Skip to main content

SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders.

Publication ,  Journal Article
Brixi, G; Ye, T; Hong, L; Wang, T; Monticello, C; Lopez-Barbosa, N; Vincoff, S; Yudistyra, V; Zhao, L; Haarer, E; Chen, T; Pertsemlidis, S ...
Published in: Communications biology
October 2023

Protein-protein interactions (PPIs) are critical for biological processes and predicting the sites of these interactions is useful for both computational and experimental applications. We present a Structure-agnostic Language Transformer and Peptide Prioritization (SaLT&PepPr) pipeline to predict interaction interfaces from a protein sequence alone for the subsequent generation of peptidic binding motifs. Our model fine-tunes the ESM-2 protein language model (pLM) with a per-position prediction task to identify PPI sites using data from the PDB, and prioritizes motifs which are most likely to be involved within inter-chain binding. By only using amino acid sequence as input, our model is competitive with structural homology-based methods, but exhibits reduced performance compared with deep learning models that input both structural and sequence features. Inspired by our previous results using co-crystals to engineer target-binding "guide" peptides, we curate PPI databases to identify partners for subsequent peptide derivation. Fusing guide peptides to an E3 ubiquitin ligase domain, we demonstrate degradation of endogenous β-catenin, 4E-BP2, and TRIM8, and highlight the nanomolar binding affinity, low off-targeting propensity, and function-altering capability of our best-performing degraders in cancer cells. In total, our study suggests that prioritizing binders from natural interactions via pLMs can enable programmable protein targeting and modulation.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Communications biology

DOI

EISSN

2399-3642

ISSN

2399-3642

Publication Date

October 2023

Volume

6

Issue

1

Start / End Page

1081

Related Subject Headings

  • Ubiquitin-Protein Ligases
  • Proteins
  • Peptides
  • Amino Acid Sequence
  • 32 Biomedical and clinical sciences
  • 31 Biological sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Brixi, G., Ye, T., Hong, L., Wang, T., Monticello, C., Lopez-Barbosa, N., … Chatterjee, P. (2023). SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders. Communications Biology, 6(1), 1081. https://doi.org/10.1038/s42003-023-05464-z
Brixi, Garyk, Tianzheng Ye, Lauren Hong, Tian Wang, Connor Monticello, Natalia Lopez-Barbosa, Sophia Vincoff, et al. “SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders.Communications Biology 6, no. 1 (October 2023): 1081. https://doi.org/10.1038/s42003-023-05464-z.
Brixi G, Ye T, Hong L, Wang T, Monticello C, Lopez-Barbosa N, et al. SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders. Communications biology. 2023 Oct;6(1):1081.
Brixi, Garyk, et al. “SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders.Communications Biology, vol. 6, no. 1, Oct. 2023, p. 1081. Epmc, doi:10.1038/s42003-023-05464-z.
Brixi G, Ye T, Hong L, Wang T, Monticello C, Lopez-Barbosa N, Vincoff S, Yudistyra V, Zhao L, Haarer E, Chen T, Pertsemlidis S, Palepu K, Bhat S, Christopher J, Li X, Liu T, Zhang S, Petersen L, DeLisa MP, Chatterjee P. SaLT&PepPr is an interface-predicting language model for designing peptide-guided protein degraders. Communications biology. 2023 Oct;6(1):1081.

Published In

Communications biology

DOI

EISSN

2399-3642

ISSN

2399-3642

Publication Date

October 2023

Volume

6

Issue

1

Start / End Page

1081

Related Subject Headings

  • Ubiquitin-Protein Ligases
  • Proteins
  • Peptides
  • Amino Acid Sequence
  • 32 Biomedical and clinical sciences
  • 31 Biological sciences