Papadopoulos, A. M. | bioRxiv Science

bioRxiv2026

AntiSite: Modality Dropout Enables Antibody Paratope Prediction With or Without Structure From a Single Model

Summary: Reliable paratope identification is central to understanding antibody antigen recognition and advancing therapeutic antibody discovery. AntiSite is a unified antibody paratope prediction framework that combines protein language-model sequence embeddings with structure-derived molecular-surface features and, through modality dropout, trains a single checkpoint to predict both with and without a structure. This lets one model support sequence-only inference when no structure is available and structure-aware inference when an antibody structure is provided. Availability and implementation: Source code, trained models and evaluation scripts are freely available at https://github.com/aggelos-michael-papadopoulos/AntiSite. Processed benchmark structures and corrected split metadata are archived on Zenodo at https://doi.org/10.5281/zenodo.21705412.

bioinformatics↗

bioRxiv2024

ParaSurf: A Surface-Based Deep Learning Approach for Paratope-Antigen Interaction Prediction

MotivationIdentifying antibody binding sites, is crucial for developing vaccines and therapeutic antibodies, processes that are time-consuming and costly. Accurate prediction of the paratopes binding site can speed up the development by improving our understanding of antibody-antigen interactions. ResultsWe present ParaSurf, a deep learning model that significantly enhances paratope prediction by incorporating both surface geometric and non-geometric factors. Trained and tested on three prominent antibody-antigen benchmarks, ParaSurf achieves state-of-the-art results across nearly all metrics. Unlike models restricted to the variable region, ParaSurf demonstrates the ability to accurately predict binding scores across the entire Fab region of the antibody. Additionally, we conducted an extensive analysis using the largest of the three datasets employed, focusing on three key components: (1) a detailed evaluation of paratope prediction for each Complementarity-Determining Region loop, (2) the performance of models trained exclusively on the heavy chain, and (3) the results of training models solely on the light chain without incorporating data from the heavy chain. Availability and ImplementationSource code for ParaSurf, along with the datasets used, preprocessing pipeline, and trained model weights, are freely available at https://github.com/aggelos-michael-papadopoulos/ParaSurf. Contactangepapa@iti.gr, axenop@iti.gr Supplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗