Attention-based Multi-Input Deep Learning Architecture for Biological Activity Prediction: An Application in EGFR Inhibitors
This work addresses the challenge of improving prediction accuracy in drug discovery for EGFR inhibitors, representing an incremental advance by integrating multiple data types and attention mechanisms.
The authors tackled the problem of predicting biological activity for EGFR inhibitors by proposing a multi-input deep learning architecture that simultaneously trains on both structural data and chemical properties, achieving a maximum MCC of 0.58 and AUC of 90% in cross-validation, outperforming reference models.
Machine learning and deep learning have gained popularity and achieved immense success in Drug discovery in recent decades. Historically, machine learning and deep learning models were trained on either structural data or chemical properties by separated model. In this study, we proposed an architecture training simultaneously both type of data in order to improve the overall performance. Given the molecular structure in the form of SMILES notation and their label, we generated the SMILES-based feature matrix and molecular descriptors. These data were trained on a deep learning model which was also integrated with the Attention mechanism to facilitate training and interpreting. Experiments showed that our model could raise the performance of prediction comparing to the reference. With the maximum MCC 0.58 and AUC 90% by cross-validation on EGFR inhibitors dataset, our architecture was outperforming the referring model. We also successfully integrated Attention mechanism into our model, which helped to interpret the contribution of chemical structures on bioactivity.