Improved pairwise alignments of proteins in the Twilight Zone using local structure predictions

AlphaFold2, SPINE-X, and Seder on Four Hard CASP Targets

We analyzed four cases from the CASP15 experiment with low prediction accuracy and compared AlphaFold2, SPINE-X, and Seder on these cases. We find that overall, AlphaFold2 performs better than SPINE-X in predicting secondary structure (SS) and solvent accessible surface area (ASA). For some cases, SPINE-X better predicts sheet and coil regions. We also find that AlphaFold2 is better than Seder in selecting the best matching tertiary structure model for one case and is worse in another case. For two cases Alphafold2 and Seder selected the same models. From the cases presented here, it appears that AlphaFold2 predicts more compact structures than the native one. We find that while, as widely reported, AlphaFold2 significantly improved protein tertiary structure prediction, there are cases, such as the four presented here, for which the tertiary structure prediction could still be significantly enhanced. The source code, license, and documentation for SPINE-X and Seder are available from Research and Information Systems, LLC at http://mamiris.com .

Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction

Predicting the backbone torsion angles corresponding to each residue of a protein from its amino acid sequence alone is a challenging problem in computational biology. Existing torsion angle predictors mainly use profile features, which are generated by performing time-consuming multiple sequence alignments, for torsion angle prediction. Compared with traditional profile features, embedding features from pretrained protein language models have significant advantages in prediction performance and computational speed. However, embedding features usually have higher dimensions and different embedding features have significantly different dimensions. To this end, we design a novel parameter-efficient deep torsion angle predictor, PHAngle, specifically for embedding features. PHAngle is a parameterized hypercomplex convolutional network consisting of parameterized hypercomplex linear and convolutional layers whose weight parameters can be characterized as the sum of Kronecker products. Experimental results on six benchmark test sets including TEST2016, TEST2018, TEST2020_HQ, CASP12, CASP13 and CASP-FM demonstrate that PHAngle achieves the state-of-the-art torsion angle performance with the fewest parameters compared to the nine existing methods. The source code and datasets are available at https://github.com/fengtuan/PHAngle .

Exploring amino acid functions in a deep mutational landscape

Amino acids fulfil a diverse range of roles in proteins, each utilising its chemical properties in different ways in different contexts to create required functions. For example, cysteines form disulphide or hydrogen bonds in different circumstances and charged amino acids do not always make use of their charge. The repertoire of amino acid functions and the frequency at which they occur in proteins remains understudied. Measuring large numbers of mutational consequences, which can elucidate the role an amino acid plays, was prohibitively time-consuming until recent developments in deep mutational scanning. In this study, we gathered data from 28 deep mutational scanning studies, covering 6,291 positions in 30 proteins, and used the consequences of mutation at each position to define a mutational landscape. We demonstrated rich relationships between this landscape and biophysical or evolutionary properties. Finally, we identified 100 functional amino acid subtypes with a data-driven clustering analysis and studied their features, including their frequencies and chemical properties such as tolerating polarity, hydrophobicity or being intolerant of charge or specific amino acids. The mutational landscape and amino acid subtypes provide a foundational catalogue of amino acid functional diversity, which will be refined as the number of studied protein positions increases.

Substitution scoring matrices for proteins - An overview

Sequence analysis is the primary and simplest approach to discover structural, functional and evolutionary details of related proteins. All the alignment based approaches of sequence analysis make use of amino acid substitution matrices, and the accuracy of the results largely depends on the type of scoring matrices used to perform alignment tasks. An amino acid substitution matrix is a 20 × 20 matrix in which the individual elements encapsulate the rates at which each of the 20 amino acid residues in proteins are substituted by other amino acid residues over time. In contrast to most globular/ordered proteins whose amino acids composition is considered as standard, there are several classes of proteins (e.g., transmembrane proteins) in which certain types of amino acid (e.g., hydrophobic residues) are enriched. These compositional differences among various classes of proteins are manifested in their underlying residue substitution frequencies. Therefore, each of the compositionally distinct class of proteins or protein segments should be studied using specific scoring matrices that reflect their distinct residue substitution pattern. In this review, we describe the development and application of various substitution scoring matrices peculiar to proteins with standard and biased compositions. Along with most commonly used standard matrices (PAM, BLOSUM, MD and VTML) that act as default parameters in various homologs search and alignment tools, different substitution scoring matrices specific to compositionally distinct class of proteins are discussed in detail.

Profile Comparer Extended: phylogeny of lytic polysaccharide monooxygenase families using profile hidden Markov model alignments

Insight into the inter- and intra-family relationship of protein families is important, since it can aid understanding of substrate specificity evolution and assign putative functions to proteins with unknown function. To study both these inter- and intra-family relationships, the ability to build phylogenetic trees using the most sensitive sequence similarity search methods (e.g. profile hidden Markov model (pHMM)-pHMM alignments) is required. However, existing solutions require a very long calculation time to obtain the phylogenetic tree. Therefore, a faster protocol is required to make this approach efficient for research. To contribute to this goal, we extended the original Profile Comparer program (PRC) for the construction of large pHMM phylogenetic trees at speeds several orders of magnitude faster compared to pHMM-tree. As an example, PRC Extended (PRCx) was used to study the phylogeny of over 10,000 sequences of lytic polysaccharide monooxygenase (LPMO) from over seven families. Using the newly developed program we were able to reveal previously unknown homologs of LPMOs, namely the PFAM Egh16-like family. Moreover, we show that the substrate specificities have evolved independently several times within the LPMO superfamily. Furthermore, the LPMO phylogenetic tree, does not seem to follow taxonomy-based classification.

Investigation of machine learning techniques on proteomics: A comprehensive survey

Proteomics is the extensive investigation of proteins which has empowered the recognizable proof of consistently expanding quantities of protein. Proteins are necessary part of living life form, with numerous capacities. The proteome is the complete arrangement of proteins that are created or altered by a life form or framework of the organism. Proteome fluctuates with time and unambiguous prerequisites, or stresses, that a cell or organism experiences. Proteomics is an interdisciplinary area that has derived from the hereditary data of different genome ventures. Much proteomics information is gathered with the assistance of high throughput techniques, for example, mass spectrometry and microarray. It would regularly take weeks or months to analyze the information and perform examinations by hand. Therefore, scholars and scientific experts are teaming up with computer science researchers and mathematicians to make projects and pipeline to computationally examine the protein information. Utilizing bioinformatics procedures, scientists are prepared to do quicker investigation and protein information storing. The goal of this paper is to brief about the review of machine learning procedures and its application in the field of proteomics.

Accurate Prediction of One-Dimensional Protein Structure Features Using SPINE-X

Accurate prediction of protein secondary structure and other one-dimensional structure features is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. SPINE-X is a software package to predict secondary structure as well as accessible surface area and dihedral angles ϕ and ψ. For secondary structure SPINE-X achieves an accuracy of between 81 and 84 % depending on the dataset and choice of tests. The Pearson correlation coefficient for accessible surface area prediction is 0.75 and the mean absolute error from the ϕ and ψ dihedral angles are 20^∘ and 33^∘, respectively. The source code and a Linux executables for SPINE-X are available from Research and Information Systems at http://mamiris.com .

Backbone Dihedral Angle Prediction

More than two decades of research have enabled dihedral angle predictions at an accuracy that makes them an interesting alternative or supplement to secondary structure prediction that provides detailed local structure information for every residue of a protein. The evolution of dihedral angle prediction methods is closely linked to advancements in machine learning and other relevant technologies. Consequently recent improvements in large-scale training of deep neural networks have led to the best method currently available, which achieves a mean absolute error of 19° for phi, and 30° for psi. This performance opens interesting perspectives for the application of dihedral angle prediction in the comparison, prediction, and design of protein structures.

Novel protein weight matrix generated from amino acid indices

In recent years, numerous protein weight matrices have been developed that include physical characteristics of proteins, such as local sequence-structure information, alpha-helix information, secondary structure information and solvent accessibility states. These protein weight matrices are shown to have generally improved protein sequence alignments over classical protein weight matrices, like Point Accepted Mutation (PAM), Blocks of Amino Acid Substitution (BLOSUM), and GONNET matrices, where important limitations have been observe in recent works. In this paper, a novel protein weight matrix is constructed and presented. This protein weight matrix is not considered based on the mutation rate, like PAM or BLOSUM matrices, but on the physicochemical properties of each amino acid. In the literature, over 500 amino acid indices exist, each one representing a unique biological protein feature. For this study, 25 amino acid indices were selected. These amino acid indices represent general and widely accepted features of the amino acids. By using the proposed protein weight matrix the following advantages can be obtained compared to the classical protein weight matrices. The proposed protein weight matrix is not biased to specific groups of protein sequences as the values are calculated from the amino acid indices, and not from the protein sequences. Additionally, for the proposed protein weight matrix, the same matrix can be considered regardless of the protein sequence's homology to be aligned or the mutation rate presented. A correlation to the physical characterisations of the amino acids that the protein weight matrix derived from can be achieved. Different similarity matrices can be generated when different physical characterisations of amino acids are considered.

General overview on structure prediction of twilight-zone proteins

Protein structure prediction from amino acid sequence has been one of the most challenging aspects in computational structural biology despite significant progress in recent years showed by critical assessment of protein structure prediction (CASP) experiments. When experimentally determined structures are unavailable, the predictive structures may serve as starting points to study a protein. If the target protein consists of homologous region, high-resolution (typically <1.5 Å) model can be built via comparative modelling. However, when confronted with low sequence similarity of the target protein (also known as twilight-zone protein, sequence identity with available templates is less than 30%), the protein structure prediction has to be initiated from scratch. Traditionally, twilight-zone proteins can be predicted via threading or ab initio method. Based on the current trend, combination of different methods brings an improved success in the prediction of twilight-zone proteins. In this mini review, the methods, progresses and challenges for the prediction of twilight-zone proteins were discussed.

Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network

Because a nearly constant distance between two neighbouring Cα atoms, local backbone structure of proteins can be represented accurately by the angle between C(αi-1)-C(αi)-C(αi+1) (θ) and a dihedral angle rotated about the C(αi)-C(αi+1) bond (τ). θ and τ angles, as the representative of structural properties of three to four amino-acid residues, offer a description of backbone conformations that is complementary to φ and ψ angles (single residue) and secondary structures (>3 residues). Here, we report the first machine-learning technique for sequence-based prediction of θ and τ angles. Predicted angles based on an independent test have a mean absolute error of 9° for θ and 34° for τ with a distribution on the θ-τ plane close to that of native values. The average root-mean-square distance of 10-residue fragment structures constructed from predicted θ and τ angles is only 1.9Å from their corresponding native structures. Predicted θ and τ angles are expected to be complementary to predicted ϕ and ψ angles and secondary structures for using in model validation and template-based as well as template-free structure prediction. The deep neural network learning technique is available as an on-line server called Structural Property prediction with Integrated DEep neuRal network (SPIDER) at http://sparks-lab.org.

Evaluation of protein dihedral angle prediction methods

Tertiary structure prediction of a protein from its amino acid sequence is one of the major challenges in the field of bioinformatics. Hierarchical approach is one of the persuasive techniques used for predicting protein tertiary structure, especially in the absence of homologous protein structures. In hierarchical approach, intermediate states are predicted like secondary structure, dihedral angles, C^α-C^α distance bounds, etc. These intermediate states are used to restraint the protein backbone and assist its correct folding. In the recent years, several methods have been developed for predicting dihedral angles of a protein, but it is difficult to conclude which method is better than others. In this study, we benchmarked the performance of dihedral prediction methods ANGLOR and SPINE X on various datasets, including independent datasets. TANGLE dihedral prediction method was not benchmarked (due to unavailability of its standalone) and was compared with SPINE X and ANGLOR on only ANGLOR dataset on which TANGLE has reported its results. It was observed that SPINE X performed better than ANGLOR and TANGLE, especially in case of prediction of dihedral angles of glycine and proline residues. The analysis suggested that angle shifting was the foremost reason of better performance of SPINE X. We further evaluated the performance of the methods on independent ccPDB30 dataset and observed that SPINE X performed better than ANGLOR.

Revisiting amino acid substitution matrices for identifying distantly related proteins

Motivation: Although many amino acid substitution matrices have been developed, it has not been well understood which is the best for similarity searches, especially for remote homology detection. Therefore, we collected information related to existing matrices, condensed it and derived a novel matrix that can detect more remote homology than ever.

Results: Using principal component analysis with existing matrices and benchmarks, we developed a novel matrix, which we designate as MIQS. The detection performance of MIQS is validated and compared with that of existing general purpose matrices using SSEARCH with optimized gap penalties for each matrix. Results show that MIQS is able to detect more remote homology than the existing matrices on an independent dataset. In addition, the performance of our developed matrix was superior to that of CS-BLAST, which was a novel similarity search method with no amino acid matrix. We also evaluated the alignment quality of matrices and methods, which revealed that MIQS shows higher alignment sensitivity than that with the existing matrix series and CS-BLAST. Fundamentally, these results are expected to constitute good proof of the availability and/or importance of amino acid matrices in sequence analysis. Moreover, with our developed matrix, sophisticated similarity search methods such as sequence–profile and profile–profile comparison methods can be improved further.

Availability and implementation: Newly developed matrices and datasets used for this study are available at http://csas.cbrc.jp/Ssearch/.

Contact:k-tomii@aist.go.jp

Supplementary information:Supplementary data are available at Bioinformatics online

Microbiome in human health and disease

Metagenomic studies have truly revolutionised biology and medicine, and changed the way we study genomics. As genome sequencing becomes cheaper it is being applied to study complex metagenomes. 'Metagenome' is the genetic material recovered directly from an environmental sample or niche. By delivering fast, cheap, and large volumes of data Next Generation Sequencing (NGS) platforms have facilitated a deeper understanding of the fundamentals of genomes, gene functions and regulation. Metagenomics, also referred to as environmental or community genomics, has brought about radical changes in our ability to analyse complex microbial communities by direct sampling of their natural habitat paving the way for the creation of innovative new areas for biomedical research. Many metagenomic studies involving the 'human microbiome'have been undertaken to date. Samples from of a number of diverse habitats including different human body sites have been subject to metagenomic examinations. Huge national and international projects with the purpose of elucidating the biogeography of microbial communities living within and on the human body, are well underway. The analysis of human microbiome data has brought about a paradigm shift in our understanding of the role of resident microflora in human health and disease and brings non-traditional areas such as gut ecology to the forefront of personalised medicine. In this chapter we present an overview of the state-of-the-art in current literature and projects pertaining to human microbiome studies.

Discriminative modelling of context-specific amino acid substitution probabilities

MOTIVATION

Protein sequence searching and alignment are fundamental tools of modern biology. Alignments are assessed using their similarity scores, essentially the sum of substitution matrix scores over all pairs of aligned amino acids. We previously proposed a generative probabilistic method that yields scores that take the sequence context around each aligned residue into account. This method showed drastically improved sensitivity and alignment quality compared with standard substitution matrix-based alignment.

RESULTS

Here, we develop an alternative discriminative approach to predict sequence context-specific substitution scores. We applied our approach to compute context-specific sequence profiles for Basic Local Alignment Search Tool (BLAST) and compared the new tool (CS-BLASTdis) to BLAST and the previous context-specific version (CS-BLASTgen). On a dataset filtered to 20% maximum sequence identity, CS-BLASTdisis was 51% more sensitive than BLAST and 17% more sensitive than CS-BLASTgenin, detecting remote homologues at 10% false discovery rate. At 30% maximum sequence identity, its alignments contain 21 and 12% more correct residue pairs than those of BLAST and CS-BLASTgen, respectively. Clear improvements are also seen when the approach is combined with PSI-BLAST and HHblits. We believe the context-specific approach should replace substitution matrices wherever sensitivity and alignment quality are critical.

TANGLE: two-level support vector regression approach for protein backbone torsion angle prediction from primary sequences

Protein backbone torsion angles (Phi) and (Psi) involve two rotation angles rotating around the C_α-N bond (Phi) and the C_α-C bond (Psi). Due to the planarity of the linked rigid peptide bonds, these two angles can essentially determine the backbone geometry of proteins. Accordingly, the accurate prediction of protein backbone torsion angle from sequence information can assist the prediction of protein structures. In this study, we develop a new approach called TANGLE (Torsion ANGLE predictor) to predict the protein backbone torsion angles from amino acid sequences. TANGLE uses a two-level support vector regression approach to perform real-value torsion angle prediction using a variety of features derived from amino acid sequences, including the evolutionary profiles in the form of position-specific scoring matrices, predicted secondary structure, solvent accessibility and natively disordered region as well as other global sequence features. When evaluated based on a large benchmark dataset of 1,526 non-homologous proteins, the mean absolute errors (MAEs) of the Phi and Psi angle prediction are 27.8° and 44.6°, respectively, which are 1% and 3% respectively lower than that using one of the state-of-the-art prediction tools ANGLOR. Moreover, the prediction of TANGLE is significantly better than a random predictor that was built on the amino acid-specific basis, with the p-value<1.46e-147 and 7.97e-150, respectively by the Wilcoxon signed rank test. As a complementary approach to the current torsion angle prediction algorithms, TANGLE should prove useful in predicting protein structural properties and assisting protein fold recognition by applying the predicted torsion angles as useful restraints. TANGLE is freely accessible at http://sunflower.kuicr.kyoto-u.ac.jp/~sjn/TANGLE/.

Structural modelling pipelines in next generation sequencing projects

Our capacity to reliably predict protein structure from sequence is steadily improving due to the increased numbers and better targeting of protein structures being experimentally determined by structural genomics projects, along with the development of better modeling methodologies. Template-based (homology) modeling and de novo modeling methods are being combined to fill in remaining gaps in template coverage, and powerful automated structural modeling pipelines are being applied to large data sets of protein sequences. The improved quality of 3D models of proteins has led to their routine use in assessing the functional impact of nonsynonymous single nucleotide polymorphisms (nsSNPs) in specific protein systems, with the development of approaches that may be applied in a predictive fashion to nsSNPs emerging from next-generation sequencing projects. The challenges encountered in deriving functionally meaningful deductions from structural modeling can be quite different for proteins of different protein functional classes. The specific challenges to the assessment of the structural and functional impact of nsSNPs in globular proteins such as binding and regulatory proteins, structural proteins, and enzymes are discussed, as well as membrane transport proteins and ion channels. The mapping of reliable predictions of the structural and functional impact of SNPs, generated from automated modeling pipelines, on to protein-protein interaction networks will facilitate new approaches to understanding complex polygenic disorders and predisposition to disease.

Aligning protein sequence and analysing substitution pattern using a class-specific matrix

Aligning protein sequences using a score matrix has became a routine but valuable method in modern biological research. However, alignment in the 'twilight zone' remains an open issue. It is feasible and necessary to construct a new score matrix as more protein structures are resolved. Three structural class-specific score matrices (all-alpha, all-beta and alpha/beta) were constructed based on the structure alignment of low identity proteins of the corresponding structural classes. The class-specific score matrices were significantly better than a structure-derived matrix (HSDM) and three other generalized matrices (BLOSUM30, BLOSUM60 and Gonnet250) in alignment performance tests. The optimized gap penalties presented here also promote alignment performance. The results indicate that different protein classes have distinct amino acid substitution patterns, and an amino acid score matrix should be constructed based on different structural classes. The class-specific score matrices could also be used in profile construction to improve homology detection.

Predicting continuous local structure and the effect of its substitution for secondary structure in fragment-free protein structure prediction

Local structures predicted from protein sequences are used extensively in every aspect of modeling and prediction of protein structure and function. For more than 50 years, they have been predicted at a low-resolution coarse-grained level (e.g., three-state secondary structure). Here, we combine a two-state classifier with real-value predictor to predict local structure in continuous representation by backbone torsion angles. The accuracy of the angles predicted by this approach is close to that derived from NMR chemical shifts. Their substitution for predicted secondary structure as restraints for ab initio structure prediction doubles the success rate. This result demonstrates the potential of predicted local structure for fragment-free tertiary-structure prediction. It further implies potentially significant benefits from using predicted real-valued torsion angles as a replacement for or supplement to the secondary-structure prediction tools used almost exclusively in many computational methods ranging from sequence alignment to function prediction.

Prediction of backbone dihedral angles and protein secondary structure using support vector machines

Background

The prediction of the secondary structure of a protein is a critical step in the prediction of its tertiary structure and, potentially, its function. Moreover, the backbone dihedral angles, highly correlated with secondary structures, provide crucial information about the local three-dimensional structure.

Results

We predict independently both the secondary structure and the backbone dihedral angles and combine the results in a loop to enhance each prediction reciprocally. Support vector machines, a state-of-the-art supervised classification technique, achieve secondary structure predictive accuracy of 80% on a non-redundant set of 513 proteins, significantly higher than other methods on the same dataset. The dihedral angle space is divided into a number of regions using two unsupervised clustering techniques in order to predict the region in which a new residue belongs. The performance of our method is comparable to, and in some cases more accurate than, other multi-class dihedral prediction methods.

Conclusions

We have created an accurate predictor of backbone dihedral angles and secondary structure. Our method, called DISSPred, is available online at http://comp.chem.nottingham.ac.uk/disspred/.

Distance matrix-based approach to protein structure prediction

Much structural information is encoded in the internal distances; a distance matrix-based approach can be used to predict protein structure and dynamics, and for structural refinement. Our approach is based on the square distance matrix D = [r(ij)(2)] containing all square distances between residues in proteins. This distance matrix contains more information than the contact matrix C, that has elements of either 0 or 1 depending on whether the distance r (ij) is greater or less than a cutoff value r (cutoff). We have performed spectral decomposition of the distance matrices D = sigma lambda(k)V(k)V(kT), in terms of eigenvalues lambda kappa and the corresponding eigenvectors v kappa and found that it contains at most five nonzero terms. A dominant eigenvector is proportional to r (2)--the square distance of points from the center of mass, with the next three being the principal components of the system of points. By predicting r (2) from the sequence we can approximate a distance matrix of a protein with an expected RMSD value of about 7.3 A, and by combining it with the prediction of the first principal component we can improve this approximation to 4.0 A. We can also explain the role of hydrophobic interactions for the protein structure, because r is highly correlated with the hydrophobic profile of the sequence. Moreover, r is highly correlated with several sequence profiles which are useful in protein structure prediction, such as contact number, the residue-wise contact order (RWCO) or mean square fluctuations (i.e. crystallographic temperature factors). We have also shown that the next three components are related to spatial directionality of the secondary structure elements, and they may be also predicted from the sequence, improving overall structure prediction. We have also shown that the large number of available HIV-1 protease structures provides a remarkable sampling of conformations, which can be viewed as direct structural information about the dynamics. After structure matching, we apply principal component analysis (PCA) to obtain the important apparent motions for both bound and unbound structures. There are significant similarities between the first few key motions and the first few low-frequency normal modes calculated from a static representative structure with an elastic network model (ENM) that is based on the contact matrix C (related to D), strongly suggesting that the variations among the observed structures and the corresponding conformational changes are facilitated by the low-frequency, global motions intrinsic to the structure. Similarities are also found when the approach is applied to an NMR ensemble, as well as to atomic molecular dynamics (MD) trajectories. Thus, a sufficiently large number of experimental structures can directly provide important information about protein dynamics, but ENM can also provide a similar sampling of conformations. Finally, we use distance constraints from databases of known protein structures for structure refinement. We use the distributions of distances of various types in known protein structures to obtain the most probable ranges or the mean-force potentials for the distances. We then impose these constraints on structures to be refined or include the mean-force potentials directly in the energy minimization so that more plausible structural models can be built. This approach has been successfully used by us in 2006 in the CASPR structure refinement (http://predictioncenter.org/caspR).

Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network

This article attempts to increase the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins through improved learning. Most methods developed for improving the backpropagation algorithm of artificial neural networks are limited to small neural networks. Here, we introduce a guided-learning method suitable for networks of any size. The method employs a part of the weights for guiding and the other part for training and optimization. We demonstrate this technique by predicting residue solvent accessibility and real-value backbone torsion angles of proteins. In this application, the guiding factor is designed to satisfy the intuitive condition that for most residues, the contribution of a residue to the structural properties of another residue is smaller for greater separation in the protein-sequence distance between the two residues. We show that the guided-learning method makes a 2-4% reduction in 10-fold cross-validated mean absolute errors (MAE) for predicting residue solvent accessibility and backbone torsion angles, regardless of the size of database, the number of hidden layers and the size of input windows. This together with introduction of two-layer neural network with a bipolar activation function leads to a new method that has a MAE of 0.11 for residue solvent accessibility, 36 degrees for psi, and 22 degrees for phi. The method is available as a Real-SPINE 3.0 server in http://sparks.informatics.iupui.edu.

Sequence context-specific profiles for homology searching

Sequence alignment and database searching are essential tools in biology because a protein's function can often be inferred from homologous proteins. Standard sequence comparison methods use substitution matrices to find the alignment with the best sum of similarity scores between aligned residues. These similarity scores do not take the local sequence context into account. Here, we present an approach that derives context-specific amino acid similarities from short windows centered on each query sequence residue. Our results demonstrate that the sequence context contains much more information about the expected mutations than just the residue itself. By employing our context-specific similarities (CS-BLAST) in combination with NCBI BLAST, we increase the sensitivity more than 2-fold on a difficult benchmark set, without loss of speed. Alignment quality is likewise improved significantly. Furthermore, we demonstrate considerable improvements when applying this paradigm to sequence profiles: Two iterations of CSI-BLAST, our context-specific version of PSI-BLAST, are more sensitive than 5 iterations of PSI-BLAST. The paradigm for biological sequence comparison presented here is very general. It can replace substitution matrices in sequence- and profile-based alignment and search methods for both protein and nucleotide sequences.

ANGLOR: a composite machine-learning algorithm for protein backbone torsion angle prediction

We developed a composite machine-learning based algorithm, called ANGLOR, to predict real-value protein backbone torsion angles from amino acid sequences. The input features of ANGLOR include sequence profiles, predicted secondary structure and solvent accessibility. In a large-scale benchmarking test, the mean absolute error (MAE) of the phi/psi prediction is 28°/46°, which is ∼10% lower than that generated by software in literature. The prediction is statistically different from a random predictor (or a purely secondary-structure-based predictor) with p-value <1.0×10⁻³⁰⁰ (or <1.0×10⁻¹⁴⁸) by Wilcoxon signed rank test. For some residues (ILE, LEU, PRO and VAL) and especially the residues in helix and buried regions, the MAE of phi angles is much smaller (10–20°) than that in other environments. Thus, although the average accuracy of the ANGLOR prediction is still low, the portion of the accurately predicted dihedral angles may be useful in assisting protein fold recognition and ab initio 3D structure modeling.

Real-value prediction of backbone torsion angles

The backbone structure of a protein is largely determined by the phi and psi torsion angles. Thus, knowing these angles, even if approximately, will be very useful for protein-structure prediction. However, in a previous work, a sequence-based, real-value prediction of psi angle could only achieve a mean absolute error of 54 degrees (83 degrees, 35 degrees, 33 degrees for coil, strand, and helix residues, respectively) between predicted and actual angles. Moreover, a real-value prediction of phi angle is not yet available. This article employs a neural-network based approach to improve psi prediction by taking advantage of angle periodicity and apply the new method to the prediction to phi angles. The 10-fold-cross-validated mean absolute error for the new method is 38 degrees (58 degrees, 33 degrees, 22 degrees for coil, strand, and helix, respectively) for psi and 25 degrees (35 degrees, 22 degrees, 16 degrees for coil, strand, and helix, respectively) for phi. The accuracy of real-value prediction is comparable to or more accurate than the predictions based on multistate classification of the phi-psi map. More accurate prediction of real-value angles will likely be useful for improving the accuracy of fold recognition and ab initio protein-structure prediction. The Real-SPINE 2.0 server is available on the website http://sparks.informatics.iupui.edu.

SP5: improving protein fold recognition by using torsion angle profiles and profile-based gap penalty model

How to recognize the structural fold of a protein is one of the challenges in protein structure prediction. We have developed a series of single (non-consensus) methods (SPARKS, SP(2), SP(3), SP(4)) that are based on weighted matching of two to four sequence and structure-based profiles. There is a robust improvement of the accuracy and sensitivity of fold recognition as the number of matching profiles increases. Here, we introduce a new profile-profile comparison term based on real-value dihedral torsion angles. Together with updated real-value solvent accessibility profile and a new variable gap-penalty model based on fractional power of insertion/deletion profiles, the new method (SP(5)) leads to a robust improvement over previous SP method. There is a 2% absolute increase (5% relative improvement) in alignment accuracy over SP(4) based on two independent benchmarks. Moreover, SP(5) makes 7% absolute increase (22% relative improvement) in success rate of recognizing correct structural folds, and 32% relative improvement in model accuracy of models within the same fold in Lindahl benchmark. In addition, modeling accuracy of top-1 ranked models is improved by 12% over SP(4) for the difficult targets in CASP 7 test set. These results highlight the importance of harnessing predicted structural properties in challenging remote-homolog recognition. The SP(5) server is available at http://sparks.informatics.iupui.edu.

Remote protein homology detection using recurrence quantification analysis and amino acid physicochemical properties

Remote homology detection refers to the detection of structure homology in evolutionarily related proteins with low sequence similarity. Supervised learning algorithms such as support vector machine (SVM) are currently the most accurate methods. In most of these SVM-based methods, efforts have been dedicated to developing new kernels to better use the pairwise alignment scores or sequence profiles. Moreover, amino acids' physicochemical properties are not generally used in the feature representation of protein sequences. In this article, we present a remote homology detection method that incorporates two novel features: (1) a protein's primary sequence is represented using amino acid's physicochemical properties and (2) the similarity between two proteins is measured using recurrence quantification analysis (RQA). An optimization scheme was developed to select different amino acid indices (up to 10 for a protein family) that are best to characterize the given protein family. The selected amino acid indices may enable us to draw better biological explanation of the protein family classification problem than using other alignment-based methods. An SVM-based classifier will then work on the space described by the RQA metrics. The classification scheme is named as SVM-RQA. Experiments at the superfamily level of the SCOP1.53 dataset show that, without using alignment or sequence profile information, the features generated from amino acid indices are able to produce results that are comparable to those obtained by the published state-of-the-art SVM kernels. In the future, better prediction accuracies can be expected by combining the alignment-based features with our amino acids property-based features. Supplementary information including the raw dataset, the best-performing amino acid indices for each protein family and the computed RQA metrics for all protein sequences can be downloaded from http://ym151113.ym.edu.tw/svm-rqa.

Bayesian methods for proteomics

Biological and medical data have been growing exponentially over the past several years [1, 2]. In particular, proteomics has seen automation dramatically change the rate at which data are generated [3]. Analysis that systemically incorporates prior information is becoming essential to making inferences about the myriad, complex data [4-6]. A Bayesian approach can help capture such information and incorporate it seamlessly through a rigorous, probabilistic framework. This paper starts with a review of the background mathematics behind the Bayesian methodology: from parameter estimation to Bayesian networks. The article then goes on to discuss how emerging Bayesian approaches have already been successfully applied to research across proteomics, a field for which Bayesian methods are particularly well suited [7-9]. After reviewing the literature on the subject of Bayesian methods in biological contexts, the article discusses some of the recent applications in proteomics and emerging directions in the field.

Periodic distributions of hydrophobic amino acids allows the definition of fundamental building blocks to align distantly related proteins

Several studies on large and small families of proteins proved in a general manner that hydrophobic amino acids are globally conserved even if they are subjected to high rate substitution. Statistical analysis of amino acids evolution within blocks of hydrophobic amino acids detected in sequences suggests their usage as a basic structural pattern to align pairs of proteins of less than 25% sequence identity, with no need of knowing their 3D structure. The authors present a new global alignment method and an automatic tool for Proteins with HYdrophobic Blocks ALignment (PHYBAL) based on the combinatorics of overlapping hydrophobic blocks. Two substitution matrices modeling a different selective pressure inside and outside hydrophobic blocks are constructed, the Inside Hydrophobic Blocks Matrix and the Outside Hydrophobic Blocks Matrix, and a 4D space of gap values is explored. PHYBAL performance is evaluated against Needleman and Wunsch algorithm run with Blosum 30, Blosum 45, Blosum 62, Gonnet, HSDM, PAM250, Johnson and Remote Homo matrices. PHYBAL behavior is analyzed on eight randomly selected pairs of proteins of >30% sequence identity that cover a large spectrum of structural properties. It is also validated on two large datasets, the 127 pairs of the Domingues dataset with >30% sequence identity, and 181 pairs issued from BAliBASE 2.0 and ranked by percentage of identity from 7 to 25%. Results confirm the importance of considering substitution matrices modeling hydrophobic contexts and a 4D space of gap values in aligning distantly related proteins. Two new notions of local and global stability are defined to assess the robustness of an alignment algorithm and the accuracy of PHYBAL. A new notion, the SAD-coefficient, to assess the difficulty of structural alignment is also introduced. PHYBAL has been compared with Hydrophobic Cluster Analysis and HMMSUM methods.

MUMMALS: multiple sequence alignment improved by using hidden Markov models with local structural information

We have developed MUMMALS, a program to construct multiple protein sequence alignment using probabilistic consistency. MUMMALS improves alignment quality by using pairwise alignment hidden Markov models (HMMs) with multiple match states that describe local structural information without exploiting explicit structure predictions. Parameters for such models have been estimated from a large library of structure-based alignments. We show that (i) on remote homologs, MUMMALS achieves statistically best accuracy among several leading aligners, such as ProbCons, MAFFT and MUSCLE, albeit the average improvement is small, in the order of several percent; (ii) a large collection (>10 000) of automatically computed pairwise structure alignments of divergent protein domains is superior to smaller but carefully curated datasets for estimation of alignment parameters and performance tests; (iii) reference-independent evaluation of alignment quality using sequence alignment-dependent structure superpositions correlates well with reference-dependent evaluation that compares sequence-based alignments to structure-based reference alignments.

Improved alignment quality by combining evolutionary information, predicted secondary structure and self-organizing maps

BACKGROUND

Protein sequence alignment is one of the basic tools in bioinformatics. Correct alignments are required for a range of tasks including the derivation of phylogenetic trees and protein structure prediction. Numerous studies have shown that the incorporation of predicted secondary structure information into alignment algorithms improves their performance. Secondary structure predictors have to be trained on a set of somewhat arbitrarily defined states (e.g. helix, strand, coil), and it has been shown that the choice of these states has some effect on alignment quality. However, it is not unlikely that prediction of other structural features also could provide an improvement. In this study we use an unsupervised clustering method, the self-organizing map, to assign sequence profile windows to "structural states" and assess their use in sequence alignment.

RESULTS

The addition of self-organizing map locations as inputs to a profile-profile scoring function improves the alignment quality of distantly related proteins slightly. The improvement is slightly smaller than that gained from the inclusion of predicted secondary structure. However, the information seems to be complementary as the two prediction schemes can be combined to improve the alignment quality by a further small but significant amount.

CONCLUSION

It has been observed in many studies that predicted secondary structure significantly improves the alignments. Here we have shown that the addition of self-organizing map locations can further improve the alignments as the self-organizing map locations seem to contain some information that is not captured by the predicted secondary structure.

Sequence comparison and protein structure prediction

Sequence comparison is a major step in the prediction of protein structure from existing templates in the Protein Data Bank. The identification of potentially remote homologues to be used as templates for modeling target sequences of unknown structure and their accurate alignment remain challenges, despite many years of study. The most recent advances have been in combining as many sources of information as possible--including amino acid variation in the form of profiles or hidden Markov models for both the target and template families, known and predicted secondary structures of the template and target, respectively, the combination of structure alignment for distant homologues and sequence alignment for close homologues to build better profiles, and the anchoring of certain regions of the alignment based on existing biological data. Newer technologies have been applied to the problem, including the use of support vector machines to tackle the fold classification problem for a target sequence and the alignment of hidden Markov models. Finally, using the consensus of many fold recognition methods, whether based on profile-profile alignments, threading or other approaches, continues to be one of the most successful strategies for both recognition and alignment of remote homologues. Although there is still room for improvement in identification and alignment methods, additional progress may come from model building and refinement methods that can compensate for large structural changes between remotely related targets and templates, as well as for regions of misalignment.