Remote Homology Detection Research Articles

A Multimodal Approach for Protein Remote Homology Detection.

Protein remote homology detection represents a crucial and challenging task in bioinformatics: even if effective methods appeared in recent years, in several cases a proper characterization of remote evolutionary correlation can not be derived. In such situations, it may be possible that information derived from other sources helps, provided that it is possible to properly integrate such (even partial) information into existing models. In this paper, we provide some evidence that this route is feasible: inspired by the multimodal retrieval literature, we show how it is possible to exploit a simple multimodal approach to improve a model learned from a set of sequences, by using knowledge derived from a partial set of corresponding 3D structures. We investigate (with the SCOP 1.53 benchmark) the suitability of the proposed multimodal scheme, showing that a beneficial effect can be obtained even when a very reduced amount of structures are available. A further detailed analysis on a member of the GPCR superfamily confirms that this multimodal approach can extract information that cannot be obtained from sequence-based techniques.

Improving protein fold recognition with hybrid profiles combining sequence and structure evolution.

Template-based modeling, the most successful approach for predicting protein 3D structure, often requires detecting distant evolutionary relationships between the target sequence and proteins of known structure. Developed for this purpose, fold recognition methods use elaborate strategies to exploit evolutionary information, mainly by encoding amino acid sequence into profiles. Since protein structure is more conserved than sequence, the inclusion of structural information can improve the detection of remote homology. Here, we present ORION, a new fold recognition method based on the pairwise comparison of hybrid profiles that contain evolutionary information from both protein sequence and structure. Our method uses the 16-state structural alphabet Protein Blocks, which provides an accurate 1D description of protein structure local conformations. ORION systematically outperforms PSI-BLAST and HHsearch on several benchmarks, including target sequences from the modeling competitions CASP8, 9 and 10, and detects ∼10% more templates at fold and superfamily SCOP levels. Software freely available for download at http://www.dsimb.inserm.fr/orion/. jean-christophe.gelly@univ-paris-diderot.fr. Supplementary data are available at Bioinformatics online.

Remote homology and the functions of metagenomic dark matter.

Predicted open reading frames (ORFs) that lack detectable homology to known proteins are termed ORFans. Despite their prevalence in metagenomes, the extent to which ORFans encode real proteins, the degree to which they can be annotated, and their functional contributions, remain unclear. To gain insights into these questions, we applied sensitive remote-homology detection methods to functionally analyze ORFans from soil, marine, and human gut metagenome collections. ORFans were identified, clustered into sequence families, and annotated through profile-profile comparison to proteins of known structure. We found that a considerable number of metagenomic ORFans (73,896 of 484,121, 15.3%) exhibit significant remote homology to structurally characterized proteins, providing a means for ORFan functional profiling. The extent of detected remote homology far exceeds that obtained for artificial protein families (1.4%). As expected for real genes, the predicted functions of ORFans are significantly similar to the functions of their gene neighbors (p < 0.001). Compared to the functional profiles predicted through standard homology searches, ORFans show biologically intriguing differences. Many ORFan-enriched functions are virus-related and tend to reflect biological processes associated with extreme sequence diversity. Each environment also possesses a large number of unique ORFan families and functions, including some known to play important community roles such as gut microbial polysaccharide digestion. Lastly, ORFans are a valuable resource for finding novel enzymes of interest, as we demonstrate through the identification of hundreds of novel ORFan metalloproteases that all possess a signature catalytic motif despite a general lack of similarity to known proteins. Our ORFan functional predictions are a valuable resource for discovering novel protein families and exploring the boundaries of protein sequence space. All remote homology predictions are available at http://doxey.uwaterloo.ca/ORFans.

Detección de homología remota de proteínas usando modelos 3D enriquecidos con propiedades fisicoquímicas

En este artículo se presenta un nuevo método para la detección de homología remota llamado remote-3DP. Elmétodo remote 3DP se basa tanto en información 3D predicha como en las propiedades fisicoquímicas de losaminoácidos. El método considera tan sólo 10 modelos estructurales para representar una proteína y distinguir loshomólogos remotos de los no remotos en 54 familias SCOP. La baja dimensionalidad de la representación permiteusar diferentes técnicas de clasificación y descubrir cuál funciona mejor para cada familia. En este artículo, semuestra que al incluir una propiedad fisicoquímica junto con la información 3D en un elemento estructural local, dehecho mejora la exactitud de la detección de homología remota. El puntaje ROC para un conjunto de modelos queincluye el índice de hidropatía alcanza un puntaje de 0. 953 para el conjunto de datos SCOP 1.53. Además, se proponeun modelo de ensamble que utiliza las salidas obtenidas para las 10 propiedades y así tomar una decisión consenso.La estrategia consenso alcanza un puntaje ROC de 0.963 sobre el conjunto de datos SCOP 1.53, sobrepasando losmétodos actuales basados en la composición de la secuencia cuya exactitud varía de 0.87 a 0.92.

Ultra-large alignments using phylogeny-aware profiles.

Many biological questions, including the estimation of deep evolutionary histories and the detection of remote homology between protein sequences, rely upon multiple sequence alignments and phylogenetic trees of large datasets. However, accurate large-scale multiple sequence alignment is very difficult, especially when the dataset contains fragmentary sequences. We present UPP, a multiple sequence alignment method that uses a new machine learning technique, the ensemble of hidden Markov models, which we propose here. UPP produces highly accurate alignments for both nucleotide and amino acid sequences, even on ultra-large datasets or datasets containing fragmentary sequences. UPP is available at https://github.com/smirarab/sepp.Electronic supplementary materialThe online version of this article (doi:10.1186/s13059-015-0688-z) contains supplementary material, which is available to authorized users.

The Phyre2 web portal for protein modeling, prediction and analysis.

Phyre2 is a suite of tools available on the web to predict and analyze protein structure, function and mutations. The focus of Phyre2 is to provide biologists with a simple and intuitive interface to state-of-the-art protein bioinformatics tools. Phyre2 replaces Phyre, the original version of the server for which we previously published a paper in Nature Protocols. In this updated protocol, we describe Phyre2, which uses advanced remote homology detection methods to build 3D models, predict ligand binding sites and analyze the effect of amino acid variants (e.g., nonsynonymous SNPs (nsSNPs)) for a user's protein sequence. Users are guided through results by a simple interface at a level of detail they determine. This protocol will guide users from submitting a protein sequence to interpreting the secondary and tertiary structure of their models, their domain composition and model quality. A range of additional available tools is described to find a protein structure in a genome, to submit large number of sequences at once and to automatically run weekly searches for proteins that are difficult to model. The server is available at http://www.sbg.bio.ic.ac.uk/phyre2. A typical structure prediction will be returned between 30 min and 2 h after submission.

Protein remote homology detection by combining Chou's distance-pair pseudo amino acid composition and principal component analysis.

Protein remote homology detection is one of the important tasks in computational proteomics, which is important for basic research and practical application. Currently, the SVM-based discriminative methods have shown superior performance. However, the existing feature vectors still cannot suitably represent the protein sequences, and often lack an interpretable model for analysis of characteristic features. Previous studies showed that sequence-order effects and physicochemical properties are important for representing protein sequences. However, how to use these kinds of information for constructing predictors is still a challenging problem. In this study, in order to incorporate the sequence-order information and physicochemical properties into the prediction, a method called disPseAAC is proposed, in which the feature vector is constructed by combining the occurrences of amino acid pairs within the Chou's pseudo amino acid composition (PseAAC) approach. The predictive performance and computational cost are further improved by employing the principal component analysis strategy. Various experiments are conducted on a benchmark dataset. Experimental results show that disPseAAC achieves an ROC score of 0.922, outperforming some existing state-of-the-art methods. Furthermore, the learnt model can easily be analyzed in terms of discriminative features, and the computational cost of the proposed method is much lower than that of other profile-based methods.

Reducing dimensionality in remote homology detection using predicted contact maps

In this paper, a new method for remote protein homology detection is presented. Most discriminative methods concatenate the values extracted from physicochemical properties to build a model that separates homolog and non-homolog examples. Each discriminative method uses a specific strategy to represent the information extracted from the protein sequence and a different number of indices. After the vector representation is achieved, support vector machines (SVM) are usually used. Most classification techniques are not suitable in remote homology detection because they do not address high dimensional datasets. In this paper, we propose a method that reduces the high dimensionality of the vector representation using models that are defined at the 3D level. Next, the models are mapped from the protein primary sequence. The new method, called remote-C3D, is presented and tested on the SCOP 1.53 and SCOP 1.55 datasets. The remote-C3D method achieves a higher accuracy than the composition-based methods and a comparable performance with profile-based methods.

A discriminative method for protein remote homology detection based on N-Gram

Protein remote homology detection refers to detecting structural homology in proteins with an extremely low rate of sequence similarity. Such detection is primarily conducted using 3 methods: pairwise sequence comparisons, generative models for protein families, and discriminative classifiers. In this study, a discriminative classification method involving N-Grams was adopted to extract features using a random forest algorithm to classify data sets. Experiments in the SCOP 1.53 data set showed that our approach improved the receiver operating characteristic by 6% compared with well-known methods. To determine a score threshold that could be used to divide the data set, we also used a heuristic method through which the precision of positive examples and recall rate reached 0.5647 and 0.8647, respectively. Few other studies have investigated the recall and precision of such examples.

Fast Model-based Protein Homology Discovery without Alignment

The need for quick gene categorization tools is growing as more genomes are sequenced. To evaluate a newly sequenced genome, the genes must first be identified and translated into amino acid sequences, which are then categorized into structural or functional classes. Protein homology detection using sequence alignment algorithms is the most effective way for protein categorization. Discriminative approaches such as support vector machines (SVMs) and position-specific scoring matrices (PSSM) derived from PSI-BLAST have recently been used to improve alignment algorithms. However, if a fresh sequence is being aligned, alignment algorithms take time. must be compared to a large number of previously published sequences — the same is true for SVMs. Building a PSSM for the PSSM is even more time-consuming than a fresh order It would take roughly 25 hours to implement the best-performing approaches to classify the sequences on today's computers. Describing a novel genome (20, 000 genes) as belonging to one single organism. There are hundreds of classes to choose from, though. Another flaw with alignment algorithms is that they do not construct a model of the positive class, instead of measuring the mutual distance between sequences or profiles. Only multiple alignments and hidden Markov models are common classification approaches for creating a positive class model, but they have poor classification performance. A model's advantage is that it may be evaluated for chemical features that are shared by all members of the class to get fresh insights into protein function and structure. We used LSTM to solve a well-known remote protein homology detection benchmark, in which a protein must be categorized as a member of the SCOP superfamily. LSTM achieves state-of-the-art classification performance while being significantly faster than other algorithms with similar classification performance. LSTM is five orders of magnitude quicker than the quickest SVM-based approaches and two orders of magnitude faster than methods that perform somewhat better in classification (which, however, have lower classification performance than LSTM). We applied LSTM to PROSITE classes and analyzed the derived patterns to test the modeling capabilities of the algorithm. Because it does not require established similarity metrics like BLOSUM or PAM matrices, LSTM is complementary to alignment-based techniques. The PROSITE motif was retrieved by LSTM in 8 out of 15 classes. In the remaining seven examples, alternative motifs are developed that, on average, outperform the PROSITE motifs in categorization.

A multimodal approach to protein remote homology detection

A multimodal approach to protein remote homology detection

NrichD database: sequence databases enriched with computationally designed protein-like sequences aid in remote homology detection.

NrichD (http://proline.biochem.iisc.ernet.in/NRICHD/) is a database of computationally designed protein-like sequences, augmented into natural sequence databases that can perform hops in protein sequence space to assist in the detection of remote relationships. Establishing protein relationships in the absence of structural evidence or natural ‘intermediately related sequences’ is a challenging task. Recently, we have demonstrated that the computational design of artificial intermediary sequences/linkers is an effective approach to fill naturally occurring voids in protein sequence space. Through a large-scale assessment we have demonstrated that such sequences can be plugged into commonly employed search databases to improve the performance of routinely used sequence search methods in detecting remote relationships. Since it is anticipated that such data sets will be employed to establish protein relationships, two databases that have already captured these relationships at the structural and functional domain level, namely, the SCOP database and the Pfam database, have been ‘enriched’ with these artificial intermediary sequences. NrichD database currently contains 3 611 010 artificial sequences that have been generated between 27 882 pairs of families from 374 SCOP folds. The data sets are freely available for download. Additional features include the design of artificial sequences between any two protein families of interest to the user.

Profile hidden Markov models for the detection of viruses within metagenomic sequence data.

Rapid, sensitive, and specific virus detection is an important component of clinical diagnostics. Massively parallel sequencing enables new diagnostic opportunities that complement traditional serological and PCR based techniques. While massively parallel sequencing promises the benefits of being more comprehensive and less biased than traditional approaches, it presents new analytical challenges, especially with respect to detection of pathogen sequences in metagenomic contexts. To a first approximation, the initial detection of viruses can be achieved simply through alignment of sequence reads or assembled contigs to a reference database of pathogen genomes with tools such as BLAST. However, recognition of highly divergent viral sequences is problematic, and may be further complicated by the inherently high mutation rates of some viral types, especially RNA viruses. In these cases, increased sensitivity may be achieved by leveraging position-specific information during the alignment process. Here, we constructed HMMER3-compatible profile hidden Markov models (profile HMMs) from all the virally annotated proteins in RefSeq in an automated fashion using a custom-built bioinformatic pipeline. We then tested the ability of these viral profile HMMs (“vFams”) to accurately classify sequences as viral or non-viral. Cross-validation experiments with full-length gene sequences showed that the vFams were able to recall 91% of left-out viral test sequences without erroneously classifying any non-viral sequences into viral protein clusters. Thorough reanalysis of previously published metagenomic datasets with a set of the best-performing vFams showed that they were more sensitive than BLAST for detecting sequences originating from more distant relatives of known viruses. To facilitate the use of the vFams for rapid detection of remote viral homologs in metagenomic data, we provide two sets of vFams, comprising more than 4,000 vFams each, in the HMMER3 format. We also provide the software necessary to build custom profile HMMs or update the vFams as more viruses are discovered (http://derisilab.ucsf.edu/software/vFam).

Improved performance of sequence search approaches in remote homology detection

The protein sequence space is vast and diverse, spanning across different families. Biologically meaningful relationships exist between proteins at superfamily level. However, it is highly challenging to establish convincing relationships at the superfamily level by means of simple sequence searches. It is necessary to design a rigorous sequence search strategy to establish remote homology relationships and achieve high coverage. We have used iterative profile-based methods, along with constraints of sequence motifs, to specify search directions. We address the importance of multiple start points (queries) to achieve high coverage at protein superfamily level. We have devised strategies to employ a structural regime to search sequence space with good specificity and sensitivity. We employ two well-known sequence search methods, PSI-BLAST and PHI-BLAST, with multiple queries and multiple patterns to enhance homologue identification at the structural superfamily level. The study suggests that multiple queries improve sensitivity, while a pattern-constrained iterative sequence search becomes stringent at the initial stages, thereby driving the search in a specific direction and also achieves high coverage. This data mining approach has been applied to the entire structural superfamily database.

Improved performance of sequence search approaches in remote homology detection

The protein sequence space is vast and diverse, spanning across different families. Biologically meaningful relationships exist between proteins at superfamily level. However, it is highly challenging to establish convincing relationships at the superfamily level by means of simple sequence searches. It is necessary to design a rigorous sequence search strategy to establish remote homology relationships and achieve high coverage. We have used iterative profile-based methods, along with constraints of sequence motifs, to specify search directions. We address the importance of multiple start points (queries) to achieve high coverage at protein superfamily level. We have devised strategies to employ a structural regime to search sequence space with good specificity and sensitivity. We employ two well-known sequence search methods, PSI-BLAST and PHI-BLAST, with multiple queries and multiple patterns to enhance homologue identification at the structural superfamily level. The study suggests that multiple queries improve sensitivity, while a pattern-constrained iterative sequence search becomes stringent at the initial stages, thereby driving the search in a specific direction and also achieves high coverage. This data mining approach has been applied to the entire structural superfamily database.

MRFalign: Protein Homology Detection through Alignment of Markov Random Fields

Sequence-based protein homology detection has been extensively studied and so far the most sensitive method is based upon comparison of protein sequence profiles, which are derived from multiple sequence alignment (MSA) of sequence homologs in a protein family. A sequence profile is usually represented as a position-specific scoring matrix (PSSM) or an HMM (Hidden Markov Model) and accordingly PSSM-PSSM or HMM-HMM comparison is used for homolog detection. This paper presents a new homology detection method MRFalign, consisting of three key components: 1) a Markov Random Fields (MRF) representation of a protein family; 2) a scoring function measuring similarity of two MRFs; and 3) an efficient ADMM (Alternating Direction Method of Multipliers) algorithm aligning two MRFs. Compared to HMM that can only model very short-range residue correlation, MRFs can model long-range residue interaction pattern and thus, encode information for the global 3D structure of a protein family. Consequently, MRF-MRF comparison for remote homology detection shall be much more sensitive than HMM-HMM or PSSM-PSSM comparison. Experiments confirm that MRFalign outperforms several popular HMM or PSSM-based methods in terms of both alignment accuracy and remote homology detection and that MRFalign works particularly well for mainly beta proteins. For example, tested on the benchmark SCOP40 (8353 proteins) for homology detection, PSSM-PSSM and HMM-HMM succeed on 48% and 52% of proteins, respectively, at superfamily level, and on 15% and 27% of proteins, respectively, at fold level. In contrast, MRFalign succeeds on 57.3% and 42.5% of proteins at superfamily and fold level, respectively. This study implies that long-range residue interaction patterns are very helpful for sequence-based homology detection. The software is available for download at http://raptorx.uchicago.edu/download/. A summary of this paper appears in the proceedings of the RECOMB 2014 conference, April 2–5.

Protein fold recognition using geometric kernel data fusion

Motivation: Various approaches based on features extracted from protein sequences and often machine learning methods have been used in the prediction of protein folds. Finding an efficient technique for integrating these different protein features has received increasing attention. In particular, kernel methods are an interesting class of techniques for integrating heterogeneous data. Various methods have been proposed to fuse multiple kernels. Most techniques for multiple kernel learning focus on learning a convex linear combination of base kernels. In addition to the limitation of linear combinations, working with such approaches could cause a loss of potentially useful information.Results: We design several techniques to combine kernel matrices by taking more involved, geometry inspired means of these matrices instead of convex linear combinations. We consider various sequence-based protein features including information extracted directly from position-specific scoring matrices and local sequence alignment. We evaluate our methods for classification on the SCOP PDB-40D benchmark dataset for protein fold recognition. The best overall accuracy on the protein fold recognition test set obtained by our methods is ∼86.7%. This is an improvement over the results of the best existing approach. Moreover, our computational model has been developed by incorporating the functional domain composition of proteins through a hybridization model. It is observed that by using our proposed hybridization model, the protein fold recognition accuracy is further improved to 89.30%. Furthermore, we investigate the performance of our approach on the protein remote homology detection problem by fusing multiple string kernels.Availability and implementation: The MATLAB code used for our proposed geometric kernel fusion frameworks are publicly available at http://people.cs.kuleuven.be/∼raf.vandebril/homepage/software/geomean.php?menu=5/Contact: pooyapaydar@gmail.com or yves.moreau@esat.kuleuven.beSupplementary information: Supplementary data are available at Bioinformatics online.

REPERTOIRE OF PROTEIN KINASES ENCODED IN THE GENOME OF ZEBRAFISH SHOWS REMARKABLY LARGE POPULATION OF PIM KINASES

In recent times, zebrafish has garnered lot of popularity as model organism to study human cancers. Despite high evolutionary divergence from humans, zebrafish develops almost all types of human tumors when induced. However, mechanistic details of tumor formation have remained largely unknown. Present study is aimed at analysis of repertoire of kinases in zebrafish proteome to provide insights into various cellular components. Annotation using highly sensitive remote homology detection methods revealed "substantial expansion" of Ser/Thr/Tyr kinase family in zebrafish compared to humans, constituting over 3% of proteome. Subsequent classification of kinases into subfamilies revealed presence of large number of CAMK group of kinases, with massive representation of PIM kinases, important for cell cycle regulation and growth. Extensive sequence comparison between human and zebrafish PIM kinases revealed high conservation of functionally important residues with a few organism specific variations. There are about 300 PIM kinases in zebrafish kinome, while human genome codes for only about 500 kinases altogether. PIM kinases have been implicated in various human cancers and are currently being targeted to explore their therapeutic potentials. Hence, in depth analysis of PIM kinases in zebrafish has opened up new avenues of research to verify the model organism status of zebrafish.

Using distances between Top-n-gram and residue pairs for protein remote homology detection

BackgroundProtein remote homology detection is one of the central problems in bioinformatics, which is important for both basic research and practical application. Currently, discriminative methods based on Support Vector Machines (SVMs) achieve the state-of-the-art performance. Exploring feature vectors incorporating the position information of amino acids or other protein building blocks is a key step to improve the performance of the SVM-based methods.ResultsTwo new methods for protein remote homology detection were proposed, called SVM-DR and SVM-DT. SVM-DR is a sequence-based method, in which the feature vector representation for protein is based on the distances between residue pairs. SVM-DT is a profile-based method, which considers the distances between Top-n-gram pairs. Top-n-gram can be viewed as a profile-based building block of proteins, which is calculated from the frequency profiles. These two methods are position dependent approaches incorporating the sequence-order information of protein sequences. Various experiments were conducted on a benchmark dataset containing 54 families and 23 superfamilies. Experimental results showed that these two new methods are very promising. Compared with the position independent methods, the performance improvement is obvious. Furthermore, the proposed methods can also provide useful insights for studying the features of protein families.ConclusionThe better performance of the proposed methods demonstrates that the position dependant approaches are efficient for protein remote homology detection. Another advantage of our methods arises from the explicit feature space representation, which can be used to analyze the characteristic features of protein families. The source code of SVM-DT and SVM-DR is available at http://bioinformatics.hitsz.edu.cn/DistanceSVM/index.jsp

Protein Remote Homology Detection by Combining Profile-based Protein Representation with Local Alignment Kernel

Protein remote homology detection has attracted a great deal of interest as it is one of the most important problems in bioinformatics. Profile-based methods recently achieve the state-of-the-art performance. A key step to improve the performance of these methods is to find a suitable approach to use the evolutionary information in the profiles. In this study, we propose the profile-based protein representation to extract the evolutionary information from frequency profiles. In this approach, the frequency profiles calculated from the multiple sequence alignments outputted by PSI-BLAST are converted into several profile-based proteins and then the local alignment kernel (LA) is combined with these profile-based proteins for the prediction. Our experiments on a well-known benchmark show that the proposed approach can significantly improve the predictive performance.