An FPT approach for predicting protein localization from yeast genomic data

Accurately predicting the localization of proteins is of paramount importance in the quest to determine their respective functions within the cellular compartment. Because of the continuous and rapid progress in the fields of genomics and proteomics, more data are available now than ever before. Coincidentally, data mining methods been developed and refined in order to handle this experimental windfall, thus allowing the scientific community to quantitatively address long-standing questions such as that of protein localization. Here, we develop a frequent pattern tree (FPT) approach to generate a minimum set of rules (mFPT) for predicting protein localization. We acquire a series of rules according to the features of yeast genomic data. The mFPT prediction accuracy is benchmarked against other commonly used methods such as Bayesian networks and logistic regression under various statistical measures. Our results show that mFPT gave better performance than other approaches in predicting protein localization. Meanwhile, setting 0.65 as the minimum hit-rate, we obtained 138 proteins that mFPT predicted differently than the simple naive bayesian method (SNB). In our analysis of these 138 proteins, we present novel predictions for the location for 17 proteins, which currently do not have any defined localization. These predictions can serve as putative annotations and should provide preliminary clues for experimentalists. We also compared our predictions against the eukaryotic subcellular localization database and related predictions by others on protein localization. Our method is quite generalized and can thus be applied to discover the underlying rules for protein-protein interactions, genomic interactions, and structure-function relationships, as well as those of other fields of research.     

Evolved cellular automata for protein secondary structure prediction imitate the determinants for folding observed in nature

We demonstrate the first application of cellular automata to the secondary structure predictions of proteins. Cellular automata use localized interactions to simulate global phenomena, which resembles the protein folding problem where individual residues interact locally to define the global protein conformation. The protein's amino acid sequence was input into the cellular automaton and rules for updating states were evolved using a genetic algorithm. An optimized accuracy (Q3) for the RS126 and CB513 dataset of 58.21% and 56.51%, respectively, could be obtained. Thus, the current work demonstrates the applicability of a rather simple algorithm on a problem as complex as protein secondary structure prediction.     

PreSPI: a domain combination based prediction system for protein-protein interaction

With the accumulation of protein and its related data on the Internet, many domain-based computational techniques to predict protein interactions have been developed. However, most techniques still have many limitations when used in real fields. They usually suffer from low accuracy in prediction and do not provide any interaction possibility ranking method for multiple protein pairs. In this paper, we propose a probabilistic framework to predict the interaction probability of proteins and develop an interaction possibility ranking method for multiple protein pairs. Using the ranking method, one can discern the protein pairs that are more likely to interact with each other in multiple protein pairs. The validity of the prediction model was evaluated using an interacting set of protein pairs in yeast and an artificially generated non-interacting set of protein pairs. When 80% of the set of interacting protein pairs in the DIP (Database of Interacting Proteins) was used as a learning set of interacting protein pairs, high sensitivity (77%) and specificity (95%) were achieved for the test groups containing common domains with the learning set of proteins within our framework. The stability of the prediction model was also evident when tested over DIP CORE, HMS-PCI and TAP data. In the validation of the ranking method, we reveal that some correlations exist between the interacting probability and the accuracy of the prediction.     

Confirmation of data mining based predictions of protein function

MOTIVATION: A central problem in bioinformatics is the assignment of function to sequenced open reading frames (ORFs). The most common approach is based on inferred homology using a statistically based sequence similarity (SIM) method, e.g. PSI-BLAST. Alternative non-SIM based bioinformatic methods are becoming popular. One such method is Data Mining Prediction (DMP). This is based on combining evidence from amino-acid attributes, predicted structure and phylogenic patterns; and uses a combination of Inductive Logic Programming data mining, and decision trees to produce prediction rules for functional class. DMP predictions are more general than is possible using homology. In 2000/1, DMP was used to make public predictions of the function of 1309 Escherichia coli ORFs. Since then biological knowledge has advanced allowing us to test our predictions. RESULTS: We examined the updated (20.02.02) Riley group genome annotation, and examined the scientific literature for direct experimental derivations of ORF function. Both tests confirmed the DMP predictions. Accuracy varied between rules, and with the detail of prediction, but they were generally significantly better than random. For voting rules, accuracies of 75-100% were obtained. Twenty-one of these DMP predictions have been confirmed by direct experimentation. The DMP rules also have interesting biological explanations. DMP is, to the best of our knowledge, the first non-SIM based prediction method to have been tested directly on new data. AVAILABILITY: We have designed the "Genepredictions" database for protein functional predictions. This is intended to act as an open repository for predictions for any organism and can be accessed at http://www.genepredictions.org     

Prediction of protein relative solvent accessibility with a two-stage SVM approach

Information on relative solvent accessibility (RSA) of amino acid residues in proteins provides valuable clues to the prediction of protein structure and function. A two-stage approach with support vector machines (SVMs) is proposed, where an SVM predictor is introduced to the output of the single-stage SVM approach to take into account the contextual relationships among solvent accessibilities for the prediction. By using the position-specific scoring matrices (PSSMs) generated by PSI-BLAST, the two-stage SVM approach achieves accuracies up to 90.4% and 90.2% on the Manesh data set of 215 protein structures and the RS126 data set of 126 nonhomologous globular proteins, respectively, which are better than the highest published scores on both data sets to date. A Web server for protein RSA prediction using a two-stage SVM method has been developed and is available (http://birc.ntu.edu.sg/~pas0186457/rsa.html).     

Consistent probabilistic outputs for protein function prediction

In predicting hierarchical protein function annotations, such as terms in the Gene Ontology (GO), the simplest approach makes predictions for each term independently. However, this approach has the unfortunate consequence that the predictor may assign to a single protein a set of terms that are inconsistent with one another; for example, the predictor may assign a specific GO term to a given protein ('purine nucleotide binding') but not assign the parent term ('nucleotide binding'). Such predictions are difficult to interpret. In this work, we focus on methods for calibrating and combining independent predictions to obtain a set of probabilistic predictions that are consistent with the topology of the ontology. We call this procedure 'reconciliation'. We begin with a baseline method for predicting GO terms from a collection of data types using an ensemble of discriminative classifiers. We apply the method to a previously described benchmark data set, and we demonstrate that the resulting predictions are frequently inconsistent with the topology of the GO. We then consider 11 distinct reconciliation methods: three heuristic methods; four variants of a Bayesian network; an extension of logistic regression to the structured case; and three novel projection methods - isotonic regression and two variants of a Kullback-Leibler projection method. We evaluate each method in three different modes - per term, per protein and joint - corresponding to three types of prediction tasks. Although the principal goal of reconciliation is interpretability, it is important to assess whether interpretability comes at a cost in terms of precision and recall. Indeed, we find that many apparently reasonable reconciliation methods yield reconciled probabilities with significantly lower precision than the original, unreconciled estimates. On the other hand, we find that isotonic regression usually performs better than the underlying, unreconciled method, and almost never performs worse; isotonic regression appears to be able to use the constraints from the GO network to its advantage. An exception to this rule is the high precision regime for joint evaluation, where Kullback-Leibler projection yields the best performance.     

MOWGLI: prediction of protein–MannOse interacting residues With ensemble classifiers usinG evoLutionary Information

Proteins interact with carbohydrates to perform various cellular interactions. Of the many carbohydrate ligands that proteins bind with, mannose constitute an important class, playing important roles in host defense mechanisms. Accurate identification of mannose-interacting residues (MIR) may provide important clues to decipher the underlying mechanisms of protein–mannose interactions during infections. This study proposes an approach using an ensemble of base classifiers for prediction of MIR using their evolutionary information in the form of position-specific scoring matrix. The base classifiers are random forests trained by different subsets of training data set Dset128 using 10-fold cross-validation. The optimized ensemble of base classifiers, MOWGLI, is then used to predict MIR on protein chains of the test data set Dtestset29 which showed a promising performance with 92.0% accurate prediction. An overall improvement of 26.6% in precision was observed upon comparison with the state-of-art. It is hoped that this approach, yielding enhanced predictions, could be eventually used for applications in drug design and vaccine development.     

Optimal breeding-value prediction using a sparse selection index

Genomic prediction uses DNA sequences and phenotypes to predict genetic values. In homogeneous populations, theory indicates that the accuracy of genomic prediction increases with sample size. However, differences in allele frequencies and linkage disequilibrium patterns can lead to heterogeneity in SNP effects. In this context, calibrating genomic predictions using a large, potentially heterogeneous, training data set may not lead to optimal prediction accuracy. Some studies tried to address this sample size/homogeneity trade-off using training set optimization algorithms; however, this approach assumes that a single training data set is optimum for all individuals in the prediction set. Here, we propose an approach that identifies, for each individual in the prediction set, a subset from the training data (i.e., a set of support points) from which predictions are derived. The methodology that we propose is a sparse selection index (SSI) that integrates selection index methodology with sparsity-inducing techniques commonly used for high-dimensional regression. The sparsity of the resulting index is controlled by a regularization parameter (λ); the G-Best Linear Unbiased Predictor (G-BLUP) (the prediction method most commonly used in plant and animal breeding) appears as a special case which happens when λ = 0. In this study, we present the methodology and demonstrate (using two wheat data sets with phenotypes collected in 10 different environments) that the SSI can achieve significant (anywhere between 5 and 10%) gains in prediction accuracy relative to the G-BLUP.     

Prediction of protein secondary structure at 80% accuracy

Secondary structure prediction involving up to 800 neural network predictions has been developed, by use of novel methods such as output expansion and a unique balloting procedure. An overall performance of 77.2%-80.2% (77.9%-80.6% mean per-chain) for three-state (helix, strand, coil) prediction was obtained when evaluated on a commonly used set of 126 protein chains. The method uses profiles made by position-specific scoring matrices as input, while at the output level it predicts on three consecutive residues simultaneously. The predictions arise from tenfold, cross validated training and testing of 1032 protein sequences, using a scheme with primary structure neural networks followed by structure filtering neural networks. With respect to blind prediction, this work is preliminary and awaits evaluation by CASP4.     

Prediction of beta-turns from amino acid sequences using the residue-coupled model.

We evaluated the prediction of beta-turns from amino acid sequences using the residue-coupled model with an enlarged representative protein data set selected from the Protein Data Bank. Our results show that the probability values derived from a data set comprising 425 protein chains yielded an overall beta-turn prediction accuracy 68.74%, compared with 94.7% reported earlier on a data set of 30 proteins using the same method. However, we noted that the overall beta-turn prediction accuracy using probability values derived from the 30-protein data set reduces to 40.74% when tested on the data set comprising 425 protein chains. In contrast, using probability values derived from the 425 data set used in this analysis, the overall beta-turn prediction accuracy yielded consistent results when tested on either the 30-protein data set (64.62%) used earlier or a more recent representative data set comprising 619 protein chains (64.66%) or on a jackknife data set comprising 476 representative protein chains (63.38%). We therefore recommend the use of probability values derived from the 425 representative protein chains data set reported here, which gives more realistic and consistent predictions of beta-turns from amino acid sequences.     

Local combinational variables: an approach used in DNA-binding helix-turn-helix motif prediction with sequence information

Sequence-based approach for motif prediction is of great interest and remains a challenge. In this work, we develop a local combinational variable approach for sequence-based helix-turn-helix (HTH) motif prediction. First we choose a sequence data set for 88 proteins of 22 amino acids in length to launch an optimized traversal for extracting local combinational segments (LCS) from the data set. Then after LCS refinement, local combinational variables (LCV) are generated to construct prediction models for HTH motifs. Prediction ability of LCV sets at different thresholds is calculated to settle a moderate threshold. The large data set we used comprises 13 HTH families, with 17 455 sequences in total. Our approach predicts HTH motifs more precisely using only primary protein sequence information, with 93.29% accuracy, 93.93% sensitivity and 92.66% specificity. Prediction results of newly reported HTH-containing proteins compared with other prediction web service presents a good prediction model derived from the LCV approach. Comparisons with profile-HMM models from the Pfam protein families database show that the LCV approach maintains a good balance while dealing with HTH-containing proteins and non-HTH proteins at the same time. The LCV approach is to some extent a complementary to the profile-HMM models for its better identification of false-positive data. Furthermore, genome-wide predictions detect new HTH proteins in both Homo sapiens and Escherichia coli organisms, which enlarge applications of the LCV approach. Software for mining LCVs from sequence data set can be obtained from anonymous ftp site ftp://cheminfo.tongji.edu.cn/LCV/freely.     

Evaluation of a sophisticated SCFG design for RNA secondary structure prediction

Predicting secondary structures of RNA molecules is one of the fundamental problems of and thus a challenging task in computational structural biology. Over the past decades, mainly two different approaches have been considered to compute predictions of RNA secondary structures from a single sequence: the first one relies on physics-based and the other on probabilistic RNA models. Particularly, the free energy minimization (MFE) approach is usually considered the most popular and successful method. Moreover, based on the paradigm-shifting work by McCaskill which proposes the computation of partition functions (PFs) and base pair probabilities based on thermodynamics, several extended partition function algorithms, statistical sampling methods and clustering techniques have been invented over the last years. However, the accuracy of the corresponding algorithms is limited by the quality of underlying physics-based models, which include a vast number of thermodynamic parameters and are still incomplete. The competing probabilistic approach is based on stochastic context-free grammars (SCFGs) or corresponding generalizations, like conditional log-linear models (CLLMs). These methods abstract from free energies and instead try to learn about the structural behavior of the molecules by learning (a manageable number of) probabilistic parameters from trusted RNA structure databases. In this work, we introduce and evaluate a sophisticated SCFG design that mirrors state-of-the-art physics-based RNA structure prediction procedures by distinguishing between all features of RNA that imply different energy rules. This SCFG actually serves as the foundation for a statistical sampling algorithm for RNA secondary structures of a single sequence that represents a probabilistic counterpart to the sampling extension of the PF approach. Furthermore, some new ways to derive meaningful structure predictions from generated sample sets are presented. They are used to compare the predictive accuracy of our model to that of other probabilistic and energy-based prediction methods. Particularly, comparisons to lightweight SCFGs and corresponding CLLMs for RNA structure prediction indicate that more complex SCFG designs might yield higher accuracy but eventually require more comprehensive and pure training sets. Investigations on both the accuracies of predicted foldings and the overall quality of generated sample sets (especially on an abstraction level, called abstract shapes of generated structures, that is relevant for biologists) yield the conclusion that the Boltzmann distribution of the PF sampling approach is more centered than the ensemble distribution induced by the sophisticated SCFG model, which implies a greater structural diversity within generated samples. In general, neither of the two distinct ensemble distributions is more adequate than the other and the corresponding results obtained by statistical sampling can be expected to bare fundamental differences, such that the method to be preferred for a particular input sequence strongly depends on the considered RNA type.     

On prediction of folding nuclei in globular proteins

The approach described in this paper on the prediction of folding nuclei in globular proteins with known three dimensional structures is based on a search of the lowest saddle points through the barrier separating the unfolded state from the native structure on the free-energy landscape of protein chain. This search is performed by a dynamic programming method. Comparison of theoretical results with experimental data on the folding nuclei of two dozen of proteins shows that our model provides good phi value predictions for proteins whose structures have been determined by X-ray analysis, with a less limited success for proteins whose structures have been determined by NMR techniques only. Consideration of a full ensemble of transition states results in more successful prediction than consideration of only the transition states with the minimal free energy. In conclusion we have predicted the localization of folding nuclei for three dimensional protein structures for which kinetics of folding is studied now but the localization of folding nuclei is still unknown.     

Modeling protein loops with knowledge-based prediction of sequence-structure alignment

MOTIVATION: As protein structure database expands, protein loop modeling remains an important and yet challenging problem. Knowledge-based protein loop prediction methods have met with two challenges in methodology development: (1) loop boundaries in protein structures are frequently problematic in constructing length-dependent loop databases for protein loop predictions; (2) knowledge-based modeling of loops of unknown structure requires both aligning a query loop sequence to loop templates and ranking the loop sequence-template matches. RESULTS: We developed a knowledge-based loop prediction method that circumvents the need of constructing hierarchically clustered length-dependent loop libraries. The method first predicts local structural fragments of a query loop sequence and then structurally aligns the predicted structural fragments to a set of non-redundant loop structural templates regardless of the loop length. The sequence-template alignments are then quantitatively evaluated with an artificial neural network model trained on a set of predictions with known outcomes. Prediction accuracy benchmarks indicated that the novel procedure provided an alternative approach overcoming the challenges of knowledge-based loop prediction. AVAILABILITY: http://cmb.genomics.sinica.edu.tw     

Predicting protein kinase specificity: Predikin update and performance in the DREAM4 challenge

Predikin is a system for making predictions about protein kinase specificity. It was declared the "best performer" in the protein kinase section of the Peptide Recognition Domain specificity prediction category of the recent DREAM4 challenge (an independent test using unpublished data). In this article we discuss some recent improvements to the Predikin web server--including a more streamlined approach to substrate-to-kinase predictions and whole-proteome predictions--and give an analysis of Predikin's performance in the DREAM4 challenge. We also evaluate these improvements using a data set of yeast kinases that have been experimentally characterised, and we discuss the usefulness of Frobenius distance in assessing the predictive power of position weight matrices.     

Topology improves phylogenetic motif functional site predictions

Prediction of protein functional sites from sequence-derived data remains an open bioinformatics problem. We have developed a phylogenetic motif (PM) functional site prediction approach that identifies functional sites from alignment fragments that parallel the evolutionary patterns of the family. In our approach, PMs are identified by comparing tree topologies of each alignment fragment to that of the complete phylogeny. Herein, we bypass the phylogenetic reconstruction step and identify PMs directly from distance matrix comparisons. In order to optimize the new algorithm, we consider three different distance matrices and 13 different matrix similarity scores. We assess the performance of the various approaches on a structurally nonredundant data set that includes three types of functional site definitions. Without exception, the predictive power of the original approach outperforms the distance matrix variants. While the distance matrix methods fail to improve upon the original approach, our results are important because they clearly demonstrate that the improved predictive power is based on the topological comparisons. Meaning that phylogenetic trees are a straightforward, yet powerful way to improve functional site prediction accuracy. While complementary studies have shown that topology improves predictions of protein-protein interactions, this report represents the first demonstration that trees improve functional site predictions as well.     

A novel biclustering approach to association rule mining for predicting HIV-1-human protein interactions

Identification of potential viral-host protein interactions is a vital and useful approach towards development of new drugs targeting those interactions. In recent days, computational tools are being utilized for predicting viral-host interactions. Recently a database containing records of experimentally validated interactions between a set of HIV-1 proteins and a set of human proteins has been published. The problem of predicting new interactions based on this database is usually posed as a classification problem. However, posing the problem as a classification one suffers from the lack of biologically validated negative interactions. Therefore it will be beneficial to use the existing database for predicting new viral-host interactions without the need of negative samples. Motivated by this, in this article, the HIV-1-human protein interaction database has been analyzed using association rule mining. The main objective is to identify a set of association rules both among the HIV-1 proteins and among the human proteins, and use these rules for predicting new interactions. In this regard, a novel association rule mining technique based on biclustering has been proposed for discovering frequent closed itemsets followed by the association rules from the adjacency matrix of the HIV-1-human interaction network. Novel HIV-1-human interactions have been predicted based on the discovered association rules and tested for biological significance. For validation of the predicted new interactions, gene ontology-based and pathway-based studies have been performed. These studies show that the human proteins which are predicted to interact with a particular viral protein share many common biological activities. Moreover, literature survey has been used for validation purpose to identify some predicted interactions that are already validated experimentally but not present in the database. Comparison with other prediction methods is also discussed.     

Quantitative prediction of protein–protein binding affinity with a potential of mean force considering volume correction

Quantitative prediction of protein–protein binding affinity is essential for understanding protein–protein interactions. In this article, an atomic level potential of mean force (PMF) considering volume correction is presented for the prediction of protein–protein binding affinity. The potential is obtained by statistically analyzing X‐ray structures of protein–protein complexes in the Protein Data Bank. This approach circumvents the complicated steps of the volume correction process and is very easy to implement in practice. It can obtain more reasonable pair potential compared with traditional PMF and shows a classic picture of nonbonded atom pair interaction as Lennard‐Jones potential. To evaluate the prediction ability for protein–protein binding affinity, six test sets are examined. Sets 1–5 were used as test set in five published studies, respectively, and set 6 was the union set of sets 1–5, with a total of 86 protein–protein complexes. The correlation coefficient (R) and standard deviation (SD) of fitting predicted affinity to experimental data were calculated to compare the performance of ours with that in literature. Our predictions on sets 1–5 were as good as the best prediction reported in the published studies, and for union set 6, R = 0.76, SD = 2.24 kcal/mol. Furthermore, we found that the volume correction can significantly improve the prediction ability. This approach can also promote the research on docking and protein structure prediction.