Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

Inspired by natural language processing techniques, we here introduce Mol2vec, which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Like the Word2vec models, where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that point in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing the vectors of the individual substructures and, for instance, be fed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pretrained once, yields dense vector representations, and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as a reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment-independent and thus can also be easily used for proteins with low sequence similarities.