ImmuneBuilder
1 Introduction
ImmuneBuilder, including ABodyBuilder2, NanoBodyBuilder2, and TCRBuilder2, is specifically designed for predicting the structure of immunoproteins (e.g., antibodies, nanobodies, and T-cell receptors), and employs AlphaFold-Multimer's structural modules with modifications specific to the immunoproteins to improve prediction accuracy.ImmuneBuilder is able to quickly generate immunoprotein structures that resemble experimental data much faster than AlphaFold2 and without the need for large sequence databases or multiple sequence comparisons. The tool's features include high accuracy, fast prediction, and open-source accessibility for structural analysis of large-scale sequence datasets, especially in the study of immunoprotein structures from next-generation sequencing data. immuneBuilder also provides error estimation to help filter out erroneous models, enhancing its value for applications in biotherapeutics and immunology research1. Figure 1 shows the architecture of AbBuilder2, and the same architecture is used for NanoBodyBuilder2 and TCRBuilder2.
Figure 1. Overall architecture of AbBuilder.
Root mean square deviation of predicted antibody structure in Angstroms (Å):
| Method | CDR-H1 | CDR-H2 | CDR-H3 | Fw-H | CDR-L1 | CDR-L2 | CDR-L3 | Fw-L |
|---|---|---|---|---|---|---|---|---|
| ABodyBuilder (ABB) | 1.53 | 1.09 | 3.46 | 0.65 | 0.71 | 0.55 | 1.18 | 0.59 |
| ABlooper (ABL) | 1.18 | 0.96 | 3.34 | 0.63 | 0.78 | 0.63 | 1.08 | 0.61 |
| IgFold (IgF) | 0.86 | 0.77 | 3.28 | 0.58 | 0.55 | 0.43 | 1.12 | 0.60 |
| EquiFold (EqF) | 0.86 | 0.80 | 3.29 | 0.56 | 0.47 | 0.41 | 0.93 | 0.54 |
| AlphaFold-M (AFM) | 0.86 | 0.68 | 2.90 | 0.55 | 0.47 | 0.40 | 0.83 | 0.54 |
| ABodyBuilder2 (AB2) | 0.85 | 0.78 | 2.81 | 0.54 | 0.46 | 0.44 | 0.87 | 0.57 |
Root mean square deviation of predicted nanobody structure in Angstroms (Å):
| Method | CDR1 | CDR2 | CDR3 | Fw |
|---|---|---|---|---|
| ABodyBuilder | 2.96 | 2.08 | 5.08 | 1.09 |
| MOE | 2.67 | 1.99 | 4.90 | 1.19 |
| AlphaFold2 | 2.08 | 1.35 | 3.44 | 0.82 |
| NanoBodyBuilder2 | 1.98 | 1.37 | 2.89 | 0.79 |
Root mean square deviation of predicted TCR structure in Angstroms (Å):
| Method | CDR-α1 | CDR-α2 | CDR-α3 | Fw-α | CDR-β1 | CDR-β2 | CDR-β3 | Fw-β |
|---|---|---|---|---|---|---|---|---|
| TCRBuilder | 1.60 | 1.31 | 2.89 | 0.87 | 0.99 | 0.90 | 3.12 | 0.81 |
| RepertoireBuilder | 1.35 | 1.00 | 2.64 | 0.75 | 0.86 | 1.59 | 2.77 | 1.05 |
| AlphaFold-M | 1.25 | 0.96 | 1.84 | 0.69 | 0.75 | 0.65 | 1.94 | 0.82 |
| ABodyBuilder2 | 3.49 | 6.57 | 3.14 | 2.89 | 3.27 | 3.77 | 3.48 | 3.65 |
| TCRBuilder2 | 1.34 | 0.93 | 1.85 | 0.90 | 0.74 | 0.63 | 1.93 | 0.67 |
2 Parameters
- mode:select prediction object.
- H:represents antibody heavy chain V region.
- L:represents antibody light chain V region.
- scheme:Antibody numbering system.
3 Results Explanation
Three-dimensional structure of the antibody predicted by the algorithm.
4 Reference
[1] Abanades, B., Wong, W.K., Boyles, F. et al. ImmuneBuilder: Deep-Learning models for predicting the structures of immune proteins. Commun Biol 6, 575 (2023). https://doi.org/10.1038/s42003-023-04927-7