Models such as AlphaFold2 and OpenFold have transformed protein structure prediction, yet their inner workings remain poorly understood. We present a methodology to systematically evaluate the contribution of individual OpenFold components to structure prediction accuracy. We identify several components that are critical for most proteins, while others vary in importance across proteins. We further show that the contribution of several components is correlated with protein length. These findings provide insight into how OpenFold achieves accurate predictions and highlight directions for interpreting protein prediction networks more broadly.
@article{arxiv.2511.14781,
title = {Quantifying the Role of OpenFold Components in Protein Structure Prediction},
author = {Tyler L. Hayes and Giri P. Krishnan},
journal= {arXiv preprint arXiv:2511.14781},
year = {2025}
}
Comments
Accepted to the NeurIPS 2025 Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences