Peer-reviewedCC BY 4.0The Journal of Biological Chemistry
EXPERT: A practical and forward-looking guide to capturing protein expression and purification metadata to develop machine learning models
40 affiliations
- 1School of Biosciences, Faculty of Health and Medical Sciences, University of Surrey, Guildford, United Kingdom
- 2European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Hinxton, United Kingdom
- 3European Molecular Biology Laboratory, Protein Expression and Purification Core Facility, Heidelberg, Germany
- 4Institut Curie, CurieCoreTech, PSL University, Recombinant Proteins Core Facility, CNRS, Paris, France
- 5Structural Genomics Consortium, University of Toronto and University Health Network, Toronto, Ontario, Canada
- 6Membrane Protein Laboratory, Research Complex at Harwell, Diamond Light Source, Didcot, United Kingdom
- 7Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Technology Platform for Protein Production & Characterization, Berlin, Germany
- 8Fraunhofer Institute for Cell Therapy and Immunology, Branch Bioanalytics and Bioprocesses (IZI-BB), Potsdam, Germany
- 9Laboratory of Environmental and Life Science, University of Nova Gorica, Nova Gorica, Slovenia
- 10Department of Protein Science, SciLifeLab, KTH-Royal Institute of Technology, Stockholm, Sweden
- 11Max Planck Institute of Molecular Cell Biology and Genetics, Protein Biochemistry facility, Dresden, Germany
- 12Biomodal, Chesterford Research Park, Cambridge, United Kingdom
- 13Department of Biotechnology and Biomedicine, Technical University of Denmark, Lyngby, Denmark
- 14Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Spain
- 15Kemp Proteins, LLC, Frederick, Maryland, USA
- 16Mammalian Protein Expression Core Facility and Protein Production Sweden, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- 17Pfizer Research and Development, Cambridge, USA
- 18Vienna BioCenter Core Facilities GmbH, Vienna, Austria
- 19University College London, Department of Computer Science and Department of Structural and Molecular Biology, London, United Kingdom
- 20Generative Biology Institute, Ellison Institute of Technology Oxford, The Oxford Science Park, Oxford, United Kingdom
- 21School of Informatics, The University of Edinburgh, Edinburgh, United Kingdom
- 22School of Biological Sciences, The University of Edinburgh, Edinburgh, United Kingdom
- 23Septerna, South San Francisco, USA
- 24Lund Protein Production Platform & Protein Production Sweden & Science for Life Laboratory, Lund University, Lund, Sweden
- 25Institute of Biophysical Chemistry, Goethe-University Frankfurt, Frankfurt/Main, Germany
- 26i3s - Instituto de Investigação e Inovação em Saúde, Universidade do Porto, Porto, Portugal
- 27IBMC - Instituto de Biologia Molecular e Celular, Universidade do Porto, Porto, Portugal
- 28Novartis, Biomedical Research, Cambridge, Massachusetts, USA
- 29Max Planck-Bristol Centre for Minimal Biology, Schools of Chemistry and Biochemistry, University of Bristol, Bristol, United Kingdom
- 30Lila Sciences, Cambridge, USA
- 31Institute of Biotechnology of the Czech Academy of Sciences, Laboratory of Structure and Function of Biomolecules, Vestec, Czech Republic
- 32School of Pharmacy and Structural Genomics Consortium, UCL, London, United Kingdom
- 33Max Planck Institute of Biochemistry, Protein Production and Structural Validation Facility, Martinsried, Germany
- 34Cleveland Clinic Center for Therapeutics Discovery, Cleveland Clinic Research, Cleveland, USA
- 35BOKU University, Department of Biotechnology and Food Science (BTLW), Institute of Bioprocess Science and Engineering (IBSE), Vienna, Austria
- 36Helmholtz Centre for Infection Research, Department of Molecular Structural Biology (MOSB), Braunschweig, Germany
- 37VIB Protein Core, VIB Technologies, VIB, Ghent, Belgium
- 38Department of Biomedical Molecular Biology, Ghent University, Ghent, Belgium
- 39Department of Chemistry, Kavli Institute of Nanoscience Discovery, University of Oxford, Oxford, United Kingdom
- 40Protein Production and Structure Characterization Core Facility (PTPSP), School of Life Sciences, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
Abstract
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.
Related
- Optimized Expression and Purification of Outer Membrane Protein 25 (Omp25) of Brucella melitensis
- An efficient system for production of highly purified inhibins using mammalian cell expression and tandem affinity purification
- Cloning, expression, and purification of small subunit human ribosomal proteins SA/uS2, S2/uS5, S3/uS3, S7/eS7, S8/eS8, S12/eS12, S13/uS15, and S14/uS11 for in vitro characterization.
- Expression and Purification of Recombinant Duck Ovalbumin in Escherichia coli
- High-yield expression and purification of the non-phosphorylated form of Human CaMKIIα Kinase
BibTeX
@article{cooper2026expert,
title = {{EXPERT: A practical and forward-looking guide to capturing protein expression and purification metadata to develop machine learning models}},
author = {Christopher D.O. Cooper and Evgeny Tankhilevich and Kim Remans and Ahmed El Marjou and Aled M. Edwards and Andrew R. Leach and Andrew Quigley and Anja Schütz and Anne Zemella and Ario de Marco and Åsa Sivertsson and Barbara Borgonovo and Ben Kemp and Bjørn Voldborg and Carlo Carolis and Carter Mitchell and Cecilia Wickstrand and Dafydd R. Owen and David Drechsel and David Jones and Diego A. Oyarzún and Dominic Esposito and Eric R. Geertsma and Ewa Krupinska and Frank Bernhard and Frederico Ferreira-da-Silva and Hanna Tegel and Ian Hunt and Imre Berger and James Love and Jan Dohnálek and Jelena Thies and Jerome Basquin and Jesse Coker and Johannes Buyel and Joop van den Heuvel and Jurgen Haustraete and Katharina L. Dürr and Kelvin Lau and Kristina Hedfalk and Kristof Bozovicar and Lihua Liu and Lisa Bamber and Luigi Angelo Scietti and Malin Bäckström and Maren Schubert and Mark Elvin and Martin Pelosse and Matthew H. Todd and Matthieu Schapira and Miroslava Alblová and Nicholas S. Berrow and Nikolay Marinchev Dobrev and Oleg Brodsky and Ondřej Vaněk and Opher Gileadi and Pam Dossang and Paola Storici and Patrick Celie and Paul Wan},
journal = {The Journal of Biological Chemistry},
year = {2026},
month = sep,
doi = {10.1016/j.jbc.2026.113610},
url = {https://doi.org/10.1016/j.jbc.2026.113610},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - EXPERT: A practical and forward-looking guide to capturing protein expression and purification metadata to develop machine learning models
AU - Christopher D.O. Cooper
AU - Evgeny Tankhilevich
AU - Kim Remans
AU - Ahmed El Marjou
AU - Aled M. Edwards
AU - Andrew R. Leach
AU - Andrew Quigley
AU - Anja Schütz
AU - Anne Zemella
AU - Ario de Marco
AU - Åsa Sivertsson
AU - Barbara Borgonovo
AU - Ben Kemp
AU - Bjørn Voldborg
AU - Carlo Carolis
AU - Carter Mitchell
AU - Cecilia Wickstrand
AU - Dafydd R. Owen
AU - David Drechsel
AU - David Jones
AU - Diego A. Oyarzún
AU - Dominic Esposito
AU - Eric R. Geertsma
AU - Ewa Krupinska
AU - Frank Bernhard
AU - Frederico Ferreira-da-Silva
AU - Hanna Tegel
AU - Ian Hunt
AU - Imre Berger
AU - James Love
AU - Jan Dohnálek
AU - Jelena Thies
AU - Jerome Basquin
AU - Jesse Coker
AU - Johannes Buyel
AU - Joop van den Heuvel
AU - Jurgen Haustraete
AU - Katharina L. Dürr
AU - Kelvin Lau
AU - Kristina Hedfalk
AU - Kristof Bozovicar
AU - Lihua Liu
AU - Lisa Bamber
AU - Luigi Angelo Scietti
AU - Malin Bäckström
AU - Maren Schubert
AU - Mark Elvin
AU - Martin Pelosse
AU - Matthew H. Todd
AU - Matthieu Schapira
AU - Miroslava Alblová
AU - Nicholas S. Berrow
AU - Nikolay Marinchev Dobrev
AU - Oleg Brodsky
AU - Ondřej Vaněk
AU - Opher Gileadi
AU - Pam Dossang
AU - Paola Storici
AU - Patrick Celie
AU - Paul Wan
PY - 2026
DA - 2026/09/29
JO - The Journal of Biological Chemistry
DO - 10.1016/j.jbc.2026.113610
UR - https://doi.org/10.1016/j.jbc.2026.113610
AB - 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.
SN - 0021-9258
SN - 1083-351X
ER -