Translating the InChI: adapting neural machine translation to predict IUPAC names from a chemical identifier

We present a sequence-to-sequence machine learning model for predicting the IUPAC name of a chemical from its standard International Chemical Identifier (InChI). The model uses two stacks of transformers in an encoder-decoder architecture, a setup similar to the neural networks used in state-of-the-art machine translation. Unlike neural machine translation, which usually tokenizes input and output into words or sub-words, our model processes the InChI and predicts the IUPAC name character by character. The model was trained on a dataset of 10 million InChI/IUPAC name pairs freely downloaded from the National Library of Medicine's online PubChem service. Training took seven days on a Tesla K80 GPU, and the model achieved a test set accuracy of 91%. The model performed particularly well on organics, with the exception of macrocycles, and was comparable to commercial IUPAC name generation software. The predictions were less accurate for inorganic and organometallic compounds. This can be explained by inherent limitations of standard InChI for representing inorganics, as well as low coverage in the training data.