ProAffiMuSeq: sequence-based method to predict the binding free energy change of protein-protein complexes upon mutation using functional classification

MOTIVATION Protein-protein interactions are essential for the cell and mediate various functions. However, mutations can disrupt these interactions and may cause diseases. Currently available computational methods require a complex structure as input for predicting the change in binding affinity. Further, they have not included the functional class information for the protein-protein complex. To address this, we have developed a method, ProAffiMuSeq, which predicts the change in binding free energy using sequence-based features and functional class. RESULTS Our method shows an average correlation between predicted and experimentally determined ΔΔG of 0.73 and mean absolute error (MAE) of 0.86 kcal/mol in 10-fold cross validation and correlation of 0.75 with MAE of 0.94 kcal/mol in the test dataset. ProAffiMuSeq was also tested on an external validation set and showed results comparable to structure-based methods. AVAILABILITY Users can access the method at https://web.iitm.ac.in/bioinfo2/proaffimuseq/. Our method can be used for large-scale analysis of disease-causing mutations in protein-protein complexes without structural information. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

[1]  Edmond J. Breen,et al.  Linking structural features of protein complexes and biological function , 2015, Protein science : a publication of the Protein Society.

[2]  Douglas E. V. Pires,et al.  mCSM: predicting the effects of mutations in proteins using graph-based signatures , 2013, Bioinform..

[3]  Conrad C. Huang,et al.  UCSF Chimera—A visualization system for exploratory research and analysis , 2004, J. Comput. Chem..

[4]  Philip M. Kim,et al.  Combining Structural Modeling with Ensemble Machine Learning to Accurately Predict Protein Fold Stability and Binding Affinity Effects upon Mutation , 2014, PloS one.

[5]  Mingming Jia,et al.  COSMIC: exploring the world's knowledge of somatic mutations in human cancer , 2014, Nucleic Acids Res..

[6]  Douglas E. V. Pires,et al.  mCSM-AB: a web server for predicting antibody–antigen affinity changes upon mutation with graph-based signatures , 2016, Nucleic Acids Res..

[7]  T. Yamazaki,et al.  Identification of the ligand-binding site of the BMP type IA receptor for BMP-4. , 2000, Biopolymers.

[8]  W. S. Valdar,et al.  Scoring residue conservation , 2002, Proteins.

[9]  Minoru Kanehisa,et al.  AAindex: amino acid index database, progress report 2008 , 2007, Nucleic Acids Res..

[10]  Wei Zheng,et al.  BindProfX: Assessing Mutation-Induced Binding Affinity Change by Protein Interface Profiles with Pseudo-Counts. , 2017, Journal of molecular biology.

[11]  Anna R. Panchenko,et al.  MutaBind estimates and interprets the effects of sequence variants on protein–protein interactions , 2016, Nucleic Acids Res..

[12]  Juan Fernández-Recio,et al.  SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation , 2018, bioRxiv.

[13]  Alexandre M J J Bonvin,et al.  iSEE: Interface structure, evolution, and energy‐based machine learning predictor of binding affinity changes upon mutations , 2019, Proteins.

[14]  M. Gromiha,et al.  Applications of Protein Thermodynamic Database for Understanding Protein Mutant Stability and Designing Stable Mutants. , 2016, Methods in molecular biology.

[15]  J. Schullek,et al.  Energetic contributions and topographical organization of ligand binding residues of tissue factor. , 1995, Biochemistry.

[16]  M. Gromiha,et al.  Discrimination of driver and passenger mutations in epidermal growth factor receptor in cancer. , 2015, Mutation research.

[17]  Markus Heinonen,et al.  Flex ddG: Rosetta ensemble-based estimation of changes in protein-protein binding affinity upon mutation , 2017, bioRxiv.

[18]  Sherlyn Jemimah,et al.  Protein-protein interactions: scoring schemes and binding affinity. , 2017, Current opinion in structural biology.

[19]  Emil Alexov,et al.  Predicting Binding Free Energy Change Caused by Point Mutations with Knowledge-Modified MM/PBSA Method , 2015, PLoS Comput. Biol..

[20]  Ricardo Villamarín-Salomón,et al.  ClinVar: public archive of interpretations of clinically relevant variants , 2015, Nucleic Acids Res..

[21]  M. Gromiha,et al.  Exploring additivity effects of double mutations on the binding affinity of protein‐protein complexes , 2018, Proteins.

[22]  Marianne Rooman,et al.  BeAtMuSiC: prediction of changes in protein–protein binding affinity on mutations , 2013, Nucleic Acids Res..

[23]  M. Michael Gromiha,et al.  Protein-protein binding affinity prediction from amino acid sequence , 2014, Bioinform..

[24]  M. Michael Gromiha,et al.  Folding RaCe: a robust method for predicting changes in protein folding rates upon point mutations , 2015, Bioinform..

[25]  R. Nussinov,et al.  Principles of protein-protein interactions: what are the preferred ways for proteins to interact? , 2008, Chemical reviews.

[26]  G Schreiber,et al.  Electrostatically optimized Ras-binding Ral guanine dissociation stimulator mutants increase the rate of association by stabilizing the encounter complex. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[27]  S. Jones,et al.  Principles of protein-protein interactions. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Geoffrey J. Barton,et al.  The contrasting properties of conservation and correlated phylogeny in protein functional residue prediction , 2015 .

[29]  R. Nussinov,et al.  Non-Redundant Unique Interface Structures as Templates for Modeling Protein Interactions , 2014, PloS one.

[30]  M. Michael Gromiha,et al.  PROXiMATE: a database of mutant protein-protein complex thermodynamics and kinetics , 2017, Bioinform..

[31]  Daniel F. A. R. Dourado,et al.  Modeling and fitting protein-protein complexes to predict change of binding energy , 2016, Scientific Reports.