Mining for Class-Specific Motifs in Protein Sequence Classification

Background: In protein sequence classification, identification of the sequence motifs or n-grams that can precisely discriminate between classes is a more interesting scientific question than the classification itself. A number of classification methods aim at accurate classification but fail to explain which sequence features indeed contribute to the accuracy. We hypothesize that sequences in lower denominations (n-grams) can be used to explore the sequence landscape and to identify class-specific motifs that discriminate between classes during classification. Discriminative n-grams are short peptide sequences that are highly frequent in one class but are either minimally present or absent in other classes. In this study, we present a new substitution-based scoring function for identifying discriminative n-grams that are highly specific to a class. Results: We present a scoring function based on discriminative n-grams that can effectively discriminate between classes. The scoring function, initially, harvests the entire set of 4- to 8-grams from the protein sequences of different classes in the dataset. Similar n-grams of the same size are combined to form new n-grams, where the similarity is defined by positive amino acid substitution scores in the BLOSUM62 matrix. Substitution has resulted in a large increase in the number of discriminatory n-grams harvested. Due to the unbalanced nature of the dataset, the frequencies of the n-grams are normalized using a dampening factor, which gives more weightage to the n-grams that appear in fewer classes and vice-versa. After the n-grams are normalized, the scoring function identifies discriminative 4- to 8-grams for each class that are frequent enough to be above a selection threshold. By mapping these discriminative n-grams back to the protein sequences, we obtained contiguous n-grams that represent short class-specific motifs in protein sequences. Our method fared well compared to an existing motif finding method known as Wordspy. We have validated our enriched set of class-specific motifs against the functionally important motifs obtained from the NLSdb, Prosite and ELM databases. We demonstrate that this method is very generic; thus can be widely applied to detect class-specific motifs in many protein sequence classification tasks. Conclusion: The proposed scoring function and methodology is able to identify class-specific motifs using discriminative n-grams derived from the protein sequences. The implementation of amino acid substitution scores for similarity detection, and the dampening factor to normalize the unbalanced datasets have significant effect on the performance of the scoring function. Our multipronged validation tests demonstrate that this method can detect class-specific motifs from a wide variety of protein sequence classes with a potential application to detecting proteome-specific motifs of different organisms.

Large-scale protein structure modeling of the Saccharomyces cerevisiae genome

The function of a protein generally is determined by its three-dimensional (3D) structure. Thus, it would be useful to know the 3D structure of the thousands of protein sequences that are emerging from the many genome projects. To this end, fold assignment, comparative protein structure modeling, and model evaluation were automated completely. As an illustration, the method was applied to the proteins in the Saccharomyces cerevisiae (baker’s yeast) genome. It resulted in all-atom 3D models for substantial segments of 1,071 (17%) of the yeast proteins, only 40 of which have had their 3D structure determined experimentally. Of the 1,071 modeled yeast proteins, 236 were related clearly to a protein of known structure for the first time; 41 of these previously have not been characterized at all.

Molecular Cloning and Characterization of a Radial Spoke Head Protein of Sea Urchin Sperm Axonemes: Involvement of the Protein in the Regulation of Sperm Motility

Monoclonal antibodies raised against axonemal proteins of sea urchin spermatozoa have been used to study regulatory mechanisms involved in flagellar motility. Here, we report that one of these antibodies, monoclonal antibody D-316, has an unusual perturbating effect on the motility of sea urchin sperm models; it does not affect the beat frequency, the amplitude of beating or the percentage of motile sperm models, but instead promotes a marked transformation of the flagellar beating pattern which changes from a two-dimensional to a three-dimensional type of movement. On immunoblots of axonemal proteins separated by SDS-PAGE, D-316 recognized a single polypeptide of 90 kDa. This protein was purified following its extraction by exposure of axonemes to a brief heat treatment at 40°C. The protein copurified and coimmunoprecipitated with proteins of 43 and 34 kDa, suggesting that it exists as a complex in its native form. Using D-316 as a probe, a full-length cDNA clone encoding the 90-kDa protein was obtained from a sea urchin cDNA library. The sequence predicts a highly acidic (pI = 4.0) protein of 552 amino acids with a mass of 62,720 Da (p63). Comparison with protein sequences in databases indicated that the protein is related to radial spoke proteins 4 and 6 (RSP4 and RSP6) of Chlamydomonas reinhardtii, which share 37% and 25% similarity, respectively, with p63. However, the sea urchin protein possesses structural features distinct from RSP4 and RSP6, such as the presence of three major acidic stretches which contains 25, 17, and 12 aspartate and glutamate residues of 34-, 22-, and 14-amino acid long stretches, respectively, that are predicted to form α-helical coiled-coil secondary structures. These results suggest a major role for p63 in the maintenance of a planar form of sperm flagellar beating and provide new tools to study the function of radial spoke heads in more evolved species.

Protein Information Resource: a community resource for expert annotation of protein data

The Protein Information Resource, in collaboration with the Munich Information Center for Protein Sequences (MIPS) and the Japan International Protein Information Database (JIPID), produces the most comprehensive and expertly annotated protein sequence database in the public domain, the PIR-International Protein Sequence Database. To provide timely and high quality annotation and promote database interoperability, the PIR-International employs rule-based and classification-driven procedures based on controlled vocabulary and standard nomenclature and includes status tags to distinguish experimentally determined from predicted protein features. The database contains about 200 000 non-redundant protein sequences, which are classified into families and superfamilies and their domains and motifs identified. Entries are extensively cross-referenced to other sequence, classification, genome, structure and activity databases. The PIR web site features search engines that use sequence similarity and database annotation to facilitate the analysis and functional identification of proteins. The PIR-Inter­national databases and search tools are accessible on the PIR web site at http://pir.georgetown.edu/ and at the MIPS web site at http://www.mips.biochem.mpg.de. The PIR-International Protein Sequence Database and other files are also available by FTP.

The Homeodomain Resource: sequences, structures, DNA binding sites and genomic information

The Homeodomain Resource is an annotated collection of non-redundant protein sequences, three-dimensional structures and genomic information for the homeodomain protein family. Release 3.0 contains 795 full-length homeodomain-containing sequences, 32 experimentally-derived structures and 143 homeo­box loci implicated in human genetic disorders. Entries are fully hyperlinked to facilitate easy retrieval of the original records from source databases. A simple search engine with a graphical user interface is provided to query the component databases and assemble customized data sets. A new feature for this release is the addition of DNA recognition sites for all human homeodomain proteins described in the literature. The Homeodomain Resource is freely available through the World Wide Web at http://genome.nhgri.nih.gov/homeodomain.

Estimation of divergence times from multiprotein sequences for a few mammalian species and several distantly related organisms

When many protein sequences are available for estimating the time of divergence between two species, it is customary to estimate the time for each protein separately and then use the average for all proteins as the final estimate. However, it can be shown that this estimate generally has an upward bias, and that an unbiased estimate is obtained by using distances based on concatenated sequences. We have shown that two concatenation-based distances, i.e., average gamma distance weighted with sequence length (d2) and multiprotein gamma distance (d3), generally give more satisfactory results than other concatenation-based distances. Using these two distance measures for 104 protein sequences, we estimated the time of divergence between mice and rats to be approximately 33 million years ago. Similarly, the time of divergence between humans and rodents was estimated to be approximately 96 million years ago. We also investigated the dependency of time estimates on statistical methods and various assumptions made by using sequence data from eubacteria, protists, plants, fungi, and animals. Our best estimates of the times of divergence between eubacteria and eukaryotes, between protists and other eukaryotes, and between plants, fungi, and animals were 3, 1.7, and 1.3 billion years ago, respectively. However, estimates of ancient divergence times are subject to a substantial amount of error caused by uncertainty of the molecular clock, horizontal gene transfer, errors in sequence alignments, etc.

Highly specific protein sequence motifs for genome analysis

We present a method for discovering conserved sequence motifs from families of aligned protein sequences. The method has been implemented as a computer program called emotif (http://motif.stanford.edu/emotif). Given an aligned set of protein sequences, emotif generates a set of motifs with a wide range of specificities and sensitivities. emotif also can generate motifs that describe possible subfamilies of a protein superfamily. A disjunction of such motifs often can represent the entire superfamily with high specificity and sensitivity. We have used emotif to generate sets of motifs from all 7,000 protein alignments in the blocks and prints databases. The resulting database, called identify (http://motif.stanford.edu/identify), contains more than 50,000 motifs. For each alignment, the database contains several motifs having a probability of matching a false positive that range from 10−10 to 10−5. Highly specific motifs are well suited for searching entire proteomes, while generating very few false predictions. identify assigns biological functions to 25–30% of all proteins encoded by the Saccharomyces cerevisiae genome and by several bacterial genomes. In particular, identify assigned functions to 172 of proteins of unknown function in the yeast genome.

Photoactive yellow protein: A structural prototype for the three-dimensional fold of the PAS domain superfamily

PAS domains are found in diverse proteins throughout all three kingdoms of life, where they apparently function in sensing and signal transduction. Although a wealth of useful sequence and functional information has become recently available, these data have not been integrated into a three-dimensional (3D) framework. The very early evolutionary development and diverse functions of PAS domains have made sequence analysis and modeling of this protein superfamily challenging. Limited sequence similarities between the ∼50-residue PAS repeats and one region of the bacterial blue-light photosensor photoactive yellow protein (PYP), for which ground-state and light-activated crystallographic structures have been determined to high resolution, originally were identified in sequence searches using consensus sequence probes from PAS-containing proteins. Here, we found that by changing a few residues particular to PYP function, the modified PYP sequence probe also could select PAS protein sequences. By mapping a typical ∼150-residue PAS domain sequence onto the entire crystallographic structure of PYP, we show that the PAS sequence similarities and differences are consistent with a shared 3D fold (the PAS/PYP module) with obvious potential for a ligand-binding cavity. Thus, PYP appears to prototypically exhibit all the major structural and functional features characteristic of the PAS domain superfamily: the shared PAS/PYP modular domain fold of ∼125–150 residues, a sensor function often linked to ligand or cofactor (chromophore) binding, and signal transduction capability governed by heterodimeric assembly (to the downstream partner of PYP). This 3D PAS/PYP module provides a structural model to guide experimental testing of hypotheses regarding ligand-binding, dimerization, and signal transduction.

Multiple DNA and protein sequence alignment based on segment-to-segment comparison.

In this paper, a new way to think about, and to construct, pairwise as well as multiple alignments of DNA and protein sequences is proposed. Rather than forcing alignments to either align single residues or to introduce gaps by defining an alignment as a path running right from the source up to the sink in the associated dot-matrix diagram, we propose to consider alignments as consistent equivalence relations defined on the set of all positions occurring in all sequences under consideration. We also propose constructing alignments from whole segments exhibiting highly significant overall similarity rather than by aligning individual residues. Consequently, we present an alignment algorithm that (i) is based on segment-to-segment comparison instead of the commonly used residue-to-residue comparison and which (ii) avoids the well-known difficulties concerning the choice of appropriate gap penalties: gaps are not treated explicity, but remain as those parts of the sequences that do not belong to any of the aligned segments. Finally, we discuss the application of our algorithm to two test examples and compare it with commonly used alignment methods. As a first example, we aligned a set of 11 DNA sequences coding for functional helix-loop-helix proteins. Though the sequences show only low overall similarity, our program correctly aligned all of the 11 functional sites, which was a unique result among the methods tested. As a by-product, the reading frames of the sequences were identified. Next, we aligned a set of ribonuclease H proteins and compared our results with alignments produced by other programs as reported by McClure et al. [McClure, M. A., Vasi, T. K. & Fitch, W. M. (1994) Mol. Biol. Evol. 11, 571-592]. Our program was one of the best scoring programs. However, in contrast to other methods, our protein alignments are independent of user-defined parameters.

Conservation and function of the transcriptional regulatory protein Runt.

A phylogenetic approach was used to identify conserved regions of the transcriptional regulator Runt. Alignment of the deduced protein sequences from Drosophila melanogaster, Drosophila pseudoobscura, and Drosophila virilis revealed eight blocks of high sequence homology separated by regions with little or no homology. The largest conserved block contains the Runt domain, a DNA and protein binding domain conserved in a small family of mammalian transcription factors. The functional properties of the Runt domain from the D. melanogaster gene and the human AML1 (acute myeloid leukemia 1) gene were compared in vitro and in vivo. Electrophoretic mobility-shift assays with Runt/AML1 chimeras demonstrated that the different DNA binding properties of Runt and AML1 are due to differences within their respective Runt domains. Ectopic expression experiments indicated that proteins containing the AML1 Runt domain function in Drosophila embryos and that sequences outside of this domain are important in vivo.

A family of proteins structurally and functionally related to the E6-AP ubiquitin-protein ligase.

E6-AP is a 100-kDa cellular protein that interacts with the E6 protein of the cancer-associated human papillomavirus types 16 and 18. The E6/E6-AP complex binds to and targets the p53 tumor-suppressor protein for ubiquitin-mediated proteolysis. E6-AP is an E3 ubiquitin-protein ligase which accepts ubiquitin from an E2 ubiquitin-conjugating enzyme in the form of a thioester and then directly transfers the ubiquitin to targeted substrates. The amino acid sequence of E6-AP shows similarity to a number of protein sequences over an approximately 350-aa region corresponding to the carboxyl termini of both E6-AP and the E6-AP-related proteins. Of particular note is a conserved cysteine residue within the last 32-34 aa, which in E6-AP is likely to be the site of ubiquitin thioester formation. Two of the E6-AP-related proteins, a rat 100-kDa protein and a yeast 95-kDa protein (RSP5), both of previously unknown function, are shown here to form thioesters with ubiquitin. Mutation of the conserved cysteine residue of these proteins destroys their ability to accept ubiquitin. These data strongly suggest that the rat 100-kDa protein and RSP5, as well as the other E6-AP-related proteins, belong to a class of functionally related E3 ubiquitin-protein ligases, defined by a domain homologous to the E6-AP carboxyl terminus (hect domain).

Differential use of signal peptides and membrane domains is a common occurrence in the protein output of transcriptional units

Membrane organization describes the orientation of a protein with respect to the membrane and can be determined by the presence, or absence, and organization within the protein sequence of two features: endoplasmic reticulum signal peptides and alpha-helical transmembrane domains. These features allow protein sequences to be classified into one of five membrane organization categories: soluble intracellular proteins, soluble secreted proteins, type I membrane proteins, type II membrane proteins, and multi- spanning membrane proteins. Generation of protein isoforms with variable membrane organizations can change a protein's subcellular localization or association with the membrane. Application of MemO, a membrane organization annotation pipeline, to the FANTOM3 Isoform Protein Sequence mouse protein set revealed that within the 8,032 transcriptional units ( TUs) with multiple protein isoforms, 573 had variation in their use of signal peptides, 1,527 had variation in their use of transmembrane domains, and 615 generated protein isoforms from distinct membrane organization classes. The mechanisms underlying these transcript variations were analyzed. While TUs were identified encoding all pairwise combinations of membrane organization categories, the most common was conversion of membrane proteins to soluble proteins. Observed within our highconfidence set were 156 TUs predicted to generate both extracellular soluble and membrane proteins, and 217 TUs generating both intracellular soluble and membrane proteins. The differential use of endoplasmic reticulum signal peptides and transmembrane domains is a common occurrence within the variable protein output of TUs. The generation of protein isoforms that are targeted to multiple subcellular locations represents a major functional consequence of transcript variation within the mouse transcriptome.

Protein and Drug Design Algorithms Using Improved Biophysical Modeling

This thesis focuses on the development of algorithms that will allow protein design calculations to incorporate more realistic modeling assumptions. Protein design algorithms search large sequence spaces for protein sequences that are biologically and medically useful. Better modeling could improve the chance of success in designs and expand the range of problems to which these algorithms are applied. I have developed algorithms to improve modeling of backbone flexibility (DEEPer) and of more extensive continuous flexibility in general (EPIC and LUTE). I’ve also developed algorithms to perform multistate designs, which account for effects like specificity, with provable guarantees of accuracy (COMETS), and to accommodate a wider range of energy functions in design (EPIC and LUTE).

Analysis Of The Ergosterol Biosynthesis Pathway Cloning, Molecular Characterization And Phylogeny Of Lanosterol 14 α-demethylase (erg11) Gene Of Moniliophthora Perniciosa.

The phytopathogenic fungus Moniliophthora perniciosa (Stahel) Aime & Philips-Mora, causal agent of witches' broom disease of cocoa, causes countless damage to cocoa production in Brazil. Molecular studies have attempted to identify genes that play important roles in fungal survival and virulence. In this study, sequences deposited in the M. perniciosa Genome Sequencing Project database were analyzed to identify potential biological targets. For the first time, the ergosterol biosynthetic pathway in M. perniciosa was studied and the lanosterol 14α-demethylase gene (ERG11) that encodes the main enzyme of this pathway and is a target for fungicides was cloned, characterized molecularly and its phylogeny analyzed. ERG11 genomic DNA and cDNA were characterized and sequence analysis of the ERG11 protein identified highly conserved domains typical of this enzyme, such as SRS1, SRS4, EXXR and the heme-binding region (HBR). Comparison of the protein sequences and phylogenetic analysis revealed that the M. perniciosa enzyme was most closely related to that of Coprinopsis cinerea.

Transcriptional profiling reveals the expression of novel genes in response to various stimuli in the human dermatophyte Trichophyton rubrum

Background: Cutaneous mycoses are common human infections among healthy and immunocompromised hosts, and the anthropophilic fungus Trichophyton rubrum is the most prevalent microorganism isolated from such clinical cases worldwide. The aim of this study was to determine the transcriptional profile of T. rubrum exposed to various stimuli in order to obtain insights into the responses of this pathogen to different environmental challenges. Therefore, we generated an expressed sequence tag (EST) collection by constructing one cDNA library and nine suppression subtractive hybridization libraries. Results: The 1388 unigenes identified in this study were functionally classified based on the Munich Information Center for Protein Sequences (MIPS) categories. The identified proteins were involved in transcriptional regulation, cellular defense and stress, protein degradation, signaling, transport, and secretion, among other functions. Analysis of these unigenes revealed 575 T. rubrum sequences that had not been previously deposited in public databases. Conclusion: In this study, we identified novel T. rubrum genes that will be useful for ORF prediction in genome sequencing and facilitating functional genome analysis. Annotation of these expressed genes revealed metabolic adaptations of T. rubrum to carbon sources, ambient pH shifts, and various antifungal drugs used in medical practice. Furthermore, challenging T. rubrum with cytotoxic drugs and ambient pH shifts extended our understanding of the molecular events possibly involved in the infectious process and resistance to antifungal drugs.