Dataset Information

Improving the accuracy of high-throughput protein-protein affinity prediction may require better training data.

ABSTRACT: One goal of structural biology is to understand how a protein's 3-dimensional conformation determines its capacity to interact with potential ligands. In the case of small chemical ligands, deconstructing a static protein-ligand complex into its constituent atom-atom interactions is typically sufficient to rapidly predict ligand affinity with high accuracy (>70% correlation between predicted and experimentally-determined affinity), a fact that is exploited to support structure-based drug design. We recently found that protein-DNA/RNA affinity can also be predicted with high accuracy using extensions of existing techniques, but protein-protein affinity could not be predicted with >60% correlation, even when the protein-protein complex was available.X-ray and NMR structures of protein-protein complexes, their associated binding affinities and experimental conditions were obtained from different binding affinity and structural databases. Statistical models were implemented using a generalized linear model framework, including the experimental conditions as new model features. We evaluated the potential for new features to improve affinity prediction models by calculating the Pearson correlation between predicted and experimental binding affinities on the training and test data after model fitting and after cross-validation. Differences in accuracy were assessed using two-sample t test and nonparametric Mann-Whitney U test.Here we evaluate a range of potential factors that may interfere with accurate protein-protein affinity prediction. We find that X-ray crystal resolution has the strongest single effect on protein-protein affinity prediction. Limiting our analyses to only high-resolution complexes (?2.5 Å) increased the correlation between predicted and experimental affinity from 54 to 68% (p?=?4.32x10-3). In addition, incorporating information on the experimental conditions under which affinities were measured (pH, temperature and binding assay) had significant effects on prediction accuracy. We also highlight a number of potential errors in large structure-affinity databases, which could affect both model training and accuracy assessment.The results suggest that the accuracy of statistical models for protein-protein affinity prediction may be limited by the information present in databases used to train new models. Improving our capacity to integrate large-scale structural and functional information may be required to substantively advance our understanding of the general principles by which a protein's structure determines its function.

SUBMITTER: Dias R

PROVIDER: S-EPMC5374557 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving the accuracy of high-throughput protein-protein affinity prediction may require better training data.

Dias Raquel R Kolaczkowski Bryan B

BMC bioinformatics 20170323 Suppl 5

<h4>Background</h4>One goal of structural biology is to understand how a protein's 3-dimensional conformation determines its capacity to interact with potential ligands. In the case of small chemical ligands, deconstructing a static protein-ligand complex into its constituent atom-atom interactions is typically sufficient to rapidly predict ligand affinity with high accuracy (>70% correlation between predicted and experimentally-determined affinity), a fact that is exploited to support structure ...[more]

PMID: 28361672

Similar Datasets

Project description:BackgroundCurrent scoring functions are not very successful in protein-ligand binding affinity prediction albeit their popularity in structure-based drug designs. Here, we propose a general knowledge-guided scoring (KGS) strategy to tackle this problem. Our KGS strategy computes the binding constant of a given protein-ligand complex based on the known binding constant of an appropriate reference complex. A good training set that includes a sufficient number of protein-ligand complexes with known binding data needs to be supplied for finding the reference complex. The reference complex is required to share a similar pattern of key protein-ligand interactions to that of the complex of interest. Thus, some uncertain factors in protein-ligand binding may cancel out, resulting in a more accurate prediction of absolute binding constants.ResultsIn our study, an automatic algorithm was developed for summarizing key protein-ligand interactions as a pharmacophore model and identifying the reference complex with a maximal similarity to the query complex. Our KGS strategy was evaluated in combination with two scoring functions (X-Score and PLP) on three test sets, containing 112 HIV protease complexes, 44 carbonic anhydrase complexes, and 73 trypsin complexes, respectively. Our results obtained on crystal structures as well as computer-generated docking poses indicated that application of the KGS strategy produced more accurate predictions especially when X-Score or PLP alone did not perform well.ConclusionsCompared to other targeted scoring functions, our KGS strategy does not require any re-parameterization or modification on current scoring methods, and its application is not tied to certain systems. The effectiveness of our KGS strategy is in theory proportional to the ever-increasing knowledge of experimental protein-ligand binding data. Our KGS strategy may serve as a more practical remedy for current scoring functions to improve their accuracy in binding affinity prediction.

Project description:BackgroundDetermining the function of uncharacterized proteins is a major challenge in the post-genomic era due to the problem's complexity and scale. Identifying a protein's function contributes to an understanding of its role in the involved pathways, its suitability as a drug target, and its potential for protein modifications. Several graph-theoretic approaches predict unidentified functions of proteins by using the functional annotations of better-characterized proteins in protein-protein interaction networks. We systematically consider the use of literature co-occurrence data, introduce a new method for quantifying the reliability of co-occurrence and test how performance differs across species. We also quantify changes in performance as the prediction algorithms annotate with increased specificity.ResultsWe find that including information on the co-occurrence of proteins within an abstract greatly boosts performance in the Functional Flow graph-theoretic function prediction algorithm in yeast, fly and worm. This increase in performance is not simply due to the presence of additional edges since supplementing protein-protein interactions with co-occurrence data outperforms supplementing with a comparably-sized genetic interaction dataset. Through the combination of protein-protein interactions and co-occurrence data, the neighborhood around unknown proteins is quickly connected to well-characterized nodes which global prediction algorithms can exploit. Our method for quantifying co-occurrence reliability shows superior performance to the other methods, particularly at threshold values around 10% which yield the best trade off between coverage and accuracy. In contrast, the traditional way of asserting co-occurrence when at least one abstract mentions both proteins proves to be the worst method for generating co-occurrence data, introducing too many false positives. Annotating the functions with greater specificity is harder, but co-occurrence data still proves beneficial.ConclusionCo-occurrence data is a valuable supplemental source for graph-theoretic function prediction algorithms. A rapidly growing literature corpus ensures that co-occurrence data is a readily-available resource for nearly every studied organism, particularly those with small protein interaction databases. Though arguably biased toward known genes, co-occurrence data provides critical additional links to well-studied regions in the interaction network that graph-theoretic function prediction algorithms can exploit.

Project description:BackgroundOrthologs (genes that have diverged after a speciation event) tend to have similar function, and so their prediction has become an important component of comparative genomics and genome annotation. The gold standard phylogenetic analysis approach of comparing available organismal phylogeny to gene phylogeny is not easily automated for genome-wide analysis; therefore, ortholog prediction for large genome-scale datasets is typically performed using a reciprocal-best-BLAST-hits (RBH) approach. One problem with RBH is that it will incorrectly predict a paralog as an ortholog when incomplete genome sequences or gene loss is involved. In addition, there is an increasing interest in identifying orthologs most likely to have retained similar function.ResultsTo address these issues, we present here a high-throughput computational method named Ortholuge that further evaluates previously predicted orthologs (including those predicted using an RBH-based approach) - identifying which orthologs most closely reflect species divergence and may more likely have similar function. Ortholuge analyzes phylogenetic distance ratios involving two comparison species and an outgroup species, noting cases where relative gene divergence is atypical. It also identifies some cases of gene duplication after species divergence. Through simulations of incomplete genome data/gene loss, we show that the vast majority of genes falsely predicted as orthologs by an RBH-based method can be identified. Ortholuge was then used to estimate the number of false-positives (predominantly paralogs) in selected RBH-predicted ortholog datasets, identifying approximately 10% paralogs in a eukaryotic data set (mouse-rat comparison) and 5% in a bacterial data set (Pseudomonas putida - Pseudomonas syringae species comparison). Higher quality (more precise) datasets of orthologs, which we term "ssd-orthologs" (supporting-species-divergence-orthologs), were also constructed. These datasets, as well as Ortholuge software that may be used to characterize other species' datasets, are available at http://www.pathogenomics.ca/ortholuge/ (software under GNU General Public License).ConclusionThe Ortholuge method reported here appears to significantly improve the specificity (precision) of high-throughput ortholog prediction for both bacterial and eukaryotic species. This method, and its associated software, will aid those performing various comparative genomics-based analyses, such as the prediction of conserved regulatory elements upstream of orthologous genes.

Dataset Information

Improving the accuracy of high-throughput protein-protein affinity prediction may require better training data.

Publications

Improving the accuracy of high-throughput protein-protein affinity prediction may require better training data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets