Size doesn't matter: predicting physico- or biochemical properties based on dozens of molecules
This work addresses data scarcity in chemistry for researchers, but it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of limited data in machine learning for chemistry by applying transfer learning with graph convolutional neural networks to small organic molecules, resulting in significant performance improvements for target properties with scarce data.
The use of machine learning in chemistry has become a common practice. At the same time, despite the success of modern machine learning methods, the lack of data limits their use. Using a transfer learning methodology can help solve this problem. This methodology assumes that a model built on a sufficient amount of data captures general features of the chemical compound structure on which it was trained and that the further reuse of these features on a dataset with a lack of data will greatly improve the quality of the new model. In this paper, we develop this approach for small organic molecules, implementing transfer learning with graph convolutional neural networks. The paper shows a significant improvement in the performance of models for target properties with a lack of data. The effects of the dataset composition on model quality and the applicability domain of the resulting models are also considered.