Modeling promoter grammars with evolving hidden Markov models

Interpretable prediction of mRNA abundance from promoter sequence using contextual regression models

While machine learning models have been successfully applied to predicting gene expression from promoter sequences, it remains a great challenge to derive intuitive interpretation of the model and reveal DNA motif grammar such as motif cooperation and distance constraint between motif sites. Previous interpretation approaches are often time-consuming or have difficulty to learn the combinatory rules. In this work, we designed interpretable neural network models to predict the mRNA expression levels from DNA sequences. By applying the Contextual Regression framework we developed, we extracted weighted features to cluster samples into different groups, which have different gene expression levels. We performed motif analysis in each cluster and found motifs with active or repressive regulation on gene expression. By comparing the co-occurrence locations of discovered motifs, we also uncovered multiple grammars of motif combination including communities of cooperative motifs and distance constraints between motif pairs. These results revealed new insights of the regulatory architecture of promoter sequences.

Evolving fisher kernels for biological sequence classification

Fisher kernels have been successfully applied to many problems in bioinformatics. However, their success depends on the quality of the generative model upon which they are built. For Fisher kernel techniques to be used on novel problems, a mechanism for creating accurate generative models is required. A novel framework is presented for automatically creating domain-specific generative models that can be used to produce Fisher kernels for support vector machines (SVMs) and other kernel methods. The framework enables the capture of prior knowledge and addresses the issue of domain-specific kernels, both of which are current areas that are lacking in many kernel-based methods. To obtain the generative model, genetic algorithms are used to evolve the structure of hidden Markov models (HMMs). A Fisher kernel is subsequently created from the HMM, and used in conjunction with an SVM, to improve the discriminative power. This paper investigates the effectiveness of the proposed method, named GA-SVM. We show that its performance is comparable if not better than other state of the art methods in classifying secretory protein sequences of malaria. More interestingly, it showed better results than the sequence-similarity-based approach, without the need for additional homologous sequence information in protein enzyme family classification. The experiments clearly demonstrate that the GA-SVM is a novel way to find features with good performance from biological sequences, that does not require extensive tuning of a complex model.

Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training

Background

Hidden Markov models are widely employed by numerous bioinformatics programs used today. Applications range widely from comparative gene prediction to time-series analyses of micro-array data. The parameters of the underlying models need to be adjusted for specific data sets, for example the genome of a particular species, in order to maximize the prediction accuracy. Computationally efficient algorithms for parameter training are thus key to maximizing the usability of a wide range of bioinformatics applications.

Results

We introduce two computationally efficient training algorithms, one for Viterbi training and one for stochastic expectation maximization (EM) training, which render the memory requirements independent of the sequence length. Unlike the existing algorithms for Viterbi and stochastic EM training which require a two-step procedure, our two new algorithms require only one step and scan the input sequence in only one direction. We also implement these two new algorithms and the already published linear-memory algorithm for EM training into the hidden Markov model compiler HMM-CONVERTER and examine their respective practical merits for three small example models.

Conclusions

Bioinformatics applications employing hidden Markov models can use the two algorithms in order to make Viterbi training and stochastic EM training more computationally efficient. Using these algorithms, parameter training can thus be attempted for more complex models and longer training sequences. The two new algorithms have the added advantage of being easier to implement than the corresponding default algorithms for Viterbi training and stochastic EM training.

An intuitionistic approach to scoring DNA sequences against transcription factor binding site motifs

Background

Transcription factors (TFs) control transcription by binding to specific regions of DNA called transcription factor binding sites (TFBSs). The identification of TFBSs is a crucial problem in computational biology and includes the subtask of predicting the location of known TFBS motifs in a given DNA sequence. It has previously been shown that, when scoring matches to known TFBS motifs, interdependencies between positions within a motif should be taken into account. However, this remains a challenging task owing to the fact that sequences similar to those of known TFBSs can occur by chance with a relatively high frequency. Here we present a new method for matching sequences to TFBS motifs based on intuitionistic fuzzy sets (IFS) theory, an approach that has been shown to be particularly appropriate for tackling problems that embody a high degree of uncertainty.

Results

We propose SC_intuit, a new scoring method for measuring sequence-motif affinity based on IFS theory. Unlike existing methods that consider dependencies between positions, SC_intuit is designed to prevent overestimation of less conserved positions of TFBSs. For a given pair of bases, SC_intuit is computed not only as a function of their combined probability of occurrence, but also taking into account the individual importance of each single base at its corresponding position. We used SC_intuit to identify known TFBSs in DNA sequences. Our method provides excellent results when dealing with both synthetic and real data, outperforming the sensitivity and the specificity of two existing methods in all the experiments we performed.

Conclusions

The results show that SC_intuit improves the prediction quality for TFs of the existing approaches without compromising sensitivity. In addition, we show how SC_intuit can be successfully applied to real research problems. In this study the reliability of the IFS theory for motif discovery tasks is proven.

Multivariate Hawkes process models of the occurrence of regulatory elements

BACKGROUND

A central question in molecular biology is how transcriptional regulatory elements (TREs) act in combination. Recent high-throughput data provide us with the location of multiple regulatory regions for multiple regulators, and thus with the possibility of analyzing the multivariate distribution of the occurrences of these TREs along the genome.

RESULTS

We present a model of TRE occurrences known as the Hawkes process. We illustrate the use of this model by analyzing two different publically available data sets. We are able to model, in detail, how the occurrence of one TRE is affected by the occurrences of others, and we can test a range of natural hypotheses about the dependencies among the TRE occurrences. In contrast to earlier efforts, pre-processing steps such as clustering or binning are not needed, and we thus retain information about the dependencies among the TREs that is otherwise lost. For each of the two data sets we provide two results: first, a qualitative description of the dependencies among the occurrences of the TREs, and second, quantitative results on the favored or avoided distances between the different TREs.

CONCLUSIONS

The Hawkes process is a novel way of modeling the joint occurrences of multiple TREs along the genome that is capable of providing new insights into dependencies among elements involved in transcriptional regulation. The method is available as an R package from http://www.math.ku.dk/~richard/ppstat/.

The construction and use of log-odds substitution scores for multiple sequence alignment

Most pairwise and multiple sequence alignment programs seek alignments with optimal scores. Central to defining such scores is selecting a set of substitution scores for aligned amino acids or nucleotides. For local pairwise alignment, substitution scores are implicitly of log-odds form. We now extend the log-odds formalism to multiple alignments, using Bayesian methods to construct "BILD" ("Bayesian Integral Log-odds") substitution scores from prior distributions describing columns of related letters. This approach has been used previously only to define scores for aligning individual sequences to sequence profiles, but it has much broader applicability. We describe how to calculate BILD scores efficiently, and illustrate their uses in Gibbs sampling optimization procedures, gapped alignment, and the construction of hidden Markov model profiles. BILD scores enable automated selection of optimal motif and domain model widths, and can inform the decision of whether to include a sequence in a multiple alignment, and the selection of insertion and deletion locations. Other applications include the classification of related sequences into subfamilies, and the definition of profile-profile alignment scores. Although a fully realized multiple alignment program must rely upon more than substitution scores, many existing multiple alignment programs can be modified to employ BILD scores. We illustrate how simple BILD score based strategies can enhance the recognition of DNA binding domains, including the Api-AP2 domain in Toxoplasma gondii and Plasmodium falciparum.

Evolutionary mirages: selection on binding site composition creates the illusion of conserved grammars in Drosophila enhancers

The clustering of transcription factor binding sites in developmental enhancers and the apparent preferential conservation of clustered sites have been widely interpreted as proof that spatially constrained physical interactions between transcription factors are required for regulatory function. However, we show here that selection on the composition of enhancers alone, and not their internal structure, leads to the accumulation of clustered sites with evolutionary dynamics that suggest they are preferentially conserved. We simulated the evolution of idealized enhancers from Drosophila melanogaster constrained to contain only a minimum number of binding sites for one or more factors. Under this constraint, mutations that destroy an existing binding site are tolerated only if a compensating site has emerged elsewhere in the enhancer. Overlapping sites, such as those frequently observed for the activator Bicoid and repressor Krüppel, had significantly longer evolutionary half-lives than isolated sites for the same factors. This leads to a substantially higher density of overlapping sites than expected by chance and the appearance that such sites are preferentially conserved. Because D. melanogaster (like many other species) has a bias for deletions over insertions, sites tended to become closer together over time, leading to an overall clustering of sites in the absence of any selection for clustered sites. Since this effect is strongest for the oldest sites, clustered sites also incorrectly appear to be preferentially conserved. Following speciation, sites tend to be closer together in all descendent species than in their common ancestors, violating the common assumption that shared features of species' genomes reflect their ancestral state. Finally, we show that selection on binding site composition alone recapitulates the observed number of overlapping and closely neighboring sites in real D. melanogaster enhancers. Thus, this study calls into question the common practice of inferring "cis-regulatory grammars" from the organization and evolutionary dynamics of developmental enhancers.

Computational models in plant-pathogen interactions: the case of Phytophthora infestans

BACKGROUND

Phytophthora infestans is a devastating oomycete pathogen of potato production worldwide. This review explores the use of computational models for studying the molecular interactions between P. infestans and one of its hosts, Solanum tuberosum.

MODELING AND CONCLUSION

Deterministic logistics models have been widely used to study pathogenicity mechanisms since the early 1950s, and have focused on processes at higher biological resolution levels. In recent years, owing to the availability of high throughput biological data and computational resources, interest in stochastic modeling of plant-pathogen interactions has grown. Stochastic models better reflect the behavior of biological systems. Most modern approaches to plant pathology modeling require molecular kinetics information. Unfortunately, this information is not available for many plant pathogens, including P. infestans. Boolean formalism has compensated for the lack of kinetics; this is especially the case where comparative genomics, protein-protein interactions and differential gene expression are the most common data resources.

Modeling tissue-specific structural patterns in human and mouse promoters

Sets of genes expressed in the same tissue are believed to be under the regulation of a similar set of transcription factors, and can thus be assumed to contain similar structural patterns in their regulatory regions. Here we present a study of the structural patterns in promoters of genes expressed specifically in 26 human and 34 mouse tissues. For each tissue we constructed promoter structure models, taking into account presences of motifs, their positioning to the transcription start site, and pairwise positioning of motifs. We found that 35 out of 60 models (58%) were able to distinguish positive test promoter sequences from control promoter sequences with statistical significance. Models with high performance include those for liver, skeletal muscle, kidney and tongue. Many of the important structural patterns in these models involve transcription factors of known importance in the tissues in question and structural patterns tend to be conserved between human and mouse. In addition to that, promoter models for related tissues tend to have high inter-tissue performance, indicating that their promoters share common structural patterns. Together, these results illustrate the validity of our models, but also indicate that the promoter structures for some tissues are easier to model than those of others.