Related Experiment Video
Updated: Jun 24, 2025
09:34
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
3.9K
Realizing Molecular Machine Learning through Communications for Biological AI: Future Directions and Challenges
Sasitharan Balasubramaniam1, Samitha Somathilaka1,2, Sehee Sun1
1School of Computing, University of Nebraska-Lincoln, NE, USA.
IEEE Nanotechnology Magazine
|June 10, 2024
Summary
Molecular Machine Learning (MML) explores using molecules for computation, moving beyond traditional devices. This research reviews MML approaches and proposes novel directions using biological systems for AI tasks.
Area of Science:
- Biotechnology
- Artificial Intelligence
- Molecular Computing
Background:
- Artificial Intelligence (AI) and Machine Learning (ML) are increasingly integrated into daily life and devices.
- Energy-efficient algorithms are crucial for low-power devices, driving innovation in computational methods.
Purpose of the Study:
- To investigate Molecular Machine Learning (MML) as a novel approach for performing machine learning functions at the molecular scale.
- To explore new directions for MML, including the use of gene regulatory networks and biological systems.
Main Methods:
- Review of current MML approaches.
- Investigation of gene regulatory networks and population interactions for creating neural networks.
- Exploration of calcium signaling mechanisms for training biological machine learning structures.
Main Results:
- Demonstration of MML principles through molecular transport, processing, and interpretation via chemical reactions.
- Proposal of novel MML architectures based on biological systems.
- Successful application of MML in biological cells to construct an Analog to Digital Converter (ADC).
Conclusions:
- MML offers a promising avenue for developing highly efficient and miniaturized machine learning systems.
- Biological systems, such as gene regulatory networks and cellular signaling, provide a viable platform for implementing MML.
- Future research in MML holds potential for solving complex computational challenges and advancing AI capabilities.
