The datasets are extracted from 203 protein-nucleic acid complexes. We have compiled a binding affinity dataset(displayed in the Supplementary_Table) along with the experimental conditions(temperature), the experimental values of ΔG and Kd. The datasets used in PNAB are available for download: SupplementaryTable1.xls In this work, we selected 28 typical numerical features commonly used for the interactions of protein and nucleic acid in the database AAindex[1] to encode amino acids. The list of AAindex physicochemical properties we used can be found in SupplementaryTable2.xls.
References [1] S. Kawashima and M. Kanehisa, “Aaindex: amino acid index database,” Nucleic acids research, vol. 28, no. 1, pp. 374–374, 2000.
