NetMHCIIphosPan: HLA Class II Phosphorylated Peptide Antigen Presentation Predictions

NetMHCIIphosPan is a machine learning tool for predicting human leukocyte antigen (HLA) class II presentation of phosphorylated peptides. The model was developed by Heli M. Garcia Alvarez using reanalyzed mass spectrometry-based immunopeptidomics datasets and was last updated in April 2026. It reportedly outperforms existing tools like NetMHCIIpan-4.3 and MixMHC2pred-1.3 for this specific prediction task.

Use Cases

• Predicting HLA class II antigen presentation for phosphorylated peptides based on the described machine learning model.
• Analyzing HLA-specific binding motifs for phospholigands as mentioned in the description.
• Benchmarking new prediction tools against NetMHCIIphosPan's reported performance.
• Informing immunotherapy and vaccine design strategies through insights into the phospholigandome.

Strengths

• Model reportedly achieves superior performance compared to models trained on original data and outperforms existing tools NetMHCIIpan-4.3 and MixMHC2pred-1.3.
• Training incorporated both phosphorylated and unmodified ligands, which enhanced predictive accuracy for HLA-DP and HLA-DQ molecules.
• Data file is 243.0 KB, indicating a compact and likely focused dataset.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset's primary content appears to be the tool's predictions or training data, not raw experimental observations.

Provenance

Source

Heli M. Garcia Alvarez via figshare.

Collection Method

Developed using mass spectrometry (MS)-based immunopeptidomics datasets reanalyzed with a refined peptide identification workflow.

Time Range

Temporal coverage of the underlying training data is not specified.

Freshness

Last updated 2026-04-17 09:29:47; freshness should be verified.

Geography

Spatial coverage is not specified; data likely relates to human immunology.