Predicting protein function from domain content

Fitting hidden Markov models of protein domains to a target species: application to Plasmodium falciparum

BACKGROUND

Hidden Markov Models (HMMs) are a powerful tool for protein domain identification. The Pfam database notably provides a large collection of HMMs which are widely used for the annotation of proteins in new sequenced organisms. In Pfam, each domain family is represented by a curated multiple sequence alignment from which a profile HMM is built. In spite of their high specificity, HMMs may lack sensitivity when searching for domains in divergent organisms. This is particularly the case for species with a biased amino-acid composition, such as P. falciparum, the main causal agent of human malaria. In this context, fitting HMMs to the specificities of the target proteome can help identify additional domains.

RESULTS

Using P. falciparum as an example, we compare approaches that have been proposed for this problem, and present two alternative methods. Because previous attempts strongly rely on known domain occurrences in the target species or its close relatives, they mainly improve the detection of domains which belong to already identified families. Our methods learn global correction rules that adjust amino-acid distributions associated with the match states of HMMs. These rules are applied to all match states of the whole HMM library, thus enabling the detection of domains from previously absent families. Additionally, we propose a procedure to estimate the proportion of false positives among the newly discovered domains. Starting with the Pfam standard library, we build several new libraries with the different HMM-fitting approaches. These libraries are first used to detect new domain occurrences with low E-values. Second, by applying the Co-Occurrence Domain Discovery (CODD) procedure we have recently proposed, the libraries are further used to identify likely occurrences among potential domains with higher E-values.

CONCLUSION

We show that the new approaches allow identification of several domain families previously absent in the P. falciparum proteome and the Apicomplexa phylum, and identify many domains that are not detected by previous approaches. In terms of the number of new discovered domains, the new approaches outperform the previous ones when no close species are available or when they are used to identify likely occurrences among potential domains with high E-values. All predictions on P. falciparum have been integrated into a dedicated website which pools all known/new annotations of protein domains and functions for this organism. A software implementing the two proposed approaches is available at the same address: http://www.lirmm.fr/~terrapon/HMMfit/

REvolver: modeling sequence evolution under domain constraints

Simulating the change of protein sequences over time in a biologically realistic way is fundamental for a broad range of studies with a focus on evolution. It is, thus, problematic that typically simulators evolve individual sites of a sequence identically and independently. More realistic simulations are possible; however, they are often prohibited by limited knowledge concerning site-specific evolutionary constraints or functional dependencies between amino acids. As a consequence, a protein's functional and structural characteristics are rapidly lost in the course of simulated evolution. Here, we present REvolver (www.cibiv.at/software/revolver), a program that simulates protein sequence alteration such that evolutionarily stable sequence characteristics, like functional domains, are maintained. For this purpose, REvolver recruits profile hidden Markov models (pHMMs) for parameterizing site-specific models of sequence evolution in an automated fashion. pHMMs derived from alignments of homologous proteins or protein domains capture information regarding which sequence sites remained conserved over time and where in a sequence insertions or deletions are more likely to occur. Thus, they describe constraints on the evolutionary process acting on these sequences. To demonstrate the performance of REvolver as well as its applicability in large-scale simulation studies, we evolved the entire human proteome up to 1.5 expected substitutions per site. Simultaneously, we analyzed the preservation of Pfam and SMART domains in the simulated sequences over time. REvolver preserved 92% of the Pfam domains originally present in the human sequences. This value drops to 15% when traditional models of amino acid sequence evolution are used. Thus, REvolver represents a significant advance toward a realistic simulation of protein sequence evolution on a proteome-wide scale. Further, REvolver facilitates the simulation of a protein family with a user-defined domain architecture at the root.

Domain architecture conservation in orthologs

Background

As orthologous proteins are expected to retain function more often than other homologs, they are often used for functional annotation transfer between species. However, ortholog identification methods do not take into account changes in domain architecture, which are likely to modify a protein's function. By domain architecture we refer to the sequential arrangement of domains along a protein sequence.

To assess the level of domain architecture conservation among orthologs, we carried out a large-scale study of such events between human and 40 other species spanning the entire evolutionary range. We designed a score to measure domain architecture similarity and used it to analyze differences in domain architecture conservation between orthologs and paralogs relative to the conservation of primary sequence. We also statistically characterized the extents of different types of domain swapping events across pairs of orthologs and paralogs.

Results

The analysis shows that orthologs exhibit greater domain architecture conservation than paralogous homologs, even when differences in average sequence divergence are compensated for, for homologs that have diverged beyond a certain threshold. We interpret this as an indication of a stronger selective pressure on orthologs than paralogs to retain the domain architecture required for the proteins to perform a specific function. In general, orthologs as well as the closest paralogous homologs have very similar domain architectures, even at large evolutionary separation.

The most common domain architecture changes observed in both ortholog and paralog pairs involved insertion/deletion of new domains, while domain shuffling and segment duplication/deletion were very infrequent.

Conclusions

On the whole, our results support the hypothesis that function conservation between orthologs demands higher domain architecture conservation than other types of homologs, relative to primary sequence conservation. This supports the notion that orthologs are functionally more similar than other types of homologs at the same evolutionary distance.

Using context to improve protein domain identification

BACKGROUND

Identifying domains in protein sequences is an important step in protein structural and functional annotation. Existing domain recognition methods typically evaluate each domain prediction independently of the rest. However, the majority of proteins are multidomain, and pairwise domain co-occurrences are highly specific and non-transitive.

RESULTS

Here, we demonstrate how to exploit domain co-occurrence to boost weak domain predictions that appear in previously observed combinations, while penalizing higher confidence domains if such combinations have never been observed. Our framework, Domain Prediction Using Context (dPUC), incorporates pairwise "context" scores between domains, along with traditional domain scores and thresholds, and improves domain prediction across a variety of organisms from bacteria to protozoa and metazoa. Among the genomes we tested, dPUC is most successful at improving predictions for the poorly-annotated malaria parasite Plasmodium falciparum, for which over 38% of the genome is currently unannotated. Our approach enables high-confidence annotations in this organism and the identification of orthologs to many core machinery proteins conserved in all eukaryotes, including those involved in ribosomal assembly and other RNA processing events, which surprisingly had not been previously known.

CONCLUSIONS

Overall, our results demonstrate that this new context-based approach will provide significant improvements in domain and function prediction, especially for poorly understood genomes for which the need for additional annotations is greatest. Source code for the algorithm is available under a GPL open source license at http://compbio.cs.princeton.edu/dpuc/. Pre-computed results for our test organisms and a web server are also available at that location.

Genome-wide computational function prediction of Arabidopsis proteins by integration of multiple data sources

Although Arabidopsis (Arabidopsis thaliana) is the best studied plant species, the biological role of one-third of its proteins is still unknown. We developed a probabilistic protein function prediction method that integrates information from sequences, protein-protein interactions, and gene expression. The method was applied to proteins from Arabidopsis. Evaluation of prediction performance showed that our method has improved performance compared with single source-based prediction approaches and two existing integration approaches. An innovative feature of our method is that it enables transfer of functional information between proteins that are not directly associated with each other. We provide novel function predictions for 5,807 proteins. Recent experimental studies confirmed several of the predictions. We highlight these in detail for proteins predicted to be involved in flowering and floral organ development.

Combining modularity, conservation, and interactions of proteins significantly increases precision and coverage of protein function prediction

BACKGROUND

While the number of newly sequenced genomes and genes is constantly increasing, elucidation of their function still is a laborious and time-consuming task. This has led to the development of a wide range of methods for predicting protein functions in silico. We report on a new method that predicts function based on a combination of information about protein interactions, orthology, and the conservation of protein networks in different species.

RESULTS

We show that aggregation of these independent sources of evidence leads to a drastic increase in number and quality of predictions when compared to baselines and other methods reported in the literature. For instance, our method generates more than 12,000 novel protein functions for human with an estimated precision of ~76%, among which are 7,500 new functional annotations for 1,973 human proteins that previously had zero or only one function annotated. We also verified our predictions on a set of genes that play an important role in colorectal cancer (MLH1, PMS2, EPHB4 ) and could confirm more than 73% of them based on evidence in the literature.

CONCLUSIONS

The combination of different methods into a single, comprehensive prediction method infers thousands of protein functions for every species included in the analysis at varying, yet always high levels of precision and very good coverage.

SUPERFAMILY 1.75 including a domain-centric gene ontology method

The SUPERFAMILY resource provides protein domain assignments at the structural classification of protein (SCOP) superfamily level for over 1400 completely sequenced genomes, over 120 metagenomes and other gene collections such as UniProt. All models and assignments are available to browse and download at http://supfam.org. A new hidden Markov model library based on SCOP 1.75 has been created and a previously ignored class of SCOP, coiled coils, is now included. Our scoring component now uses HMMER3, which is in orders of magnitude faster and produces superior results. A cloud-based pipeline was implemented and is publicly available at Amazon web services elastic computer cloud. The SUPERFAMILY reference tree of life has been improved allowing the user to highlight a chosen superfamily, family or domain architecture on the tree of life. The most significant advance in SUPERFAMILY is that now it contains a domain-based gene ontology (GO) at the superfamily and family levels. A new methodology was developed to ensure a high quality GO annotation. The new methodology is general purpose and has been used to produce domain-based phenotypic ontologies in addition to GO.

EuPathDomains: the divergent domain database for eukaryotic pathogens

Eukaryotic pathogens (e.g. Plasmodium, Leishmania, Trypanosomes, etc.) are a major source of morbidity and mortality worldwide. In Africa, one of the most impacted continents, they cause millions of deaths and constitute an immense economic burden. While the genome sequence of several of these organisms is now available, the biological functions of more than half of their proteins are still unknown. This is a serious issue for bringing to the foreground the expected new therapeutic targets. In this context, the identification of protein domains is a key step to improve the functional annotation of the proteins. However, several domains are missed in eukaryotic pathogens because of the high phylogenetic distance of these organisms from the classical eukaryote models. We recently proposed a method, co-occurrence domain detection (CODD), that improves the sensitivity of Pfam domain detection by exploiting the tendency of domains to appear preferentially with a few other favorite domains in a protein. In this paper, we present EuPathDomains (http://www.atgc-montpellier.fr/EuPathDomains/), an extended database of protein domains belonging to ten major eukaryotic human pathogens. EuPathDomains gathers known and new domains detected by CODD, along with the associated confidence measurements and the GO annotations that can be deduced from the new domains. This database significantly extends the Pfam domain coverage of all selected genomes, by proposing new occurrences of domains as well as new domain families that have never been reported before. For example, with a false discovery rate lower than 20%, EuPathDomains increases the number of detected domains by 13% in Toxoplasma gondii genome and up to 28% in Cryptospordium parvum, and the total number of domain families by 10% in Plasmodium falciparum and up to 16% in C. parvum genome. The database can be queried by protein names, domain identifiers, Pfam or Interpro identifiers, or organisms, and should become a valuable resource to decipher the protein functions of eukaryotic pathogens.

FACT: functional annotation transfer between proteins with similar feature architectures

Background

The increasing number of sequenced genomes provides the basis for exploring the genetic and functional diversity within the tree of life. Only a tiny fraction of the encoded proteins undergoes a thorough experimental characterization. For the remainder, bioinformatics annotation tools are the only means to infer their function. Exploiting significant sequence similarities to already characterized proteins, commonly taken as evidence for homology, is the prevalent method to deduce functional equivalence. Such methods fail when homologs are too diverged, or when they have assumed a different function. Finally, due to convergent evolution, functional equivalence is not necessarily linked to common ancestry. Therefore complementary approaches are required to identify functional equivalents.

Results

We present the Feature Architecture Comparison Tool http://www.cibiv.at/FACT to search for functionally equivalent proteins. FACT uses the similarity between feature architectures of two proteins, i.e., the arrangements of functional domains, secondary structure elements and compositional properties, as a proxy for their functional equivalence. A scoring function measures feature architecture similarities, which enables searching for functional equivalents in entire proteomes. Our evaluation of 9,570 EC classified enzymes revealed that FACT, using the full feature, set outperformed the existing architecture-based approaches by identifying significantly more functional equivalents as highest scoring proteins. We show that FACT can identify functional equivalents that share no significant sequence similarity. However, when the highest scoring protein of FACT is also the protein with the highest local sequence similarity, it is in 99% of the cases functionally equivalent to the query. We demonstrate the versatility of FACT by identifying a missing link in the yeast glutathione metabolism and also by searching for the human GolgA5 equivalent in Trypanosoma brucei.

Conclusions

FACT facilitates a quick and sensitive search for functionally equivalent proteins in entire proteomes. FACT is complementary to approaches using sequence similarity to identify proteins with the same function. Thus, FACT is particularly useful when functional equivalents need to be identified in evolutionarily distant species, or when functional equivalents are not homologous. The most reliable annotation transfers, however, are achieved when feature architecture similarity and sequence similarity are jointly taken into account.

PoGO: Prediction of Gene Ontology terms for fungal proteins

Background

Automated protein function prediction methods are the only practical approach for assigning functions to genes obtained from model organisms. Many of the previously reported function annotation methods are of limited utility for fungal protein annotation. They are often trained only to one species, are not available for high-volume data processing, or require the use of data derived by experiments such as microarray analysis. To meet the increasing need for high throughput, automated annotation of fungal genomes, we have developed a tool for annotating fungal protein sequences with terms from the Gene Ontology.

Results

We describe a classifier called PoGO (Prediction of Gene Ontology terms) that uses statistical pattern recognition methods to assign Gene Ontology (GO) terms to proteins from filamentous fungi. PoGO is organized as a meta-classifier in which each evidence source (sequence similarity, protein domains, protein structure and biochemical properties) is used to train independent base-level classifiers. The outputs of the base classifiers are used to train a meta-classifier, which provides the final assignment of GO terms. An independent classifier is trained for each GO term, making the system amenable to updating, without having to re-train the whole system. The resulting system is robust. It provides better accuracy and can assign GO terms to a higher percentage of unannotated protein sequences than other methods that we tested.

Conclusions

Our annotation system overcomes many of the shortcomings that we found in other methods. We also provide a web server where users can submit protein sequences to be annotated.

Protein subcellular localization prediction of eukaryotes using a knowledge-based approach

BACKGROUND

The study of protein subcellular localization (PSL) is important for elucidating protein functions involved in various cellular processes. However, determining the localization sites of a protein through wet-lab experiments can be time-consuming and labor-intensive. Thus, computational approaches become highly desirable. Most of the PSL prediction systems are established for single-localized proteins. However, a significant number of eukaryotic proteins are known to be localized into multiple subcellular organelles. Many studies have shown that proteins may simultaneously locate or move between different cellular compartments and be involved in different biological processes with different roles.

RESULTS

In this study, we propose a knowledge based method, called KnowPredsite, to predict the localization site(s) of both single-localized and multi-localized proteins. Based on the local similarity, we can identify the "related sequences" for prediction. We construct a knowledge base to record the possible sequence variations for protein sequences. When predicting the localization annotation of a query protein, we search against the knowledge base and used a scoring mechanism to determine the predicted sites. We downloaded the dataset from ngLOC, which consisted of ten distinct subcellular organelles from 1923 species, and performed ten-fold cross validation experiments to evaluate KnowPred site's performance. The experiment results show that KnowPred site achieves higher prediction accuracy than ngLOC and Blast-hit method. For single-localized proteins, the overall accuracy of KnowPred site is 91.7%. For multi-localized proteins, the overall accuracy of KnowPred site is 72.1%, which is significantly higher than that of ngLOC by 12.4%. Notably, half of the proteins in the dataset that cannot find any Blast hit sequence above a specified threshold can still be correctly predicted by KnowPred site.

CONCLUSION

KnowPred site demonstrates the power of identifying related sequences in the knowledge base. The experiment results show that even though the sequence similarity is low, the local similarity is effective for prediction. Experiment results show that KnowPred site is a highly accurate prediction method for both single- and multi-localized proteins. It is worth-mentioning the prediction process of KnowPred site is transparent and biologically interpretable and it shows a set of template sequences to generate the prediction result. The KnowPred site prediction server is available at http://bio-cluster.iis.sinica.edu.tw/kbloc/.

Detection of new protein domains using co-occurrence: application to Plasmodium falciparum

MOTIVATION

Hidden Markov models (HMMs) have proved to be a powerful tool for protein domain identification in newly sequenced organisms. However, numerous domains may be missed in highly divergent proteins. This is the case for Plasmodium falciparum proteins, the main causal agent of human malaria.

RESULTS

We propose a method to improve the sensitivity of HMM domain detection by exploiting the tendency of the domains to appear preferentially with a few other favorite domains in a protein. When sequence information alone is not sufficient to warrant the presence of a particular domain, our method enables its detection on the basis of the presence of other Pfam or InterPro domains. Moreover, a shuffling procedure allows us to estimate the false discovery rate associated with the results. Applied to P. falciparum, our method identifies 585 new Pfam domains (versus the 3683 already known domains in the Pfam database) with an estimated error rate <20%. These new domains provide 387 new Gene Ontology (GO) annotations to the P. falciparum proteome. Analogous and congruent results are obtained when applying the method to related Plasmodium species (P. vivax and P. yoelii).

AVAILABILITY

Supplementary Material and a database of the new domains and GO predictions achieved on Plasmodium proteins are available at http://www.lirmm.fr/~terrapon/codd/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

UFO: a web server for ultra-fast functional profiling of whole genome protein sequences

Background

Functional profiling is a key technique to characterize and compare the functional potential of entire genomes. The estimation of profiles according to an assignment of sequences to functional categories is a computationally expensive task because it requires the comparison of all protein sequences from a genome with a usually large database of annotated sequences or sequence families.

Description

Based on machine learning techniques for Pfam domain detection, the UFO web server for ultra-fast functional profiling allows researchers to process large protein sequence collections instantaneously. Besides the frequencies of Pfam and GO categories, the user also obtains the sequence specific assignments to Pfam domain families. In addition, a comparison with existing genomes provides dissimilarity scores with respect to 821 reference proteomes. Considering the underlying UFO domain detection, the results on 206 test genomes indicate a high sensitivity of the approach. In comparison with current state-of-the-art HMMs, the runtime measurements show a considerable speed up in the range of four orders of magnitude. For an average size prokaryotic genome, the computation of a functional profile together with its comparison typically requires about 10 seconds of processing time.

Conclusion

For the first time the UFO web server makes it possible to get a quick overview on the functional inventory of newly sequenced organisms. The genome scale comparison with a large number of precomputed profiles allows a first guess about functionally related organisms. The service is freely available and does not require user registration or specification of a valid email address.

d-Omix: a mixer of generic protein domain analysis tools

Domain combination provides important clues to the roles of protein domains in protein function, interaction and evolution. We have developed a web server d-Omix (a Mixer of Protein Domain Analysis Tools) aiming as a unified platform to analyze, compare and visualize protein data sets in various aspects of protein domain combinations. With InterProScan files for protein sets of interest provided by users, the server incorporates four services for domain analyses. First, it constructs protein phylogenetic tree based on a distance matrix calculated from protein domain architectures (DAs), allowing the comparison with a sequence-based tree. Second, it calculates and visualizes the versatility, abundance and co-presence of protein domains via a domain graph. Third, it compares the similarity of proteins based on DA alignment. Fourth, it builds a putative protein network derived from domain–domain interactions from DOMINE. Users may select a variety of input data files and flexibly choose domain search tools (e.g. hmmpfam, superfamily) for a specific analysis. Results from the d-Omix could be interactively explored and exported into various formats such as SVG, JPG, BMP and CSV. Users with only protein sequences could prepare an InterProScan file using a service provided by the server as well. The d-Omix web server is freely available at http://www.biotec.or.th/isl/Domix.