Article
作者: Storici, Paola ; Knecht, Wolfgang ; Kemp, Ben ; Mitchell, Carter ; Schiavone, Lovisa Holmberg ; Cuesta, Sergio Martinez ; Berrow, Nicholas S ; Marinchev Dobrev, Nikolay ; Danieli, Tsafi ; Ferreira-da-Silva, Frederico ; Vaněk, Ondřej ; Alblová, Miroslava ; Thies, Jelena ; Cooper, Christopher D O ; Petres, Stéphane ; Coker, Jesse ; Oyarzún, Diego A ; de Marco, Ario ; Todd, Matthew H ; Voldborg, Bjørn ; Schütz, Anja ; Bamber, Lisa ; Kim, Robbert ; Tegel, Hanna ; Harborne, Steven ; Krupinska, Ewa ; Jones, David ; Edwards, Aled M ; Celie, Patrick ; Leach, Andrew R ; van den Heuvel, Joop ; Owen, Dafydd R ; Harding, Rachel J ; El Marjou, Ahmed ; Sarkans, Ugis ; Bäckström, Malin ; Craig, Timothy ; Elvin, Mark ; Tankhilevich, Evgeny ; Owens, Ray ; Basquin, Jerome ; Pasqualato, Sebastiano ; Altman, Richard ; Gileadi, Opher ; Pelosse, Martin ; Unger, Tamar ; Dossang, Pam ; Suppmann, Sabine ; Berger, Imre ; Kuttenlochner, Wolfgang ; Carolis, Carlo ; Love, James ; Hunt, Ian ; Wickstrand, Cecilia ; Burgess-Brown, Nicola A ; Zemella, Anne ; Dürr, Katharina L ; Schubert, Maren ; Buyel, Johannes ; Meijers, Rob ; Quigley, Andrew ; Brodsky, Oleg ; Dohnálek, Jan ; Hedfalk, Kristina ; Haustraete, Jurgen ; Wan, Paul ; Sivertsson, Åsa ; Bozovicar, Kristof ; Scietti, Luigi Angelo ; Peleg, Yoav ; Vincentelli, Renaud ; Borgonovo, Barbara ; Schapira, Matthieu ; Drechsel, David ; Davies, Rick ; Velankar, Sameer ; Saxl, Ruth ; Bernhard, Frank ; Kjaer, Svend ; Lau, Kelvin ; Liu, Lihua ; Loppnau, Peter A ; Remans, Kim ; Geertsma, Eric R ; Esposito, Dominic ; Witt, Susanne
As machine learning (ML) becomes increasingly important in protein engineering, synthetic biology, and bioprocess optimization, the lack of consistent, complete, and standardized experimental reporting remains a major barrier to building effective models. EXPERT (EXpression and Purification Experimental Reporting Template) defines a structured framework for capturing protein expression and purification data across the community, to increase reproducibility across laboratories and support downstream ML applications. We propose here the essential data that should be recorded during expression and purification workflows by both novice and experienced protein production scientists. These recommendations are informed by expert contributions from across academia and industry. The reporting requirements were distilled to a focused set of parameters deemed sufficient for workflow reproducibility and constructing robust ML models aimed at improving protein production. By deploying these guidelines, we hope to enable the collection of larger data sets to support future model building.