Deep convolutional and fully-connected DNA neural networks

Xiao Liu, Ziyang Zheng, Pei Liu, Zheng Yang, Hao Hu, Meng Wu, Xiaoding Lou, Fan Xia, Kaixiong Tao, Longjie Li (), Jun Dai () and Xianjin Xiao ()
Additional contact information
Xiao Liu: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Ziyang Zheng: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Pei Liu: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Zheng Yang: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Hao Hu: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Meng Wu: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Xiaoding Lou: China University of Geosciences, Laboratory of Biogeology and Environmental Geology, Faculty of Materials Science and Chemistry
Fan Xia: China University of Geosciences, Laboratory of Biogeology and Environmental Geology, Faculty of Materials Science and Chemistry
Kaixiong Tao: Huazhong University of Science and Technology, Department of Gastrointestinal Surgery, Union Hospital, Tongji Medical College
Longjie Li: Wuhan Polytechnic University, School of Life Science and Technology
Jun Dai: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College
Xianjin Xiao: Huazhong University of Science and Technology, Department of Obstetrics and Gynecology of Tongji Hospital and Institute of Reproductive Health, Tongji Medical College

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract DNA molecules can be used to build “neural networks” that function like the brain, enabling them to perform complex computational tasks. However, a fundamental limitation of existing DNA networks is that their most basic computing units cannot perform true continuous and precise analog calculations, which restricts their ability to process complex information effectively. To address this, here we develop a DNA computing unit called CALCUL. This system successfully achieves fully analog computation, where all inputs, weighting parameters, and outputs are continuous and precise values. It performs the core operations of a neural network rapidly with high accuracy and is reusable. By integrating magnetic bead technology, we also enable modular operations and the construction of multilayer networks. Ultimately, we use this technology to construct a deep DNA neural network that correctly identifies complex color images with 100% accuracy. These developments provide a robust foundation for building more powerful and precise molecular computers.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-65618-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-65618-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-65618-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().