SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties

By Garrett B. Goh, Nathan Oken Hodas, Charles Siegel, Abhinav Vishnu. 2017

166 citations recorded by the source corpus.

Chemical databases store information in text representations, and the SMILES format is a universal standard used in many cheminformatics software. Encoded in each SMILES string is structural information that can be used to predict complex chemical properties. In this work, we develop SMILES2vec, a deep RNN that automatically learns features from SMILES to predict chemical properties, without the need for additional explicit feature engineering. Using Bayesian optimization methods to tune the network architecture, we show that an optimized SMILES2vec model can serve as a general-purpose neural network for predicting distinct chemical properties including toxicity, activity, solubility and solvation energy, while also outperforming contemporary MLP neural networks that uses engineered features. Furthermore, we demonstrate proof-of-concept of interpretability by developing an explanation mask that localizes on the most important characters used in making a prediction. When tested on the solubility dataset, it identified specific parts of a chemical that is consistent with established first-principles knowledge with an accuracy of 88%. Our work demonstrates that neural networks can learn technically accurate chemical concept and provide state-of-the-art accuracy, making interpretable deep neural networks a useful tool of relevance to the chemical industry.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Physical and Theoretical Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Physical and Theoretical Chemistry

Citations in the corpus

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction (2017, methodology): “To ensure that our results are comparable with contemporary DNN models reported in the literature [34] and earlier work on Chemception CNN models [15, 16] and SMILES2vec RNN models [13], we used the Tox21, HIV, and FreeSolv dataset from the MoleculeNet benchmark [34] for predicting toxicity, activit”
Do Large Scale Molecular Language Representations Capture Important Structural Information? (2021, methodology): “Learning on SMILES has been widely adopted for molecular property prediction Goh et al. (2017); Öztürk et al. (2018); Paul et al. (2018); Shin et al. (2019), as SMILES is generally more compact compared to most other methods of representing structure, including graphs.”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, background): “…which predicts the toxicity properties and chemical characteristics features of drug compounds such as SMILES2Vec (predicts chemical properties) [339], Chemception (DNN-based prediction of chemical properties) [245], DeepSynergy (prediction of anti-cancer drug synergy with DL) [340], and…”