Pre-training Transformers for Molecular Property Prediction Using Reaction Prediction
This work addresses data scarcity in molecular property prediction for drug discovery, but it is incremental as it applies existing pre-training methods to a new domain.
The authors tackled the problem of limited molecular property data by pre-training a SMILES Transformer using reaction data, and found that this approach led to statistically significant improvements on 5 out of 12 tasks compared to a non-pre-trained baseline.
Molecular property prediction is essential in chemistry, especially for drug discovery applications. However, available molecular property data is often limited, encouraging the transfer of information from related data. Transfer learning has had a tremendous impact in fields like Computer Vision and Natural Language Processing signaling for its potential in molecular property prediction. We present a pre-training procedure for molecular representation learning using reaction data and use it to pre-train a SMILES Transformer. We fine-tune and evaluate the pre-trained model on 12 molecular property prediction tasks from MoleculeNet within physical chemistry, biophysics, and physiology and show a statistically significant positive effect on 5 of the 12 tasks compared to a non-pre-trained baseline model.