Back

Transposon-Display of AI-designed binders enables manipulation of the proteome in human cells

Hoch, A.; Fandrey, C. I.; Coventry, B.; Virreira Winter, S.; Geyer, P. E.; Kempchen, T. N.; Ebert, T. S.; Hoelzel, M.; Baker, D.; Schmid-Burgk, J. L.

2025-05-15 bioengineering
10.1101/2025.05.11.653342 bioRxiv
Show abstract

Transposon-Display is a highly scalable screening method that links proteins to their encoding DNA during expression in E. coli via a mutant transposase. Leveraging this system, we identified AI-designed binders targeting four intracellular human proteins, saturation-mutagenized top candidates, and charge-balanced variants to improve compatibility with the intracellular environment while preserving target binding. The resulting neutral binders can be fused to EGFP allowing antibody-free intracellular staining. Expressing neutral binders in human cells as fusions with functional domains can drive small molecule-controlled protein aggregation and trigger proteasomal degradation of endogenous target proteins in living cells. Manipulating the proteome of living cells using libraries of AI-designed binders may provide a new avenue to screen for disease-relevant protein functions and large-scale functional data may help to refine protein design algorithms.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 14%
12.7%
Similar papers in this journal
2
Nature Biotechnology
○ 172 papers in training set
Top 0.1%
11.7%
Similar papers in this journal
3
Nature Methods
○ 385 papers in training set
Top 1.0%
10.5%
Similar papers in this journal
4
Science
● 477 papers in training set
Top 0.7%
9.6%
Similar papers in this journal
5
Nature Chemical Biology
○ 119 papers in training set
Top 0.2%
9.5%
Similar papers in this journal
50% of probability mass above
6
Cell
○ 431 papers in training set
Top 1%
6.2%
7
Science Advances
● 1243 papers in training set
Top 7%
4.3%
8
Nature Nanotechnology
○ 32 papers in training set
Top 0.1%
4.0%
9
eLife
● 5828 papers in training set
Top 33%
3.5%
10
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 16%
3.2%
11
Nature Biomedical Engineering
○ 47 papers in training set
Top 0.6%
2.4%
12
Nature
○ 645 papers in training set
Top 6%
2.4%
13
ACS Chemical Biology
● 167 papers in training set
Top 2%
1.5%
14
Cell Chemical Biology
○ 94 papers in training set
Top 0.9%
1.4%
15
Journal of the American Chemical Society
● 217 papers in training set
Top 2%
1.4%
16
Neuron
○ 337 papers in training set
Top 4%
1.3%
17
Cell Genomics
○ 172 papers in training set
Top 4%
1.1%
18
Cell Systems
○ 201 papers in training set
Top 4%
1.1%
19
Cell Reports Methods
○ 165 papers in training set
Top 3%
1.0%
20
Molecular Cell
○ 350 papers in training set
Top 5%
0.8%
21
Cell Reports
○ 1498 papers in training set
Top 27%
0.8%
22
ACS Synthetic Biology
● 287 papers in training set
Top 3%
0.6%
23
Advanced Science
○ 286 papers in training set
Top 11%
0.6%
24
Angewandte Chemie International Edition
○ 93 papers in training set
Top 2%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.