Jove
Visualize
Contact Us

Related Concept Videos

Molecular Models02:00

Molecular Models

38.1K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
38.1K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

45
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
45
Ligand Binding Sites02:40

Ligand Binding Sites

12.8K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.8K

You might also read

Related Articles

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

Sort by
Same author

Design and realization of high performance textured lead-free piezoelectric ceramics through human-AI collaboration.

Nature communications·2026
Same author

Real-Space Local Dynamics in 1,2,3-Triazole Using Inelastic Neutron Scattering.

The journal of physical chemistry. B·2025
Same author

Controlling Chloride Crossover in Bipolar Membrane Water Electrolysis.

ACS electrochemistry·2025
Same author

Structured Polymer-Derived Ceramic Composites via Near-Infrared Thermal Stereolithography.

ACS applied polymer materials·2025
Same author

Multimodal Machine Learning Analysis of GaSe Molecular Beam Epitaxy Growth Conditions.

ACS applied materials & interfaces·2025
Same author

Methodology for Selecting Anion and Cation Exchange Membranes Based on Salt Transport Properties for Bipolar Membrane Fabrication.

ACS applied polymer materials·2025
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 14, 2025

Interactive Molecular Model Assembly with 3D Printing
06:15

Interactive Molecular Model Assembly with 3D Printing

Published on: August 13, 2020

9.9K

Large Language Models as Molecular Design Engines.

Debjyoti Bhattacharya1, Harrison J Cassady2, Michael A Hickner2

  • 1Materials Science and Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, United States.

Journal of Chemical Information and Modeling
|September 4, 2024
PubMed
Summary

Large Language Models (LLMs) can now design novel molecules with 97% accuracy. This breakthrough in computational molecular design offers a powerful new tool for scientific innovation.

More Related Videos

Modeling an Enzyme Active Site using Molecular Visualization Freeware
14:37

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

9.7K
Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K

Related Experiment Videos

Last Updated: Jun 14, 2025

Interactive Molecular Model Assembly with 3D Printing
06:15

Interactive Molecular Model Assembly with 3D Printing

Published on: August 13, 2020

9.9K
Modeling an Enzyme Active Site using Molecular Visualization Freeware
14:37

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

9.7K
Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K

Area of Science:

  • Computational chemistry
  • Artificial intelligence in chemistry

Background:

  • Small molecule design is vital for applications like drug discovery and energy storage.
  • Data-driven and machine learning methods are increasingly used to navigate vast chemical design spaces.
  • Existing generative machine learning models for molecular design often have complex training and generate invalid or non-unique molecules.

Purpose of the Study:

  • To investigate the potential of pretrained Large Language Models (LLMs) for molecular design.
  • To evaluate the ability of the Claude 3 Opus LLM to generate, read, and modify molecules using natural language prompts.
  • To systematically assess the validity and uniqueness of LLM-generated molecules and their behavior under varying prompt conditions.

Main Methods:

  • Utilized the Claude 3 Opus Large Language Model (LLM) for molecular design tasks.
  • Employed natural language prompts to instruct the LLM in creating and modifying molecular structures.
  • Quantified molecular modifications within a low-dimensional latent space to analyze model behavior.
  • Evaluated the validity and uniqueness of generated molecules.

Main Results:

  • The Claude 3 Opus LLM demonstrated a high success rate, generating 97% valid and unique molecules.
  • Systematic evaluation revealed predictable model behavior under different prompting strategies.
  • The LLM successfully performed guided molecular generation, including manipulation of electronic structures via natural language prompts.

Conclusions:

  • Pretrained LLMs, specifically Claude 3 Opus, show significant promise as versatile engines for molecular design.
  • LLMs offer a more accessible and effective approach to computational molecular design compared to traditional generative methods.
  • This research highlights the potential of leveraging natural language for complex chemical manipulation and design.