Evaluation of methods for AlphaFold-based integrative modeling
- 1NCBS, TIFR
Abstract
Motivation Recent methods enable incorporation of experimental data into AlphaFold for predicting structures consistent with the data. However, the applicability of these methods for integrative modeling remains to be determined. It is unclear how these methods balance the input experimental data with the learned structural priors. Results We assess the performance of state-of-the-art AlphaFold-based integrative modeling methods, including AlphaLink2, Boltz2, and GRASP, on a dataset of 37 complexes based on crosslinking data. We evaluate these methods based on their ability to predict structures that satisfy the input crosslinks. We further assess the robustness of these methods to noise in the crosslinking data. Finally, we probe their ability to predict distinct states using crosslinks from multiple states. Overall, our study highlights the limitations of the AF-based IM methods and points to directions for future improvements. Availability and implementation All scripts used to obtain the predictions and perform the analysis in this study are available at https://github.com/isblab/af_im.
Related
- On the variability of generative artificial intelligence methods in conceptual modeling: an experimental evaluation on combining causal maps
- Cross-Frequency Coupling as a Neural Substrate for Prediction Error Evaluation: A Laminar Neural Mass Modeling Approach
- Proteome scale drug prioritization from AlphaFold 3 interaction confidence
- Retrieval of binding sites across the AlphaFold human proteome using protein language model representations
- General prediction of T cell receptor antigen specificity from sequence using AlphaFold 3
BibTeX
@misc{majila2026evaluation,
title = {{Evaluation of methods for AlphaFold-based integrative modeling}},
author = {K. Majila and S. Viswanath},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.13.751323},
url = {https://www.biorxiv.org/content/10.64898/2026.09.13.751323v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Evaluation of methods for AlphaFold-based integrative modeling
AU - K. Majila
AU - S. Viswanath
PY - 2026
DA - 2026/09/13
PB - bioRxiv
DO - 10.64898/2026.09.13.751323
UR - https://www.biorxiv.org/content/10.64898/2026.09.13.751323v1
AB - Motivation Recent methods enable incorporation of experimental data into AlphaFold for predicting structures consistent with the data. However, the applicability of these methods for integrative modeling remains to be determined. It is unclear how these methods balance the input experimental data with the learned structural priors. Results We assess the performance of state-of-the-art AlphaFold-based integrative modeling methods, including AlphaLink2, Boltz2, and GRASP, on a dataset of 37 complexes based on crosslinking data. We evaluate these methods based on their ability to predict structures that satisfy the input crosslinks. We further assess the robustness of these methods to noise in the crosslinking data. Finally, we probe their ability to predict distinct states using crosslinks from multiple states. Overall, our study highlights the limitations of the AF-based IM methods and points to directions for future improvements. Availability and implementation All scripts used to obtain the predictions and perform the analysis in this study are available at https://github.com/isblab/af_im.
ER -