《生命科学》 2021, 33(12): 1483-1492

合成生物数据库与大数据智能分析展望

胡如云 , 陈永灿 , 张建志 , 郭二鹏 , 付立豪 , 乔　宇^* , 司　同^*

中国科学院深圳先进技术研究院，深圳 518055

摘　要：

合成生物通过“设计- 构建- 测试- 学习”闭环研究积累海量数据，推动合成生物数据储存、共享和分析等方面的发展。该文以合成生物数据库和数据智能分析为核心内容，描述了合成生物数据库建设的现状，讨论了合成生物数据质控和标准、存储和共享等方面的瓶颈问题和未来发展；另一方面，概述了人工智能技术在合成生物大数据智能分析方面的关键进展，讨论了系统建模、异构数据集成、智能设计与功能预测等方面的挑战与发展趋势。

通讯作者：乔　宇 , Email:yu.qiao@siat.ac.cn 司　同 , Email:tong.si@siat.ac.cn

Perspective of synthetic biology database and intelligent data analysis

HU Ru-Yun , CHEN Yong-Can , ZHANG Jian-Zhi , GUO Er-Peng , FU Li-Hao , QIAO Yu^* , SI Tong^*

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China

Abstract:

Synthetic biology accumulates massive data through the "design-build-test-learn" cycle, which has promoted the development of big data storage, sharing, and analysis. This prospective focuses on synthetic biology database and intelligent data analysis. For the former, we discuss the current status, bottleneck, and future development of data quality control and standards, storage and sharing in biology. For the latter, we highlight the use of artificial intelligence, particularly machine learning, in big data analysis in synthetic biology. We summarized the challenges and potentials of system modeling, heterogeneous data integration, intelligent design and function prediction.

Communication Author：QIAO Yu , Email:yu.qiao@siat.ac.cn SI Tong , Email:tong.si@siat.ac.cn