Protein complex prediction with AlphaFold-Multimer

Evans, Rhett; O’Neill, Michael D.; Pritzel, Alexander; Антропова, Н. В.; Senior, Andrew W.; Green, Timothy; Žídek, Augustin; Bates, Russell; Blackwell, Sam; Yim, Jason; Ronneberger, Olaf; Bodenstein, Sebastian; Zieliński, Michał; Bridgland, Alex; Potapenko, Anna; Cowie, Andrew; Tunyasuvunakool, Kathryn; Jain, Rishub; Clancy, Ellen; Kohli, Pushmeet; Jumper, John; Hassabis, Demis

doi:10.1101/2021.10.04.463034

Cited by 2,516 publications

(3,030 citation statements)

References 41 publications

Supporting

Mentioning

2,985

Contrasting

Unclassified

Order By: Relevance

“…Recently, methods that use deep learning have been very successful in ab initio structure prediction [36][37][38][39]. The most successful of these, AlphaFold2, has shown atomic-accuracy prediction in community blind-prediction experiments and other structure-prediction challenges [40].…”

Section: Analyzing Design Foldability By Alphafold2mentioning

confidence: 99%

Assessing and enhancing foldability in designed proteins

Listov

Lipsh‐Sokolik

Rosset

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent advances in protein-design methodology have led to a dramatic increase in its reliability and scale. With these advances, dozens and even thousands of designed proteins are automatically generated and screened. Nevertheless, the success rate, particularly in design of functional proteins, is low and fundamental goals such as reliable de novo design of efficient enzymes remain beyond reach. Experimental analyses have consistently indicated that a major cause of design failure is inaccuracy and misfolding relative to the design model. To address this challenge, we describe complementary methods to diagnose and ameliorate suboptimal regions in designed proteins: first, we develop a Rosetta atomistic computational mutation scanning approach to detect energetically suboptimal positions in designs; second, we demonstrate that the AlphaFold2 ab initio structure prediction method flags regions that may misfold in designed enzymes and binders; and third, we focus FuncLib design calculations on suboptimal positions in a previously designed low-efficiency enzyme, thereby improving its catalytic efficiency by 330 fold. Thus, foldability analysis and enhancement may dramatically increase the success rate in design of functional proteins.

show abstract

Section: Analyzing Design Foldability By Alphafold2mentioning

confidence: 99%

Assessing and enhancing foldability in designed proteins

Listov

Lipsh‐Sokolik

Rosset

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The predicted structures by AlphaFold and RoseTTAFold both describe a protein that is composed of a winged helix-turn-helix (wHTH) DNA binding domain (DBD), followed by a PVQ-repeat leading into a carboxy-terminal coiled-coil domain ( Figure 9 a). Since the AlphaFold method is capable of modeling oligomers [ 62 ], the Gp05 was submitted for prediction as a homodimer.…”

Section: Non-conserved Exo-xis Region Proteins Of Interestmentioning

confidence: 99%

Molecular Modeling the Proteins from the exo-xis Region of Lambda and Shigatoxigenic Bacteriophages

Donaldson

2021

Antibiotics

View full text Add to dashboard Cite

Despite decades of intensive research on bacteriophage lambda, a relatively uncharacterized region remains between the exo and xis genes. Collectively, exo-xis region genes are expressed during the earliest stages of the lytic developmental cycle and are capable of affecting the molecular events associated with the lysogenic-lytic developmental decision. In Shiga toxin-producing E. coli (STEC) and enterohemorragic E. coli (EHEC) that are responsible for food- and water-borne outbreaks throughout the world, there are distinct differences of exo-xis region genes from their counterparts in lambda phage. Together, these differences may help EHEC-specific phage and their bacterial hosts adapt to the complex environment within the human intestine. Only one exo-xis region protein, Ea8.5, has been solved to date. Here, I have used the AlphaFold and RoseTTAFold machine learning algorithms to predict the structures of six exo-xis region proteins from lambda and STEC/EHEC phages. Together, the models suggest possible roles for exo-xis region proteins in transcription and the regulation of RNA polymerase.

show abstract

“…As this manuscript is being completed rapid advances are being made in adapting and extending AlphaFold2 to allow it to model homomeric and heteromeric protein complexes (e.g. [35][36][37]). It seems likely, therefore, that in the near future the same strategy reported here might be used to identify ligand binding sites that lie at the interface between separate polypeptide chains.…”

Section: Discussionmentioning

confidence: 99%

Identification of Iron-Sulfur (Fe-S) and Zn-binding Sites Within Proteomes Predicted by DeepMind’s AlphaFold2 Program Dramatically Expands the Metalloproteome

Wehrspan

McDonnell

Elcock

2021

Preprint

View full text Add to dashboard Cite

DeepMind′s AlphaFold2 software has ushered in a revolution in high quality, 3D protein structure prediction. In very recent work by the DeepMind team, structure predictions have been made for entire proteomes of twenty-one organisms, with >360,000 structures made available for download. Here we show that thousands of novel binding sites for iron-sulfur (Fe-S) clusters and zinc ions can be identified within these predicted structures by exhaustive enumeration of all potential ligand-binding orientations. We demonstrate that AlphaFold2 routinely makes highly specific predictions of ligand binding sites: for example, binding sites that are comprised exclusively of four cysteine sidechains fall into three clusters, representing binding sites for 4Fe-4S clusters, 2Fe-2S clusters, or individual Zn ions. We show further: (a) that the majority of known Fe-S cluster and Zn-binding sites documented in UniProt are recovered by the AlphaFold2 structures, (b) that there are occasional disputes between AlphaFold2 and UniProt with AlphaFold2 predicting highly plausible alternative binding sites, (c) that the Fe-S cluster binding sites that we identify in E. coli agree well with previous bioinformatics predictions, (d) that cysteines predicted here to be part of Fe-S cluster or Zn-binding sites show little overlap with those shown via chemoproteomics techniques to be highly reactive, and (e) that AlphaFold2 occasionally appears to build erroneous disulfide bonds between cysteines that should instead coordinate a ligand. These results suggest that AlphaFold2 could be an important tool for the functional annotation of proteomes, and the methodology presented here is likely to be useful for predicting other ligand-binding sites.

show abstract

Protein complex prediction with AlphaFold-Multimer

Cited by 2,516 publications

References 41 publications

Assessing and enhancing foldability in designed proteins

Assessing and enhancing foldability in designed proteins

Molecular Modeling the Proteins from the exo-xis Region of Lambda and Shigatoxigenic Bacteriophages

Identification of Iron-Sulfur (Fe-S) and Zn-binding Sites Within Proteomes Predicted by DeepMind’s AlphaFold2 Program Dramatically Expands the Metalloproteome

Contact Info

Product

Resources

About