Leveraging Implicit Knowledge in Neural Networks for Functional Dissection and Engineering of Proteins 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. The files are tab-separated and contain the following columns: Pos Position in the sequence, starting from zero AA Amino acid in that position sec Secondary structure as annotated in the RCSB Protein Databank dis if a region has not been experimentally observed (sometimes explains mismatches with crystal structures) GO:_______ Sensitivity for the GO term References 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. & 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).

Authorship Statement The following are members of the iGEM (international genetically engineered machines) Team Heidelberg 2017: Lukas Adam, Thore Bürgel, Roland Eils, Catharina Gandor, Daniel Heid, Mareike Daniela Hoffmann, Stefan Holderbach, Michael Jendrusch, Marita Klein, Irina Lehmann, Jan Mathony, Dominik Niopek, Pauline Pfuderer, Lukas Platz, Moritz Przybilla, Carolin Schmelas, Max Schwendemann, Julius Upmeier zu Belzen, Max Waldhauer (all from Germany). Acknowledgements This work was funded by the Klaus-Tschira foundation, the German Research Council (DFG) and the Federal Ministry of Education and Research (BMBF). We thank Jürgen Quittek and Matthias Niepert (both NEC, Heidelberg), Thomas Wollmann (IPMB, BioQuant and German Cancer Research Center (DKFZ), Heidelberg) for helpful discussions and Marc Hemberger (BioQuant, Heidelberg) for support with IT and GPU cluster use.

{"references": ["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. & 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)."]}