Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis

Most chemical experiments are planned by human scientists and therefore are subject to a variety of human cognitive biases1, heuristics2 and social influences3. These anthropogenic chemical reaction data are widely used to train machine-learning models4 that are used to predict organic5 and inorganic6,7 syntheses. However, it is known that societal biases are encoded in datasets and are perpetuated in machine-learning models8. Here we identify as-yet-unacknowledged anthropogenic biases in both the reagent choices and reaction conditions of chemical reaction datasets using a combination of data mining and experiments. We find that the amine choices in the reported crystal structures of hydrothermal synthesis of amine-templated metal oxides9 follow a power-law distribution in which 17% of amine reactants occur in 79% of reported compounds, consistent with distributions in social influence models10–12. An analysis of unpublished historical laboratory notebook records shows similarly biased distributions of reaction condition choices. By performing 548 randomly generated experiments, we demonstrate that the popularity of reactants or the choices of reaction conditions are uncorrelated to the success of the reaction. We show that randomly generated experiments better illustrate the range of parameter choices that are compatible with crystal formation. Machine-learning models that we train on a smaller randomized reaction dataset outperform models trained on larger human-selected reaction datasets, demonstrating the importance of identifying and addressing anthropogenic biases in scientific data. Human scientists make unrepresentative chemical reagent and reaction condition choices, and machine-learning algorithms trained on human-selected experiments are less capable of successfully predicting reaction outcomes than those trained on randomly generated experiments.