Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

By Sabrina Jaeger, Simone Fulle, Samo Turk. 2018

650 citations recorded by the source corpus.

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.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Representation & Self-Supervised Learning, Computational Chemistry & Drug Discovery

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

1. Marinka Zitnik
2. Jure Leskovec
3. Bowen Liu
4. Weihua Hu
5. Joseph Gomes
6. Percy Liang
7. Heng Ji
8. Tuan Manh Lai

In Materials Chemistry

1. Jure Leskovec
2. Marinka Zitnik
3. Bowen Liu
4. Weihua Hu
5. Joseph Gomes
6. Percy Liang
7. Vijay S. Pande
8. Heng Ji

In Molecular Biology

1. Marinka Zitnik
2. Jure Leskovec
3. Weihua Hu
4. Bowen Liu
5. Percy Liang
6. Joseph Gomes
7. Vijay S. Pande
8. Heng Ji

In Representation & Self-Supervised Learning

1. Marinka Zitnik
2. Jure Leskovec
3. Weihua Hu
4. Bowen Liu
5. Percy Liang
6. Vijay S. Pande
7. Joseph Gomes
8. Heng Ji

In Computational Chemistry & Drug Discovery

1. Jure Leskovec
2. Bowen Liu
3. Joseph Gomes
4. Marinka Zitnik
5. Weihua Hu
6. Percy Liang
7. Vijay S. Pande
8. Heng Ji

Citations in the corpus

• Strategies for Pre-training Graph Neural Networks (2019, background): “A number of recent works have also explored how node embeddings generalize across tasks (Jaeger et al., 2018; Zhou et al., 2018; Chakravarti, 2018; Narayanan et al., 2016).”
• Deep learning improves prediction of drug–drug and drug–food interactions (2018, methodology): “Also, SSP showed a slightly greater mean accuracy than feature vectors generated by two state-of-the-art vectorization methods, namely Molecular Autoencoder (19) and Mol2vec (20), when used with the DeepDDI framework ( SI Appendix , Fig.”
• Translation between Molecules and Natural Language (2022, methodology): “Jaeger et al. (2018) use the Morgan fin-gerprinting algorithm to convert each molecule into a ‘sentence’ of its substructures, to which it applies the Word2vec algorithm (Mikolov et al., 2013a,b).”
• Pre-training Graph Neural Networks (2019, background): “It should be noted that similar intuition has been explored in the literature [32, 19, 63].”