Deep-learning-based design of an orthogonal self-labeling protein from K-Ras(G12C)

Abstract

Self-labeling protein (SLP) tags enable versatile labeling of proteins in live cells, yet only two SLPs are commonly used, limiting multiplexing. Here, we repurposed the oncoprotein K-Ras(G12C) and its covalent inhibitors to create a third, orthogonal SLP system. We used a deep-learning-based approach to radically redesign the sequence of K-Ras(G12C) while preserving its covalent-inhibitor binding pocket. Our top design, LUCI-tag, is a 19 kDa, monomeric, thermostable SLP that rapidly and covalently reacts with commercially available K-Ras(G12C) inhibitors bearing diverse payloads. Unlike existing SLPs, LUCI-tag exhibited payload-agnostic labeling kinetics, outperforming HaloTag7 and SNAP-tag for a negatively charged payload. X-ray crystal structures of drug-bound and drug-free LUCI-tag showed the design was structurally accurate and contained a preorganized inhibitor-binding pocket that could explain its rapid labeling kinetics. Proteomics and cell-signaling experiments confirmed LUCI-tag is biologically inert. LUCI-tag enabled rapid, wash-free, live-cell imaging and simultaneous three-color multiplexed experiments with HaloTag7 and SNAP-tag. This work establishes LUCI-tag as an immediately useful orthogonal SLP and demonstrates that covalent drug-target pairs can be repurposed into a broadly applicable platform for protein labeling.

De novo design of lipopeptides with antimicrobial potency enabled by a chain-as-prompt deep learning framework
Fan Zhang, Xuchang Yu, Yuzhu Wu +1
Nature Communications17 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textMicrobiologyCrossref
PredIDR3: A new output-encoding scheme and abundant negative source provide more information for deep learning-based protein intrinsic disorder prediction
K.-S. Han, K. Hwang, S.-M. O +4
bioRxiv1 Sep 2026PreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
SurfGraphPro: Integrating Protein Language Models with Geometric Deep Learning On Coarse Protein Surfaces for Binding Site Prediction
A. Habib, L.-W. Hung, K. Gibson +3
bioRxiv17 Sep 2026PreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv
Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction
L. Wang, J. Cheng
bioRxiv17 Sep 2026PreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv
Deep learning based design of buried hydrogen bond networks with HBDesigner
H. Dieckhaus, B. T. Harvey, T. Mulikova +4
bioRxiv8 Jun 2026PreprintCC BY-NC-NDFull textSystems & synthetic biologybioRxiv

Cite

BibTeX RIS

BibTeX

@misc{mou2026deeplearningbased,
  title = {{Deep-learning-based design of an orthogonal self-labeling protein from K-Ras(G12C)}},
  author = {J. Mou and J. W. Leong and S. Gao and K. Slaw and M. McGill and K. A. Donovan and R. J. Metivier and F. L. Sendker and Q. Kong and D. Lin and A. M. Dharani and X. D. Chen and K. M. Haigis and E. S. Fischer and F. Chen and N. F. Polizzi},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.27.754867},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.27.754867v1},
  note = {CC BY-NC},
}

RIS

TY  - UNPB
TI  - Deep-learning-based design of an orthogonal self-labeling protein from K-Ras(G12C)
AU  - J. Mou
AU  - J. W. Leong
AU  - S. Gao
AU  - K. Slaw
AU  - M. McGill
AU  - K. A. Donovan
AU  - R. J. Metivier
AU  - F. L. Sendker
AU  - Q. Kong
AU  - D. Lin
AU  - A. M. Dharani
AU  - X. D. Chen
AU  - K. M. Haigis
AU  - E. S. Fischer
AU  - F. Chen
AU  - N. F. Polizzi
PY  - 2026
DA  - 2026/09/27
PB  - bioRxiv
DO  - 10.64898/2026.09.27.754867
UR  - https://www.biorxiv.org/content/10.64898/2026.09.27.754867v1
AB  - Self-labeling protein (SLP) tags enable versatile labeling of proteins in live cells, yet only two SLPs are commonly used, limiting multiplexing. Here, we repurposed the oncoprotein K-Ras(G12C) and its covalent inhibitors to create a third, orthogonal SLP system. We used a deep-learning-based approach to radically redesign the sequence of K-Ras(G12C) while preserving its covalent-inhibitor binding pocket. Our top design, LUCI-tag, is a 19 kDa, monomeric, thermostable SLP that rapidly and covalently reacts with commercially available K-Ras(G12C) inhibitors bearing diverse payloads. Unlike existing SLPs, LUCI-tag exhibited payload-agnostic labeling kinetics, outperforming HaloTag7 and SNAP-tag for a negatively charged payload. X-ray crystal structures of drug-bound and drug-free LUCI-tag showed the design was structurally accurate and contained a preorganized inhibitor-binding pocket that could explain its rapid labeling kinetics. Proteomics and cell-signaling experiments confirmed LUCI-tag is biologically inert. LUCI-tag enabled rapid, wash-free, live-cell imaging and simultaneous three-color multiplexed experiments with HaloTag7 and SNAP-tag. This work establishes LUCI-tag as an immediately useful orthogonal SLP and demonstrates that covalent drug-target pairs can be repurposed into a broadly applicable platform for protein labeling.
ER  -

Abstract

Related

Cite