Jove
Visualize
Contact Us
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 Concept Videos

Structural Isomerism02:34

Structural Isomerism

21.4K
Isomerism in Complexes
Isomers are different chemical species that have the same chemical formula. Structural isomerism of coordination compounds can be divided into two subcategories, the linkage isomers and coordination-sphere isomers.
Linkage isomers occur when the coordination compound contains a ligand that can bind to the transition metal center through two different atoms. For example, the CN− ligand can bind through the carbon atom or through the nitrogen atom. Similarly, SCN− can...
21.4K
[3,3] Sigmatropic Rearrangement of 1,5-Dienes: Cope Rearrangement01:21

[3,3] Sigmatropic Rearrangement of 1,5-Dienes: Cope Rearrangement

3.3K
The Cope rearrangement is classified as a [3,3] sigmatropic shift in 1,5-dienes, leading to a more stable, isomeric 1,5-diene. The reaction involves a concerted movement of six electrons, four from two π bonds and two from a σ bond, via an energetically favorable chair-like transition state.
3.3K
Structure-Activity Relationships and Drug Design01:28

Structure-Activity Relationships and Drug Design

1.7K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.7K
¹H NMR Chemical Shift Equivalence: Enantiotopic and Diastereotopic Protons00:58

¹H NMR Chemical Shift Equivalence: Enantiotopic and Diastereotopic Protons

3.1K
Replacing each alpha-hydrogen in chloroethane by bromine (or a different functional group) yields a pair of enantiomers. Such protons are called prochiral or enantiotopic and are related by a mirror plane. Enantiotopic protons are chemically equivalent in an achiral environment. Because most proton NMR spectra are recorded using achiral solvents, enantiotopic hydrogens yield a single signal.
In chiral compounds such as 2-butanol, replacing the methylene hydrogens at C3 produces a pair of...
3.1K
Olefin Metathesis Polymerization: Overview01:13

Olefin Metathesis Polymerization: Overview

2.5K
Recently, the development of olefin metathesis polymerization advanced the field of polymer synthesis. Simply put, the reorganization of substituents on their double bonds between two olefins in the presence of a catalyst is known as the olefin metathesis reaction. The use of metathesis reaction for polymer synthesis is called olefin metathesis polymerization.
Ruthenium-based Grubbs catalyst is the most commonly used catalyst for olefin metathesis polymerization. Grubbs catalyst consists of a...
2.5K
[3,3] Sigmatropic Rearrangement of Allyl Vinyl Ethers: Claisen Rearrangement01:24

[3,3] Sigmatropic Rearrangement of Allyl Vinyl Ethers: Claisen Rearrangement

2.7K
The Claisen rearrangement is a [3,3] sigmatropic rearrangement of allyl vinyl ethers to unsaturated carbonyl compounds. The rearrangement is a concerted pericyclic reaction proceeding via a chair-like transition state.
2.7K

You might also read

Related Articles

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

Sort by
Same author

Bridging data and discovery: a survey on knowledge graphs in AI for science.

National science review·2026
Same author

Integrated UPLC-QTOF-MS and Network Pharmacology for Predicting Active Constituents and Pharmacological Mechanisms of Yinxingye Tablets Against Oxidative Stress.

Biomedical chromatography : BMC·2026
Same author

Metabolomics Integrated with Mass Spectrometry Imaging Reveals Novel Action of Rb1 in Ischemic Stroke.

Journal of proteome research·2026
Same author

Harnessing biosynthetic logic for next-generation ADC payloads.

Chemical Society reviews·2026
Same author

Overcoming the Thermodynamic Diffusion Barrier in DNA Cascade Amplifiers via Spatially Confined Entropy Reduction: A Versatile Kinetic Engineering Framework.

Analytical chemistry·2026
Same author

Association between novel hematological inflammatory indices and prevalent peripheral arterial disease: A cross-sectional analysis from the national health and nutrition examination survey.

Science progress·2026

Related Experiment Video

Updated: Jan 12, 2026

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products
11:13

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products

Published on: March 12, 2020

11.5K

MSformer: A Meta-Structure Based Interpretable Framework for Representation Learning of Natural Products.

Bingjie Zhu1,2, Jie Liao1,2,3, Huihui Liu1,2

  • 1College of Pharmaceutical Sciences, Zhejiang University, 310058 Hangzhou, China.

Analytical Chemistry
|November 7, 2025
PubMed
Summary

MSformer, a new AI model, decodes complex natural products (NPs) using molecule fragments called meta-structures. This approach accelerates drug discovery by navigating nature's vast chemical space.

More Related Videos

Single-throughput Complementary High-resolution Analytical Techniques for Characterizing Complex Natural Organic Matter Mixtures
09:38

Single-throughput Complementary High-resolution Analytical Techniques for Characterizing Complex Natural Organic Matter Mixtures

Published on: January 7, 2019

9.1K
Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
07:08

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

7.7K

Related Experiment Videos

Last Updated: Jan 12, 2026

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products
11:13

Mass Spectrometry-Guided Genome Mining as a Tool to Uncover Novel Natural Products

Published on: March 12, 2020

11.5K
Single-throughput Complementary High-resolution Analytical Techniques for Characterizing Complex Natural Organic Matter Mixtures
09:38

Single-throughput Complementary High-resolution Analytical Techniques for Characterizing Complex Natural Organic Matter Mixtures

Published on: January 7, 2019

9.1K
Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
07:08

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

7.7K

Area of Science:

  • Computational chemistry
  • Artificial intelligence in drug discovery
  • Natural product chemistry

Background:

  • Natural products (NPs) are vital for drug discovery but face challenges due to structural complexity and limited data for AI analysis.
  • Existing AI models struggle with the unique chemical space of NPs, hindering their potential.
  • A novel approach is needed to effectively leverage NP data for drug discovery.

Purpose of the Study:

  • To develop an AI architecture, MSformer, capable of systematically encoding the chemical space of natural products.
  • To overcome data scarcity issues in NP drug discovery through a unique pretraining strategy.
  • To enhance the interpretability and predictive power of AI models for NP-based drug discovery.

Main Methods:

  • Developed MSformer, a transformer-based architecture utilizing molecule fragments (meta-structures) for NP encoding.
  • Generated 234 million meta-structures by fragmenting 400,000 NPs using a mass spectrometry-inspired algorithm.
  • Pretrained MSformer exclusively on this limited NP dataset, unlike models trained on broad chemical databases.

Main Results:

  • MSformer demonstrated superior performance on 14 tasks across MoleculeNet and Therapeutics Data Commons datasets, outperforming state-of-the-art models.
  • The model exhibited excellent generalizability in predicting NP properties.
  • Hierarchical interpretability revealed task-specific structural determinants and enabled deconstruction of approved drugs into bioactive fragments.

Conclusions:

  • MSformer offers a transformative paradigm for natural product-based drug discovery by integrating domain knowledge and deep learning.
  • The model provides a scalable framework for exploring nature's chemical repertoire and identifying bioactive candidates.
  • This approach addresses the critical data scarcity and structural complexity challenges in AI-driven NP drug discovery.