Protein complex prediction with AlphaFold-Multimer

By Richard Evans, Michael O’Neill, Alexander Pritzel, Natasha Antropova, Andrew Senior, Tim Green, Augustin Žídek, Russ Bates, Sam Blackwell, Jason Yim and 12 more. 2021

3,230 citations recorded by the source corpus.

While the vast majority of well-structured single protein chains can now be predicted to high accuracy due to the recent AlphaFold [1] model, the prediction of multi-chain protein complexes remains a challenge in many cases. In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy. On a benchmark dataset of 17 heterodimer proteins without templates (introduced in [2]) we achieve at least medium accuracy (DockQ [3] ≥ 0.49) on 13 targets and high accuracy (DockQ ≥ 0.8) on 7 targets, compared to 9 targets of at least medium accuracy and 4 of high accuracy for the previous state of the art system (an AlphaFold-based system from [2]). We also predict structures for a large dataset of 4,446 recent protein complexes, from which we score all non-redundant interfaces with low template identity. For heteromeric interfaces we successfully predict the interface (DockQ ≥ 0.23) in 70% of cases, and produce high accuracy predictions (DockQ ≥ 0.8) in 26% of cases, an improvement of +27 and +14 percentage points over the flexible linker modification of AlphaFold [4] respectively. For homomeric inter-faces we successfully predict the interface in 72% of cases, and produce high accuracy predictions in 36% of cases, an improvement of +8 and +7 percentage points respectively.

Subfields: Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Accurate structure prediction of biomolecular interactions with AlphaFold 3 (2024, methodology): “…accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3 7,8 .”
In silico protein interaction screening uncovers DONSON’s role in replication initiation (2023, methodology): “Briefly, 1 volume of streptavidin-coated magnetic beads (Dynabeads M-280, Invitrogen 11206D) was incubated with 6 volumes of binding buffer (50 mM Tris-HCl pH 7.5, 150 mM NaCl, 1 mM EDTA, 0.02% Tween 20) containing 0.2 m M of biotinylated recombinant LacI for 40 min at room temperature.”
AlphaFold2 and its applications in the fields of biology and medicine (2023, background): “Evans et al. 139 extended AF2 to the prediction of multiple-chain complex, and the system was named as AlphaFold-Multimer.”
Evolutionary-scale prediction of atomic level protein structure with a language model (2022, background): “[45] Richard Evans, Michael O’Neill, Alexander Pritzel, Natasha Antropova, Andrew Senior, Tim Green, Augustin Žı́dek, Russ Bates, Sam Blackwell, Jason Yim, Olaf Ronneberger, Sebastian Bodenstein, Michal Zielinski, Alex Bridgland, Anna Potapenko, Andrew Cowie, Kathryn Tunyasuvunakool, Rishub Jain, El”
High-resolution de novo structure prediction from primary sequence (2022, methodology): “…models, which has been demonstrated to be able to extract biologically meaningful representations for various tasks such as protein contact prediction ( 11–14 ), protein function prediction ( 15,16 ), zero-shot mutation effect prediction ( 17 ), and viral evolution and escape prediction ( 18, 19 ).”
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, methodology): “A related problem is protein-protein docking in which recent methods have performed direct prediction of the complex structure from the two concatenated input sequences using evolutionary information (Evans et al., 2021), or have leveraged geometric deep learning to model rigid body docking (Ganea e”
Plasmodium 6-Cysteine Proteins: Functional Diversity, Transmission-Blocking Antibodies and Structural Scaffolds (2022, methodology): “It could be utilized for P. falciparum to provide insights into ligand recognition by 6- cysteine proteins (Evans et al., 2022).”
P HYSICS - INFORMED DEEP NEURAL NETWORK FOR RIGID - BODY PROTEIN DOCKING (2022, background): “Evans et al. (2021) capital-ized on the success of AlphaFold to develop AlphaFold-multimer which both folds and docks two protein structures.”