Investigation of chemical structure recognition by encoder–decoder models in learning progress

Descriptor generation methods using latent representations of encoder–decoder (ED) models with SMILES as input are useful because of the continuity of descriptor and restorability to the structure. However, it is not clear how the structure is recognized in the learning progress of ED models. In thi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of cheminformatics Jg. 15; H. 1; S. 45 - 9
Hauptverfasser: Nemoto, Shumpei, Mizuno, Tadahaya, Kusuhara, Hiroyuki
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 12.04.2023
BioMed Central Ltd
Springer Nature B.V
BMC
Schlagworte:
Accuracy
Analysis
Chemicals
Chemistry
Chemistry and Materials Science
Coders
Computational Biology/Bioinformatics
Computational linguistics
Computer Applications in Chemistry
Datasets
Descriptor
Documentation and Information in Chemistry
Encoder–decoder model
Investigations
Language processing
Learning
Natural language interfaces
Performance evaluation
Sensitivity analysis
Theoretical and Computational Chemistry
Descriptor
Encoder–decoder model
ISSN:1758-2946, 1758-2946
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Descriptor generation methods using latent representations of encoder–decoder (ED) models with SMILES as input are useful because of the continuity of descriptor and restorability to the structure. However, it is not clear how the structure is recognized in the learning progress of ED models. In this work, we created ED models of various learning progress and investigated the relationship between structural information and learning progress. We showed that compound substructures were learned early in ED models by monitoring the accuracy of downstream tasks and input–output substructure similarity using substructure-based descriptors, which suggests that existing evaluation methods based on the accuracy of downstream tasks may not be sensitive enough to evaluate the performance of ED models with SMILES as descriptor generation methods. On the other hand, we showed that structure restoration was time-consuming, and in particular, insufficient learning led to the estimation of a larger structure than the actual one. It can be inferred that determining the endpoint of the structure is a difficult task for the model. To our knowledge, this is the first study to link the learning progress of SMILES by ED model to chemical structures for a wide range of chemicals. Graphical Abstract
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1758-2946
1758-2946
DOI:10.1186/s13321-023-00713-z