Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants
By Rui Yin, Brandon Yushan Feng, Amitabh Varshney, Brian G. Pierce. 2021
270 citations recorded by the source corpus.
High resolution experimental structural determination of protein-protein interactions has led to valuable mechanistic insights, yet due to the massive number of interactions and experimental limitations there is a need for computational methods that can accurately model their structures. Here we explore the use of the recently developed deep learning method, AlphaFold, to predict structures of protein complexes from sequence. With a benchmark of 152 diverse heterodimeric protein complexes, multiple implementations and parameters of AlphaFold were tested for accuracy. Remarkably, many cases had highly accurate models generated as top-ranked predictions, greatly surpassing the performance of unbound protein-protein docking, whereas antibody-antigen docking was largely unsuccessful. While AlphaFold-generated accuracy predictions were able to discriminate near-native models, previously developed scoring protocols improved performance. Our study demonstrates that end-to-end deep learning can accurately model transient protein complexes, and identifies areas for improvement to guide future developments to reliably model any protein-protein interaction of interest.
Subfields: Molecular Biology, Radiology, Nuclear Medicine and Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Molecular Biology
In Radiology, Nuclear Medicine and Imaging
Citations in the corpus
- AlphaFold2 and its applications in the fields of biology and medicine (2023, background): “143 Yin et al. 144 examined the performance of AF2 in predicting structures of protein complexes from amino acid sequence.”
- The impact of AlphaFold2 one year on (2022, unknown): “And unlike the job of painting the Forth Bridge, which now only needs to be done every 25 years, updating of the AlphaFold Database will need to be done much more often.”