Complementing sequence-derived features with structural information extracted from fragment libraries for protein structure prediction.
Ontology highlight
ABSTRACT: Background
Fragment libraries play a key role in fragment-assembly based protein structure prediction, where protein fragments are assembled to form a complete three-dimensional structure. Rich and accurate structural information embedded in fragment libraries has not been systematically extracted and used beyond fragment assembly.Methods
To better leverage the valuable structural information for protein structure prediction, we extracted seven types of structural information from fragment libraries. We broadened the usage of such structural information by transforming fragment libraries into protein-specific potentials for gradient-descent based protein folding and encoding fragment libraries as structural features for protein property prediction.Results
Fragment libraires improved the accuracy of protein folding and outperformed state-of-the-art algorithms with respect to predicted properties, such as torsion angles and inter-residue distances.Conclusion
Our work implies that the rich structural information extracted from fragment libraries can complement sequence-derived features to help protein structure prediction.
SUBMITTER: Liu S
PROVIDER: S-EPMC8240311 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The use of fragment libraries is a popular approach among protein structure prediction methods and has proven to substantially improve the quality of predicted structures. However, some vital aspects of a fragment library that influence the accuracy of modeling a native structure remain to be determined. This study investigates some of these features. Particularly, we analyze the effect of using secondary structure prediction guiding fragments selection, different fragments sizes and the effect of structural clustering of fragments within libraries. To have a clearer view of how these factors affect protein structure prediction, we isolated the process of model building by fragment assembly from some common limitations associated with prediction methods, e.g., imprecise energy functions and optimization algorithms, by employing an exact structure-based objective function under a greedy algorithm. Our results indicate that shorter fragments reproduce the native structure more accurately than the longer. Libraries composed of multiple fragment lengths generate even better structures, where longer fragments show to be more useful at the beginning of the simulations. The use of many different fragment sizes shows little improvement when compared to predictions carried out with libraries that comprise only three different fragment sizes. Models obtained from libraries built using only sequence similarity are, on average, better than those built with a secondary structure prediction bias. However, we found that the use of secondary structure prediction allows greater reduction of the search space, which is invaluable for prediction methods. The results of this study can be critical guidelines for the use of fragment libraries in protein structure prediction.
| S-EPMC5235372 | biostudies-literature
Project description:Identification of essential genes is not only useful for our understanding of the minimal gene set required for cellular life but also aids the identification of novel drug targets in pathogens. In this work, we present a simple and effective gene essentiality prediction method using information-theoretic features that are derived exclusively from the gene sequences.We developed a Random Forest classifier and performed an extensive model performance evaluation among and within 15 selected bacteria. In intra-organism predictions, where training and testing sets are taken from the same organism, AUC (Area Under the Curve) scores ranging from 0.73 to 0.90, 0.84 on average, were obtained. Cross-organism predictions using 5-fold cross-validation, pairwise, leave-one-species-out, leave-one-taxon-out, and cross-taxon yielded average AUC scores of 0.88, 0.75, 0.80, 0.82, and 0.78, respectively. To further show the applicability of our method in other domains of life, we predicted the essential genes of the yeast Schizosaccharomyces pombe and obtained a similar accuracy (AUC 0.84).The proposed method enables a simple and reliable identification of essential genes without searching in databases for orthologs and demanding further experimental data such as network topology and gene-expression.
| S-EPMC5679510 | biostudies-literature
Project description:Proteolytic signaling, or regulated proteolysis, is an essential part of many important pathways such as Notch, Wnt, and Hedgehog. How the structure of the cleaved substrate regions influences the efficacy of proteolytic processing remains underexplored. Here, we analyzed the relative importance in proteolysis of various structural features derived from substrate sequences using a dataset of more than 5000 experimentally verified proteolytic events captured in CutDB. Accessibility to the solvent was recognized as an essential property of a proteolytically processed polypeptide chain. Proteolytic events were found nearly uniformly distributed among three types of secondary structure, although with some enrichment in loops. Cleavages in ?-helices were found to be relatively abundant in regions apparently prone to unfolding, while cleavages in ?-structures tended to be located at the periphery of ?-sheets. Application of the same statistical procedures to proteolytic events divided into separate sets according to the catalytic classes of proteases proved consistency of the results and confirmed that the structural mechanisms of proteolysis are universal. The estimated prediction power of sequence-derived structural features, which turned out to be sufficiently high, presents a rationale for their use in bioinformatic prediction of proteolytic events.
| S-EPMC3926948 | biostudies-literature
Project description:Tuberculosis is one of the leading cause of death worldwide, particularly due to evolution of drug resistant strains. Antitubercular peptides may provide an alternate approach to combat antibiotic tolerance. Sequence analysis reveals that certain residues (e.g., Lysine, Arginine, Leucine, Tryptophan) are more prevalent in antitubercular peptides. This study describes the models developed for predicting antitubercular peptides by using sequence features of the peptides. We have developed support vector machine based models using different sequence features like amino acid composition, binary profile of terminus residues, dipeptide composition. Our ensemble classifiers that combines models based on amino acid composition and N5C5 binary pattern, achieves highest Acc of 73.20% with 0.80 AUROC on our main dataset. Similarly, the ensemble classifier achieved maximum Acc 75.62% with 0.83 AUROC on secondary dataset. Beside this, hybrid model achieves Acc of 75.87 and 78.54% with 0.83 and 0.86 AUROC on main and secondary dataset, respectively. In order to facilitate scientific community in designing of antitubercular peptides, we implement above models in a user friendly webserver (http://webs.iiitd.edu.in/raghava/antitbpred/).
| S-EPMC6121089 | biostudies-literature
Project description:Small ribonucleic acid (sRNA) sequences are 50-500 nucleotide long, noncoding RNA (ncRNA) sequences that play an important role in regulating transcription and translation within a bacterial cell. As such, identifying sRNA sequences within an organism's genome is essential to understand the impact of the RNA molecules on cellular processes. Recently, numerous machine learning models have been applied to predict sRNAs within bacterial genomes. In this study, we considered the sRNA prediction as an imbalanced binary classification problem to distinguish minor positive sRNAs from major negative ones within imbalanced data and then performed a comparative study with six learning algorithms and seven assessment metrics. First, we collected numerical feature groups extracted from known sRNAs previously identified in Salmonella typhimurium LT2 (SLT2) and Escherichia coli K12 (E. coli K12) genomes. Second, as a preliminary study, we characterized the sRNA-size distribution with the conformity test for Benford's law. Third, we applied six traditional classification algorithms to sRNA features and assessed classification performance with seven metrics, varying positive-to-negative instance ratios, and utilizing stratified 10-fold cross-validation. We revisited important individual features and feature groups and found that classification with combined features perform better than with either an individual feature or a single feature group in terms of Area Under Precision-Recall curve (AUPR). We reconfirmed that AUPR properly measures classification performance on imbalanced data with varying imbalance ratios, which is consistent with previous studies on classification metrics for imbalanced data. Overall, eXtreme Gradient Boosting (XGBoost), even without exploiting optimal hyperparameter values, performed better than the other five algorithms with specific optimal parameter settings. As a future work, we plan to extend XGBoost further to a large amount of published sRNAs in bacterial genomes and compare its classification performance with recent machine learning models' performance.
| S-EPMC9397377 | biostudies-literature
Project description:BACKGROUND: A lot of high-throughput studies produce protein-protein interaction networks (PPINs) with many errors and missing information. Even for genome-wide approaches, there is often a low overlap between PPINs produced by different studies. Second-level neighbors separated by two protein-protein interactions (PPIs) were previously used for predicting protein function and finding complexes in high-error PPINs. We retrieve second level neighbors in PPINs, and complement these with structural domain-domain interactions (SDDIs) representing binding evidence on proteins, forming PPI-SDDI-PPI triangles. RESULTS: We find low overlap between PPINs, SDDIs and known complexes, all well below 10%. We evaluate the overlap of PPI-SDDI-PPI triangles with known complexes from Munich Information center for Protein Sequences (MIPS). PPI-SDDI-PPI triangles have ~20 times higher overlap with MIPS complexes than using second-level neighbors in PPINs without SDDIs. The biological interpretation for triangles is that a SDDI causes two proteins to be observed with common interaction partners in high-throughput experiments. The relatively few SDDIs overlapping with PPINs are part of highly connected SDDI components, and are more likely to be detected in experimental studies. We demonstrate the utility of PPI-SDDI-PPI triangles by reconstructing myosin-actin processes in the nucleus, cytoplasm, and cytoskeleton, which were not obvious in the original PPIN. Using other complementary datatypes in place of SDDIs to form triangles, such as PubMed co-occurrences or threading information, results in a similar ability to find protein complexes. CONCLUSION: Given high-error PPINs with missing information, triangles of mixed datatypes are a promising direction for finding protein complexes. Integrating PPINs with SDDIs improves finding complexes. Structural SDDIs partially explain the high functional similarity of second-level neighbors in PPINs. We estimate that relatively little structural information would be sufficient for finding complexes involving most of the proteins and interactions in a typical PPIN.
| S-EPMC2714575 | biostudies-literature
Project description:BackgroundThere is a significant need for affinity reagents with high target affinity/specificity that can be developed rapidly and inexpensively. Existing affinity reagent development approaches, including protein mutagenesis, directed evolution, and fragment-based design utilize large libraries and/or require structural information thereby adding time and expense. Until now, no systematic approach to affinity reagent development existed that could produce nanomolar affinity from small chemically synthesized peptide libraries without the aid of structural information.Methodology/principal findingsBased on the principle of additivity, we have developed an algorithm for generating high affinity peptide ligands. In this algorithm, point-variations in a lead sequence are screened and combined in a systematic manner to achieve additive binding energies. To demonstrate this approach, low-affinity lead peptides for multiple protein targets were identified from sparse random sequence space and optimized to high affinity in just two chemical steps. In one example, a TNF-? binding peptide with K(d)?= 90 nM and high target specificity was generated. The changes in binding energy associated with each variation were generally additive upon combining variations, validating the basis of the algorithm. Interestingly, cooperativity between point-variations was not observed, and in a few specific cases, combinations were less than energetically additive.Conclusions/significanceBy using this additivity algorithm, peptide ligands with high affinity for protein targets were generated. With this algorithm, one of the highest affinity TNF-? binding peptides reported to date was produced. Most importantly, high affinity was achieved from small, chemically-synthesized libraries without the need for structural information at any time during the process. This is significantly different than protein mutagenesis, directed evolution, or fragment-based design approaches, which rely on large libraries and/or structural guidance. With this algorithm, high affinity/specificity peptide ligands can be developed rapidly, inexpensively, and in an entirely chemical manner.
| S-EPMC2978705 | biostudies-literature
Project description:N(6)-methyladenosine (m(6)A) is a prevalent RNA methylation modification involved in the regulation of degradation, subcellular localization, splicing and local conformation changes of RNA transcripts. High-throughput experiments have demonstrated that only a small fraction of the m(6)A consensus motifs in mammalian transcriptomes are modified. Therefore, accurate identification of RNA m(6)A sites becomes emergently important. For the above purpose, here a computational predictor of mammalian m(6)A site named SRAMP is established. To depict the sequence context around m(6)A sites, SRAMP combines three random forest classifiers that exploit the positional nucleotide sequence pattern, the K-nearest neighbor information and the position-independent nucleotide pair spectrum features, respectively. SRAMP uses either genomic sequences or cDNA sequences as its input. With either kind of input sequence, SRAMP achieves competitive performance in both cross-validation tests and rigorous independent benchmarking tests. Analyses of the informative features and overrepresented rules extracted from the random forest classifiers demonstrate that nucleotide usage preferences at the distal positions, in addition to those at the proximal positions, contribute to the classification. As a public prediction server, SRAMP is freely available at http://www.cuilab.cn/sramp/.
| S-EPMC4889921 | biostudies-literature
Project description:BackgroundAccurate prediction of binding residues involved in the interactions between proteins and small ligands is one of the major challenges in structural bioinformatics. Heme is an essential and commonly used ligand that plays critical roles in electron transfer, catalysis, signal transduction and gene expression. Although much effort has been devoted to the development of various generic algorithms for ligand binding site prediction over the last decade, no algorithm has been specifically designed to complement experimental techniques for identification of heme binding residues. Consequently, an urgent need is to develop a computational method for recognizing these important residues.ResultsHere we introduced an efficient algorithm HemeBIND for predicting heme binding residues by integrating structural and sequence information. We systematically investigated the characteristics of binding interfaces based on a non-redundant dataset of heme-protein complexes. It was found that several sequence and structural attributes such as evolutionary conservation, solvent accessibility, depth and protrusion clearly illustrate the differences between heme binding and non-binding residues. These features can then be separately used or combined to build the structure-based classifiers using support vector machine (SVM). The results showed that the information contained in these features is largely complementary and their combination achieved the best performance. To further improve the performance, an attempt has been made to develop a post-processing procedure to reduce the number of false positives. In addition, we built a sequence-based classifier based on SVM and sequence profile as an alternative when only sequence information can be used. Finally, we employed a voting method to combine the outputs of structure-based and sequence-based classifiers, which demonstrated remarkably better performance than the individual classifier alone.ConclusionsHemeBIND is the first specialized algorithm used to predict binding residues in protein structures for heme ligands. Extensive experiments indicated that both the structure-based and sequence-based methods have effectively identified heme binding residues while the complementary relationship between them can result in a significant improvement in prediction performance. The value of our method is highlighted through the development of HemeBIND web server that is freely accessible at http://mleg.cse.sc.edu/hemeBIND/.
| S-EPMC3124436 | biostudies-literature
Project description:Unlabelledβ-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively.ConclusionThe NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.
| S-EPMC2994801 | biostudies-literature