# Neural message passing for joint paratope-epitope prediction

Source: [Neural message passing for joint paratope-epitope prediction](<https://www.sota2.com/research/paper/68fa5f171e209131ce9e76e0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:07:52.793Z

Authors: Alice Del Vecchio, Andreea Deac, Pietro Li\\\`o, Petar Veli\\v{c}kovi\\'c

Published: 2021-05-31T16:37:55.000Z

## Abstract

Antibodies are proteins in the immune system which bind to antigens to detect and neutralise them. The binding sites in an antibody-antigen interaction are known as the paratope and epitope, respectively, and the prediction of these regions is key to vaccine and synthetic antibody development. Contrary to prior art, we argue that paratope and epitope predictors require asymmetric treatment, and propose distinct neural message passing architectures that are geared towards the specific aspects of paratope and epitope prediction, respectively. We obtain significant improvements on both tasks, setting the new state-of-the-art and recovering favourable qualitative predictions on antigens of relevance to COVID-19.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Joint Paratope-Epitope Prediction on SAbDab](<https://www.sota2.com/research/sota/joint-paratope-epitope-prediction-on-sabdab.md>): Joint Paratope-Epitope Prediction; SAbDab; Paratope AUC: 87.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.00757>)

[PDF](<https://arxiv.org/pdf/2106.00757.pdf>)