Chemical data management: an open way forward

(Image: Pixabay CC0) - Writing , three scientists propose an open platform for managing the vast amounts of diverse data produced in chemical research. Based on principles of accessibility, collaboration and efficiency, the proposed platform could be spearheaded by EPFL. One of the most challenging aspects of modern chemistry is managing data. For example, when synthesizing a new compound, scientists will go through multiple attempts of trial-and-error to find the right conditions for the reaction, generating in the process massive amounts of raw data. Such data is of incredible value, as, like humans, machine-learning algorithms can learn much from failed and partially successful experiments. The current practice is, however, to publish only the most successful experiments, since no human can meaningfully process the massive amounts of failed ones. But AI has changed this; it is exactly what these machine-learning methods can do provided the data are stored in a machine-actionable format for anyone to use.