mlsanityData to 14 Oct 2026

SELFIES and the future of molecular string representations

arXiv 2204.00056 ↗First posted 31 Mar 2022physics.chem-ph cs.LGcited by 76

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, SMILES, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, SMILES has several shortcomings -- most pertinently, most combinations of symbols lead to invalid results with no valid chemical interpretation. To overcome this issue, a new language for molecules was introduced in 2020 that guarantees 100% robustness: SELFIES (SELF-referencIng Embedded Strings). SELFIES has since simplified and enabled numerous new applications in chemistry. In this manuscript, we look to the future and discuss molecular string representations, along with their respective opportunities and challenges. We propose 16 concrete Future Projects for robust molecular representations. These involve the extension toward new chemical domains, exciting questions at the interface of AI and robust languages and interpretability for both humans and machines. We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 30 of its 188 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

30 of 188 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  4. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  5. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  6. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 344
  7. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
  8. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 275
  9. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  10. 2018Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Predictioncited by 229
  11. 2020Machine Learning Force Fieldscited by 207
  12. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
18 more
  1. 2017Learning to Plan Chemical Synthesescited by 179
  2. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  3. 2018Discovering physical concepts with neural networkscited by 117
  4. 2017Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Networkcited by 103
  5. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  6. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  7. 2019Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Spacecited by 66
  8. 2020Guiding Deep Molecular Optimization with Genetic Explorationcited by 51
  9. 2021JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Designcited by 32
  10. 2018CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networkscited by 31
  11. 2020Machine learning for electronically excited states of moleculescited by 30
  12. 2020Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representationscited by 20
  13. 2020Big-Data Science in Porous Materials: Materials Genomics and Machine Learningcited by 19
  14. 2020Computer-inspired Quantum Experimentscited by 18
  15. 2020Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learningcited by 16
  16. 2021Inverse design of two-dimensional materials with invertible neural networkscited by 15
  17. 2021Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Modelscited by 12
  18. 2022FastFlows: Flow-Based Models for Molecular Graph Generationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 17; 2024: 20; 2025: 22; 2026: 14.

76 papers.

Sort:

By area:

  1. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  2. 2022Graph neural networks for materials science and chemistrycited by 182
  3. 2022Large Language Models Meet NL2Code: A Surveycited by 138
  4. 2023Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Modelscited by 133
  5. 2023BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associationscited by 100
  6. 202314 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathoncited by 86
  7. 2023Gotta be SAFE: A New Framework for Molecular Designcited by 48
  8. 2025El Agente: An Autonomous Agent for Quantum Chemistrycited by 44
  9. 2023SELFormer: Molecular Representation Learning via SELFIES Language Modelscited by 40
  10. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  11. 2023Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPTcited by 30
  12. 2023nach0: Multimodal Natural and Chemical Languages Foundation Modelcited by 26
38 more
  1. 2024Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generationcited by 25
  2. 2023MolGrapher: Graph-based Visual Recognition of Chemical Structurescited by 24
  3. 2023Domain-Agnostic Molecular Generation with Chemical Feedbackcited by 22
  4. 2023Searching for High-Value Molecules Using Reinforcement Learning and Transformerscited by 18
  5. 2024SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Taskscited by 18
  6. 2024Saturn: Sample-efficient Generative Molecular Design using Memory Manipulationcited by 15
  7. 2023t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generationcited by 14
  8. 2023Classifier-free graph diffusion for molecular property targetingcited by 14
  9. 2023Transformers and Large Language Models for Chemistry and Drug Discoverycited by 13
  10. 2024BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learningcited by 12
  11. 2025MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMscited by 12
  12. 2024Less can be more for predicting properties with large language modelscited by 11
  13. 20243D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modelingcited by 9
  14. 2025ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Modelscited by 9
  15. 2023Recent advances in the Self-Referencing Embedding Strings (SELFIES) librarycited by 8
  16. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  17. 2024Transformers for molecular property prediction: Lessons learned from the past five yearscited by 8
  18. 2024Learning Molecular Representation in a Cellcited by 8
  19. 2024Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generationcited by 7
  20. 2025TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Taskscited by 6
  21. 2024Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Modelcited by 5
  22. 2025MolVision: Molecular Property Prediction with Vision Language Modelscited by 5
  23. 2026El Agente Estructural: An Artificially Intelligent Molecular Editorcited by 5
  24. 2025RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literaturecited by 4
  25. 2026MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimizationcited by 4
  26. 2024FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interactioncited by 3
  27. 2024Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Treescited by 3
  28. 2025Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworkscited by 3
  29. 2026Polymer-Agent: Large Language Model Agent for Polymer Designcited by 3
  30. 2022ParticleGrid: Enabling Deep Learning using 3D Representation of Materialscited by 2
  31. 2023Predicting small molecules solubilities on endpoint devices using deep ensemble neural networkscited by 2
  32. 2024SAFE setup for generative molecular designcited by 2
  33. 2025A Reinforcement Learning-Driven Transformer GAN for Molecular Generationcited by 2
  34. 2026Learning Molecular Chirality via Chiral Determinant Kernelscited by 2
  35. 2023Synergistic Fusion of Graph and Transformer Features for Enhanced Molecular Property Predictioncited by 1
  36. 2024Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representationcited by 1
  37. 2024Quantum Computing-Enhanced Algorithm Unveils Novel Inhibitors for KRAScited by 1
  38. 2024Polyatomic Complexes: A topologically-informed learning representation for atomistic systemscited by 1

50 most cited of 76 All 76 (JSON)