# Learning to SMILE(S)

arXiv: https://arxiv.org/abs/1602.06289 · HTML: https://mlsanity.com/paper/1602.06289/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2016.

## Built on by (most cited first, 8 of 8)

- [Molecular Contrastive Learning with Chemical Element Knowledge Graph](https://mlsanity.com/paper/2112.00544/) (2021)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [Relative Molecule Self-Attention Transformer](https://mlsanity.com/paper/2110.05841/) (2021)
- [Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences](https://mlsanity.com/paper/2411.04165/) (2024)
- [Large Knowledge Model: Perspectives and Challenges](https://mlsanity.com/paper/2312.02706/) (2023)
- [3D-Mol: A Novel Contrastive Learning Framework for Molecular Property Prediction with 3D Information](https://mlsanity.com/paper/2309.17366/) (2023)
- [Knowledge-informed Molecular Learning: A Survey on Paradigm Transfer](https://mlsanity.com/paper/2202.10587/) (2022)
- [Pretraining a Foundation Model for Small-Molecule Natural Products](https://mlsanity.com/paper/2503.17656/) (2025)

## Abstract (arXiv)

This paper shows how one can directly apply natural language processing (NLP) methods to classification problems in cheminformatics. Connection between these seemingly separate fields is shown by considering standard textual representation of compound, SMILES. The problem of activity prediction against a target protein is considered, which is a crucial part of computer aided drug design process. Conducted experiments show that this way one can not only outrank state of the art results of hand crafted representations but also gets direct structural insights into the way decisions are made.