ArticleNature communications2024
Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 17 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
17 citing papers in PubMed.
- Scalable molecular representations enabled by multimodal fusion and sequence distillation.Nature communications · 2026Article
- Chalcogen-bonding-mediated chiral recognition and enantioenrichment of organoselenocyanates.Chemical science · 2026Article
- From Algorithms to Assets: A Comprehensive Review of AI's Role in Preclinical Drug Discovery and the Hurdles to Clinical Translation.Pharmaceuticals (Basel, Switzerland) · 2026Review
- Atom-level machine learning of protein-glycan interactions and cross-chiral recognition in glycobiology.Science advances · 2025Article
- Enhancing deep chemical reaction prediction with advanced chirality and fragment representation.Chemical communications (Cambridge, England) · 2025Article
- ProtoMol: enhancing molecular property prediction via prototype-guided multimodal learning.Briefings in bioinformatics · 2025Article
- Unified and explainable molecular representation learning for imperfectly annotated data from the hypergraph view.Nature communications · 2025Article
- Leveraging scenario differences for cross-task generalization in water plant transfer machine learning models.Environmental science and ecotechnology · 2025Article
- Evaluation of chirality descriptors derived from SMILES heteroencoders.Journal of cheminformatics · 2025Article
- Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning.Communications chemistry · 2025Article
- fragSMILES as a chemical string notation for advanced fragment and chirality representation.Communications chemistry · 2025Article
- Artificial intelligence in drug development.Nature medicine · 2025Review
- Mothra: MultiobjectiveJournal of chemical information and modeling · 2024Article
- Artificial intelligence-based prediction of pathogen emergence and evolution in the world of synthetic biology.Microbial biotechnology · 2024Review
- Exploring Molecular Heteroencoders with Latent Space Arithmetic: Atomic Descriptors and Molecular Operators.Molecules (Basel, Switzerland) · 2024Article
- NIMO: A Natural Product-Inspired Molecular Generative Model Based on Conditional Transformer.Molecules (Basel, Switzerland) · 2024Article
- Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations.Nature communications · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
Abstract
Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language processing (NLP) models to SMILES, a literal representation of molecular structure. However, little research has been done on how these models understand chemical structure. To address this black box, we investigated the relationship between the learning progress of SMILES and chemical structure using a representative NLP model, the Transformer. We show that while the Transformer learns partial structures of molecules quickly, it requires extended training to understand overall structures. Consistently, the accuracy of molecular property predictions using descriptors generated from models at different learning steps was similar from the beginning to the end of training. Furthermore, we found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers. These findings are expected to deepen the understanding of NLP models in chemistry.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.