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.

Leveraging Implicit Knowledge in Neural Networks for Functional Dissection and Engineering of Proteins Weights for DeeProtein in four replicates with different random initializations. Please refer to the GitHub repository for further information: https://github.com/juzb/DeeProtein