AF2Complex predicts direct physical interactions in multimeric proteins with deep learning
By Mu Gao, Davi Nakajima An, Jerry M. Parks, Jeffrey Skolnick. 2022
229 citations recorded by the source corpus.
Accurate descriptions of protein-protein interactions are essential for understanding biological systems. Remarkably accurate atomic structures have been recently computed for individual proteins by AlphaFold2 (AF2). Here, we demonstrate that the same neural network models from AF2 developed for single protein sequences can be adapted to predict the structures of multimeric protein complexes without retraining. In contrast to common approaches, our method, AF2Complex, does not require paired multiple sequence alignments. It achieves higher accuracy than some complex protein-protein docking strategies and provides a significant improvement over AF-Multimer, a development of AlphaFold for multimeric proteins. Moreover, we introduce metrics for predicting direct protein-protein interactions between arbitrary protein pairs and validate AF2Complex on some challenging benchmark sets and the E. coli proteome. Lastly, using the cytochrome c biogenesis system I as an example, we present high-confidence models of three sought-after assemblies formed by eight members of this system. Accurate descriptions of protein-protein interactions are essential for understanding biological systems. Here the authors present AF2Complex and show that application to the E. coli cytochrome biogenesis system I yields confident computational models for three sought-after assemblies.
Subfields: Molecular Biology
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
- Andriy Kryshtafovych
- Maya Topf
- Daniel J. Rigden
- Rhiju Das
- Thomas Mulvaney
- J. Beton
- Rachael Kretsch
- Manuel Rodríguez‐Paredes
Citations in the corpus
- AlphaFold2 and its applications in the fields of biology and medicine (2023, background): “Gao et al.(145) developed an AF2-based system called AF2Complex, which can predict direct physical interactions in multimeric proteins.”
- CASP15 cryoEM protein and RNA targets: refinement and analysis using experimental maps (2023, background): “Since then, AlphaFold-Multimer, RosettaFold 5 and AF2Complex 6 are a few examples of a growing number of deep-learning approaches to complex prediction.”
- Mapping the interaction between Trim28 and the KRAB domain at the center of Trim28 silencing of endogenous retroviruses (2022, unknown): “The development of AF-multimer trained on multimeric inputs and recent work on AF2Complex is seeking to make complex modeling more accurate and routine.(31,33) While still in its infancy for predicting protein complexes, the interaction between Trim28 and the KRAB domain is an ideal model to examine”
- The high mobility group protein HMG20A cooperates with the histone reader PHF14 to modulate TGFβ and Hippo pathways (2022, methodology): “The Alphafold2 software has successfully been used to predict protein-protein complex formation and interaction domains (30,41).”