My-Diem Nguyen Pham

This paper develops a cell-free DNA fragmentomic classifier using first-trimester NIPT data to predict spontaneous preterm birth with high accuracy.

CALFP-MHC improves peptide-MHC binding prediction by using chemically grounded fingerprints and contrastive learning, achieving high AUC and PPV across diverse alleles and class imbalance.

epiTCR-KDA improves TCR-peptide binding prediction by incorporating structural dihedral angles and knowledge distillation, achieving high AUC for both seen and unseen data.