Fig. 2: Analysis of the data distribution and composition of PhotoCatDB.
From: An artificial intelligence-driven synthesis planning platform (PhotoCat) for photocatalysis
a Multicomponent reactions comprise 34.46% of the dataset, with three-component and four-component reactions marked in green and blue, respectively. b The dataset displays a skewed distribution, with most data points falling within the lower similarity range (below 0.21). c An example of PhotoCatDB data entry, illustrating the format and structure of the dataset.
