Back

Benchmarking TCR-pMHC structure prediction: a unified evaluation and CDR3-based functional insights

Lu, J.; Zhu, X.; Hu, X.; Zhang, C.; Feng, F.

2025-12-02 bioinformatics
10.64898/2025.11.30.691400 bioRxiv
Show abstract

Interactions between T cell receptors (TCRs) and peptide-major histocompatibility complexes (pMHCs) are central to adaptive immunity. Recent advances in structure prediction tools have enabled atomic-level modeling of TCR-pMHC interactions. However, the lack of systematic evaluation forces practitioners to invest substantial resources in selecting appropriate tools. Here, we present a comprehensive benchmark of TCR-pMHC structure prediction with 70 previously unseen complexes and ten models spanning MSA-based, PLM-based, and docking-based approaches, revealing the superior modeling accuracy and docking quality of MSA-based methods, especially AlphaFold3. To further enhance the utility of AlphaFold3 predictions, we identify the pLDDT score of the TCR CDR3 region as an informative indicator of both structural correctness and functional relevance. Specifically, it enables up to 4.3% Top-1 success gain through reranking and captures mutation-induced affinity changes in over 80% of cases. Overall, our analysis would facilitate the practical usage of immune structure prediction models and guide the advancement of these models.

Published in Briefings in Bioinformatics (predicted rank #3) · training set

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 1%
18.0%
Similar papers in this journal
2
PLOS Computational Biology
● 1863 papers in training set
Top 3%
11.6%
Similar papers in this journal
Briefings in Bioinformatics · published here
◐ 354 papers in training set
Top 1%
7.1%
Similar papers in this journal
4
Nature Communications
○ 5641 papers in training set
Top 24%
6.5%
Similar papers in this journal
5
Journal of Molecular Biology
○ 232 papers in training set
Top 0.3%
6.1%
Similar papers in this journal
6
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.8%
4.7%
50% of probability mass above
7
Nature Methods
○ 385 papers in training set
Top 2%
4.2%
8
Structure
○ 193 papers in training set
Top 0.8%
3.1%
9
Protein Science
○ 246 papers in training set
Top 1%
3.1%
10
Communications Biology
○ 993 papers in training set
Top 6%
3.1%
11
Journal of Chemical Information and Modeling
● 238 papers in training set
Top 1%
2.7%
12
eLife
● 5828 papers in training set
Top 44%
2.3%
13
Cell Systems
○ 201 papers in training set
Top 2%
2.3%
14
Bioinformatics Advances
◐ 203 papers in training set
Top 3%
2.1%
15
Frontiers in Immunology
○ 638 papers in training set
Top 5%
2.1%
16
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 26%
1.9%
17
Proteins: Structure, Function, and Bioinformatics
○ 88 papers in training set
Top 0.7%
1.9%
18
Nucleic Acids Research
◐ 1281 papers in training set
Top 11%
1.1%
19
Nature Computational Science
○ 55 papers in training set
Top 1%
1.0%
20
Scientific Reports
○ 3612 papers in training set
Top 70%
1.0%
21
Advanced Science
○ 286 papers in training set
Top 10%
0.8%
22
Biomolecules
○ 100 papers in training set
Top 3%
0.8%
23
Journal of Chemical Theory and Computation
● 140 papers in training set
Top 1%
0.8%
24
Cell Reports Methods
○ 165 papers in training set
Top 4%
0.8%
25
Journal of Cheminformatics
○ 29 papers in training set
Top 0.7%
0.8%
26
Science Advances
● 1243 papers in training set
Top 34%
0.6%
27
Nature Machine Intelligence
○ 70 papers in training set
Top 3%
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.