Calibrating AlphaFold confidence scores for interface quality
Abstract
AlphaFold confidence scores are widely used to rank protein complex predictions and to select subsets of models for downstream applications. Although these scores provide strong discriminatory power for distinguishing prediction quality, their numerical values were never intended to represent the probability that a prediction satisfies a given structural quality criterion. In this work, we calibrate commonly used confidence scores to estimate the probability that a predicted complex exceeds a chosen threshold of DockQ, an established measure of interface quality. On antibody-antigen and general multimer datasets, post-hoc isotonic calibration consistently improves agreement between predicted probabilities and observed DockQ success rates while preserving the underlying score ordering. The calibrated probabilities also provide more accurate estimates of the fraction of selected models expected to pass a given structural quality threshold. Although the mapping is fitted within a given prediction distribution and therefore transfers imperfectly across prediction domains, we show that reliable estimates are recovered from a small number of labeled target-domain samples. Because the calibration is entirely post hoc and requires no underlying AlphaFold model fine-tuning, it provides a straightforward and customizable way to convert existing model quality rankings into calibrated probabilities of passing a chosen structural quality threshold.
Related
- Mitochondrial quality control at the ferroptosis-pyroptosis interface in diabetic cardiomyopathy: a narrative critical synthesis
- Combining AlphaFold 3 with microscale thermophoresis for aptamer optimisation
- Characterizing the fragmentation of AlphaFold predictions.
- When can AlphaFold predict the oligomeric states of proteins?
- Residue-Level Energetic Analysis of Transient Misfolding in the Whirlin PDZ Tandem Reveals a Possible Connection to an AlphaFold-Predicted Alternative Topology.
BibTeX
@misc{sagadinov2026calibrating,
title = {{Calibrating AlphaFold confidence scores for interface quality}},
author = {Sagyndyk Sagadinov and Vsevolod Viliuga and Arne Elofsson},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17108},
eprint = {2610.17108},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17108},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Calibrating AlphaFold confidence scores for interface quality
AU - Sagyndyk Sagadinov
AU - Vsevolod Viliuga
AU - Arne Elofsson
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17108
UR - https://arxiv.org/abs/2610.17108
AB - AlphaFold confidence scores are widely used to rank protein complex predictions and to select subsets of models for downstream applications. Although these scores provide strong discriminatory power for distinguishing prediction quality, their numerical values were never intended to represent the probability that a prediction satisfies a given structural quality criterion. In this work, we calibrate commonly used confidence scores to estimate the probability that a predicted complex exceeds a chosen threshold of DockQ, an established measure of interface quality. On antibody-antigen and general multimer datasets, post-hoc isotonic calibration consistently improves agreement between predicted probabilities and observed DockQ success rates while preserving the underlying score ordering. The calibrated probabilities also provide more accurate estimates of the fraction of selected models expected to pass a given structural quality threshold. Although the mapping is fitted within a given prediction distribution and therefore transfers imperfectly across prediction domains, we show that reliable estimates are recovered from a small number of labeled target-domain samples. Because the calibration is entirely post hoc and requires no underlying AlphaFold model fine-tuning, it provides a straightforward and customizable way to convert existing model quality rankings into calibrated probabilities of passing a chosen structural quality threshold.
ER -