Subtopic Deep Dive

← vaccines and immunoinformatics approaches

T-Cell Epitope Prediction
Research Guide

What is T-Cell Epitope Prediction?

T-Cell Epitope Prediction uses computational models to identify peptides presented by MHC class I molecules to CD8+ T cells, integrating proteasomal cleavage, TAP transport, and MHC binding predictions.

Tools like NetMHCpan-4.1 predict MHC antigen presentation by combining motif deconvolution with mass spectrometry ligand data (Reynisson et al., 2020, 2097 citations). NetMHCpan-4.0 improves peptide-MHC class I predictions using eluted ligand and binding affinity data (Jurtz et al., 2017, 1465 citations). SYFPEITHI provides a database of MHC ligands and peptide motifs for benchmarking (Rammensee et al., 1999, 2312 citations).

Curated Papers

Key Challenges

Why It Matters

T-cell epitope prediction identifies neoantigens for personalized RNA mutanome vaccines that mobilize poly-specific immunity against cancer (Şahin et al., 2017, 2337 citations). It supports vaccine design against SARS-CoV-2 by predicting immunogenic targets from spike mutations enabling immune escape (Harvey et al., 2021, 3740 citations). Combining mass spectrometry and exome sequencing predicts immunogenic tumor mutations for targeted therapies (Yadav et al., 2014, 1160 citations).

Key Research Challenges

Pan-Specific MHC Prediction Accuracy

NetMHCpan-4.1 integrates MS data but struggles with rare alleles and low-affinity ligands (Reynisson et al., 2020). Models require concurrent motif deconvolution to handle diverse MHC variants. Benchmarking against SYFPEITHI databases reveals gaps in immunogenicity classifiers (Rammensee et al., 1999).

Immunogenicity Beyond MHC Binding

NetMHCpan-4.0 predicts binding but not T-cell recognition, missing proteasomal cleavage and TAP transport integration (Jurtz et al., 2017). Validating predictions needs mass spectrometry-eluted ligands for true positives (Yadav et al., 2014). Full epitope processing pathway modeling remains incomplete.

Neoantigen Prediction in Tumors

Personalized vaccines require accurate tumor mutation immunogenicity, combining exome sequencing with MS (Şahin et al., 2017). Tools like ElliPro aid structure-based predictions but overlook T-cell specifics (Ponomarenko et al., 2008). Viral variant escape complicates predictions (Harvey et al., 2021).

Essential Papers

SARS-CoV-2 variants, spike mutations and immune escape

William T. Harvey, Alessandro M. Carabelli, Ben Jackson et al. · 2021 · Nature Reviews Microbiology · 3.7K citations

Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer

Uğur Şahin, Evelyna Derhovanessian, Matthias Miller et al. · 2017 · Nature · 2.3K citations

SYFPEITHI: database for MHC ligands and peptide motifs

Hans‐Georg Rammensee, Jutta Bachmann, Niels Emmerich et al. · 1999 · Immunogenetics · 2.3K citations

NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data

Birkir Reynisson, Bruno Alvarez, Sinu Paul et al. · 2020 · Nucleic Acids Research · 2.1K citations

Abstract Major histocompatibility complex (MHC) molecules are expressed on the cell surface, where they present peptides to T cells, which gives them a key role in the development of T-cell immune ...

Designing antimicrobial peptides: form follows function

Christopher D. Fjell, Jan A. Hiss, Robert E. W. Hancock et al. · 2011 · Nature Reviews Drug Discovery · 1.9K citations

In Silico Approach for Predicting Toxicity of Peptides and Proteins

Sudheer Gupta, Pallavi Kapoor, Kumardeep Chaudhary et al. · 2013 · PLoS ONE · 1.9K citations

ToxinPred is a unique in silico method of its kind, which will be useful in predicting toxicity of peptides/proteins. In addition, it will be useful in designing least toxic peptides and discoverin...

ElliPro: a new structure-based tool for the prediction of antibody epitopes

Julia Ponomarenko, Huynh‐Hoa Bui, Wei Li et al. · 2008 · BMC Bioinformatics · 1.6K citations

The results from ElliPro suggest that further research on antibody epitopes considering more features that discriminate epitopes from non-epitopes may further improve predictions. As ElliPro is bas...

Reading Guide

Foundational Papers

Start with SYFPEITHI database (Rammensee et al., 1999, 2312 citations) for MHC ligand motifs, then ElliPro for epitope structure basics (Ponomarenko et al., 2008, 1641 citations), and Yadav et al. (2014) for MS-based immunogenicity.

Recent Advances

Study NetMHCpan-4.1 (Reynisson et al., 2020) for MS-integrated predictions and Harvey et al. (2021) for SARS-CoV-2 applications.

Core Methods

Core techniques: pan-specific neural networks (NetMHCpan series), mass spectrometry ligand elution, motif databases (SYFPEITHI), binding affinity assays.

How PapersFlow Helps You Research T-Cell Epitope Prediction

Discover & Search

Research Agent uses searchPapers and exaSearch to find NetMHCpan-4.1 papers (Reynisson et al., 2020), then citationGraph reveals SYFPEITHI connections (Rammensee et al., 1999) and findSimilarPapers uncovers related MS ligand datasets.

Analyze & Verify

Analysis Agent applies readPaperContent to NetMHCpan-4.0 methods (Jurtz et al., 2017), verifies predictions with runPythonAnalysis on binding affinity datasets using NumPy/pandas, and employs verifyResponse (CoVe) with GRADE grading for immunogenicity classifier performance.

Synthesize & Write

Synthesis Agent detects gaps in proteasomal cleavage models across NetMHC papers, flags contradictions in MS data integration; Writing Agent uses latexEditText, latexSyncCitations for epitope prediction reviews, and latexCompile for vaccine design manuscripts with exportMermaid for MHC processing pathway diagrams.

Use Cases

"Benchmark NetMHCpan-4.1 vs SYFPEITHI for SARS-CoV-2 epitopes"

Research Agent → searchPapers + citationGraph → Analysis Agent → runPythonAnalysis (pandas AUC comparison on MS datasets) → CSV export of prediction accuracies.

"Draft LaTeX review on T-cell epitope tools for tumor vaccines"

Synthesis Agent → gap detection (Şahin et al., 2017) → Writing Agent → latexEditText + latexSyncCitations (Reynisson/Jurtz papers) + latexCompile → PDF with epitope workflow diagram.

"Find GitHub repos implementing NetMHCpan immunogenicity classifiers"

Research Agent → paperExtractUrls (NetMHCpan-4.1) → Code Discovery → paperFindGithubRepo + githubRepoInspect → runPythonAnalysis on repo code for prediction benchmarks.

Automated Workflows

Deep Research workflow scans 50+ NetMHC/SYFPEITHI papers for systematic review of MHC prediction advances, generating structured reports with GRADE-scored evidence. DeepScan applies 7-step analysis to benchmark immunogenicity classifiers from Yadav et al. (2014) MS data with CoVe checkpoints. Theorizer builds hypotheses on integrating proteasomal models from Harvey et al. (2021) variants.

Try Doxa for T-Cell Epitope Prediction Research

Frequently Asked Questions

What is T-Cell Epitope Prediction?

T-Cell Epitope Prediction computationally identifies peptides from proteasomal cleavage, TAP transport, and MHC class I presentation for CD8+ T-cell recognition. Key tools include NetMHCpan-4.1 (Reynisson et al., 2020).

What are main methods in T-Cell Epitope Prediction?

Methods use motif deconvolution, MS-eluted ligand integration (NetMHCpan-4.0, Jurtz et al., 2017), and databases like SYFPEITHI (Rammensee et al., 1999). Pan-specific models predict across MHC alleles.

What are key papers on T-Cell Epitope Prediction?

NetMHCpan-4.1 (Reynisson et al., 2020, 2097 citations), NetMHCpan-4.0 (Jurtz et al., 2017, 1465 citations), SYFPEITHI (Rammensee et al., 1999, 2312 citations).

What are open problems in T-Cell Epitope Prediction?

Challenges include accurate immunogenicity beyond MHC binding, neoantigen validation via MS/exome (Yadav et al., 2014), and handling viral escape mutations (Harvey et al., 2021).