The dataset and experimental and predicted amenability calls are provided in the supplemental file “Supplemental_ToxCast_PhaseII.xlsx”.

PaDEL descriptors were generated for each candidate and amenability predictions were calculated using both ESI+ and ESI- downsampled models. The resulting dataset is available in the supplemental file “Supplemental_Application.xlsx”. It should be noted that the dataset used in this demonstration is biased toward environmentally relevant chemicals, many of which appear in a large number of chemical lists on the Dashboard (see the DATA_SOURCES column in “Supplemental_Application.xlsx” for both ESI+ and ESI-).

Training and test datasets were constructed using the PaDEL descriptors and the ESI+ and ESI- endpoint values discussed previously. These training and test sets are provided in the supplemental file “Supplemental_train_test.xlsx”.

A list of descriptors is provided in the supplemental file “Supplemental_Descriptors.xlsx”.

A similar plot (Figure S1) of variable importance for the ESI+ upsampled model, and a similar plot (Figure S2) of variable importance for the ESI- upsampled model can be found in “Supplemental_Figures.docx”.

This dataset is associated with the following publication: Lowe, C., K. Isaacs, A. McEachran, C. Grulke, J. Sobus, E. Ulrich, A. Richard, A. Chao, J. Wambaugh, and A. Williams. Predicting compound amenability with liquid chromatography-mass spectrometry to improve non-targeted analysis. Analytical and Bioanalytical Chemistry. Springer, New York, NY, USA, 413(30): 7495-7508, (2021).