Back

Integrating Machine-learning and Ultra-high-throughput Screening for Enzyme spaces exploration

Ke, Y.; Zhang, Y.; Fang, M.; Zhao, J.; Zhu, H.; Xu, Z.; Cao, L.

2026-06-24 biochemistry
10.64898/2026.06.23.733994 bioRxiv
Show abstract

AbstractThe systematic navigation of biocatalyst space is constrained by elusive structure-activity rules and a lack of evolutionary history. Here, we present IMUSE, a strategy integrating machine learning with ultra-high-throughput screening. By screening millions of droplet-encapsulated de novo enzymes, we generated massive synthetic sequence-structure datasets to train models that capture their complex fitness landscapes and biophysical principles. These models effectively guide functional exploration across both sequence and novel structure spaces. IMUSE identified synergistic triple mutations yielding [~]5-fold activity improvements and discovered active second-generation designs with novel catalytic pockets, boosting the experimental success rate >4.9-fold ([~]30%). This work demonstrates how synthetic fitness landscapes bridge the data gap in de novo enzyme space, transforming stochastic search into deterministic navigation to unlock highly proficient biocatalysts beyond natural boundaries.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
5641 papers in training set
Top 9%
18.2%
2
Proceedings of the National Academy of Sciences
2444 papers in training set
Top 4%
9.6%
3
Nature
645 papers in training set
Top 2%
7.7%
4
Science
477 papers in training set
Top 2%
5.1%
5
Journal of Chemical Information and Modeling
238 papers in training set
Top 1%
4.8%
6
ACS Catalysis
18 papers in training set
Top 0.1%
4.2%
7
Nature Chemistry
42 papers in training set
Top 0.2%
4.0%
50% of probability mass above
8
Cell Systems
201 papers in training set
Top 1%
4.0%
9
Nature Chemical Biology
119 papers in training set
Top 0.7%
3.4%
10
Communications Chemistry
48 papers in training set
Top 0.3%
2.7%
11
Chemical Science
73 papers in training set
Top 0.6%
2.4%
12
eLife
5828 papers in training set
Top 42%
2.3%
13
ACS Central Science
71 papers in training set
Top 0.6%
2.1%
14
Nucleic Acids Research
1281 papers in training set
Top 8%
2.1%
15
Angewandte Chemie International Edition
93 papers in training set
Top 0.9%
2.1%
16
PLOS Computational Biology
1863 papers in training set
Top 14%
1.7%
17
Nature Methods
385 papers in training set
Top 4%
1.7%
18
Molecular Cell
350 papers in training set
Top 4%
1.1%
19
Journal of the American Chemical Society
217 papers in training set
Top 2%
1.1%
20
ACS Synthetic Biology
287 papers in training set
Top 2%
1.0%
21
Cell
431 papers in training set
Top 9%
1.0%
22
Science Advances
1243 papers in training set
Top 28%
1.0%
23
Nature Machine Intelligence
70 papers in training set
Top 3%
0.8%
24
Advanced Science
286 papers in training set
Top 10%
0.8%
25
Cell Reports Methods
165 papers in training set
Top 4%
0.8%
26
Nature Structural & Molecular Biology
18 papers in training set
Top 0.5%
0.8%
27
Nature Biotechnology
172 papers in training set
Top 5%
0.6%
28
Advanced Intelligent Systems
11 papers in training set
Top 0.4%
0.6%
29
Communications Biology
993 papers in training set
Top 36%
0.6%