Debraj Das

Learning the spatial cell-cell communication network to decode multi-channel signaling and predict network-hub vulnerabilities with MOSANIC

MOSANIC learns a spatial cell-cell communication network from transcriptomics data to identify network hubs and predict vulnerabilities in breast cancer.

GraphTox: A Semi-Supervised Pre-Trained Framework for Peptide Toxicity Prediction using Geometric Graph Transformer and LORA-Based Finetuning

GraphTox predicts peptide toxicity using a geometric graph transformer and LORA-based finetuning, outperforming existing methods by incorporating structural information.

DeepPROTECTNeo: A Context-aware Personalized and Reverse Vaccinology-guided Deep Learning Framework for Immunogenicity Prediction

DeepPROTECTNeo predicts immunogenic neoepitopes by integrating genomic data and TCR-epitope interactions, outperforming existing methods with high accuracy and interpretability.