TLimmuno2

What is TLimmuno2?

TLimmuno2 predicts whether a peptide presented by an MHC class II molecule will trigger a CD4+ T cell immune response. Where most immunogenicity tools focus on MHC class I (CD8+ T cells), TLimmuno2 addresses the less-covered class II pathway, which is central to helper T cell activation, vaccine design, and cancer neoantigen identification.

The model uses transfer learning: an LSTM network is first trained on over 100,000 peptide-MHC binding affinity measurements, then fine-tuned on immunogenicity data. This two-stage approach compensates for the limited amount of experimentally validated immunogenicity data available for MHC-II epitopes.

How does TLimmuno2 work?

Two-stage prediction

TLimmuno2 runs two neural networks in sequence:

1. Binding affinity model (BAmodel): An LSTM trained on 107,008 binding measurements from NetMHCIIpan across 71 MHC-II molecules. Rather than using the final binding prediction, TLimmuno2 extracts intermediate features from this model's penultimate layer, capturing learned representations of peptide-MHC interaction patterns.

2. Immunogenicity model: A second LSTM that takes three inputs — the BLOSUM62-encoded peptide, the encoded MHC pseudosequence, and the binding affinity features from stage one — and predicts the probability that the complex will elicit a T cell response.

Sequence encoding

Both peptides and MHC pseudosequences are encoded using the BLOSUM62 substitution matrix, which captures biochemical similarity between amino acids. Peptides are padded to 21 residues and MHC pseudosequences to 34 residues, producing fixed-size matrices that the LSTM layers can process.

Percentile ranking

Raw immunogenicity scores lack context without a reference distribution. When percentile ranking is enabled, TLimmuno2 scores approximately 90,000 random human peptides (sampled across lengths 13–21) against the same HLA allele and reports where the query peptide falls in that distribution. A percentile rank of 0.95 means the peptide scores higher than 95% of background peptides for that allele.

How to use TLimmuno2 online

ProteinIQ provides cloud-hosted access to TLimmuno2 with support for over 2,000 HLA class II alleles, covering the DRB1, DRB3, DRB4, DRB5, and DPA/DPB loci. No installation or Python environment required.

Inputs

Settings

Output columns

Interpreting results

The immunogenicity score is a continuous probability. A peptide scoring 0.8 is not necessarily four times as immunogenic as one scoring 0.2 — the score reflects model confidence, not magnitude of immune response.

Percentile rank provides additional context. A peptide with a moderate score of 0.5 but a high percentile rank (> 0.9) is still notable — it scores above 90% of random peptides for that allele, suggesting genuine immunogenic potential even if the absolute score appears modest.

MHC class I vs class II

MHC class I molecules present intracellular peptides (typically 8–11 residues) to CD8+ cytotoxic T cells. MHC class II molecules present extracellular peptides (typically 13–25 residues) to CD4+ helper T cells. The two pathways involve different antigen processing machinery, binding groove geometry, and downstream immune effects.

TLimmuno2 specifically models the class II pathway. For MHC class I immunogenicity prediction, DeepImmuno covers 20 HLA-A/B/C alleles with a CNN-based approach.

Limitations

• Predictions are for immunogenicity (T cell activation), not binding affinity alone. High binding does not guarantee immunogenicity, and the model accounts for factors beyond binding.
• The MHC-II binding groove is open-ended, meaning peptides of varying lengths can bind. TLimmuno2 handles this through padding, but very long peptides (> 21 residues) are truncated internally.
• Percentile ranking is computationally expensive. Each unique HLA allele requires scoring ~90,000 background peptides through both models, adding several minutes per allele.
• The model was trained primarily on human data. Mouse H-2 alleles are present in the pseudosequence database but have not been independently validated.

Related tools

• DeepImmuno: MHC class I peptide immunogenicity prediction for CD8+ T cells
• ScanNet: Predicts antibody epitope binding sites on protein structures
• IgBLAST: Analyzes immunoglobulin and T cell receptor sequences, identifying V/D/J segments
• ImmuneBuilder: 3D structure prediction for antibodies, nanobodies, and T cell receptors
• PepMLM: Designs linear peptide binders for target proteins using masked language modeling