NetMHCIIphosPan: HLA Class II Phosphorylated Peptide Antigen Presentation Predictions

A machine learning tool for predicting HLA class II antigen presentation of phosphorylated peptides, developed by Heli M. Garcia Alvarez and released on 2026-04 17. The model was trained on reanalyzed mass spectrometry-based immunopeptidomics data sets and incorporates unmodified ligands to enhance accuracy. It is shared as an 88.4 KB XLSX file under a CC-BY-NC-4.0 license.

Use Cases

• Predict HLA-II antigen presentation of phosphorylated peptides based on the described mass spectrometry data.
• Analyze HLA-specific binding motifs for phospholigands based on the described motif analysis.
• Benchmark new prediction tools against NetMHCIIphosPan, NetMHCIIpan-4.3, and MixMHC2pred-1.3 based on the described performance comparison.
• Investigate the HLA-II phospholigandome for immune regulation studies based on the described application areas.

Strengths

• The tool is described as achieving superior performance and robustness compared to existing tools like NetMHCIIpan-4.3 and MixMHC2pred-1.3.
• Training incorporated unmodified ligands, which is described as enhancing predictive accuracy, particularly for HLA-DP and HLA-DQ molecules.
• Data was generated using a refined peptide identification workflow on mass spectrometry-based immunopeptidomics data sets.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 88.4 KB, indicating limited scope.

Provenance

Source

Heli M. Garcia Alvarez via figshare.

Collection Method

Developed using reanalyzed mass spectrometry (MS)-based immunopeptidomics data sets.

Time Range

Publication date is 2026-04-17; temporal coverage of underlying data is not specified.

Freshness

Last updated 2026-04-17 09:29:49; freshness should be verified.

Geography

Spatial coverage is not specified.