学术头条 | 基于网络科学的人工智能揭示基因信息如何利用单细胞塑造形体
图:这个名为de novo coalescent embedding(D-CE)的算法,基于基因组重建单细胞三维空间组织结构,表明可以通过构建转录组概况网络,直接从基因表达中推断出单细胞的三维空间结构。利用联合嵌入技术将该网络映射到三维几何空间中,从而实现单细胞的空间重建。
Graphic: Representation of the topological and geometrical paths in a complex network and their congruence with the underlying geometry.
Prof. Carlo Vittorio Cannistraci who is chair professor of complex network intelligence at Tsinghua University, and a corresponding author of the study for the complex physics modelling and the algorithm design says: “During my childhood, I wondered how nature could decide the shape of flowers and insects around me. Then, in the crystal-clear Sicilian sea, I put my head underwater holding the breath, freediving the submarine world, and the same question appeared in my mind on the shape of anemones and starfishes. When I started to study biology at school, the question revisited on me in a more precise way: how could the spatial organization of cells in my body tissues arise so precisely? How the individual single cells in our bodies are genetically fingerprinted and genomically programmed to evolve towards a three-dimensional (3D) spatial tissue continuum?”. This is what we call today a topic of physics of life.
Prof. Cannistraci would never imagine that Coalescent Embedding, a machine learning methodology that he invented in 2016 to map complex networks in a geometrical space, could also pave a milestone solution in the still long path to solve this enigma which, in science, is called: “de novo reconstruction of single cell 3D spatial tissue organization”. In 2018 professor Cannistraci, at that moment principal investigator of a team of scientists at the BIOTEC institute of TU Dresden in Germany, was presenting a seminar on Coalescent Embedding in China. Coalescent Embedding is an algorithm that can recover the hidden geometry of the parts composing a connected system starting from its complex network. During the seminar, he showed an example: taking a graph representing connectivity between brain regions, without any knowledge about the spatial location of the brain areas, Coalescent Embedding algorithm was able to reconstruct the 3D anatomical organization of the human brain. Prof. Jing-Dong Jackie Han from Peking University was present at that talk and was inspired, after the talk approached Prof. Cannistraci with a comment: “I think your artificial intelligence algorithm may help to reconstruct the spatial 3D organization of single cells dissected from a tissue, as you did for the brain’s areas, perhaps by embedding single-cells transcriptomic similarity networks ”. That keen intuition of Prof. Han put Prof. Cannistraci in front of one of the enigmas that have populated his childhood without he ever noticed a possible link with his current work. Meanwhile, Prof. Cannistraci moved to Tsinghua University in China founding the Center of Complex Network Intelligence (CCNI). The two scientists teamed up for 5 years together with their groups to address Prof. Han’s proposal. Prof. Cannistraci with his ability to design network-based algorithms for artificial intelligence and Prof. Han with her expertise in computational and experimental systems biology.
The result of this effort is a new algorithm called de novo coalescent embedding (D-CE) which is an evolution of the coalescent embedding theory for genome-based reconstruction of single cell 3D spatial tissue organization. The results of this new study are now published on the prestigious journal Advanced Science, and they show that indeed it is possible to infer 3D spatial organization of single cells directly from their gene expression, by building a network of their transcriptomic profiles and performing the mapping of this network in a 3D geometrical space using coalescent embedding techniques.
发表文章
“Spatial Reconstruction of Oligo and Single Cells by De Novo Coalescent Embedding of Transcriptomic Networks”
作者: Yuxuan Zhao, Shiqiang Zhang, Jian Xu, Yangyang Yu, Guangdun Peng,Carlo Vittorio Cannistraci, Jing-Dong J. Han
2023年7月18日发表于《先进科学》Advanced Science
https://doi.org/10.1002/advs.202206307
作者介绍
Author
Carlo Vittorio Cannistraci
Cannistraci教授是一位理论工程师和计算创新者,他是清华大学脑与智能实验室(THBI)首席研究员,THBI复杂网络智能中心(CCNI)主任,也是清华大学计算机系和生物医学工程系兼职教授。
Carlo Vittorio Cannistraci is a theoretical engineer and computational innovator. He is a Professor in the Tsinghua Laboratory of Brain and Intelligence (THBI) and an adjunct professor in the Department of Computer Science and in the Department of Biomedical Engineering at Tsinghua University. He directs the Center for Complex Network Intelligence (CCNI) in THBI, which seeks to create pioneering algorithms at the interface between information science, physics of complex systems, complex networks and machine intelligence, with a focus in brain/life-inspired computing for big data analysis. These computational methods are often applied to precision biomedicine, neuroscience, social and economic science.
https://brain.tsinghua.edu.cn/en/info/1010/1003.htm
韩敬东 教授
北京大学
联系方式 / Press Contact
Carlo Vittorio Cannistraci Prof. PhD. Eng.
邮箱 / E-mail:
研究机构
Research institution
清华大学脑与智能实验室(THBI)
清华大学脑与智能实验室(Tsinghua Laboratory of Brain and Intelligence, THBI)是清华大学校级实体跨学科研究所。THBI专注于脑科学与人工智能领域的交叉科学研究,旨在回答智能的本质是什么这一核心科学问题。https://brain.tsinghua.edu.cn/en/index.htm
THBI复杂网络智能中心(CCNI)
THBI复杂网络智能中心(CCNI)研究介于信息科学、复杂系统物理学、复杂网络和机器智能等领域之间的开创性算法,重点运用于大数据分析的脑、生物启发式计算。这些计算方法经常应用在精准生物医学、神经科学、社会和经济科学等领域。
更多内容请关注
最新评论
推荐文章
作者最新文章
你可能感兴趣的文章
Copyright Disclaimer: The copyright of contents (including texts, images, videos and audios) posted above belong to the User who shared or the third-party website which the User shared from. If you found your copyright have been infringed, please send a DMCA takedown notice to [email protected]. For more detail of the source, please click on the button "Read Original Post" below. For other communications, please send to [email protected].
版权声明:以上内容为用户推荐收藏至CareerEngine平台,其内容(含文字、图片、视频、音频等)及知识版权均属用户或用户转发自的第三方网站,如涉嫌侵权,请通知[email protected]进行信息删除。如需查看信息来源,请点击“查看原文”。如需洽谈其它事宜,请联系[email protected]。
版权声明:以上内容为用户推荐收藏至CareerEngine平台,其内容(含文字、图片、视频、音频等)及知识版权均属用户或用户转发自的第三方网站,如涉嫌侵权,请通知[email protected]进行信息删除。如需查看信息来源,请点击“查看原文”。如需洽谈其它事宜,请联系[email protected]。