EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships

Alexander Kroll, Sahasra Ranjan, Martin J Lercher iD

PLOS Computational Biology · 20.05.2024 · 20 (5) · e1012100

DOI: 10.1371/journal.pcbi.1012100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 20.05.2024. Verfasst von Alexander Kroll und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computer Science and Department of Biology, Heinrich Heine University, Düsseldorf, Germany. Hauptthemen laut MEDLINE: Computational Biology, Machine Learning. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 European Research Council, Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The activities of most enzymes and drugs depend on interactions between proteins and small molecules. Accurate prediction of these interactions could greatly accelerate pharmaceutical and biotechnological research. Current machine learning models designed for this task have a limited ability to generalize beyond the proteins used for training. This limitation is likely due to a lack of information exchange between the protein and the small molecule during the generation of the required numerical representations. Here, we introduce ProSmith, a machine learning framework that employs a multimodal Transformer Network to simultaneously process protein amino acid sequences and small molecule strings in the same input. This approach facilitates the exchange of all relevant information between the two molecule types during the computation of their numerical representations, allowing the model to account for their structural and functional interactions. Our final model combines gradient boosting predictions based on the resulting multimodal Transformer Network with independent predictions based on separate deep learning representations of the proteins and small molecules. The resulting predictions outperform recently published state-of-the-art models for predicting protein-small molecule interactions across three diverse tasks: predicting kinase inhibitions; inferring potential substrates for enzymes; and predicting Michaelis constants K M . The Python code provided can be used to easily implement and improve machine learning predictions involving arbitrary protein-small molecule interactions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyMachine LearningProtein Kinase InhibitorsSubstrate SpecificitySmall Molecule LibrariesProteinsAmino Acid SequenceDeep LearningProtein BindingProtein KinasesHumans

Substanzen

Protein Kinase InhibitorsSmall Molecule LibrariesProteinsProtein Kinases

Autor:innen und Institutionen

  • Institute for Computer Science and Department of Biology, Heinrich Heine University, Düsseldorf, Germany.
  • Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, India.

ORCID-Profile: Martin J Lercher

Förderung

  • H2020 European Research Council
  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Kroll, A., Ranjan, S., & Lercher, M. J. (2024). A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships. PLOS Computational Biology, 20(5), e1012100. https://doi.org/10.1371/journal.pcbi.1012100

Vancouver

Kroll A, Ranjan S, Lercher MJ. A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships. PLOS Computational Biology. 2024;20(5):e1012100. doi:10.1371/journal.pcbi.1012100

BibTeX
@article{Kroll2024,
  author = {Kroll, Alexander and Ranjan, Sahasra and Lercher, Martin J},
  title = {A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships},
  journal = {PLOS Computational Biology},
  year = {2024},
  volume = {20},
  number = {5},
  pages = {e1012100},
  doi = {10.1371/journal.pcbi.1012100}
}
Kostenlos starten →