Combining Structural Modeling with Ensemble Machine Learning to Accurately Predict Protein Fold Stability and Binding Affinity Effects upon Mutation
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Advances in sequencing have led to a rapid accumulation of mutations, some of which are associated with diseases. However, to draw mechanistic conclusions, a biochemical understanding of these mutations is necessary. For coding mutations, accurate prediction of significant changes in either the stability of proteins or their affinity to their binding partners is required. Traditional methods have used semi-empirical force fields, while newer methods employ machine learning of sequence and structural features. Here, we show how combining both of these approaches leads to a marked boost in accuracy. We introduce ELASPIC, a novel ensemble machine learning approach that is able to predict stability effects upon mutation in both, domain cores and domain-domain interfaces. We combine semi-empirical energy terms, sequence conservation, and a wide variety of molecular details with a Stochastic Gradient Boosting of Decision Trees (SGB-DT) algorithm. The accuracy of our predictions surpasses existing methods by a considerable margin, achieving correlation coefficients of 0.77 for stability, and 0.75 for affinity predictions. Notably, we integrated homology modeling to enable proteome-wide prediction and show that accurate prediction on modeled structures is possible. Lastly, ELASPIC showed significant differences between various types of disease-associated mutations, as well as between disease and common neutral mutations. Unlike pure sequence-based prediction methods that try to predict phenotypic effects of mutations, our predictions unravel the molecular details governing the protein instability, and help us better understand the molecular causes of diseases.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kumar, P., Henikoff, S., & Ng, P. C. (2009) · Nature Protocols · doi:10.1038/nprot.2009.86 · Cited by 6,521 · cited 6×
“The most popular method among the sequence-based algorithms is SIFT (Sorting Intolerant from Tolerant) [16], which uses multiple sequence alignments of homologous sequences to generate scores at each position based on patterns of amino acid substitutions.”
MethodInfluentialHMMER web server: interactive sequence similarity searching
Finn, R. D., Clements, J., & Eddy, S. R. (2011) · Nucleic Acids Research · doi:10.1093/nar/gkr367 · Cited by 5,952
Network medicine: a network-based approach to human disease
Barabási, A.-L., Gulbahce, N., & Loscalzo, J. (2011) · Nature Reviews Genetics · doi:10.1038/nrg2918 · Cited by 5,034 · cited 1×
“However, other relevant cellular factors, such as expression or protein essentiality, should be taken into account [55].”
BackgroundKollman, P. A., Massova, I., Reyes, C., Kuhn, B., Huo, S., Chong, L., Lee, M., Lee, T., Duan, Y., Wang, W., et al. (2000) · Accounts of Chemical Research · doi:10.1021/ar000033j · Cited by 4,978
Blume-Jensen, P., & Hunter, T. (2001) · Nature · doi:10.1038/35077225 · Cited by 3,738
MutationTaster evaluates disease-causing potential of sequence alterations
Schwarz, J. M., Rödelsperger, C., Schuelke, M., & Seelow, D. (2010) · Nature Methods · doi:10.1038/nmeth0810-575 · Cited by 2,975 · cited 1×
“Therefore, ELASPIC should not be taken as a predictor of disease mutations, such as the sequence-based methods MutationTaster [56] or SNAP [57], since it was trained to predict stability rather than phenotype effect of mutations.”
MethodCOSMIC: mining complete cancer genomes in the Catalogue of Somatic Mutations in Cancer
Forbes, S. A., Bindal, N., Bamford, S., Cole, C., Kok, C. Y., Beare, D., Jia, M., Shepherd, R., Leung, K., Menzies, A., et al. (2011) · Nucleic Acids Research · doi:10.1093/nar/gkq929 · Cited by 2,278 · cited 1×
“To define driver and passenger mutations, we used cancer mutation frequency information from the Catalogue of Somatic Mutations in Cancer (COSMIC [62,63]).”
MethodAnatomy of hot spots in protein interfaces
Bogan, A. A., & Thorn, K. S. (1998) · Journal of Molecular Biology · doi:10.1006/jmbi.1998.1843 · Cited by 1,988
Searching for genetic determinants in the new millennium
Risch, N. J. (2000) · Nature · doi:10.1038/35015718 · Cited by 1,839 · cited 2×
“diagnosis, prevention and treatments [3].”
BackgroundGuerois, R., Nielsen, J. E., & Serrano, L. (2002) · Journal of Molecular Biology · doi:10.1016/s0022-2836(02)00442-4 · Cited by 1,728 · cited 12×
“The second factor is that ProMaya relies on a single DDG prediction value from Prethermut, whereas we provide all independent FoldX energy terms as features in combination with molecular and sequence features.”
BackgroundMethodInfluentialA comprehensive catalogue of somatic mutations from a human cancer genome
Pleasance, E. D., Cheetham, R. K., Stephens, P. J., McBride, D. J., Humphray, S. J., Greenman, C. D., Varela, I., Lin, M.-L., Ordóñez, G. R., Bignell, G. R., et al. (2010) · Nature · doi:10.1038/nature08658 · Cited by 1,696
Evolution and functional impact of rare coding variation from deep sequencing of human exomes
Tennessen, J. A., Bigham, A. W., O’Connor, T. D., Fu, W., Kenny, E. E., Gravel, S., McGee, S., Do, R., Liu, X., Jun, G., et al. (2012) · Science · doi:10.1126/science.1219240 · Cited by 1,613 · cited 1×
“Recent efforts to map human genetic variation by sequencing exomes [4] and whole genomes [5–7] have characterized the vast majority of common and low frequency SNPs and many structural variants.”
BackgroundCharacterization of single-nucleotide polymorphisms in coding regions of human genes
Cargill, M., Altshuler, D., Ireland, J., Sklar, P., Ardlie, K., Patil, N., Lane, C. R., Lim, E. P., Kalyanaraman, N., Nemesh, J., et al. (1999) · Nature Genetics · doi:10.1038/10290 · Cited by 1,547
Human Genome Sequencing Using Unchained Base Reads on Self-Assembling DNA Nanoarrays
Drmanac, R., Sparks, A. B., Callow, M. J., Halpern, A. L., Burns, N. L., Kermani, B. G., Carnevali, P., Nazarenko, I., Nilsen, G. B., Yeung, G., et al. (2010) · Science · doi:10.1126/science.1181498 · Cited by 1,212
Mapping copy number variation by population-scale genome sequencing
1000 Genomes Project, Mills, R. E., Walter, K., Stewart, C., Handsaker, R. E., Chen, K., Alkan, C., Abyzov, A., Yoon, S. C., Ye, K., et al. (2011) · Nature · doi:10.1038/nature09708 · Cited by 1,140
Understanding the contribution of synonymous mutations to human disease
Sauna, Z. E., & Kimchi-Sarfaty, C. (2011) · Nature Reviews Genetics · doi:10.1038/nrg3051 · Cited by 1,022 · cited 1×
“general, SNPs can occur either at non-coding [1] or at coding regions [2], in which only non-synonymous SNPs (nsSNPs) induce”
BackgroundInteractome3D: adding structural details to protein networks
Mosca, R., Céol, A., & Aloy, P. (2013) · Nature Methods · doi:10.1038/nmeth.2289 · Cited by 479 · cited 5×
“modelled structures While the coverage of the PDB of any given proteome is low, it can be greatly expanded by modeling proteins and their complexes using homologous structures as templates [39].”
BackgroundMethodInfluentialThree-dimensional reconstruction of protein networks provides insight into human genetic disease
Wang, X., Wei, X., Thijssen, B., Das, J., Lipkin, S. M., & Yu, H. (2012) · Nature Biotechnology · doi:10.1038/nbt.2106 · Cited by 385
Potapov, V., Cohen, M., & Schreiber, G. (2009) · Protein Engineering Design and Selection · doi:10.1093/protein/gzp030 · Cited by 349
BeAtMuSiC: prediction of changes in protein–protein binding affinity on mutations
Dehouck, Y., Kwasigroch, J. M., Rooman, M., & Gilis, D. (2013) · Nucleic Acids Research · doi:10.1093/nar/gkt450 · Cited by 338
Moal, I. H., & Fernández-Recio, J. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts489 · Cited by 281
Cited by
Jankauskaitė, J., Jiménez-García, B., Dapkūnas, J., Fernández-Recio, J., & Moal, I. H. (2019) · Bioinformatics · doi:10.1093/bioinformatics/bty635 · Cited by 389
Cang, Z., & Wei, G.-W. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005690 · Cited by 330
Brender, J. R., & Zhang, Y. (2015) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1004494 · Cited by 140
Petukh, M., Li, M., & Alexov, E. (2015) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1004276 · Cited by 107
“(for some examples see [21–29]).”
Geng, C., Vangone, A., Folkers, G. E., Xue, L. C., & Bonvin, A. M. J. J. (2019) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25630 · Cited by 82
Metadata
- Authors
- Berliner, N., Teyra, J., Çolak, R., Garcia Lopez, S., & Kim, P. M.
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2014-09-22
- Volume
- 9
- Issue
- 9
- Pages
- e107353
- ISSN
- 1932-6203 (ISSN-L)
- OpenAlex
- W2058714876
- Cited by
- 79
- References
- 21
- FWCI
- 2.68
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.