Back

Stoic: Fast and accurate protein stoichiometry prediction

Litvinov, D.; Pantolini, L.; Skrinjar, P.; Tauriello, G.; McCafferty, C. L.; Engel, B. D.; Schwede, T.; Durairaj, J.

2026-03-16 bioinformatics
10.64898/2026.03.13.711535 bioRxiv
Show abstract

MotivationProtein complexes are central to cellular function, but experimental determination of their structures remains challenging. Structure prediction methods require prior knowledge of stoichiometry - the number of copies of each protein entity within a complex. Current approaches rely on computationally expensive brute-force methods that run structure prediction on multiple stoichiometry combinations, often with limited accuracy. ResultsWe introduce Stoic, a method that uses protein language model embeddings to predict protein complex stoichiometry. Our approach learns to identify interface residues that participate in protein-protein interactions, rather than relying on global sequence features. By integrating these interface-aware embeddings into a graph neural network, Stoic achieves fast and accurate stoichiometry prediction for both homomeric and heteromeric targets. AvailabilitySource code for inference and training along with web versions are available in the repository at https://github.com/PickyBinders/stoic. Contactjanani.durairaj@unibas.ch

Matching journals

The top 1 journal accounts for 50% of the predicted probability mass.

1
Bioinformatics
1061 papers in training set
Top 0.2%
51.1%
50% of probability mass above
2
Nature Communications
4913 papers in training set
Top 30%
6.3%
3
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 16%
4.3%
4
Bioinformatics Advances
184 papers in training set
Top 1%
3.9%
5
BMC Bioinformatics
383 papers in training set
Top 2%
3.9%
6
Nature Methods
336 papers in training set
Top 3%
3.6%
7
Cell Systems
167 papers in training set
Top 5%
3.0%
8
PLOS Computational Biology
1633 papers in training set
Top 11%
3.0%
9
Briefings in Bioinformatics
326 papers in training set
Top 3%
1.9%
10
Nucleic Acids Research
1128 papers in training set
Top 11%
1.7%
11
Nature Biotechnology
147 papers in training set
Top 6%
1.3%
12
Scientific Reports
3102 papers in training set
Top 67%
1.2%
13
Protein Science
221 papers in training set
Top 1%
1.2%
14
Journal of Cheminformatics
25 papers in training set
Top 0.5%
0.9%
15
Nature Machine Intelligence
61 papers in training set
Top 3%
0.9%
16
Structure
175 papers in training set
Top 3%
0.8%
17
Nature
575 papers in training set
Top 15%
0.8%
18
Journal of Molecular Biology
217 papers in training set
Top 4%
0.7%
19
Protein Engineering, Design and Selection
14 papers in training set
Top 0.1%
0.7%
20
Biophysical Journal
545 papers in training set
Top 6%
0.6%
21
eLife
5422 papers in training set
Top 62%
0.6%
22
Communications Biology
886 papers in training set
Top 30%
0.6%