EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli

Evgeny Tankhilevich iD, Sergio Martinez Cuesta, Ian Barrett, Carolina Berg, Lovisa Holmberg Schiavone, Andrew R Leach iD

Bioinformatics · 02.01.2026 · 42 (1)

DOI: 10.1093/bioinformatics/btag003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 11.01.2026. Verfasst von Evgeny Tankhilevich und 5 weiteren Autor:innen. Beteiligte Einrichtung: European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB10 1SD, United Kingdom. Hauptthemen laut MEDLINE: Escherichia coli, Recombinant Proteins, Deep Learning, Computational Biology. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Member States of the European Molecular Biology Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Recombinant protein expression can be a limiting step in the production of protein reagents for drug discovery and other biotechnology applications. We introduce RP3Net (Recombinant Protein Production Prediction Network), an AI model of small-scale heterologous soluble protein expression in Escherichia coli. RP3Net utilizes the most recent protein and genomic foundational models. A curated dataset of internal experimental results from AstraZeneca and publicly available data from the Structural Genomics Consortium was used for training, validation and testing of RP3Net. Results RP3Net achieves an increase in area under the receiver operator curve (AUROC) of 0.15, compared to a baseline model. When experimentally validated on an independent, prospective, manually selected set of 97 constructs, RP3Net outperformed currently available models, with an AUROC of 0.83, delivering accurate predictions in 77% of the cases, and correctly identifying successfully expressing constructs in 92% of cases. Availability and implementation The model, along with installation and running instructions, is available under an MIT licence at https://github.com/RP3Net/RP3Net, DOI 10.5281/zenodo.17243498.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Escherichia coliRecombinant ProteinsDeep LearningComputational Biology

Substanzen

Recombinant Proteins

Autor:innen und Institutionen

  • European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB10 1SD, United Kingdom.
  • Data Sciences and Quantitative Biology, Discovery Sciences, BioPharmaceuticals R&D, Astra-Zeneca, Cambridge, CB2 0AA, United Kingdom.
  • Protein Science, Structure and Biophysics, Discovery Sciences, BioPharmaceuticals R&D, Astra-Zeneca, Mölndal, 431 83, Sweden.

ORCID-Profile: Evgeny Tankhilevich, Andrew R Leach

Förderung

  • Member States of the European Molecular Biology Laboratory

Zitieren

APA

Tankhilevich, E., Martinez Cuesta, S., Barrett, I., Berg, C., Holmberg Schiavone, L., & Leach, A. R. (2026). RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli. Bioinformatics, 42(1). https://doi.org/10.1093/bioinformatics/btag003

Vancouver

Tankhilevich E, Martinez Cuesta S, Barrett I, Berg C, Holmberg Schiavone L, Leach AR. RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli. Bioinformatics. 2026;42(1). doi:10.1093/bioinformatics/btag003

BibTeX
@article{Tankhilevich2026,
  author = {Tankhilevich, Evgeny and Martinez Cuesta, Sergio and Barrett, Ian and Berg, Carolina and Holmberg Schiavone, Lovisa and Leach, Andrew R},
  title = {RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {1},
  doi = {10.1093/bioinformatics/btag003}
}
Kostenlos starten →