Augmented training of hidden Markov models to recognize remote homologs via simulated evolution

Protein sequence design and its applications

Design of proteins has far-reaching potentials in diverse areas that span repurposing of the protein scaffold for reactions and substrates that they were not naturally meant for, to catching a glimpse of the ephemeral proteins that nature might have sampled during evolution. These non-natural proteins, either in synthesized or virtual form have opened the scope for the design of entities that not only rival their natural counterparts but also offer a chance to visualize the protein space continuum that might help to relate proteins and understand their associations. Here, we review the recent advances in protein engineering and design, in multiple areas, with a view to drawing attention to their future potential.

MRFy: Remote Homology Detection for Beta-Structural Proteins Using Markov Random Fields and Stochastic Search

We introduce MRFy, a tool for protein remote homology detection that captures beta-strand dependencies in the Markov random field. Over a set of 11 SCOP beta-structural superfamilies, MRFy shows a 14 percent improvement in mean Area Under the Curve for the motif recognition problem as compared to HMMER, 25 percent improvement as compared to RAPTOR, 14 percent improvement as compared to HHPred, and a 18 percent improvement as compared to CNFPred and RaptorX. MRFy was implemented in the Haskell functional programming language, and parallelizes well on multi-core systems. MRFy is available, as source code as well as an executable, from http://mrfy.cs.tufts.edu/.

Identifying Affinity Classes of Inorganic Materials Binding Sequences via a Graph-Based Model

Rapid advances in bionanotechnology have recently generated growing interest in identifying peptides that bind to inorganic materials and classifying them based on their inorganic material affinities. However, there are some distinct characteristics of inorganic materials binding sequence data that limit the performance of many widely-used classification methods when applied to this problem. In this paper, we propose a novel framework to predict the affinity classes of peptide sequences with respect to an associated inorganic material. We first generate a large set of simulated peptide sequences based on an amino acid transition matrix tailored for the specific inorganic material. Then the probability of test sequences belonging to a specific affinity class is calculated by minimizing an objective function. In addition, the objective function is minimized through iterative propagation of probability estimates among sequences and sequence clusters. Results of computational experiments on two real inorganic material binding sequence data sets show that the proposed framework is highly effective for identifying the affinity classes of inorganic material binding sequences. Moreover, the experiments on the structural classification of proteins (SCOP) data set shows that the proposed framework is general and can be applied to traditional protein sequences.

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

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

Discriminative motif discovery via simulated evolution and random under-sampling

Conserved motifs in biological sequences are closely related to their structure and functions. Recently, discriminative motif discovery methods have attracted more and more attention. However, little attention has been devoted to the data imbalance problem, which is one of the main reasons affecting the performance of the discriminative models. In this article, a simulated evolution method is applied to solve the multi-class imbalance problem at the stage of data preprocessing, and at the stage of Hidden Markov Models (HMMs) training, a random under-sampling method is introduced for the imbalance between the positive and negative datasets. It is shown that, in the task of discovering targeting motifs of nine subcellular compartments, the motifs found by our method are more conserved than the methods without considering data imbalance problem and recover the most known targeting motifs from Minimotif Miner and InterPro. Meanwhile, we use the found motifs to predict protein subcellular localization and achieve higher prediction precision and recall for the minority classes.

Filling-in void and sparse regions in protein sequence space by protein-like artificial sequences enables remarkable enhancement in remote homology detection capability

Protein functional annotation relies on the identification of accurate relationships, sequence divergence being a key factor. This is especially evident when distant protein relationships are demonstrated only with three-dimensional structures. To address this challenge, we describe a computational approach to purposefully bridge gaps between related protein families through directed design of protein-like "linker" sequences. For this, we represented SCOP domain families, integrated with sequence homologues, as multiple profiles and performed HMM-HMM alignments between related domain families. Where convincing alignments were achieved, we applied a roulette wheel-based method to design 3,611,010 protein-like sequences corresponding to 374 SCOP folds. To analyze their ability to link proteins in homology searches, we used 3024 queries to search two databases, one containing only natural sequences and another one additionally containing designed sequences. Our results showed that augmented database searches showed up to 30% improvement in fold coverage for over 74% of the folds, with 52 folds achieving all theoretically possible connections. Although sequences could not be designed between some families, the availability of designed sequences between other families within the fold established the sequence continuum to demonstrate 373 difficult relationships. Ultimately, as a practical and realistic extension, we demonstrate that such protein-like sequences can be "plugged-into" routine and generic sequence database searches to empower not only remote homology detection but also fold recognition. Our richly statistically supported findings show that complementary searches in both databases will increase the effectiveness of sequence-based searches in recognizing all homologues sharing a common fold.

Compressive genomics for protein databases

MOTIVATION

The exponential growth of protein sequence databases has increasingly made the fundamental question of searching for homologs a computational bottleneck. The amount of unique data, however, is not growing nearly as fast; we can exploit this fact to greatly accelerate homology search. Acceleration of programs in the popular PSI/DELTA-BLAST family of tools will not only speed-up homology search directly but also the huge collection of other current programs that primarily interact with large protein databases via precisely these tools.

RESULTS

We introduce a suite of homology search tools, powered by compressively accelerated protein BLAST (CaBLASTP), which are significantly faster than and comparably accurate with all known state-of-the-art tools, including HHblits, DELTA-BLAST and PSI-BLAST. Further, our tools are implemented in a manner that allows direct substitution into existing analysis pipelines. The key idea is that we introduce a local similarity-based compression scheme that allows us to operate directly on the compressed data. Importantly, CaBLASTP's runtime scales almost linearly in the amount of unique data, as opposed to current BLASTP variants, which scale linearly in the size of the full protein database being searched. Our compressive algorithms will speed-up many tasks, such as protein structure prediction and orthology mapping, which rely heavily on homology search.

AVAILABILITY

CaBLASTP is available under the GNU Public License at http://cablastp.csail.mit.edu/

CONTACT

bab@mit.edu.

A conditional neural fields model for protein threading

Motivation: Alignment errors are still the main bottleneck for current template-based protein modeling (TM) methods, including protein threading and homology modeling, especially when the sequence identity between two proteins under consideration is low (<30%).

Results: We present a novel protein threading method, CNFpred, which achieves much more accurate sequence–template alignment by employing a probabilistic graphical model called a Conditional Neural Field (CNF), which aligns one protein sequence to its remote template using a non-linear scoring function. This scoring function accounts for correlation among a variety of protein sequence and structure features, makes use of information in the neighborhood of two residues to be aligned, and is thus much more sensitive than the widely used linear or profile-based scoring function. To train this CNF threading model, we employ a novel quality-sensitive method, instead of the standard maximum-likelihood method, to maximize directly the expected quality of the training set. Experimental results show that CNFpred generates significantly better alignments than the best profile-based and threading methods on several public (but small) benchmarks as well as our own large dataset. CNFpred outperforms others regardless of the lengths or classes of proteins, and works particularly well for proteins with sparse sequence profiles due to the effective utilization of structure information. Our methodology can also be adapted to protein sequence alignment.

Contact:j3xu@ttic.edu

Supplementary information:Supplementary data are available at Bioinformatics online.

A computational framework for boosting confidence in high-throughput protein-protein interaction datasets

Improving the quality and coverage of the protein interactome is of tantamount importance for biomedical research, particularly given the various sources of uncertainty in high-throughput techniques. We introduce a structure-based framework, Coev2Net, for computing a single confidence score that addresses both false-positive and false-negative rates. Coev2Net is easily applied to thousands of binary protein interactions and has superior predictive performance over existing methods. We experimentally validate selected high-confidence predictions in the human MAPK network and show that predicted interfaces are enriched for cancer -related or damaging SNPs. Coev2Net can be downloaded at http://struct2net.csail.mit.edu.

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/

SMURFLite: combining simplified Markov random fields with simulated evolution improves remote homology detection for beta-structural proteins into the twilight zone

Motivation: One of the most successful methods to date for recognizing protein sequences that are evolutionarily related has been profile hidden Markov models (HMMs). However, these models do not capture pairwise statistical preferences of residues that are hydrogen bonded in beta sheets. These dependencies have been partially captured in the HMM setting by simulated evolution in the training phase and can be fully captured by Markov random fields (MRFs). However, the MRFs can be computationally prohibitive when beta strands are interleaved in complex topologies. We introduce SMURFLite, a method that combines both simplified MRFs and simulated evolution to substantially improve remote homology detection for beta structures. Unlike previous MRF-based methods, SMURFLite is computationally feasible on any beta-structural motif.

Results: We test SMURFLite on all propeller and barrel folds in the mainly-beta class of the SCOP hierarchy in stringent cross-validation experiments. We show a mean 26% (median 16%) improvement in area under curve (AUC) for beta-structural motif recognition as compared with HMMER (a well-known HMM method) and a mean 33% (median 19%) improvement as compared with RAPTOR (a well-known threading method) and even a mean 18% (median 10%) improvement in AUC over HHPred (a profile–profile HMM method), despite HHpred's use of extensive additional training data. We demonstrate SMURFLite's ability to scale to whole genomes by running a SMURFLite library of 207 beta-structural SCOP superfamilies against the entire genome of Thermotoga maritima, and make over a 100 new fold predictions.

Availability and implementaion: A webserver that runs SMURFLite is available at: http://smurf.cs.tufts.edu/smurflite/

Contact:lenore.cowen@tufts.edu; bab@mit.edu

RaptorX: exploiting structure information for protein alignment by statistical inference

This work presents RaptorX, a statistical method for template-based protein modeling that improves alignment accuracy by exploiting structural information in a single or multiple templates. RaptorX consists of three major components: single-template threading, alignment quality prediction, and multiple-template threading. This work summarizes the methods used by RaptorX and presents its CASP9 result analysis, aiming to identify major bottlenecks with RaptorX and template-based modeling and hopefully directions for further study. Our results show that template structural information helps a lot with both single-template and multiple-template protein threading especially when closely-related templates are unavailable, and there is still large room for improvement in both alignment and template selection. The RaptorX web server is available at http://raptorx.uchicago.edu.

Recognition of beta-structural motifs using hidden Markov models trained with simulated evolution

Motivation: One of the most successful methods to date for recognizing protein sequences that are evolutionarily related, has been profile hidden Markov models. However, these models do not capture pairwise statistical preferences of residues that are hydrogen bonded in β-sheets. We thus explore methods for incorporating pairwise dependencies into these models.

Results: We consider the remote homology detection problem for β-structural motifs. In particular, we ask if a statistical model trained on members of only one family in a SCOP β-structural superfamily, can recognize members of other families in that superfamily. We show that HMMs trained with our pairwise model of simulated evolution achieve nearly a median 5% improvement in AUC for β-structural motif recognition as compared to ordinary HMMs.

Availability: All datasets and HMMs are available at: http://bcb.cs.tufts.edu/pairwise/

Contact:anoop.kumar@tufts.edu; lenore.cowen@tufts.edu

Physicochemical property distributions for accurate and rapid pairwise protein homology detection

Background

The challenge of remote homology detection is that many evolutionarily related sequences have very little similarity at the amino acid level. Kernel-based discriminative methods, such as support vector machines (SVMs), that use vector representations of sequences derived from sequence properties have been shown to have superior accuracy when compared to traditional approaches for the task of remote homology detection.

Results

We introduce a new method for feature vector representation based on the physicochemical properties of the primary protein sequence. A distribution of physicochemical property scores are assembled from 4-mers of the sequence and normalized based on the null distribution of the property over all possible 4-mers. With this approach there is little computational cost associated with the transformation of the protein into feature space, and overall performance in terms of remote homology detection is comparable with current state-of-the-art methods. We demonstrate that the features can be used for the task of pairwise remote homology detection with improved accuracy versus sequence-based methods such as BLAST and other feature-based methods of similar computational cost.

Conclusions

A protein feature method based on physicochemical properties is a viable approach for extracting features in a computationally inexpensive manner while retaining the sensitivity of SVM protein homology detection. Furthermore, identifying features that can be used for generic pairwise homology detection in lieu of family-based homology detection is important for applications such as large database searches and comparative genomics.