TSNAD

TSNAD predicts tumor-specific neoantigens from whole-genome or whole-exome sequencing of tumor–normal pairs to support identification of targets for cancer immunotherapy.

Key Features:

• Tumor-normal WGS/WES support: Processes whole-genome and whole-exome sequencing data from tumor–normal pairs to identify tumor-specific mutations and candidate neoantigens.
• Integrated RNA-Seq analysis: Performs RNA-Seq-based gene expression profiling and gene fusion analysis to complement neoantigen prediction.
• Flexible reference genome support: Supports multiple reference genome versions for analysis consistency across datasets.
• Advanced neoantigen prediction: Implements DeepHLApan (replacing NetMHCpan) to predict peptide–MHC binding affinity and the immunogenicity of peptide–MHC (pMHC) complexes.
• Membrane protein and MHC I peptide detection: Identifies extracellular mutations of membrane proteins and mutated peptides presented by class I MHC molecules.
• Performance validation: Has been validated on standard datasets to assess neoantigen prediction performance.

Scientific Applications:

• Cancer immunotherapy target discovery: Enables identification of candidate neoantigens for vaccine development and other immunotherapeutic interventions.
• Analysis of large-scale cancer cohorts: Applicable to large genomic datasets such as the International Cancer Genome Consortium for discovery of candidate neoantigens across cancer types.
• Translational research support: Facilitates discovery of tumor-specific mutations to inform diagnostic, prognostic, and therapeutic research.

Methodology:

Detects tumor-specific mutations from tumor–normal WGS/WES, integrates RNA‑Seq gene expression profiling and gene fusion analysis, predicts peptide–MHC binding and pMHC immunogenicity using DeepHLApan (replacing NetMHCpan), supports multiple reference genomes, and has been validated on standard datasets.