化炳^3,* , 毛冠男^4,* , 周冰心^5,*

¹上海交通大学生命科学技术学院，深部生命国际研究中心，上海 200240 ²生物医学大数据中 心，中国科学院上海营养与健康研究所，上海 200032 ³中国科学院南京地理与湖泊研究所，湖 泊与流域水安全全国重点实验室，南京 211135 ⁴兰州大学泛第三极环境中心，兰州 730000 ⁵上海交通大学自然科学研究院，上海国家应用数学中心(上海交大分中心)，上海 200240

摘　要：

地球水圈生境( 如浅海、深海、湖泊、冰川等) 连接了地球的表层与深部，蕴藏着丰富且多样的微生物，其中部分水圈生境( 如深海、高原湖泊、冰川等) 还具有极端环境的理化因素，如剧烈变化的温度、压力、pH、盐度等，是研究微生物物种与代谢多样性、解析微生物分布和生态驱动，并反演其中记录的不同圈层的动力学过程( 如洋流、板块运动等) 的绝佳研究对象。随着近年来水圈生境微生物取样和分析技术的飞速发展，已经积累了大量水圈微生物环境基因组序列信息及其对应的环境理化参数，为全面解析水圈微生物特征及环境影响提供了有力支撑。本文全面综述了过去十年间国内外水圈生境微生物研究计划的进展、大数据获取与分析的变化趋势以及环境微生物理论的迭代，讨论了微生物物种对环境变化的记录及微生物代谢体现的环境约束，并展望了人工智能给解析跨生境的水圈微生物的适应演化机制带来的新机遇。

通讯作者：赵维殳 , Email:zwsh88@sjtu.edu.cn 凌鋆超 , Email:lingyunchao@sinh.ac.cn 李化炳 , Email:hbli@niglas.ac.cn 毛冠男 , Email:maogn@lzu.edu.cn 周冰心 , Email:bingxin.zhou@sjtu.edu.cn

Cross-habitat microbiome research in the artificial intelligence era: environmental constraints and life records

ZHAO Wei-Shu^1,* , LING Yun-Chao^2,* , LI Hua-Bing^3,* , MAO Guan-Nan^4,* , ZHOU Bing-Xin^5,*

¹International Center for Deep Life Investigation (IC-DLI), School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China ²Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, Chinese Academy of Sciences, Shanghai 200032, China ³Key Laboratory of Lake and Watershed Science for Water Security, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 211135, China ⁴Center for the Pan-third Pole Environment, Lanzhou University, Lanzhou 73000, China ⁵Shanghai National Center for Applied Mathematics (SJTU Center), Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai 200240, China

Abstract:

Earth's aquatic habitats (e.g., shallow marine, deep seas, lakes, glaciers) connect the surface and deep layers of our planet, harboring rich and diverse microbial ecosystems. Some aquatic habitats (e.g., deep seas, alpine lakes, and glaciers) also exhibit extreme physicochemical factors including dramatic variations in temperature, pressure, pH, salinity, making them excellent subjects for studying microbial diversity in both species and metabolism, analyzing microbial distribution and ecological drivers, and reconstructing the dynamic processes of different Earth spheres (e.g., ocean currents and tectonic plate movements) recorded within them. With the rapid development of microbial sampling and analytical techniques in aquatic habitats in recent years, substantial amounts of aquatic microbial environmental genomic sequence information and corresponding environmental physicochemical parameters have been rapidly accumulated, providing strong support for comprehensive analysis of aquatic microbial characteristics and environmental interactions. This review comprehensively summarizes the progress of international and domestic aquatic habitat microbial research programs over the past decade, the changing trends in big data acquisition and analysis, and the evolution of environmental microbial theories. This review discusses the records of environmental changes by microbial species and the environmental constraints reflected by microbial metabolism, and prospects the new opportunities that artificial intelligence brings to analyze the adaptive evolutionary mechanisms of cross-habitat aquatic microbes.

Communication Author：ZHAO Wei-Shu , Email:zwsh88@sjtu.edu.cn LING Yun-Chao , Email:lingyunchao@sinh.ac.cn LI Hua-Bing , Email:hbli@niglas.ac.cn MAO Guan-Nan , Email:maogn@lzu.edu.cn ZHOU Bing-Xin , Email:bingxin.zhou@sjtu.edu.cn