Systematic and fully automated identification of protein sequence patterns.

We present an efficient algorithm to systematically and automatically identify patterns in protein sequence families. The procedure is based on the Splash deterministic pattern discovery algorithm and on a framework to assess the statistical significance of patterns. We demonstrate its application to the fully automated discovery of patterns in 974 PROSITE families (the complete subset of PROSITE families which are defined by patterns and contain DR records). Splash generates patterns with better specificity and undiminished sensitivity, or vice versa, in 28% of the families; identical statistics were obtained in 48% of the families, worse statistics in 15%, and mixed behavior in the remaining 9%. In about 75% of the cases, Splash patterns identify sequence sites that overlap more than 50% with the corresponding PROSITE pattern. The procedure is sufficiently rapid to enable its use for daily curation of existing motif and profile databases. Third, our results show that the statistical significance of discovered patterns correlates well with their biological significance. The trypsin subfamily of serine proteases is used to illustrate this method's ability to exhaustively discover all motifs in a family that are statistically and biologically significant. Finally, we discuss applications of sequence patterns to multiple sequence alignment and the training of more sensitive score-based motif models, akin to the procedure used by PSI-BLAST. All results are available at httpl//www.research.ibm.com/spat/.     

A comparison of profile hidden Markov model procedures for remote homology detection

Profile hidden Markov models (HMMs) are amongst the most successful procedures for detecting remote homology between proteins. There are two popular profile HMM programs, HMMER and SAM. Little is known about their performance relative to each other and to the recently improved version of PSI-BLAST. Here we compare the two programs to each other and to non-HMM methods, to determine their relative performance and the features that are important for their success. The quality of the multiple sequence alignments used to build models was the most important factor affecting the overall performance of profile HMMs. The SAM T99 procedure is needed to produce high quality alignments automatically, and the lack of an equivalent component in HMMER makes it less complete as a package. Using the default options and parameters as would be expected of an inexpert user, it was found that from identical alignments SAM consistently produces better models than HMMER and that the relative performance of the model-scoring components varies. On average, HMMER was found to be between one and three times faster than SAM when searching databases larger than 2000 sequences, SAM being faster on smaller ones. Both methods were shown to have effective low complexity and repeat sequence masking using their null models, and the accuracy of their E-values was comparable. It was found that the SAM T99 iterative database search procedure performs better than the most recent version of PSI-BLAST, but that scoring of PSI-BLAST profiles is more than 30 times faster than scoring of SAM models.     

IMPALA: matching a protein sequence against a collection of PSI-BLAST-constructed position-specific score matrices

MOTIVATION: Many studies have shown that database searches using position-specific score matrices (PSSMs) or profiles as queries are more effective at identifying distant protein relationships than are searches that use simple sequences as queries. One popular program for constructing a PSSM and comparing it with a database of sequences is Position-Specific Iterated BLAST (PSI-BLAST). RESULTS: This paper describes a new software package, IMPALA, designed for the complementary procedure of comparing a single query sequence with a database of PSI-BLAST-generated PSSMs. We illustrate the use of IMPALA to search a database of PSSMs for protein folds, and one for protein domains involved in signal transduction. IMPALA's sensitivity to distant biological relationships is very similar to that of PSI-BLAST. However, IMPALA employs a more refined analysis of statistical significance and, unlike PSI-BLAST, guarantees the output of the optimal local alignment by using the rigorous Smith-Waterman algorithm. Also, it is considerably faster when run with a large database of PSSMs than is BLAST or PSI-BLAST when run against the complete non-redundant protein database.     

A sequence sub-sampling algorithm increases the power to detect distant homologues

Searching databases for distant homologues using alignments instead of individual sequences increases the power of detection. However, most methods assume that protein evolution proceeds in a regular fashion, with the inferred tree of sequences providing a good estimation of the evolutionary process. We investigated the combined HMMER search results from random alignment subsets (with three sequences each) drawn from the parent alignment (Rand-shuffle algorithm), using the SCOP structural classification to determine true similarities. At false-positive rates of 5%, the Rand-shuffle algorithm improved HMMER's sensitivity, with a 37.5% greater sensitivity compared with HMMER alone, when easily identified similarities (identifiable by BLAST) were excluded from consideration. An extension of the Rand-shuffle algorithm (Ali-shuffle) weighted towards more informative sequence subsets. This approach improved the performance over HMMER alone and PSI-BLAST, particularly at higher false-positive rates. The improvements in performance of these sequence sub-sampling methods may reflect lower sensitivity to alignment error and irregular evolutionary patterns. The Ali-shuffle and Rand-shuffle sequence homology search programs are available by request from the authors.     

Use of multiple profiles corresponding to a sequence alignment enables effective detection of remote homologues

MOTIVATION: Position specific scoring matrices (PSSMs) corresponding to aligned sequences of homologous proteins are commonly used in homology detection. A PSSM is generated on the basis of one of the homologues as a reference sequence, which is the query in the case of PSI-BLAST searches. The reference sequence is chosen arbitrarily while generating PSSMs for reverse BLAST searches. In this work we demonstrate that the use of multiple PSSMs corresponding to a given alignment and variable reference sequences is more effective than using traditional single PSSMs and hidden Markov models. RESULTS: Searches for proteins with known 3-D structures have been made against three databases of protein family profiles corresponding to known structures: (1) One PSSM per family; (2) multiple PSSMs corresponding to an alignment and variable reference sequences for every family; and (3) hidden Markov models. A comparison of the performances of these three approaches suggests that the use of multiple PSSMs is most effective. CONTACT: ns@mbu.iisc.ernet.in.     

Automatic generation and evaluation of sparse protein signatures for families of protein structural domains

We identified key residues from the structural alignment of families of protein domains from SCOP which we represented in the form of sparse protein signatures. A signature-generating algorithm (SigGen) was developed and used to automatically identify key residues based on several structural and sequence-based criteria. The capacity of the signatures to detect related sequences from the SWISSPROT database was assessed by receiver operator characteristic (ROC) analysis and jack-knife testing. Test signatures for families from each of the main SCOP classes are described in relation to the quality of the structural alignments, the SigGen parameters used, and their diagnostic performance. We show that automatically generated signatures are potently diagnostic for their family (ROC50 scores typically >0.8), consistently outperform random signatures, and can identify sequence relationships in the "twilight zone" of protein sequence similarity (<40%). Signatures based on 15%-30% of alignment positions occurred most frequently among the best-performing signatures. When alignment quality is poor, sparser signatures perform better, whereas signatures generated from higher-quality alignments of fewer structures require more positions to be diagnostic. Our validation of signatures from the Globin family shows that when sequences from the structural alignment are removed and new signatures generated, the omitted sequences are still detected. The positions highlighted by the signature often correspond (alignment specificity >0.7) to the key positions in the original (non-jack-knifed) alignment. We discuss potential applications of sparse signatures in sequence annotation and homology modeling.     

Profile-based string kernels for remote homology detection and motif extraction

We introduce novel profile-based string kernels for use with support vector machines (SVMs) for the problems of protein classification and remote homology detection. These kernels use probabilistic profiles, such as those produced by the PSI-BLAST algorithm, to define position-dependent mutation neighborhoods along protein sequences for inexact matching of k-length subsequences ("k-mers") in the data. By use of an efficient data structure, the kernels are fast to compute once the profiles have been obtained. For example, the time needed to run PSI-BLAST in order to build the profiles is significantly longer than both the kernel computation time and the SVM training time. We present remote homology detection experiments based on the SCOP database where we show that profile-based string kernels used with SVM classifiers strongly outperform all recently presented supervised SVM methods. We further examine how to incorporate predicted secondary structure information into the profile kernel to obtain a small but significant performance improvement. We also show how we can use the learned SVM classifier to extract "discriminative sequence motifs"--short regions of the original profile that contribute almost all the weight of the SVM classification score--and show that these discriminative motifs correspond to meaningful structural features in the protein data. The use of PSI-BLAST profiles can be seen as a semi-supervised learning technique, since PSI-BLAST leverages unlabeled data from a large sequence database to build more informative profiles. Recently presented "cluster kernels" give general semi-supervised methods for improving SVM protein classification performance. We show that our profile kernel results also outperform cluster kernels while providing much better scalability to large datasets.     

A comparison of position-specific score matrices based on sequence and structure alignments

Sequence comparison methods based on position-specific score matrices (PSSMs) have proven a useful tool for recognition of the divergent members of a protein family and for annotation of functional sites. Here we investigate one of the factors that affects overall performance of PSSMs in a PSI-BLAST search, the algorithm used to construct the seed alignment upon which the PSSM is based. We compare PSSMs based on alignments constructed by global sequence similarity (ClustalW and ClustalW-pairwise), local sequence similarity (BLAST), and local structure similarity (VAST). To assess performance with respect to identification of conserved functional or structural sites, we examine the accuracy of the three-dimensional molecular models predicted by PSSM-sequence alignments. Using the known structures of those sequences as the standard of truth, we find that model accuracy varies with the algorithm used for seed alignment construction in the pattern local-structure (VAST) > local-sequence (BLAST) > global-sequence (ClustalW). Using structural similarity of query and database proteins as the standard of truth, we find that PSSM recognition sensitivity depends primarily on the diversity of the sequences included in the alignment, with an optimum around 30-50% average pairwise identity. We discuss these observations, and suggest a strategy for constructing seed alignments that optimize PSSM-sequence alignment accuracy and recognition sensitivity.     

Strategies for the effective identification of remotely related sequences in multiple PSSM search approach

Searches using position specific scoring matrices (PSSMs) have been commonly used in remote homology detection procedures such as PSI-BLAST and RPS-BLAST. A PSSM is generated typically using one of the sequences of a family as the reference sequence. In the case of PSI-BLAST searches the reference sequence is same as the query. Recently we have shown that searches against the database of multiple family-profiles, with each one of the members of the family used as a reference sequence, are more effective than searches against the classical database of single family-profiles. Despite relatively a better overall performance when compared with common sequence-profile matching procedures, searches against the multiple family-profiles database result in a few false positives and false negatives. Here we show that profile length and divergence of sequences used in the construction of a PSSM have major influence on the performance of multiple profile based search approach. We also identify that a simple parameter defined by the number of PSSMs corresponding to a family that is hit, for a query, divided by the total number of PSSMs in the family can distinguish effectively the true positives from the false positives in the multiple profiles search approach.     

ProClass protein family database

ProClass is a protein family database that organizes non-redundant sequence entries into families defined collectively by PIR superfamilies and PROSITE patterns. By combining global similarities and functional motifs into a single classification scheme, ProClass helps to reveal domain and family relationships and classify multi-domain proteins. The database currently consists of >155 000 sequence entries retrieved from both PIR-International and SWISS-PROT databases. Approximately 92 000 or 60% of the ProClass entries are classified into approximately 6000 families, including a large number of new members detected by our GeneFIND family identification system. The ProClass motif collection contains approximately 72 000 motif sequences and >1300 multiple alignments for all PROSITE patterns, including >21 000 matches not listed in PROSITE and mostly detected from unique PIR sequences. To maximize family information retrieval, the database provides links to various protein family, domain, alignment and structural class databases. With its high classification rate and comprehensive family relationships, ProClass can be used to support full-scale genomic annotation. The database, now being implemented in an object-relational database management system, is available for online sequence search and record retrieval from our WWW server at http://pir.georgetown.edu/gfserver/proclass.html     

Accurate prediction of protein structural class using auto covariance transformation of PSI-BLAST profiles

Computational prediction of protein structural class based solely on sequence data remains a challenging problem in protein science. Existing methods differ in the protein sequence representation models and prediction engines adopted. In this study, a powerful feature extraction method, which combines position-specific score matrix (PSSM) with auto covariance (AC) transformation, is introduced. Thus, a sample protein is represented by a series of discrete components, which could partially incorporate the long-range sequence order information and evolutionary information reflected from the PSI-BLAST profile. To verify the performance of our method, jackknife cross-validation tests are performed on four widely used benchmark datasets. Comparison of our results with existing methods shows that our method provides the state-of-the-art performance for structural class prediction. A Web server that implements the proposed method is freely available at http://202.194.133.5/xinxi/AAC_PSSM_AC/index.htm.     

Protein homology detection by HMM-HMM comparison

MOTIVATION: Protein homology detection and sequence alignment are at the basis of protein structure prediction, function prediction and evolution. RESULTS: We have generalized the alignment of protein sequences with a profile hidden Markov model (HMM) to the case of pairwise alignment of profile HMMs. We present a method for detecting distant homologous relationships between proteins based on this approach. The method (HHsearch) is benchmarked together with BLAST, PSI-BLAST, HMMER and the profile-profile comparison tools PROF_SIM and COMPASS, in an all-against-all comparison of a database of 3691 protein domains from SCOP 1.63 with pairwise sequence identities below 20%.Sensitivity: When the predicted secondary structure is included in the HMMs, HHsearch is able to detect between 2.7 and 4.2 times more homologs than PSI-BLAST or HMMER and between 1.44 and 1.9 times more than COMPASS or PROF_SIM for a rate of false positives of 10%. Approximately half of the improvement over the profile-profile comparison methods is attributable to the use of profile HMMs in place of simple profiles. Alignment quality: Higher sensitivity is mirrored by an increased alignment quality. HHsearch produced 1.2, 1.7 and 3.3 times more good alignments ('balanced' score >0.3) than the next best method (COMPASS), and 1.6, 2.9 and 9.4 times more than PSI-BLAST, at the family, superfamily and fold level, respectively.Speed: HHsearch scans a query of 200 residues against 3691 domains in 33 s on an AMD64 2GHz PC. This is 10 times faster than PROF_SIM and 17 times faster than COMPASS.     

A comparison of scoring functions for protein sequence profile alignment

MOTIVATION: In recent years, several methods have been proposed for aligning two protein sequence profiles, with reported improvements in alignment accuracy and homolog discrimination versus sequence-sequence methods (e.g. BLAST) and profile-sequence methods (e.g. PSI-BLAST). Profile-profile alignment is also the iterated step in progressive multiple sequence alignment algorithms such as CLUSTALW. However, little is known about the relative performance of different profile-profile scoring functions. In this work, we evaluate the alignment accuracy of 23 different profile-profile scoring functions by comparing alignments of 488 pairs of sequences with identity < or =30% against structural alignments. We optimize parameters for all scoring functions on the same training set and use profiles of alignments from both PSI-BLAST and SAM-T99. Structural alignments are constructed from a consensus between the FSSP database and CE structural aligner. We compare the results with sequence-sequence and sequence-profile methods, including BLAST and PSI-BLAST. RESULTS: We find that profile-profile alignment gives an average improvement over our test set of typically 2-3% over profile-sequence alignment and approximately 40% over sequence-sequence alignment. No statistically significant difference is seen in the relative performance of most of the scoring functions tested. Significantly better results are obtained with profiles constructed from SAM-T99 alignments than from PSI-BLAST alignments. AVAILABILITY: Source code, reference alignments and more detailed results are freely available at http://phylogenomics.berkeley.edu/profilealignment/     

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.     

A method for probabilistic mapping between protein structure and function taxonomies through cross training

Background

Prediction of function of proteins on the basis of structure and vice versa is a partially solved problem, largely in the domain of biophysics and biochemistry. This underlies the need of computational and bioinformatics approach to solve the problem. Large and organized latent knowledge on protein classification exists in the form of independently created protein classification databases. By creating probabilistic maps between classes of structural classification databases (e.g. SCOP [1]) and classes of functional classification databases (e.g. PROSITE [2]), structure and function of proteins could be probabilistically related.

Results

We demonstrate that PROSITE and SCOP have significant semantic overlap, in spite of independent classification schemes. By training classifiers of SCOP using classes of PROSITE as attributes and vice versa, accuracy of Support Vector Machine classifiers for both SCOP and PROSITE was improved. Novel attributes, 2-D elastic profiles and Blocks were used to improve time complexity and accuracy. Many relationships were extracted between classes of SCOP and PROSITE using decision trees.

Conclusion

We demonstrate that presented approach can discover new probabilistic relationships between classes of different taxonomies and render a more accurate classification. Extensive mappings between existing protein classification databases can be created to link the large amount of organized data. Probabilistic maps were created between classes of SCOP and PROSITE allowing predictions of structure using function, and vice versa. In our experiments, we also found that functions are indeed more strongly related to structure than are structure to functions.     

DP-Bind: a web server for sequence-based prediction of DNA-binding residues in DNA-binding proteins

This article describes DP-Bind, a web server for predicting DNA-binding sites in a DNA-binding protein from its amino acid sequence. The web server implements three machine learning methods: support vector machine, kernel logistic regression and penalized logistic regression. Prediction can be performed using either the input sequence alone or an automatically generated profile of evolutionary conservation of the input sequence in the form of PSI-BLAST position-specific scoring matrix (PSSM). PSSM-based kernel logistic regression achieves the accuracy of 77.2%, sensitivity of 76.4% and specificity of 76.6%. The outputs of all three individual methods are combined into a consensus prediction to help identify positions predicted with high level of confidence. AVAILABILITY: Freely available at http://lcg.rit.albany.edu/dp-bind. SUPPLEMENTARY INFORMATION: http://lcg.rit.albany.edu/dp-bind/dpbind_supplement.html.     

Prediction of the conformation and geometry of loops in globular proteins: testing ArchDB, a structural classification of loops

In protein structure prediction, a central problem is defining the structure of a loop connecting 2 secondary structures. This problem frequently occurs in homology modeling, fold recognition, and in several strategies in ab initio structure prediction. In our previous work, we developed a classification database of structural motifs, ArchDB. The database contains 12,665 clustered loops in 451 structural classes with information about phi-psi angles in the loops and 1492 structural subclasses with the relative locations of the bracing secondary structures. Here we evaluate the extent to which sequence information in the loop database can be used to predict loop structure. Two sequence profiles were used, a HMM profile and a PSSM derived from PSI-BLAST. A jack-knife test was made removing homologous loops using SCOP superfamily definition and predicting afterwards against recalculated profiles that only take into account the sequence information. Two scenarios were considered: (1) prediction of structural class with application in comparative modeling and (2) prediction of structural subclass with application in fold recognition and ab initio. For the first scenario, structural class prediction was made directly over loops with X-ray secondary structure assignment, and if we consider the top 20 classes out of 451 possible classes, the best accuracy of prediction is 78.5%. In the second scenario, structural subclass prediction was made over loops using PSI-PRED (Jones, J Mol Biol 1999;292:195-202) secondary structure prediction to define loop boundaries, and if we take into account the top 20 subclasses out of 1492, the best accuracy is 46.7%. Accuracy of loop prediction was also evaluated by means of RMSD calculations.