Sensitivity Datasets - Leveraging Implicit Knowledge in Neural Networks for Functional Dissection and Engineering of Proteins

<strong>Leveraging Implicit Knowledge in Neural Networks for Functional Dissection and Engineering of Proteins</strong> The Sensitivity datasets cover more than 800 proteins and are structured as follows. The sensitivity values are the mean of four DeeProtein replicates. It is uploaded as tar.gz. and contains one directory. File names contain the PDB¹ identifier and the respective chain identifier. The sequences and secondary structure information were downloaded from the RCSB Protein Databank and are available here: https://cdn.rcsb.org/etl/kabschSander/ss_dis.txt.gz This URL can be found with some explanation at http://www.rcsb.org/pdb/static.do?p=download/http/index.html The secondary structure annotation relies on the DSSP Algorithm by Kabsch and Sander². <strong>The files are tab-separated and contain the following columns:</strong> <strong>Pos</strong> Position in the sequence, starting from zero <strong>AA</strong> Amino acid in that position <strong>sec</strong> Secondary structure as annotated in the RCSB Protein Databank <strong>dis</strong> if a region has not been experimentally observed (sometimes explains mismatches with crystal structures) <strong>GO:_______</strong> Sensitivity for the GO term <strong>References</strong> The Protein Data Bank H.M. Berman, J. Westbrook, Z. Feng, G. Gilliland, T.N. Bhat, H. Weissig, I.N. Shindyalov, P.E. Bourne (2000) Nucleic Acids Research, 28: 235-242. doi:10.1093/nar/28.1.235 Kabsch, W. &amp; Sander, C. Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 2577-2637, doi:10.1002/bip.360221211 (1983).