[Nature Machine Intelligence] ImmunoStruct enables multimodal deep learning for immunogenicity prediction

Annotation of mutated peptide sequences with published or novel potential neoantigen descriptors

The official implementation of "Improving Antibody Humanness Prediction using Patent Data".

Implementation of the Analytic Hierarchy Process (AHP) to obtain the immunogenicity score of wheat lines based on their celiac disease (CD) epitopes matches on alpha- and gamma-gliadins amplicons by NGS and the score for oligopeptides based on an IFN-g ELISpot assays with fresh peripherical blood mononuclear cells (PBMCs).

Code for ImmunoGeNN: Accelerating Early Immunogenicity Assessment for Generative Design of Biologics

An ML-based immunogenicity predictor for T-cell epitopes of Mycobacterium Tuberculosis. It is purely based on amino acid sequences of epitope. Used Physicochemical descriptors and Amino Acid composition to make this proteomic data ML ready.

Code and data associated with Billings et al., "High dose inactivated influenza vaccine inconsistently improves heterologous antibody responses in an elderly human cohort", JID 2025.