Article

SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning

2020-05-21

Abstract excerpt

SMILES-based deep learning models are slowly emerging as an important research topic in cheminformatics. In this study, we introduce SMILES Pair Encoding (SPE), a data-driven tokenization algorithm. SPE first learns a vocabulary of high frequency SMILES substrings from a large chemical dataset (e.g., ChEMBL) and then tokenizes SMILES based on the learned vocabulary for deep learning models. As a result, SPE a...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: e67bdac6-eb09-5ff7-a49a-e85d06684039
DOI: 10.26434/chemrxiv.12339368.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep LearningDOI 10.26434/chemrxiv.12339368.v1Read

Deep Molecular Generative Model Based on Variant Transformer for Antiviral Drug DesignSemantic proximity Read

ChemBERTaDDI: Transformer Driven Molecular Structures and Clinical Data for predicting drug-drug interactionsSemantic proximity Read

Human-Readable SMILES: Translating Cheminformatics to ChemistrySemantic proximity Read

STOUT: SMILES to IUPAC Names Using Neural Machine TranslationSemantic proximity Read

Predicting Enzymatic Reactions with a Molecular TransformerSemantic proximity Read

Integrating Coverage-Attention Mechanisms for Improved Chemical Image RecognitionSemantic proximity Read

Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical RepresentationsSemantic proximity Read

PepSeek: Universal Functional Peptide Discovery with Cooperation Between Specialized Deep Learning Models and Large Language ModelSemantic proximity Read

PanGu Drug Model: Learn a Molecule Like a HumanSemantic proximity Read

METAGENE-1: Metagenomic Foundation Model for Pandemic MonitoringSemantic proximity Read

Toward Learned Chemical Perception of Force Field Typing RulesSemantic proximity Read

Pool PaRTI: A PageRank-Based Pooling Method for Identifying Critical Residues and Enhancing Protein Sequence RepresentationsSemantic proximity Read