The reason for such a significant decrease in the accuracy lies in that the dataset employed in this study comprises relatively large organic molecules with molecular weights ranging from 200 to 500 amu.
While the above GPCR ligand dataset was based on rather diverse ligands, the NNRTI dataset employed in this study covers a more neatly defined area of both chemical (ligand) space as well as biological (target) space and hence we also included the set.
The mass spectrometry datasets employed in this proteogenomic annotation study have been previously described, detailing the annotated Salmonella Typhimurium proteome response to the above growth conditions [ 21, 23, 24].
This section describes the datasets employed in this manuscript for demonstrating the utility of REDHORSE.
Two sets of datasets were employed in this study.
The evaluation of multiple datasets as employed in this study has been shown to yield more reliable and valid results, because they are based on large sample numbers and the individual bias caused by each study is weakened [30].
Two datasets were employed in this study, both of which have been described in detail elsewhere [ 14, 15].
There were two datasets employed in our study.
The values of accuracy (Acc), specificity (Sp), sensitivity (Sn), and Matthew's correlation efficients (MCC) are obtained from Chen et al. [ 23] as the exact same independent dataset was employed in this study.
