Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Non-equilibrium in the Cell

Non-equilibrium in the Cell

An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Synergistic Coupling between Nanoconfinement and Grain Boundary Improves Electrocatalytic CO<sub>2</sub> Reduction to <i>n</i>-Propanol.

ACS nano·2026

Same author

Reference-Free Quantitative Mass Spectrometry Enables Sequencing of Resist Copolymers and Reveals Sequence-Dependent Deprotection Sensitivity.

Macromolecules·2026

Same author

Global remapping of the sensory homunculus emerges early in childhood development.

Nature communications·2026

Same author

Scalable robot collective resilience by sharing resources.

Science robotics·2026

Same author

Organic-inorganic heterostructure empowers infected wound healing.

Journal of materials chemistry. B·2025

Same author

Metamaterial robotics.

Science robotics·2025

Same journal

Anion-Engineered Organic Electrochemical Transistors With Multi-Timescale Synaptic Dynamics for Task-Adaptive Spiking Neural Networks.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same journal

Dimensional Effect on the Lattice Anharmonicity in Graphene and Graphite.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same journal

A Modular Core-Shell Nanoparticle Platform for Dual-Modal MRI-Luminescence With High Relaxivity.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same journal

Highly Selective Construction of D<sub>2</sub>-Symmetric Chiral Carbon Nanorings and the Diverse Assembly With Fullerenes.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same journal

A Synergistic Process Optimization and Data-Driven Modeling Strategy for Unraveling and Enhancing the Low-Light Response in Back-Contact Solar Cells.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same journal

Porous Hydrogel-Mediated One-Step Selection of Mannoprotein-Targeted Aptamers for Early Diagnosis of Invasive Saccharomyces cerevisiae Infections.

Small (Weinheim an der Bergstrasse, Germany)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 25, 2025

Pattern Generation for Micropattern Traction Microscopy

Pattern Generation for Micropattern Traction Microscopy

Published on: February 17, 2022

Text-to-Microstructure Generation Using Generative Deep Learning.

Xiaoyang Zheng^1,2, Ikumu Watanabe¹, Jamie Paik²

¹Center for Basic Research on Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, 305-0047, Japan.

Small (Weinheim an Der Bergstrasse, Germany)

|May 21, 2024

Summary

This summary is machine-generated.

This study introduces a text-to-microstructure deep generative network (Txt2Microstruct-Net) for generating 3D material microstructures from text prompts. This novel approach enhances material design diversity and user interaction without extra optimization steps.

Keywords:

architected material artificial intelligence deep generative model deep learning inverse design metamaterial microstructure

More Related Videos

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

Related Experiment Videos

Last Updated: Jun 25, 2025

Pattern Generation for Micropattern Traction Microscopy

Pattern Generation for Micropattern Traction Microscopy

Published on: February 17, 2022

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

Area of Science:

Materials Science
Computational Materials Science
Artificial Intelligence

Background:

Designing material microstructures traditionally requires extensive expertise and iterative trial-and-error.
Existing deep generative networks for inverse material design often lack diversity and user-friendliness.

Purpose of the Study:

To develop a novel text-to-microstructure deep generative network (Txt2Microstruct-Net) for direct 3D material microstructure generation from text prompts.
To overcome limitations in generation diversity and human-computer interaction in current microstructure design methods.

Main Methods:

Developed and trained a Txt2Microstruct-Net model on a large dataset of microstructure-caption pairs.
The model supports extensible dataset creation using provided algorithms.
The network is designed for flexibility, generating various geometric representations like voxels and point clouds.

Main Results:

Successfully generated 3D material microstructures directly from text descriptions without optimization.
Demonstrated the model's effectiveness in inverse design for materials and metamaterials.
The Txt2Microstruct-Net model shows flexibility in generating diverse geometric representations.

Conclusions:

Txt2Microstruct-Net offers a pioneering approach to microstructure generation directly from text.
The model has significant potential for interactive material design, especially when integrated with large language models.
This tool could streamline material design and discovery processes, making them more user-friendly.