mlsanityData to 7 Oct 2026

Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention

arXiv 2103.00213 ↗First posted 27 Feb 2021cs.LG physics.chem-phcited by 20

Not on the map. Why?

Abstract (arXiv)

Discovering new materials better suited to specific purposes is an important issue in improving the quality of human life. Here, a neural network that creates molecules that meet some desired conditions based on a deep understanding of chemical language is proposed (Generative Chemical Transformer, GCT). The attention mechanism in GCT allows a deeper understanding of molecular structures beyond the limitations of chemical language itself which cause semantic discontinuity by paying attention to characters sparsely. It is investigated that the significance of language models for inverse molecular design problems by quantitatively evaluating the quality of the generated molecules. GCT generates highly realistic chemical strings that satisfy both chemical and linguistic grammar rules. Molecules parsed from generated strings simultaneously satisfy the multiple target properties and vary for a single condition set. These advances will contribute to improving the quality of human life by accelerating the process of desired material discovery.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 17 of its 47 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

17 of 47 references.

References · 17

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2020On Layer Normalization in the Transformer Architecturecited by 906
  5. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  6. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  7. 2015Generating Sentences from a Continuous Spacecited by 607
  8. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  9. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  10. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  11. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 191
  12. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
5 more
  1. 2017Learning to Plan Chemical Synthesescited by 175
  2. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
  3. 2019Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Spacecited by 66
  4. 2017ChemTS: An Efficient Python Library for de novo Molecular Generationcited by 32
  5. 2017Application of generative autoencoder in de novo molecular designcited by 32

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 4; 2024: 7; 2025: 2.

20 papers.

Sort:

By area:

  1. 2023Emergent autonomous scientific research capabilities of large language modelscited by 127
  2. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 94
  3. 2024Scientific Large Language Models: A Survey on Biological & Chemical Domainscited by 80
  4. 2022A smile is all you need: Predicting limiting activity coefficients from SMILES with natural language processingcited by 19
  5. 2024SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Taskscited by 17
  6. 2022SPT-NRTL: A physics-guided machine learning model to predict thermodynamically consistent activity coefficientscited by 11
  7. 2022Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materialscited by 8
  8. 2023ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generationcited by 8
  9. 2023Difficulty in chirality recognition for Transformer architectures learning chemical structures from stringcited by 7
  10. 2023LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Designcited by 6
  11. 2024A novel molecule generative model of VAE combined with Transformer for unseen structure generationcited by 4
  12. 2024A Large Language Model-based multi-agent manufacturing system for intelligent shopfloorcited by 4
8 more
  1. 2022Investigation of a Data Split Strategy Involving the Time Axis in Adverse Event Prediction Using Machine Learningcited by 3
  2. 2022Materials Transformers Language Models for Generative Materials Design: a benchmark studycited by 1
  3. 2022Investigation of chemical structure recognition by encoder-decoder models in learning progresscited by 0
  4. 2022Scaffold-Based Multi-Objective Drug Candidate Optimizationcited by 0
  5. 2024CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liabilitycited by 0
  6. 2024Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletabilitycited by 0
  7. 2025The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?cited by 0
  8. 2025ChemFixer: Correcting Invalid Molecules to Unlock Previously Unseen Chemical Spacecited by 0