Remote Homology Detection Research Articles

Using deep learning to annotate the protein universe.

Understanding the relationship between amino acid sequence and protein function is a long-standing challenge with far-reaching scientific and translational implications. State-of-the-art alignment-based techniques cannot predict function for one-third of microbial protein sequences, hampering our ability to exploit data from diverse organisms. Here, we train deep learning models to accurately predict functional annotations for unaligned amino acid sequences across rigorous benchmark assessments built from the 17,929 families of the protein families database Pfam. The models infer known patterns of evolutionary substitutions and learn representations that accurately cluster sequences from unseen families. Combining deep models with existing methods significantly improves remote homology detection, suggesting that the deep models learn complementary information. This approach extends the coverage of Pfam by >9.5%, exceeding additions made over the last decade, and predicts function for 360 human reference proteome proteins with no previous Pfam annotation. These results suggest that deep learning models will be a core component of future protein annotation tools.

PHR-search: a search framework for protein remote homology detection based on the predicted protein hierarchical relationships.

Protein remote homology detection is one of the most fundamental research tool for protein structure and function prediction. Most search methods for protein remote homology detection are evaluated based on the Structural Classification of Proteins-extended (SCOPe) benchmark, but the diverse hierarchical structure relationships between the query protein and candidate proteins are ignored by these methods. In order to further improve the predictive performance for protein remote homology detection, a search framework based on the predicted protein hierarchical relationships (PHR-search) is proposed. In the PHR-search framework, the superfamily level prediction information is obtained by extracting the local and global features of the Hidden Markov Model (HMM) profile through a convolution neural network and it is converted to the fold level and class level prediction information according to the hierarchical relationships of SCOPe. Based on these predicted protein hierarchical relationships, filtering strategy and re-ranking strategy are used to construct the two-level search of PHR-search. Experimental results show that the PHR-search framework achieves the state-of-the-art performance by employing five basic search methods, including HHblits, JackHMMER, PSI-BLAST, DELTA-BLAST and PSI-BLASTexB. Furthermore, the web server of PHR-search is established, which can be accessed at http://bliulab.net/PHR-search.

Reducing Dimensionality in Remote Homology Detection

Abstract: Homology detection plays a major role in bioinformatics. Different type of methods is used for Homology detection. Here we extract the information from protein sequences and then uses the various algorithm to predict the similarity between protein families. SVM most commonly used the algorithm in homology detection. Classification techniques are not suitable for homology detection because theyare not suitable for high dimensional datasets. Soreducing the higher dimensionality is very important than easily can predict the similarity of protein families. Keywords: Homology detection, Protein, Sequence, Reducing dimensionality, BLAST, SCOP.

Protein remote homology detection combining PCA and multiobjective optimization tools

Protein remote homology detection combining PCA and multiobjective optimization tools

Remote Homology Detection Identifies a Eukaryotic RPA DBD-C-like DNA Binding Domain as a Conserved Feature of Archaeal Rpa1-Like Proteins.

The eukaryotic single-stranded DNA binding factor replication protein A (RPA) is essential for DNA replication, repair and recombination. RPA is a heterotrimer containing six related OB folds and a winged helix-turn-helix (wH) domain. The OB folds are designated DBD-A through DBD-F, with DBD-A through DBD-D being directly involved in ssDNA binding. DBD-C is located at the C-terminus of the RPA1 protein and has a distinctive structure that includes an integral C4 zinc finger, while the wH domain is found at the C-terminus of the RPA2 protein. Previously characterised archaeal RPA proteins fall into a number of classes with varying numbers of OB folds, but one widespread class includes proteins that contain a C4 or C3H zinc finger followed by a 100–120 amino acid C-terminal region reported to lack detectable sequence or structural similarity. Here, the sequences spanning this zinc finger and including the C-terminal region are shown to comprise a previously unrecognised DBD-C-like OB fold, confirming the evolutionary relatedness of this group of archaeal RPA proteins to eukaryotic RPA1. The evolutionary relationship between eukaryotic and archaeal RPA is further underscored by the presence of RPA2-like proteins comprising an OB fold and C-terminal winged helix (wH) domain in multiple species and crucially, suggests that several biochemically characterised archaeal RPA proteins previously thought to exist as monomers are likely to be RPA1-RPA2 heterodimers.

S2L-PSIBLAST: a supervised two-layer search framework based on PSI-BLAST for protein remote homology detection.

Protein remote homology detection is a challenging task for the studies of protein evolutionary relationships. PSI-BLAST is an important and fundamental search method for detecting homology proteins. Although many improved versions of PSI-BLAST have been proposed, their performance is limited by the search processes of PSI-BLAST. For further improving the performance of PSI-BLAST for protein remote homology detection, a supervised two-layer search framework based on PSI-BLAST (S2L-PSIBLAST) is proposed. S2L-PSIBLAST consists of a two-level search: the first-level search provides high-quality search results by using SMI-BLAST framework and double-link strategy to filter the non-homology protein sequences, the second-level search detects more homology proteins by profile-link similarity, and more accurate ranking lists for those detected protein sequences are obtained by learning to rank strategy. Experimental results on the updated version of Structural Classification of Proteins-extended benchmark dataset show that S2L-PSIBLAST not only obviously improves the performance of PSI-BLAST, but also achieves better performance on two improved versions of PSI-BLAST: DELTA-BLAST and PSI-BLASTexB. http://bliulab.net/S2L-PSIBLAST. Supplementary data are available at Bioinformatics online.

PHROG: families of prokaryotic virus proteins clustered using remote homology.

Viruses are abundant, diverse and ancestral biological entities. Their diversity is high, both in terms of the number of different protein families encountered and in the sequence heterogeneity of each protein family. The recent increase in sequenced viral genomes constitutes a great opportunity to gain new insights into this diversity and consequently urges the development of annotation resources to help functional and comparative analysis. Here, we introduce PHROG (Prokaryotic Virus Remote Homologous Groups), a library of viral protein families generated using a new clustering approach based on remote homology detection by HMM profile-profile comparisons. Considering 17 473 reference (pro)viruses of prokaryotes, 868 340 of the total 938 864 proteins were grouped into 38 880 clusters that proved to be a 2-fold deeper clustering than using a classical strategy based on BLAST-like similarity searches, and yet to remain homogeneous. Manual inspection of similarities to various reference sequence databases led to the annotation of 5108 clusters (containing 50.6 % of the total protein dataset) with 705 different annotation terms, included in 9 functional categories, specifically designed for viruses. Hopefully, PHROG will be a useful tool to better annotate future prokaryotic viral sequences thus helping the scientific community to better understand the evolution and ecology of these entities.

CHLAMYDIA TRACHOMATIS EXPRESSES PHYLOGENETICALLY HOMOLOGOUS PROTEINS TO HUMAN PAPILLOMA VIRUS TYPE 16: INFERENCES FOR ORAL AND OROPHARYNGEAL SQUAMOUS CELL CARCINOMA

Background Oral and oropharyngeal squamous cell carcinoma have been linked to infection by human papilloma virus (HPV) types 16 and 18. They produce proteins E6 and E7 that interfere with p53 and pRb1 proteins and hence support oncogenesis. HPV infection is typically via oro-genital contact and other organisms cohabiting the genitalia may have had sufficient time for a genetic exchange with HPV oncoproteins and hence develop oncogenic potential also within the oral cavity. Objective Our aim was to search for organisms with homologous match for HPV 16 E6/E7 protein sequences. Methods HPV 16 sequences were obtained from the NCBI database. E6 and E7 homologous sequences with accession numbers >ACQ90217 and >ACQ90218 were retrieved through BLAST search. The SWISS-MODEL template library was searched with BLAST and HHBlits for evolutionary related structures matching the target sequence. Utilizing the MPI Bioinformatics remote homology detection method linked with the UniProt database, best matches of E6 and E7 protein sequences were retrieved. Multiple sequence alignment was done and ProMod3 was used to build a protein model for E7. Results HPV 16 E7 protein and Chlamydia trachomatis homologous protein sequences were the most closely related from our bioinformatic search. Conclusions This similarity between C. trachomatis proteins and HPV 16 E7 oncogenic proteins could be because both organisms inhabit similar mucosae and have had considerable time to exchange genes. We postulate that a possible co-infection of C. trachomatis may be implicated in the development of oral and oropharyngeal squamous cell carcinoma as documented with cervical cancers. Oral and oropharyngeal squamous cell carcinoma have been linked to infection by human papilloma virus (HPV) types 16 and 18. They produce proteins E6 and E7 that interfere with p53 and pRb1 proteins and hence support oncogenesis. HPV infection is typically via oro-genital contact and other organisms cohabiting the genitalia may have had sufficient time for a genetic exchange with HPV oncoproteins and hence develop oncogenic potential also within the oral cavity. Our aim was to search for organisms with homologous match for HPV 16 E6/E7 protein sequences. HPV 16 sequences were obtained from the NCBI database. E6 and E7 homologous sequences with accession numbers >ACQ90217 and >ACQ90218 were retrieved through BLAST search. The SWISS-MODEL template library was searched with BLAST and HHBlits for evolutionary related structures matching the target sequence. Utilizing the MPI Bioinformatics remote homology detection method linked with the UniProt database, best matches of E6 and E7 protein sequences were retrieved. Multiple sequence alignment was done and ProMod3 was used to build a protein model for E7. HPV 16 E7 protein and Chlamydia trachomatis homologous protein sequences were the most closely related from our bioinformatic search. This similarity between C. trachomatis proteins and HPV 16 E7 oncogenic proteins could be because both organisms inhabit similar mucosae and have had considerable time to exchange genes. We postulate that a possible co-infection of C. trachomatis may be implicated in the development of oral and oropharyngeal squamous cell carcinoma as documented with cervical cancers.

FastSK: fast sequence analysis with gapped string kernels.

Gapped k-mer kernels with support vector machines (gkm-SVMs) have achieved strong predictive performance on regulatory DNA sequences on modestly sized training sets. However, existing gkm-SVM algorithms suffer from slow kernel computation time, as they depend exponentially on the sub-sequence feature length, number of mismatch positions, and the task's alphabet size. In this work, we introduce a fast and scalable algorithm for calculating gapped k-mer string kernels. Our method, named FastSK, uses a simplified kernel formulation that decomposes the kernel calculation into a set of independent counting operations over the possible mismatch positions. This simplified decomposition allows us to devise a fast Monte Carlo approximation that rapidly converges. FastSK can scale to much greater feature lengths, allows us to consider more mismatches, and is performant on a variety of sequence analysis tasks. On multiple DNA transcription factor binding site prediction datasets, FastSK consistently matches or outperforms the state-of-the-art gkmSVM-2.0 algorithms in area under the ROC curve, while achieving average speedups in kernel computation of ∼100× and speedups of ∼800× for large feature lengths. We further show that FastSK outperforms character-level recurrent and convolutional neural networks while achieving low variance. We then extend FastSK to 7 English-language medical named entity recognition datasets and 10 protein remote homology detection datasets. FastSK consistently matches or outperforms these baselines. Our algorithm is available as a Python package and as C++ source code at https://github.com/QData/FastSK. Supplementary data are available at Bioinformatics online.

ReFold-MAP: Protein remote homology detection and fold recognition based on features extracted from profiles

Protein remote homology detection and protein fold recognition are two important tasks in protein structure and function prediction. There are three kinds of methods in this field, including the discriminative methods, the alignment methods, and the ranking methods. In this study, a new discriminative method called ReFold-MAP is proposed. The proposed method extracts comprehensive features based on three profile-based features: Motif-PSSM, ACC-PSSM, and PDT-profile. We call these features as MAP features, which incorporate the structural motif kernel information, the evolutionary information, and the sequence information. The experiments prove that ReFold-MAP outperforms other approaches. Therefore, ReFold-MAP will be a useful tool for protein remote homology detection and fold recognition.

SMI-BLAST: a novel supervised search framework based on PSI-BLAST for protein remote homology detection.

As one of the most important and widely used mainstream iterative search tool for protein sequence search, an accurate Position-Specific Scoring Matrix (PSSM) is the key of PSI-BLAST. However, PSSMs containing non-homologous information obviously reduce the performance of PSI-BLAST for protein remote homology. To further study this problem, we summarize three types of Incorrectly Selected Homology (ISH) errors in PSSMs. A new search tool Supervised-Manner-based Iterative BLAST (SMI-BLAST) is proposed based on PSI-BLAST for solving these errors. SMI-BLAST obviously outperforms PSI-BLAST on the Structural Classification of Proteins-extended (SCOPe) dataset. Compared with PSI-BLAST on the ISH error subsets of SCOPe dataset, SMI-BLAST detects 1.6-2.87 folds more remote homologous sequences, and outperforms PSI-BLAST by 35.66% in terms of ROC1 scores. Furthermore, this framework is applied to JackHMMER, DELTA-BLAST and PSI-BLASTexB, and their performance is further improved. User-friendly webservers for SMI-BLAST, JackHMMER, DELTA-BLAST and PSI-BLASTexB are established at http://bliulab.net/SMI-BLAST/, by which the users can easily get the results without the need to go through the mathematical details. Supplementary data are available at Bioinformatics online.

PL-search: a profile-link-based search method for protein remote homology detection

Protein remote homology detection is a fundamental and important task for protein structure and function analysis. Several search methods have been proposed to improve the detection performance of the remote homologues and the accuracy of ranking lists. The position-specific scoring matrix (PSSM) profile and hidden Markov model (HMM) profile can contribute to improving the performance of the state-of-the-art search methods. In this paper, we improved the profile-link (PL) information for constructing PSSM or HMM profiles, and proposed a PL-based search method (PL-search). In PL-search, more robust PLs are constructed through the double-link and iterative extending strategies, and an accurate similarity score of sequence pairs is calculated from the two-level Jaccard distance for remote homologues. We tested our method on two widely used benchmark datasets. Our results show that whether HHblits, JackHMMER or position-specific iterated-BLAST is used, PL-search obviously improves the search performance in terms of ranking quality as well as the number of detected remote homologues. For ease of use of PL-search, both its stand-alone tool and the web server are constructed, which can be accessed at http://bliulab.net/PL-search/.

Probing Protein Interaction Networks by Combining MS-Based Proteomics and Structural Data Integration

Protein-protein interactions play a major role in the molecular machinery of life, and various techniques such as AP-MS are dedicated to their identification. However, those techniques return lists of proteins devoid of organizational structure, not detailing which proteins interact with which others. Proposing a hierarchical view of the interactions between the members of the flat list becomes highly tedious for large data sets when done by hand. To help hierarchize this data, we introduce a new bioinformatics protocol that integrates information of the multimeric protein 3D structures available in the Protein Data Bank using remote homology detection, as well as information related to Short Linear Motifs and interaction data from the BioGRID. We illustrate on two unrelated use-cases of different complexity how our approach can be useful to decipher the network of interactions hidden in the list of input proteins, and how it provides added value compared to state-of-the-art resources such as Interactome3D or STRING. Particularly, we show the added value of using homology detection to distinguish between orthologs and paralogs, and to distinguish between core obligate and more facultative interactions. We also demonstrate the potential of considering interactions occurring through Short Linear Motifs.

How to choose templates for modeling of protein complexes: Insights from benchmarking template-based docking.

Comparative docking is based on experimentally determined structures of protein-protein complexes (templates), following the paradigm that proteins with similar sequences and/or structures form similar complexes. Modeling utilizing structure similarity of target monomers to template complexes significantly expands structural coverage of the interactome. Template-based docking by structure alignment can be performed for the entire structures or by aligning targets to the bound interfaces of the experimentally determined complexes. Systematic benchmarking of docking protocols based on full and interface structure alignment showed that both protocols perform similarly, with top 1 docking success rate 26%. However, in terms of the models' quality, the interface-based docking performed marginally better. The interface-based docking is preferable when one would suspect a significant conformational change in the full protein structure upon binding, for example, a rearrangement of the domains in multidomain proteins. Importantly, if the same structure is selected as the top template by both full and interface alignment, the docking success rate increases 2-fold for both top 1 and top 10 predictions. Matching structural annotations of the target and template proteins for template detection, as a computationally less expensive alternative to structural alignment, did not improve the docking performance. Sophisticated remote sequence homology detection added templates to the pool of those identified by structure-based alignment, suggesting that for practical docking, the combination of the structure alignment protocols and the remote sequence homology detection may be useful in order to avoid potential flaws in generation of the structural templates library.

Remote homology detection using GA and NSGA-II on physicochemical properties

Remote homology detection at amino acid level is a complex problem in the area of computational biology. We have used machine learning algorithms to predict the homology of un-annotated protein sequences which can save time and cost. This work is divided in three phases. Initially the features are extracted from protein sequences using Principal Component Analysis (PCA) to build a chromosome set with representative features of each protein based on physicochemical properties. Second stage involves GA for the construction of a set of chromosomes for classification based on PCA and initialises the classifier to build up an error matrix. Third stage uses NSGA-II, crossover and mutation, and tournament selection for the next set of chromosomes. The output of this experiment is a set of minimum classification error values and minimum number of features used for classification of protein families. This approach gives superior accuracy over the profile-based methods.

Remote homology detection using GA and NSGA-II on physicochemical properties

Remote homology detection at amino acid level is a complex problem in the area of computational biology. We have used machine learning algorithms to predict the homology of un-annotated protein sequences which can save time and cost. This work is divided in three phases. Initially the features are extracted from protein sequences using Principal Component Analysis (PCA) to build a chromosome set with representative features of each protein based on physicochemical properties. Second stage involves GA for the construction of a set of chromosomes for classification based on PCA and initialises the classifier to build up an error matrix. Third stage uses NSGA-II, crossover and mutation, and tournament selection for the next set of chromosomes. The output of this experiment is a set of minimum classification error values and minimum number of features used for classification of protein families. This approach gives superior accuracy over the profile-based methods.

Sequence alignment generation using intermediate sequence search for homology modeling

Protein tertiary structure is important information in various areas of biological research, however, the experimental cost associated with structure determination is high, and computational prediction methods have been developed to facilitate a more economical approach. Currently, template-based modeling methods are considered to be the most practical because the resulting predicted structures are often accurate, provided an appropriate template protein is available. During the first stage of template-based modeling, sensitive homology detection is essential for accurate structure prediction. However, sufficient structural models cannot always be obtained due to a lack of quality in the sequence alignment generated by a homology detection program. Therefore, an automated method that detects remote homologs accurately and generates appropriate alignments for accurate structure prediction is needed. In this paper, we propose an algorithm for suitable alignment generation using an intermediate sequence search for use with template-based modeling. We used intermediate sequence search for remote homology detection and intermediate sequences for alignment generation of remote homologs. We then evaluated the proposed method by comparing the sensitivity and selectivity of homology detection. Furthermore, based on the accuracy of the predicted structure model, we verify the accuracy of the alignments generated by our method. We demonstrate that our method generates more appropriate alignments for template-based modeling, especially for remote homologs. All source codes are available at https://github.com/shuichiro-makigaki/agora.

Graph Theory-Based Sequence Descriptors as Remote Homology Predictors.

Alignment-free (AF) methodologies have increased in popularity in the last decades as alternative tools to alignment-based (AB) algorithms for performing comparative sequence analyses. They have been especially useful to detect remote homologs within the twilight zone of highly diverse gene/protein families and superfamilies. The most popular alignment-free methodologies, as well as their applications to classification problems, have been described in previous reviews. Despite a new set of graph theory-derived sequence/structural descriptors that have been gaining relevance in the detection of remote homology, they have been omitted as AF predictors when the topic is addressed. Here, we first go over the most popular AF approaches used for detecting homology signals within the twilight zone and then bring out the state-of-the-art tools encoding graph theory-derived sequence/structure descriptors and their success for identifying remote homologs. We also highlight the tendency of integrating AF features/measures with the AB ones, either into the same prediction model or by assembling the predictions from different algorithms using voting/weighting strategies, for improving the detection of remote signals. Lastly, we briefly discuss the efforts made to scale up AB and AF features/measures for the comparison of multiple genomes and proteomes. Alongside the achieved experiences in remote homology detection by both the most popular AF tools and other less known ones, we provide our own using the graphical–numerical methodologies, MARCH-INSIDE, TI2BioP, and ProtDCal. We also present a new Python-based tool (SeqDivA) with a friendly graphical user interface (GUI) for delimiting the twilight zone by using several similar criteria.

R3D Prediction Model: Remote Homology Prediction using Protein Contact Map with Dimensionality Reduction

Bioinformatics is one of a developing field that utilizations evaluation to extort information from Biological Data. Bioinformatics approaches are regularly utilized for significant activities that create expansive informational collections. Two basic tremendous scale practices that use bioinformatics are genomics and proteomics. Proteins are the far reaching, complex atoms that are essential for normal working of cells. 20% of the human body is involved proteins. Proteins are involved smaller units called amino acids, which are building squares of proteins. Protein remote homology identification and recognition are focal issues in bioinformatics. Sequence homologies are a vital source of data about proteins. In this research, the framework propose different strategy that diminishes the high dimensionality of the vector representation in remote homology detection by utilizing models that are characterized at the 3D level and consequently are very structurally and practically related. Subsequently, the 3D models are mapped from the protein primary sequence. The framework proposes to address the issue of remote homology identification by reducing 3D structure models. The new technique, called remote homology identification by the Reduction of 3D models (remote-R3D), is introduced and tested on various protein families.

HH-suite3 for fast remote homology detection and deep protein annotation

BackgroundHH-suite is a widely used open source software suite for sensitive sequence similarity searches and protein fold recognition. It is based on pairwise alignment of profile Hidden Markov models (HMMs), which represent multiple sequence alignments of homologous proteins.ResultsWe developed a single-instruction multiple-data (SIMD) vectorized implementation of the Viterbi algorithm for profile HMM alignment and introduced various other speed-ups. These accelerated the search methods HHsearch by a factor 4 and HHblits by a factor 2 over the previous version 2.0.16. HHblits3 is ∼10× faster than PSI-BLAST and ∼20× faster than HMMER3. Jobs to perform HHsearch and HHblits searches with many query profile HMMs can be parallelized over cores and over cluster servers using OpenMP and message passing interface (MPI). The free, open-source, GPLv3-licensed software is available at https://github.com/soedinglab/hh-suite.ConclusionThe added functionalities and increased speed of HHsearch and HHblits should facilitate their use in large-scale protein structure and function prediction, e.g. in metagenomics and genomics projects.