AlphaFold2 Update and Perspectives

Access to the three-dimensional (3D) structural information of macromolecules is of major interest in both fundamental and applied research. Obtaining this experimental data can be complex, time consuming, and costly. Therefore, in silico computational approaches are an alternative of interest, and sometimes present a unique option. In this context, the Protein Structure Prediction method AlphaFold2 represented a revolutionary advance in structural bioinformatics. Named method of the year in 2021, and widely distributed by DeepMind and EBI, it was thought at this time that protein-folding issues had been resolved. However, the reality is slightly more complex. Due to a lack of input experimental data, related to crystallographic challenges, some targets have remained highly challenging or not feasible. This perspective exercise, dedicated to a non-expert audience, discusses and correctly places AlphaFold2 methodology in its context and, above all, highlights its use, limitations, and opportunities. After a review of the interest in the 3D structure and of the previous methods used in the field, AF2 is brought into its historical context. Its spatial interests are detailed before presenting precise quantifications showing some limitations of this approach and finishing with the perspectives in the field.

[1]  A. D. de Brevern,et al.  A novel high‐prevalence antigen in the Lutheran system, LUGA (LU24), and an updated, full‐length 3D BCAM model , 2023, Transfusion.

[2]  R. Brüschweiler,et al.  Predicting protein flexibility with AlphaFold , 2023, Proteins.

[3]  Zeming Lin,et al.  Evolutionary-scale prediction of atomic level protein structure with a language model , 2022, bioRxiv.

[4]  E. McDonagh,et al.  EMBL’s European Bioinformatics Institute (EMBL-EBI) in 2022 , 2022, Nucleic Acids Res..

[5]  R. Joosten,et al.  AlphaFill: enriching AlphaFold models with ligands and cofactors , 2022, Nature Methods.

[6]  Cathy H. Wu,et al.  UniProt: the Universal Protein Knowledgebase in 2023 , 2022, Nucleic acids research.

[7]  R. Cusick,et al.  Two new Scianna variants causing loss of high prevalence antigens: ERMAP model and 3D analysis of the antigens , 2022, Transfusion.

[8]  A. D. de Brevern.  An agnostic analysis of the human AlphaFold2 proteome using local protein conformations. , 2022, Biochimie.

[9]  Tristan Bitard-Feildel,et al.  A sequence‐based foldability score combined with AlphaFold2 predictions to disentangle the protein order/disorder continuum , 2022, Proteins.

[10]  S. Lindert,et al.  Prediction of Intrinsic Disorder Using Rosetta ResidueDisorder and AlphaFold2. , 2022, The journal of physical chemistry. B.

[11]  Silvio C. E. Tosatto,et al.  Intrinsic protein disorder and conditional folding in AlphaFoldDB , 2022, Protein science : a publication of the Protein Society.

[12]  J. Fantini,et al.  The Epigenetic Dimension of Protein Structure Is an Intrinsic Weakness of the AlphaFold Program , 2022, Biomolecules.

[13]  J. Mornon,et al.  Digging into the 3D Structure Predictions of AlphaFold2 with Low Confidence: Disorder and Beyond , 2022, Biomolecules.

[14]  Chengcheng Shi,et al.  Deep learning-based molecular dynamics simulation for structure-based drug design against SARS-CoV-2 , 2022, Computational and Structural Biotechnology Journal.

[15]  K. Cowtan,et al.  ModelCraft: an advanced automated model-building pipeline using Buccaneer , 2022, Acta crystallographica. Section D, Structural biology.

[16]  R. Nussinov,et al.  AlphaFold, Artificial Intelligence (AI), and Allostery , 2022, The journal of physical chemistry. B.

[17]  T. Akutsu,et al.  PROST: AlphaFold2-aware Sequence-Based Predictor to Estimate Protein Stability Changes upon Missense Mutations , 2022, J. Chem. Inf. Model..

[18]  Takashi Yoshidome,et al.  AlphaFold-predicted Protein Structure vs Experimentally Obtained Protein Structure: An Emphasis on the Side Chains , 2022, Journal of the Physical Society of Japan.

[19]  M. Tangney,et al.  An Overview of Alphafold's Breakthrough , 2022, Frontiers in Artificial Intelligence.

[20]  Su Datt Lam,et al.  AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms , 2022, bioRxiv.

[21]  S. Burley,et al.  Assessing PDB Macromolecular Crystal Structure Confidence at the Individual Amino Acid Residue Level , 2022, bioRxiv.

[22]  B. Grzybowski,et al.  AlphaFold2 can predict single-mutation effects , 2022, bioRxiv.

[23]  M. Graille,et al.  The X-ray crystallography phase problem solved thanks to AlphaFold and RoseTTAFold models: a case-study report. , 2022, Acta crystallographica. Section D, Structural biology.

[24]  Devlina Chakravarty,et al.  AlphaFold2 fails to predict protein fold switching , 2022, bioRxiv.

[25]  Aisha Al-Janabi.  Has DeepMind's AlphaFold solved the protein folding problem? , 2022, BioTechniques.

[26]  V. Marx.  Method of the Year: protein structure prediction , 2022, Nature Methods.

[27]  D. Hassabis,et al.  Protein structure predictions to atomic accuracy with AlphaFold , 2022, Nature Methods.

[28]  Method of the Year 2021: Protein structure prediction , 2022, Nature Methods.

[29]  D. Hassabis,et al.  AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models , 2021, Nucleic Acids Res..

[30]  I. Anishchenko,et al.  The trRosetta server for fast and accurate protein structure prediction , 2021, Nature Protocols.

[31]  D. Hassabis,et al.  Protein complex prediction with AlphaFold-Multimer , 2021, bioRxiv.

[32]  Oriol Vinyals,et al.  Applying and improving AlphaFold at CASP14 , 2021, Proteins.

[33]  R. Laskowski,et al.  AlphaFold heralds a data-driven revolution in biology and medicine , 2021, Nature Medicine.

[34]  Jeffrey Skolnick,et al.  AlphaFold 2: Why It Works and Its Implications for Understanding the Relationships of Protein Sequence, Structure, and Function , 2021, J. Chem. Inf. Model..

[35]  Douglas E. V. Pires,et al.  A structural biology community assessment of AlphaFold2 applications , 2021, bioRxiv.

[36]  D. Ivankov,et al.  Using AlphaFold to predict the impact of single mutations on protein stability and function , 2021, bioRxiv.

[37]  D. Rigden,et al.  MrParse: finding homologues in the PDB and the EBI AlphaFold database for molecular replacement and more , 2021, bioRxiv.

[38]  C. Harrison,et al.  Current and future status of JAK inhibitors , 2021, The Lancet.

[39]  S. Ovchinnikov,et al.  ColabFold: making protein folding accessible to all , 2022, Nature Methods.

[40]  R. Russell,et al.  Next generation protein structure predictions and genetic variant interpretation. , 2021, Journal of molecular biology.

[41]  K. Kavukcuoglu,et al.  Highly accurate protein structure prediction for the human proteome , 2021, Nature.

[42]  Gyu Rie Lee,et al.  Accurate prediction of protein structures and interactions using a 3-track neural network , 2021, Science.

[43]  Oriol Vinyals,et al.  Highly accurate protein structure prediction with AlphaFold , 2021, Nature.

[44]  A. Fersht.  AlphaFold - A personal perspective on the impact of Machine Learning. , 2021, Journal of molecular biology.

[45]  A. D. de Brevern,et al.  Insights into anti‐D formation in carriers of RhD variants through studies of 3D intraprotein interactions , 2021, Transfusion.

[46]  E. Schönbrunn,et al.  Structural Insights into JAK2 Inhibition by Ruxolitinib, Fedratinib, and Derivatives Thereof. , 2021, Journal of Medicinal Chemistry.

[47]  Ewen Callaway,et al.  ‘It will change everything’: DeepMind’s AI makes gigantic leap in solving protein structures , 2020, Nature.

[48]  Peter B. McGarvey,et al.  UniProt: the universal protein knowledgebase in 2021 , 2020, Nucleic Acids Res..

[49]  Brian D. Weitzner,et al.  Macromolecular modeling and design in Rosetta: recent methods and frameworks , 2020, Nature Methods.

[50]  David T. Jones,et al.  Improved protein structure prediction using potentials from deep learning , 2020, Nature.

[51]  Mohammed AlQuraishi,et al.  AlphaFold at CASP13 , 2019, Bioinform..

[52]  Nicolas K. Shinada,et al.  Discrete analyses of protein dynamics , 2019, Journal of biomolecular structure & dynamics.

[53]  Matteo T Degiacomi,et al.  Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space. , 2019, Structure.

[54]  A. D. de Brevern,et al.  Alloimmunization risk associated with amino acid 223 substitution in the RhD protein: analysis in the light of molecular modeling , 2018, Transfusion.

[55]  Torsten Schwede,et al.  SWISS-MODEL: homology modelling of protein structures and complexes , 2018, Nucleic Acids Res..

[56]  K. Ahmad,et al.  Protein-protein Interactions and their Role in Various Diseases and their Prediction Techniques. , 2017, Current protein & peptide science.

[57]  Alexander D. MacKerell,et al.  CHARMM‐GUI 10 years for biomolecular modeling and simulation , 2017, J. Comput. Chem..

[58]  A. G. Brevern,et al.  Recent advances on polyproline II , 2017, Amino Acids.

[59]  Torsten Schwede,et al.  The SWISS-MODEL Repository—new features and functionality , 2016, Nucleic Acids Res..

[60]  Vladimir N. Uversky,et al.  Order, Disorder, and Everything in Between , 2016, Molecules.

[61]  Ben M. Webb,et al.  Comparative Protein Structure Modeling Using MODELLER , 2016, Current protocols in bioinformatics.

[62]  Lisa N Kinch,et al.  Evaluation of free modeling targets in CASP11 and ROLL , 2016, Proteins.

[63]  R. Horuk.  The Duffy Antigen Receptor for Chemokines DARC/ACKR1 , 2015, Front. Immunol..

[64]  Bohdan Schneider,et al.  Protein flexibility in the light of structural alphabets , 2015, Front. Mol. Biosci..

[65]  Michael J E Sternberg,et al.  The Phyre2 web portal for protein modeling, prediction and analysis , 2015, Nature Protocols.

[66]  Yang Zhang,et al.  The I-TASSER Suite: protein structure and function prediction , 2014, Nature Methods.

[67]  Yang Zhang.  Interplay of I‐TASSER and QUARK for template‐based and ab initio protein structure prediction in CASP10 , 2014, Proteins.

[68]  A. G. Brevern,et al.  Cis–trans isomerization of omega dihedrals in proteins , 2013, Amino Acids.

[69]  L. S. Swapna,et al.  Comparison of tertiary structures of proteins in protein-protein complexes with unbound forms suggests prevalence of allostery in signalling proteins , 2012, BMC Structural Biology.

[70]  Yang Zhang,et al.  I-TASSER: a unified platform for automated protein structure and function prediction , 2010, Nature Protocols.

[71]  Andrej Sali,et al.  Fold assessment for comparative protein structure modeling , 2007, Protein science : a publication of the Protein Society.

[72]  A. G. Brevern,et al.  A structural model of a seven-transmembrane helix receptor: the Duffy antigen/receptor for chemokine (DARC). , 2005, Biochimica et biophysica acta.

[73]  Manuel C. Peitsch,et al.  SWISS-MODEL: an automated protein homology-modeling server , 2003, Nucleic Acids Res..

[74]  Christopher Bystroff,et al.  Fully automated ab initio protein structure prediction using I-STES, HMMSTR and ROSETTA , 2002, ISMB.

[75]  P E Bourne,et al.  The Protein Data Bank. , 2002, Nucleic acids research.

[76]  A. Sali,et al.  Protein Structure Prediction and Structural Genomics , 2001, Science.

[77]  M. James,et al.  A critical assessment of comparative molecular modeling of tertiary structures of proteins * , 1995, Proteins.

[78]  T. Blundell,et al.  Comparative protein modelling by satisfaction of spatial restraints. , 1993, Journal of molecular biology.

[79]  G J Williams,et al.  The Protein Data Bank: a computer-based archival file for macromolecular structures. , 1977, Journal of molecular biology.

[80]  Christopher J. Williams,et al.  Title: AlphaFold predictions: great hypotheses but no match for experiment , 2022 .

[81]  OUP accepted manuscript , 2021, Nucleic Acids Research.

[82]  OUP accepted manuscript , 2021, Briefings In Bioinformatics.

[83]  Pushmeet Kohli,et al.  Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13) , 2019, Proteins.

[84]  David E. Kim,et al.  Free modeling with Rosetta in CASP6 , 2005, Proteins.

[85]  Marcin Feder,et al.  A “FRankenstein's monster” approach to comparative modeling: Merging the finest fragments of Fold‐Recognition models and iterative model refinement aided by 3D structure evaluation , 2003, Proteins.

[86]  Narayanan Eswar,et al.  MODBASE, a database of annotated comparative protein structure models , 2002, Nucleic Acids Res..

[87]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..