Chemical Property Prediction Under Experimental Biases
This work addresses bias in chemical property prediction for drug and material discovery, but it is incremental as it applies existing causal methods to a specific domain.
The study tackled the problem of biased chemical property prediction datasets by mitigating experimental biases using causal inference techniques combined with graph neural networks, resulting in solid improvements in four bias scenarios.
Predicting the chemical properties of compounds is crucial in discovering novel materials and drugs with specific desired characteristics. Recent significant advances in machine learning technologies have enabled automatic predictive modeling from past experimental data reported in the literature. However, these datasets are often biased because of various reasons, such as experimental plans and publication decisions, and the prediction models trained using such biased datasets often suffer from over-fitting to the biased distributions and perform poorly on subsequent uses. Hence, this study focused on mitigating bias in the experimental datasets. We adopted two techniques from causal inference combined with graph neural networks that can represent molecular structures. The experimental results in four possible bias scenarios indicated that the inverse propensity scoring-based method and the counter-factual regression-based method made solid improvements.