EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins

Tian Cai, Li Xie, Shuo Zhang iD, Muge Chen, Di He, Amitesh Badkul, Yang Liu, Hari Krishna Namballa, Michael Dorogan, Wayne W Harding, Cameron Mura iD, Philip E Bourne und 1 weitere

PLOS Computational Biology · 2023

DOI: 10.1371/journal.pcbi.1010851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2023. Verfasst von Tian Cai und 12 weiteren Autor:innen. Beteiligte Einrichtung: Ph.D. Program in Computer Science, The Graduate Center, The City University of New York, New York, New York, United States of America. Hauptthemen laut MEDLINE: Proteins, Algorithms. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIGMS NIH HHS, National Institute of General Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsAlgorithmsHumansLigandsBinding SitesMachine LearningProtein Binding

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Ph.D. Program in Computer Science, The Graduate Center, The City University of New York, New York, New York, United States of America.
  • Department of Computer Science, Hunter College, The City University of New York, New York, New York, United States of America.
  • Master Program in Computer Science, Courant Institute of Mathematical Sciences, New York University, New York, New York, United States of America.
  • Department of Chemistry, Hunter College, The City University of New York, New York, New York, United States of America.
  • School of Data Science & Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia, United States of America.
  • Helen and Robert Appel Alzheimer's Disease Research Institute, Feil Family Brain & Mind Research Institute, Weill Cornell Medicine, Cornell University, New York, New York, United States of America.

ORCID-Profile: Shuo Zhang, Cameron Mura, Lei Xie

Förderung

  • NIA NIH HHS
  • NIGMS NIH HHS
  • National Institute of General Medical Sciences
  • National Institute on Aging
  • National Science Foundation

Zitieren

APA

Cai, T., Xie, L., Zhang, S., Chen, M., He, D., Badkul, A., Liu, Y., Namballa, H. K., Dorogan, M., Harding, W. W., Mura, C., Bourne, P. E., & Xie, L. (2023). End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1010851

Vancouver

Cai T, Xie L, Zhang S, Chen M, He D, Badkul A, et al. End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins. PLOS Computational Biology. 2023. doi:10.1371/journal.pcbi.1010851

BibTeX
@article{Cai2023,
  author = {Cai, Tian and Xie, Li and Zhang, Shuo and Chen, Muge and He, Di and Badkul, Amitesh and Liu, Yang and Namballa, Hari Krishna and Dorogan, Michael and Harding, Wayne W and Mura, Cameron and Bourne, Philip E and Xie, Lei},
  title = {End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins},
  journal = {PLOS Computational Biology},
  year = {2023},
  doi = {10.1371/journal.pcbi.1010851}
}
Kostenlos starten →