@article {Evans2021.10.04.463034, author = {Richard Evans and Michael O{\textquoteright}Neill and Alexander Pritzel and Natasha Antropova and Andrew Senior and Tim Green and Augustin {\v Z}{\'\i}dek and Russ Bates and Sam Blackwell and Jason Yim and Olaf Ronneberger and Sebastian Bodenstein and Michal Zielinski and Alex Bridgland and Anna Potapenko and Andrew Cowie and Kathryn Tunyasuvunakool and Rishub Jain and Ellen Clancy and Pushmeet Kohli and John Jumper and Demis Hassabis}, title = {Protein complex prediction with AlphaFold-Multimer}, elocation-id = {2021.10.04.463034}, year = {2021}, doi = {10.1101/2021.10.04.463034}, publisher = {Cold Spring Harbor Laboratory}, abstract = {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 14 targets and high accuracy (DockQ >= 0.8) on 6 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 4,433 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 67\% of cases, and produce high accuracy predictions (DockQ >= 0.8) in 23\% of cases, an improvement of +25 and +11 percentage points over the flexible linker modification of AlphaFold [4] respectively. For homomeric interfaces we successfully predict the interface in 69\% of cases, and produce high accuracy predictions in 34\% of cases, an improvement of +5 percentage points in both instances.Competing Interest StatementThe authors have declared no competing interest.}, URL = {https://www.biorxiv.org/content/early/2021/10/04/2021.10.04.463034}, eprint = {https://www.biorxiv.org/content/early/2021/10/04/2021.10.04.463034.full.pdf}, journal = {bioRxiv} }