A genetic algorithm with conformational memories for structure prediction of polypeptides

We have developed an iterative hybrid algorithm (HA) to predict the 3D structure of peptides starting from their amino acid sequence. The HA is made of a modified genetic algorithm (GA) coupled to a local optimizer. Each HA iteration is carried out in two phases. In the first phase several GA runs are performed upon the entire peptide conformational space. In the second phase we used the manifestation of what we have called conformational memories, that arises at the end of the first phase, as a way of reducing the peptide conformational space in subsequent HA iterations. Use of conformational memories speeds up and refines the localization of the structure at the putative Global Energy Minimum (GEM) since conformational barriers are avoided. The algorithm has been used to predict successfully the putative GEM for Met- and Leu-enkephalin, and to obtain useful information regarding the 3D structure for the 8mer of polyglycine and the 16 residue (AAQAA)(3)Y peptide. The number of fitness function evaluations needed to locate the putative GEMs are fewer than those reported for other heuristic methods. This study opens the possibility of using Genetic Algorithms in high level predictions of secondary structure of polypeptides.     

A fast algorithm for BayesB type of prediction of genome-wide estimates of genetic value

Genomic selection uses genome-wide dense SNP marker genotyping for the prediction of genetic values, and consists of two steps: (1) estimation of SNP effects, and (2) prediction of genetic value based on SNP genotypes and estimates of their effects. For the former step, BayesB type of estimators have been proposed, which assume a priori that many markers have no effects, and some have an effect coming from a gamma or exponential distribution, i.e. a fat-tailed distribution. Whilst such estimators have been developed using Monte Carlo Markov chain (MCMC), here we derive a much faster non-MCMC based estimator by analytically performing the required integrations. The accuracy of the genome-wide breeding value estimates was 0.011 (s.e. 0.005) lower than that of the MCMC based BayesB predictor, which may be because the integrations were performed one-by-one instead of for all SNPs simultaneously. The bias of the new method was opposite to that of the MCMC based BayesB, in that the new method underestimates the breeding values of the best selection candidates, whereas MCMC-BayesB overestimated their breeding values. The new method was computationally several orders of magnitude faster than MCMC based BayesB, which will mainly be advantageous in computer simulations of entire breeding schemes, in cross-validation testing, and practical schemes with frequent re-estimation of breeding values.     

Features for computational operon prediction in prokaryotes

Accurate prediction of operons can improve the functional annotation and application of genes within operons in prokaryotes. Here, we review several features: (i) intergenic distance, (ii) metabolic pathways, (iii) homologous genes, (iv) promoters and terminators, (v) gene order conservation, (vi) microarray, (vii) clusters of orthologous groups, (viii) gene length ratio, (ix) phylogenetic profiles, (x) operon length/size and (xi) STRING database scores, as well as some other features, which have been applied in recent operon prediction methods in prokaryotes in the literature. Based on a comparison of the prediction performances of these features, we conclude that other, as yet undiscovered features, or feature selection with a receiver operating characteristic analysis before algorithm processing can improve operon prediction in prokaryotes.     

A nearest-neighboring-end algorithm for genetic mapping

MOTIVATION: High-throughput methods are beginning to make possible the genotyping of thousands of loci in thousands of individuals, which could be useful for tightly associating phenotypes to candidate loci. Current mapping algorithms cannot handle so many data without building hierarchies of framework maps. RESULTS: A version of Kruskal's minimum spanning tree algorithm can solve any genetic mapping problem that can be stated as marker deletion from a set of linkage groups. These include backcross, recombinant inbred, haploid and double-cross recombinational populations, in addition to conventional deletion and radiation hybrid populations. The algorithm progressively joins linkage groups at increasing recombination fractions between terminal markers, and attempts to recognize and correct erroneous joins at peaks in recombination fraction. The algorithm is O (mn3) for m individuals and n markers, but the mean run time scales close to mn2. It is amenable to parallel processing and has recovered true map order in simulations of large backcross, recombinant inbred and deletion populations with up to 37,005 markers. Simulations were used to investigate map accuracy in response to population size, allelic dominance, segregation distortion, missing data and random typing errors. It produced accurate maps when marker distribution was sufficiently uniform, although segregation distortion could induce translocated marker orders. The algorithm was also used to map 1003 loci in the F7 ITMI population of bread wheat, Triticum aestivum L. emend Thell., where it shortened an existing standard map by 16%, but it failed to associate blocks of markers properly across gaps within linkage groups. This was because it depends upon the rankings of recombination fractions at individual markers, and is susceptible to sampling error, typing error and joint selection involving the terminal markers of nearly finished linkage groups. Therefore, the current form of the algorithm is useful mainly to improve local marker ordering in linkage groups obtained in other ways. AVAILABILITY: The source code and supplemental data are http://www.iubio.bio.indiana.edu/soft/molbio/qtl/flipper/ CONTACT: ccrane@purdue.edu.     

A novel fuzzy Fisher classifier for signal peptide prediction

Signal peptides recognition by bioinformatics approaches is particularly important for the efficient secretion and production of specific proteins. We concentrate on developing an integrated fuzzy Fisher clustering (IFFC) and designing a novel classifier based on IFFC for predicting secretory proteins. IFFC provides a powerful optimal discriminant vector calculated by fuzzy intra-cluster scatter matrix and fuzzy inter-cluster scatter matrix. Because the training samples and test samples are processed together in IFFC, it is convenient for users to employ their own specific samples of high reliability as training data if necessary. The cross-validation results on some existing datasets indicate that the fuzzy Fisher classifier is quite promising for signal peptide prediction.     

基于遗传算法的蛋白质结构预测方法

遗传算法源于自然界的进化规律,是一种自适应启发式概率性迭代式全局搜索算法。本文主要介绍了GA的基本原理,算法及优点;总结GA在蛋白质结构预测中建立模型和执行策略,以及多种算法相互结合预测蛋白质结构的研究进展。     

Reliable prediction of adsorption isotherms via genetic algorithm molecular simulation

Conventional molecular simulation techniques such as grand canonical Monte Carlo (GCMC) strictly rely on purely random search inside the simulation box for predicting the adsorption isotherms. This blind search is usually extremely time demanding for providing a faithful approximation of the real isotherm and in some cases may lead to non-optimal solutions. A novel approach is presented in this article which does not use any of the classical steps of the standard GCMC method, such as displacement, insertation, and removal. The new approach is based on the well-known genetic algorithm to find the optimal configuration for adsorption of any adsorbate on a structured adsorbent under prevailing pressure and temperature. The proposed approach considers the molecular simulation problem as a global optimization challenge. A detailed flow chart of our so-called genetic algorithm molecular simulation (GAMS) method is presented, which is entirely different from traditions molecular simulation approaches. Three real case studies (for adsorption of CO₂ and H₂ over various zeolites) are borrowed from literature to clearly illustrate the superior performances of the proposed method over the standard GCMC technique. For the present method, the average absolute values of percentage errors are around 11% (RHO-H₂), 5% (CHA-CO₂), and 16% (BEA-CO₂), while they were about 70%, 15%, and 40% for the standard GCMC technique, respectively.     

A novel algorithm for network-based prediction of cancer recurrence

To develop accurate prognostic models is one of the biggest challenges in “omics”-based cancer research. Here, we propose a novel computational method for identifying dysregulated gene subnetworks as biomarkers to predict cancer recurrence. Applying our method to the DNA methylome of endometrial cancer patients, we identified a subnetwork consisting of differentially methylated (DM) genes, and non-differentially methylated genes, termed Epigenetic Connectors (EC), that are topologically important for connecting the DM genes in a protein-protein interaction network. The ECs are statistically significantly enriched in well-known tumorgenesis and metastasis pathways, and include known epigenetic regulators. Importantly, combining the DMs and ECs as features using a novel random walk procedure, we constructed a support vector machine classifier that significantly improved the prediction accuracy of cancer recurrence and outperformed several alternative methods, demonstrating the effectiveness of our network-based approach.     

A novel neural response algorithm for protein function prediction

Background

Large amounts of data are being generated by high-throughput genome sequencing methods. But the rate of the experimental functional characterization falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOFigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. Adding to this, the lack of annotation specificity advocates the need to improve automated protein function prediction.

Results

We designed a novel automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. Firstly, we predict the most similar target protein for a given query protein and thereby assign its GO term to the query sequence. When assessed on test set, our method ranked the actual leaf GO term among the top 5 probable GO terms with accuracy of 86.93%.

Conclusions

The proposed algorithm is the first instance of neural response algorithm being used in the biological domain. The use of HMM profiles along with the secondary structure information to define the neural response gives our method an edge over other available methods on annotation accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.

     

A binary matrix factorization algorithm for protein complex prediction

BACKGROUND: Identifying biologically relevant protein complexes from a large protein-protein interaction (PPI) network, is essential to understand the organization of biological systems. However, high-throughput experimental techniques that can produce a large amount of PPIs are known to yield non-negligible rates of false-positives and false-negatives, making the protein complexes difficult to be identified. RESULTS: We propose a binary matrix factorization (BMF) algorithm under the Bayesian Ying-Yang (BYY) harmony learning, to detect protein complexes by clustering the proteins which share similar interactions through factorizing the binary adjacent matrix of a PPI network. The proposed BYY-BMF algorithm automatically determines the cluster number while this number is pre-given for most existing BMF algorithms. Also, BYY-BMF's clustering results does not depend on any parameters or thresholds, unlike the Markov Cluster Algorithm (MCL) that relies on a so-called inflation parameter. On synthetic PPI networks, the predictions evaluated by the known annotated complexes indicate that BYY-BMF is more robust than MCL for most cases. On real PPI networks from the MIPS and DIP databases, BYY-BMF obtains a better balanced prediction accuracies than MCL and a spectral analysis method, while MCL has its own advantages, e.g., with good separation values.     

A biased random-key genetic algorithm for data clustering

Cluster analysis aims at finding subsets (clusters) of a given set of entities, which are homogeneous and/or well separated.     

A Boltzmann filter improves the prediction of RNA folding pathways in a massively parallel genetic algorithm

RNA folding using the massively parallel genetic algorithm (GA) has been enhanced by the addition of a Boltzmann filter. The filter uses the Boltzmann probability distribution in conjunction with Metropolis' relaxation algorithm. The combination of these two concepts within the GA's massively parallel computational environment helps guide the genetic algorithm to more accurately reflect RNA folding pathways and thus final solution structures. Helical regions (base-paired stems) now form in the structures based upon the stochastic properties of the thermodynamic parameters that have been determined from experiments. Thus, structural changes occur based upon the relative energetic impact that the change causes rather than just geometric conflicts alone. As a result, when comparing the predictions to phylogenetically determined structures, over multiple runs, fewer false-positive stems (predicted incorrectly) and more true-positive stems (predicted correctly) are generated, and the total number of predicted stems representing a solution is diminished. In addition, the significance (rate of occurrence) of the true-positive stems is increased. Thus, the predicted results more accurately reflect phylogenetically determined structures.     

Protein structure prediction using mutually orthogonal Latin squares and a genetic algorithm

We combine a new, extremely fast technique to generate a library of low energy structures of an oligopeptide (by using mutually orthogonal Latin squares to sample its conformational space) with a genetic algorithm to predict protein structures. The protein sequence is divided into oligopeptides, and a structure library is generated for each. These libraries are used in a newly defined mutation operator that, together with variation, crossover, and diversity operators, is used in a modified genetic algorithm to make the prediction. Application to five small proteins has yielded near native structures.     

A probabilistic fragment-based protein structure prediction algorithm

Conformational sampling is one of the bottlenecks in fragment-based protein structure prediction approaches. They generally start with a coarse-grained optimization where mainchain atoms and centroids of side chains are considered, followed by a fine-grained optimization with an all-atom representation of proteins. It is during this coarse-grained phase that fragment-based methods sample intensely the conformational space. If the native-like region is sampled more, the accuracy of the final all-atom predictions may be improved accordingly. In this work we present EdaFold, a new method for fragment-based protein structure prediction based on an Estimation of Distribution Algorithm. Fragment-based approaches build protein models by assembling short fragments from known protein structures. Whereas the probability mass functions over the fragment libraries are uniform in the usual case, we propose an algorithm that learns from previously generated decoys and steers the search toward native-like regions. A comparison with Rosetta AbInitio protocol shows that EdaFold is able to generate models with lower energies and to enhance the percentage of near-native coarse-grained decoys on a benchmark of [Formula: see text] proteins. The best coarse-grained models produced by both methods were refined into all-atom models and used in molecular replacement. All atom decoys produced out of EdaFold's decoy set reach high enough accuracy to solve the crystallographic phase problem by molecular replacement for some test proteins. EdaFold showed a higher success rate in molecular replacement when compared to Rosetta. Our study suggests that improving low resolution coarse-grained decoys allows computational methods to avoid subsequent sampling issues during all-atom refinement and to produce better all-atom models. EdaFold can be downloaded from http://www.riken.jp/zhangiru/software/.     

An effective hybrid of hill climbing and genetic algorithm for 2D triangular protein structure prediction

Background

Proteins play fundamental and crucial roles in nearly all biological processes, such as, enzymatic catalysis, signaling transduction, DNA and RNA synthesis, and embryonic development. It has been a long-standing goal in molecular biology to predict the tertiary structure of a protein from its primary amino acid sequence. From visual comparison, it was found that a 2D triangular lattice model can give a better structure modeling and prediction for proteins with short primary amino acid sequences.

Methods

This paper proposes a hybrid of hill-climbing and genetic algorithm (HHGA) based on elite-based reproduction strategy for protein structure prediction on the 2D triangular lattice.

Results

The simulation results show that the proposed HHGA can successfully deal with the protein structure prediction problems. Specifically, HHGA significantly outperforms conventional genetic algorithms and is comparable to the state-of-the-art method in terms of free energy.

Conclusions

Thanks to the enhancement of local search on the global search, the proposed HHGA achieves promising results on the 2D triangular protein structure prediction problem. The satisfactory simulation results demonstrate the effectiveness of the proposed HHGA and the utility of the 2D triangular lattice model for protein structure prediction.