Fragment Graphical Variational AutoEncoding for Screening Molecules with Small Data
This work addresses the challenge of screening molecules in domains like organic semiconductors where big datasets are unavailable, offering a method for small-data regimes, though it is incremental as it builds on existing autoencoder and fingerprint techniques.
The paper tackled the problem of molecular optimization with limited experimental data by using a fragment-based graphical autoencoder to generate structural fingerprints, reducing prediction error for physical characteristics like solubility and partition coefficient and accurately predicting 92% of test molecules in a real-world task with only 69 training examples.
In the majority of molecular optimization tasks, predictive machine learning (ML) models are limited due to the unavailability and cost of generating big experimental datasets on the specific task. To circumvent this limitation, ML models are trained on big theoretical datasets or experimental indicators of molecular suitability that are either publicly available or inexpensive to acquire. These approaches produce a set of candidate molecules which have to be ranked using limited experimental data or expert knowledge. Under the assumption that structure is related to functionality, here we use a molecular fragment-based graphical autoencoder to generate unique structural fingerprints to efficiently search through the candidate set. We demonstrate that fragment-based graphical autoencoding reduces the error in predicting physical characteristics such as the solubility and partition coefficient in the small data regime compared to other extended circular fingerprints and string based approaches. We further demonstrate that this approach is capable of providing insight into real world molecular optimization problems, such as searching for stabilization additives in organic semiconductors by accurately predicting 92% of test molecules given 69 training examples. This task is a model example of black box molecular optimization as there is minimal theoretical and experimental knowledge to accurately predict the suitability of the additives.