T-SCAPE: T-cell immunogenicity scoring via cross-domain aided predictive engine

T-cell immunogenicity is a critical determinant of safety and efficacy for protein therapeutics and vaccines, but prediction is hampered by data scarcity. We present T-SCAPE, a multi-domain deep learning framework that uses adversarial domain adaptation to integrate diverse immunologically relevant data sources, including MHC presentation, peptide-MHC binding affinity, TCR-pMHC interaction, source organism information, and T-cell activation. Validated through rigorous leakage-controlled benchmarks, T-SCAPE shows exceptional performance in predicting T-cell activation for specific peptide-MHC pairs. Remarkably, it also accurately predicts the anti-drug antibody-inducing potential of therapeutic antibodies without MHC inputs, a success attributed to its biologically grounded pretraining. Confirmed by extensive case studies and ablation studies, T-SCAPE’s flexible architecture also supports broader tasks like molecular binding prediction. Its robust performance highlights its potential to ..., , # T-SCAPE: T-cell immunogenicity scoring via cross-domain aided predictive engine

**Dataset DOI:** 10.5061/dryad.s7h44j1k7

## 1. Description of the Dataset

This dataset serves as the official training, validation, and benchmarking repository for **TITANiAN (T-SCAPE)**, a deep learning model designed to predict T-cell immunogenicity. The data compiles T-cell receptor (TCR) sequences, epitope sequences, and MHC alleles from multiple public immunology databases.

This repository contains all data files used for training and benchmarking. The source code is hosted separately due to licensing requirements (see Section 4).

## 2. File Structure and Contents

The dataset is organized into three zipped archives.

### A. train.zip

Contains the primary datasets used for model training.

* `TITANiAN_pretrain_train.csv`: Dataset used for self-supervised pre-training.
* `TITANiAN_finetune_train.csv`: Dataset used for supervised fine-tuning.

### B. valid.zip

Contains datasets used for model val...,