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

Search research articles

Related Experiment Video

Updated: Jul 5, 2026

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

Efficient and valid large molecule generation via self-supervised generative models.

Doyoung Kwak¹, Md Raiyan Chowdhury¹, Byung-Jun Yoon^1,2

¹Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA.

Npj Drug Discovery

|July 3, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Predicting Treatment Failure With Sodium-Glucose Cotransporter-2 Inhibitors in People With Type 2 Diabetes: Novel Artificial Intelligence and Machine Learning Approach.

JMIR diabetes·2026

Same author

An integrated computational antigen discovery pipeline with hierarchical filtering for emerging viral variants.

NAR molecular medicine·2026

Same author

Enhancing protein immunogenicity prediction via uncertainty weighted deep ensemble.

Oxford open immunology·2026

Same author

Variable rate neural compression for sparse detector data.

Patterns (New York, N.Y.)·2026

Same author

ImmUQBench: a benchmark on uncertainty quantification of protein immunogenicity prediction.

Oxford open immunology·2026

Same author

Epidemiological model calibration via graybox Bayesian optimization.

Infectious Disease Modelling·2026

Same journal

Generative AI for controllable protein sequence design: A survey.

npj drug discovery·2026

Same journal

V-SYNTHES2-the next generation tool for structure-based virtual screening of giga-scale chemical spaces.

npj drug discovery·2026

Same journal

Drugging Ras trafficking-are there new roads to travel?

npj drug discovery·2026

Same journal

Quantum-machine-assisted drug discovery.

npj drug discovery·2026

Same journal

Mechanisms that matter: unbiased cellular screening for degraders.

npj drug discovery·2026

Same journal

Author Correction: The AI drug revolution needs a revolution.

npj drug discovery·2026

See all related articles

Generative AI models struggle with large molecule design. Advanced tokenization like Atom-Pair Encoding (APE) shows promise for improving AI

Area of Science:

Computational chemistry and drug discovery
Artificial intelligence in molecular design

Background:

Large molecule design is complex and less explored than small molecule design, posing challenges for generative AI.
Existing AI models effective for small molecules may not scale to large molecular structures.

Purpose of the Study:

Establish baselines for scalability, efficiency, and generative performance in large molecule design.
Evaluate generative AI models for creating large molecules for therapeutic applications.
Explore methods to enhance AI capabilities for complex molecular structures.

Main Methods:

Evaluated scalability and performance of generative AI models on large molecule generation.
Investigated masked language modeling strategies.
Applied advanced tokenization methods, including Atom-Pair Encoding (APE).

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jul 5, 2026

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Main Results:

Small molecule AI strategies do not readily extend to large molecular structures.
Atom-Pair Encoding (APE) significantly improves AI design capabilities for complex molecules.
Demonstrated potential and challenges of deep generative modeling for large molecules.

Conclusions:

Deep generative modeling holds potential for large molecule discovery but faces challenges.
Enhanced AI strategies, like APE tokenization, can bridge the gap in generating novel large molecules.
Further research is needed to optimize AI for large molecule design in drug discovery.