SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
This work addresses the need for interpretable and accurate chemical property prediction for the chemical industry, though it is incremental as it builds on existing deep learning methods for SMILES data.
The authors tackled the problem of predicting chemical properties from SMILES strings by developing SMILES2vec, a deep RNN that automatically learns features without explicit engineering, and showed it outperforms MLP neural networks with engineered features across multiple properties like toxicity and solubility, achieving 88% accuracy in interpretability tests.
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.