Back

AI-guided design of common light chains to enable manufacturable bispecific antibodies

Greisen, P.; Garces, F.; French, J. B.; Zhou, Y.; Richardson, B. M.; Cong, L.; Pang, Z.; Lang, Y.; Li, T.; Shek, R.

2025-10-14 bioengineering
10.1101/2025.10.11.681265 bioRxiv
Show abstract

Bispecific antibodies (BsAbs) offer therapeutic advantages but face manufacturing bottlenecks from light chain mispairing, which can generate a substantial fraction of incorrect products and increase manufacturing complexity and cost of goods. Common light chains (cLC) eliminate mispairing, yet existing approaches require screening thousands of variants per target. We present an AI-driven framework that computationally designs cLCs through structure-guided pairing of non-cognate VH-VL interfaces, reducing experimental screening by three orders of magnitude. The platform successfully engineers therapeutic antibodies lacking experimental structures, expanding applicability beyond crystallographic databases. Among 10 therapeutic targets, we successfully generated designs for 7 targets, comprising 55 unique BsAb pairs. Of these, 43.6% (24/55) were successfully as BsAb cLCs. Three bispecific antibodies reached production-ready specifications: >90% purity and 1.6-1.8 g/L titers. This platform democratizes bispecific antibody development, expanding access beyond well-resourced programs.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 9%
18.4%
Similar papers in this journal
2
Cell Systems
○ 201 papers in training set
Top 0.4%
7.2%
Similar papers in this journal
3
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 6%
6.7%
Similar papers in this journal
4
ACS Central Science
● 71 papers in training set
Top 0.1%
6.7%
Similar papers in this journal
5
Nature Methods
○ 385 papers in training set
Top 2%
5.5%
Similar papers in this journal
6
mAbs
○ 32 papers in training set
Top 0.1%
4.3%
7
Cell Chemical Biology
○ 94 papers in training set
Top 0.3%
4.0%
50% of probability mass above
8
Nature Biotechnology
○ 172 papers in training set
Top 1%
4.0%
9
Science Advances
● 1243 papers in training set
Top 8%
4.0%
10
Science
● 477 papers in training set
Top 3%
3.2%
11
Nature Biomedical Engineering
○ 47 papers in training set
Top 0.4%
3.2%
12
Nature
○ 645 papers in training set
Top 6%
2.1%
13
Advanced Science
○ 286 papers in training set
Top 4%
1.9%
14
eLife
● 5828 papers in training set
Top 50%
1.7%
15
Communications Biology
○ 993 papers in training set
Top 15%
1.7%
16
Cell Genomics
○ 172 papers in training set
Top 3%
1.5%
17
Nature Chemistry
○ 42 papers in training set
Top 0.6%
1.4%
18
Journal of the American Chemical Society
● 217 papers in training set
Top 2%
1.3%
19
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.1%
20
Cell Reports
○ 1498 papers in training set
Top 25%
1.0%
21
Angewandte Chemie International Edition
○ 93 papers in training set
Top 2%
0.9%
22
Cell
○ 431 papers in training set
Top 10%
0.8%
23
PLOS Computational Biology
● 1863 papers in training set
Top 20%
0.8%
24
Molecular Therapy
○ 81 papers in training set
Top 2%
0.8%
25
Blood
● 74 papers in training set
Top 1%
0.8%
26
Structure
○ 193 papers in training set
Top 3%
0.6%
27
Nature Chemical Biology
○ 119 papers in training set
Top 3%
0.6%
28
iScience
○ 1154 papers in training set
Top 41%
0.6%
29
Nature Computational Science
○ 55 papers in training set
Top 2%
0.6%
30
Cell Reports Medicine
○ 153 papers in training set
Top 6%
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.