Towards accurate human promoter recognition: a review of currently used sequence features and classification methods

Machine Learning Strategies in MicroRNA Research: Bridging Genome to Phenome

MicroRNAs (miRNAs) have emerged as a prominent layer of regulation of gene expression. This article offers the salient and current aspects of machine learning (ML) tools and approaches from genome to phenome in miRNA research. First, we underline that the complexity in the analysis of miRNA function ranges from their modes of biogenesis to the target diversity in diverse biological conditions. Therefore, it is imperative to first ascertain the miRNA coding potential of genomes and understand the regulatory mechanisms of their expression. This knowledge enables the efficient classification of miRNA precursors and the identification of their mature forms and respective target genes. Second, and because one miRNA can target multiple mRNAs and vice versa, another challenge is the assessment of the miRNA-mRNA target interaction network. Furthermore, long-noncoding RNA (lncRNA)and circular RNAs (circRNAs) also contribute to this complexity. ML has been used to tackle these challenges at the high-dimensional data level. The present expert review covers more than 100 tools adopting various ML approaches pertaining to, for example, (1) miRNA promoter prediction, (2) precursor classification, (3) mature miRNA prediction, (4) miRNA target prediction, (5) miRNA- lncRNA and miRNA-circRNA interactions, (6) miRNA-mRNA expression profiling, (7) miRNA regulatory module detection, (8) miRNA-disease association, and (9) miRNA essentiality prediction. Taken together, we unpack, critically examine, and highlight the cutting-edge synergy of ML approaches and miRNA research so as to develop a dynamic and microlevel understanding of human health and diseases.

DeePromClass: Delineator for Eukaryotic Core Promoters Employing Deep Neural Networks

Computational promoter identification in eukaryotes is a classical biological problem that should be refurbished with the availability of an avalanche of experimental data and emerging deep learning technologies. The current knowledge indicates that eukaryotic core promoters display multifarious signals such as TATA-Box, Inr element, TCT, and Pause-button, etc., and structural motifs such as G-quadruplexes. In the present study, we combined the power of deep learning with a plethora of promoter motifs to delineate promoter and non-promoters gleaned from the statistical properties of DNA sequence arrangement. To this end, we implemented convolutional neural network (CNN) and long short-term memory (LSTM) recurrent neural network architecture for five model systems with [-100 to +50] segments relative to the transcription start site being the core promoter. Unlike previous state-of-the-art tools, which furnish a binary decision of promoter or non-promoter, we classify a chunk of 151mer sequence into a promoter along with the consensus signal type or a non-promoter. The combined CNN-LSTM model; we call "DeePromClass", achieved testing accuracy of 90.6%, 93.6%, 91.8%, 86.5%, and 84.0% for S. cerevisiae, C. elegans, D. melanogaster, Mus musculus, and Homo sapiens respectively. In total, our tool provides an insightful update on next-generation promoter prediction tools for promoter biologists.

A successful hybrid deep learning model aiming at promoter identification

BACKGROUND

The zone adjacent to a transcription start site (TSS), namely, the promoter, is primarily involved in the process of DNA transcription initiation and regulation. As a result, proper promoter identification is critical for further understanding the mechanism of the networks controlling genomic regulation. A number of methodologies for the identification of promoters have been proposed. Nonetheless, due to the great heterogeneity existing in promoters, the results of these procedures are still unsatisfactory. In order to establish additional discriminative characteristics and properly recognize promoters, we developed the hybrid model for promoter identification (HMPI), a hybrid deep learning model that can characterize both the native sequences of promoters and the morphological outline of promoters at the same time. We developed the HMPI to combine a method called the PSFN (promoter sequence features network), which characterizes native promoter sequences and deduces sequence features, with a technique referred to as the DSPN (deep structural profiles network), which is specially structured to model the promoters in terms of their structural profile and to deduce their structural attributes.

RESULTS

The HMPI was applied to human, plant and Escherichia coli K-12 strain datasets, and the findings showed that the HMPI was successful at extracting the features of the promoter while greatly enhancing the promoter identification performance. In addition, after the improvements of synthetic sampling, transfer learning and label smoothing regularization, the improved HMPI models achieved good results in identifying subtypes of promoters on prokaryotic promoter datasets.

CONCLUSIONS

The results showed that the HMPI was successful at extracting the features of promoters while greatly enhancing the performance of identifying promoters on both eukaryotic and prokaryotic datasets, and the improved HMPI models are good at identifying subtypes of promoters on prokaryotic promoter datasets. The HMPI is additionally adaptable to different biological functional sequences, allowing for the addition of new features or models.

Critical assessment of computational tools for prokaryotic and eukaryotic promoter prediction

Promoters are crucial regulatory DNA regions for gene transcriptional activation. Rapid advances in next-generation sequencing technologies have accelerated the accumulation of genome sequences, providing increased training data to inform computational approaches for both prokaryotic and eukaryotic promoter prediction. However, it remains a significant challenge to accurately identify species-specific promoter sequences using computational approaches. To advance computational support for promoter prediction, in this study, we curated 58 comprehensive, up-to-date, benchmark datasets for 7 different species (i.e. Escherichia coli, Bacillus subtilis, Homo sapiens, Mus musculus, Arabidopsis thaliana, Zea mays and Drosophila melanogaster) to assist the research community to assess the relative functionality of alternative approaches and support future research on both prokaryotic and eukaryotic promoters. We revisited 106 predictors published since 2000 for promoter identification (40 for prokaryotic promoter, 61 for eukaryotic promoter, and 5 for both). We systematically evaluated their training datasets, computational methodologies, calculated features, performance and software usability. On the basis of these benchmark datasets, we benchmarked 19 predictors with functioning webservers/local tools and assessed their prediction performance. We found that deep learning and traditional machine learning-based approaches generally outperformed scoring function-based approaches. Taken together, the curated benchmark dataset repository and the benchmarking analysis in this study serve to inform the design and implementation of computational approaches for promoter prediction and facilitate more rigorous comparison of new techniques in the future.

Mathematical Algorithm for Identification of Eukaryotic Promoter Sequences

Identification of promoter sequences in the eukaryotic genome, by computer methods, is an important task of bioinformatics. However, this problem has not been solved since the best algorithms have a false positive probability of 10−3–10−4 per nucleotide. As a result of full genome analysis, there may be more false positives than annotated gene promoters. The probability of a false positive should be reduced to 10−6–10−8 to reduce the number of false positives and increase the reliability of the prediction. The method for multi alignment of the promoter sequences was developed. Then, mathematical methods were developed for calculation of the statistically important classes of the promoter sequences. Five promoter classes, from the rice genome, were created. We developed promoter classes to search for potential promoter sequences in the rice genome with a false positive number less than 10−8 per nucleotide. Five classes of promoter sequences contain 1740, 222, 199, 167 and 130 promoters, respectively. A total of 145,277 potential promoter sequences (PPSs) were identified. Of these, 18,563 are promoters of known genes, 87,233 PPSs intersect with transposable elements, and 37,390 PPSs were found in previously unannotated sequences. The number of false positives for a randomly mixed rice genome is less than 10−8 per nucleotide. The method developed for detecting PPSs was compared with some previously used approaches. The developed mathematical method can be used to search for genes, transposable elements, and transcript start sites in eukaryotic genomes.

The APOE gene cluster responds to air pollution factors in mice with coordinated expression of genes that differs by age in humans

Little is known of gene-environment interactions for Alzheimer's disease (AD) risk factors. Apolipoprotein E (APOE) and neighbors on chromosome 19q13.3 have variants associated with risks of AD, but with unknown mechanism. This study describes novel links among the APOE network, air pollution, and age-related diseases. Mice exposed to air pollution nano-sized particulate matter (nPM) had coordinate responses of Apoe-Apoc1-Tomm40 in the cerebral cortex. In humans, the AD vulnerable hippocampus and amygdala had stronger age decline in APOE cluster expression than the AD-resistant cerebellum and hypothalamus. Using consensus weighted gene co-expression network, we showed that APOE has a conserved co-expressed network in rodent and primate brains. SOX1, which has AD-associated single nucleotide polymorphisms, was among the co-expressed genes in the human hippocampus. Humans and mice shared 87% of potential binding sites for transcription factors in APOE cluster promoter, suggesting similar inducibility and a novel link among environment, APOE cluster, and risk of AD.

Multiple Alignment of Promoter Sequences from the Arabidopsis thaliana L. Genome

In this study, we developed a new mathematical method for performing multiple alignment of highly divergent sequences (MAHDS), i.e., sequences that have on average more than 2.5 substitutions per position (x). We generated sets of artificial DNA sequences with x ranging from 0 to 4.4 and applied MAHDS as well as currently used multiple sequence alignment algorithms, including ClustalW, MAFFT, T-Coffee, Kalign, and Muscle to these sets. The results indicated that most of the existing methods could produce statistically significant alignments only for the sets with x < 2.5, whereas MAHDS could operate on sequences with x = 4.4. We also used MAHDS to analyze a set of promoter sequences from the Arabidopsis thaliana genome and discovered many conserved regions upstream of the transcription initiation site (from -499 to +1 bp); a part of the downstream region (from +1 to +70 bp) also significantly contributed to the obtained alignments. The possibilities of applying the newly developed method for the identification of promoter sequences in any genome are discussed. A server for multiple alignment of nucleotide sequences has been created.

An energy model for recognizing the prokaryotic promoters based on molecular structure

Promoter is an important functional elements of DNA sequences, which is in charge of gene transcription initiation. Recognizing promoter have important help for understanding the relative life phenomena. Based on the concept that promoter is mainly determined by its sequence and structure, a novel statistical physics model for predicting promoter in Escherichia coli K-12 is proposed. The total energies of DNA local structure of sequence segments in the three benchmark promoter sequence datasets, the sole prediction parameter, are calculated by using principles from statistical physics and information theory. The better results are obtained. And a web-server PhysMPrePro for predicting promoter is established at http://202.207.14.87:8032/bioinformation/PhysMPrePro/index.asp, so that other scientists can easily get their desired results by our web-server.

DCDE: An Efficient Deep Convolutional Divergence Encoding Method for Human Promoter Recognition

Efficient human promoter feature extraction is still a major challenge in genome analysis as it can better understand human gene regulation and will be useful for experimental guidance. Although many machine learning algorithms have been developed for eukaryotic gene recognition, performance on promoters is unsatisfactory due to the diverse nature. To extract discriminative features from human promoters, an efficient deep convolutional divergence encoding method (DCDE) is proposed based on statistical divergence (SD) and convolutional neural network (CNN). SD can help optimize kmer feature extraction for human promoters. CNN can also be used to automatically extract features in gene analysis. In DCDE, we first perform informative kmers settlement to encode original gene sequences. A series of SD methods can optimize the most discriminative kmers distributions while maintaining important positional information. Then, CNN is utilized to extract lower dimensional deep features by secondary encoding. Finally, we construct a hybrid recognition architecture with multiple support vector machines and a bilayer decision method. It is flexible to add new features or new models and can be extended to identify other genomic functional elements. The extensive experiments demonstrate that DCDE is effective in promoter encoding and can significantly improve the performance of promoter recognition.

Methods of MicroRNA Promoter Prediction and Transcription Factor Mediated Regulatory Network

MicroRNAs (miRNAs) are short (~22 nucleotides) noncoding RNAs and disseminated throughout the genome, either in the intergenic regions or in the intronic sequences of protein-coding genes. MiRNAs have been proved to play important roles in regulating gene expression. Hence, understanding the transcriptional mechanism of miRNA genes is a very critical step to uncover the whole regulatory network. A number of miRNA promoter prediction models have been proposed in the past decade. This review summarized several most popular miRNA promoter prediction models which used genome sequence features, or other features, for example, histone markers, RNA Pol II binding sites, and nucleosome-free regions, achieved by high-throughput sequencing data. Some databases were described as resources for miRNA promoter information. We then performed comprehensive discussion on prediction and identification of transcription factor mediated microRNA regulatory networks.

The impact of sequence length and number of sequences on promoter prediction performance

BACKGROUND

The advent of rapid evolution on sequencing capacity of new genomes has evidenced the need for data analysis automation aiming at speeding up the genomic annotation process and reducing its cost. Given that one important step for functional genomic annotation is the promoter identification, several studies have been taken in order to propose computational approaches to predict promoters. Different classifiers and characteristics of the promoter sequences have been used to deal with this prediction problem. However, several works in literature have addressed the promoter prediction problem using datasets containing sequences of 250 nucleotides or more. As the sequence length defines the amount of dataset attributes, even considering a limited number of properties to characterize the sequences, datasets with a high number of attributes are generated for training classifiers. Once high-dimensional datasets can degrade the classifiers predictive performance or even require an infeasible processing time, predicting promoters by training classifiers from datasets with a reduced number of attributes, it is essential to obtain good predictive performance with low computational cost. To the best of our knowledge, there is no work in literature that verified in a systematic way the relation between the sequences length and the predictive performance of classifiers. Thus, in this work, we have evaluated the impact of sequence length variation and training dataset size (number of sequences) on the predictive performance of classifiers.

RESULTS

We have built sixteen datasets composed of different sized sequences (ranging in length from 12 to 301 nucleotides) and evaluated them using the SVM, Random Forest and k-NN classifiers. The best predictive performances reached by SVM and Random Forest remained relatively stable for datasets composed of sequences varying in length from 301 to 41 nucleotides, while k-NN achieved its best performance for the dataset composed of 101 nucleotides. We have also analyzed, using sequences composed of only 41 nucleotides, the impact of increasing the number of sequences in a dataset on the predictive performance of the same three classifiers. Datasets containing 14,000, 80,000, 100,000 and 120,000 sequences were built and evaluated. All classifiers achieved better predictive performance for datasets containing 80,000 sequences or more.

CONCLUSION

The experimental results show that several datasets composed of shorter sequences achieved better predictive performance when compared with datasets composed of longer sequences, and also consumed a significantly shorter processing time. Furthermore, increasing the number of sequences in a dataset proved to be beneficial to the predictive power of classifiers.

Rare k-mer DNA: Identification of sequence motifs and prediction of CpG island and promoter

Empirical analysis on k-mer DNA has been proven as an effective tool in finding unique patterns in DNA sequences which can lead to the discovery of potential sequence motifs. In an extensive study of empirical k-mer DNA on hundreds of organisms, the researchers found unique multi-modal k-mer spectra occur in the genomes of organisms from the tetrapod clade only which includes all mammals. The multi-modality is caused by the formation of the two lowest modes where k-mers under them are referred as the rare k-mers. The suppression of the two lowest modes (or the rare k-mers) can be attributed to the CG dinucleotide inclusions in them. Apart from that, the rare k-mers are selectively distributed in certain genomic features of CpG Island (CGI), promoter, 5' UTR, and exon. We correlated the rare k-mers with hundreds of annotated features using several bioinformatic tools, performed further intrinsic rare k-mer analyses within the correlated features, and modeled the elucidated rare k-mer clustering feature into a classifier to predict the correlated CGI and promoter features. Our correlation results show that rare k-mers are highly associated with several annotated features of CGI, promoter, 5' UTR, and open chromatin regions. Our intrinsic results show that rare k-mers have several unique topological, compositional, and clustering properties in CGI and promoter features. Finally, the performances of our RWC (rare-word clustering) method in predicting the CGI and promoter features are ranked among the top three, in eight of the CGI and promoter evaluations, among eight of the benchmarked datasets.

MicroRNA Promoter Identification in Arabidopsis Using Multiple Histone Markers

A microRNA is a small noncoding RNA molecule, which functions in RNA silencing and posttranscriptional regulation of gene expression. To understand the mechanism of the activation of microRNA genes, the location of promoter regions driving their expression is required to be annotated precisely. Only a fraction of microRNA genes have confirmed transcription start sites (TSSs), which hinders our understanding of the transcription factor binding events. With the development of the next generation sequencing technology, the chromatin states can be inferred precisely by virtue of a combination of specific histone modifications. Using the genome-wide profiles of nine histone markers including H3K4me2, H3K4me3, H3K9Ac, H3K9me2, H3K18Ac, H3K27me1, H3K27me3, H3K36me2, and H3K36me3, we developed a computational strategy to identify the promoter regions of most microRNA genes in Arabidopsis, based upon the assumption that the distribution of histone markers around the TSSs of microRNA genes is similar to the TSSs of protein coding genes. Among 298 miRNA genes, our model identified 42 independent miRNA TSSs and 132 miRNA TSSs, which are located in the promoters of upstream genes. The identification of promoters will provide better understanding of microRNA regulation and can play an important role in the study of diseases at genetic level.

Sample Subset Optimization Techniques for Imbalanced and Ensemble Learning Problems in Bioinformatics Applications

Data sampling is a widely used technique in a broad range of machine learning problems. Traditional sampling approaches generally rely on random resampling from a given dataset. However, these approaches do not take into consideration additional information, such as sample quality and usefulness. We recently proposed a data sampling technique, called sample subset optimization (SSO). The SSO technique relies on a cross-validation procedure for identifying and selecting the most useful samples as subsets. In this paper, we describe the application of SSO techniques to imbalanced and ensemble learning problems, respectively. For imbalanced learning, the SSO technique is employed as an under-sampling technique for identifying a subset of highly discriminative samples in the majority class. In ensemble learning, the SSO technique is utilized as a generic ensemble technique where multiple optimized subsets of samples from each class are selected for building an ensemble classifier. We demonstrate the utilities and advantages of the proposed techniques on a variety of bioinformatics applications where class imbalance, small sample size, and noisy data are prevalent.

Rule-based knowledge acquisition method for promoter prediction in human and Drosophila species

The rapid and reliable identification of promoter regions is important when the number of genomes to be sequenced is increasing very speedily. Various methods have been developed but few methods investigate the effectiveness of sequence-based features in promoter prediction. This study proposes a knowledge acquisition method (named PromHD) based on if-then rules for promoter prediction in human and Drosophila species. PromHD utilizes an effective feature-mining algorithm and a reference feature set of 167 DNA sequence descriptors (DNASDs), comprising three descriptors of physicochemical properties (absorption maxima, molecular weight, and molar absorption coefficient), 128 top-ranked descriptors of 4-mer motifs, and 36 global sequence descriptors. PromHD identifies two feature subsets with 99 and 74 DNASDs and yields test accuracies of 96.4% and 97.5% in human and Drosophila species, respectively. Based on the 99- and 74-dimensional feature vectors, PromHD generates several if-then rules by using the decision tree mechanism for promoter prediction. The top-ranked informative rules with high certainty grades reveal that the global sequence descriptor, the length of nucleotide A at the first position of the sequence, and two physicochemical properties, absorption maxima and molecular weight, are effective in distinguishing promoters from non-promoters in human and Drosophila species, respectively.

PROmiRNA: a new miRNA promoter recognition method uncovers the complex regulation of intronic miRNAs

The regulation of intragenic miRNAs by their own intronic promoters is one of the open problems of miRNA biogenesis. Here, we describe PROmiRNA, a new approach for miRNA promoter annotation based on a semi-supervised statistical model trained on deepCAGE data and sequence features. We validate our results with existing annotation, PolII occupancy data and read coverage from RNA-seq data. Compared to previous methods PROmiRNA increases the detection rate of intronic promoters by 30%, allowing us to perform a large-scale analysis of their genomic features, as well as elucidate their contribution to tissue-specific regulation. PROmiRNA can be downloaded from http://promirna.molgen.mpg.de.

A composite method based on formal grammar and DNA structural features in detecting human polymerase II promoter region

An important step in understanding gene regulation is to identify the promoter regions where the transcription factor binding takes place. Predicting a promoter region de novo has been a theoretical goal for many researchers for a long time. There exists a number of in silico methods to predict the promoter region de novo but most of these methods are still suffering from various shortcomings, a major one being the selection of appropriate features of promoter region distinguishing them from non-promoters. In this communication, we have proposed a new composite method that predicts promoter sequences based on the interrelationship between structural profiles of DNA and primary sequence elements of the promoter regions. We have shown that a Context Free Grammar (CFG) can formalize the relationships between different primary sequence features and by utilizing the CFG, we demonstrate that an efficient parser can be constructed for extracting these relationships from DNA sequences to distinguish the true promoter sequences from non-promoter sequences. Along with CFG, we have extracted the structural features of the promoter region to improve upon the efficiency of our prediction system. Extensive experiments performed on different datasets reveals that our method is effective in predicting promoter sequences on a genome-wide scale and performs satisfactorily as compared to other promoter prediction techniques.

ADJUSTED GEOMETRIC-MEAN: A NOVEL PERFORMANCE MEASURE FOR IMBALANCED BIOINFORMATICS DATASETS LEARNING

One common and challenging problem faced by many bioinformatics applications, such as promoter recognition, splice site prediction, RNA gene prediction, drug discovery and protein classification, is the imbalance of the available datasets. In most of these applications, the positive data examples are largely outnumbered by the negative data examples, which often leads to the development of sub-optimal prediction models having high negative recognition rate (Specificity = SP) and low positive recognition rate (Sensitivity = SE). When class imbalance learning methods are applied, usually, the SE is increased at the expense of reducing some amount of the SP. In this paper, we point out that in these data-imbalanced bioinformatics applications, the goal of applying class imbalance learning methods would be to increase the SE as high as possible by keeping the reduction of SP as low as possible. We explain that the existing performance measures used in class imbalance learning can still produce sub-optimal models with respect to this classification goal. In order to overcome these problems, we introduce a new performance measure called Adjusted Geometric-mean (AGm). The experimental results obtained on ten real-world imbalanced bioinformatics datasets demonstrates that the AGm metric can achieve a lower rate of reduction of SP than the existing performance metrics, when increasing the SE through class imbalance learning methods. This characteristic of AGm metric makes it more suitable for achieving the proposed classification goal in imbalanced bioinformatics datasets learning.

DEPPDB - DNA electrostatic potential properties database. Electrostatic properties of genome DNA elements

Electrostatic properties of genome DNA are important to its interactions with different proteins, in particular, related to transcription. DEPPDB - DNA Electrostatic Potential (and other Physical) Properties Database - provides information on the electrostatic and other physical properties of genome DNA combined with its sequence and annotation of biological and structural properties of genomes and their elements. Genomes are organized on taxonomical basis, supporting comparative and evolutionary studies. Currently, DEPPDB contains all completely sequenced bacterial, viral, mitochondrial, and plastids genomes according to the NCBI RefSeq, and some model eukaryotic genomes. Data for promoters, regulation sites, binding proteins, etc., are incorporated from established DBs and literature. The database is complemented by analytical tools. User sequences calculations are available. Case studies discovered electrostatics complementing DNA bending in E.coli plasmid BNT2 promoter functioning, possibly affecting host-environment metabolic switch. Transcription factors binding sites gravitate to high potential regions, confirming the electrostatics universal importance in protein-DNA interactions beyond the classical promoter-RNA polymerase recognition and regulation. Other genome elements, such as terminators, also show electrostatic peculiarities. Most intriguing are gene starts, exhibiting taxonomic correlations. The necessity of the genome electrostatic properties studies is discussed.

A comparison study on feature selection of DNA structural properties for promoter prediction

Background

Promoter prediction is an integrant step for understanding gene regulation and annotating genomes. Traditional promoter analysis is mainly based on sequence compositional features. Recently, many kinds of structural features have been employed in promoter prediction. However, considering the high-dimensionality and overfitting problems, it is unfeasible to utilize all available features for promoter prediction. Thus it is necessary to choose some appropriate features for the prediction task.

Results

This paper conducts an extensive comparison study on feature selection of DNA structural properties for promoter prediction. Firstly, to examine whether promoters possess some special structures, we carry out a systematical comparison among the profiles of thirteen structural features on promoter and non-promoter sequences. Secondly, we investigate the correlations between these structural features and promoter sequences. Thirdly, both filter and wrapper methods are utilized to select appropriate feature subsets from thirteen different kinds of structural features for promoter prediction, and the predictive power of the selected feature subsets is evaluated. Finally, we compare the prediction performance of the feature subsets selected in this paper with nine existing promoter prediction approaches.

Conclusions

Experimental results show that the structural features are differentially correlated to promoters. Specifically, DNA-bending stiffness, DNA denaturation and energy-related features are highly correlated with promoters. The predictive power for promoter sequences differentiates greatly among different structural features. Selecting the relevant features can significantly improve the accuracy of promoter prediction.

SCS: signal, context, and structure features for genome-wide human promoter recognition

This paper integrates the signal, context, and structure features for genome-wide human promoter recognition, which is important in improving genome annotation and analyzing transcriptional regulation without experimental supports of ESTs, cDNAs, or mRNAs. First, CpG islands are salient biological signals associated with approximately 50 percent of mammalian promoters. Second, the genomic context of promoters may have biological significance, which is based on n-mers (sequences of n bases long) and their statistics estimated from training samples. Third, sequence-dependent DNA flexibility originates from DNA 3D structures and plays an important role in guiding transcription factors to the target site in promoters. Employing decision trees, we combine above signal, context, and structure features to build a hierarchical promoter recognition system called SCS. Experimental results on controlled data sets and the entire human genome demonstrate that SCS is significantly superior in terms of sensitivity and specificity as compared to other state-of-the-art methods. The SCS promoter recognition system is available online as supplemental materials for academic use and can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TCBB.2008.95.

Deppdb--DNA electrostatic potential properties database: electrostatic properties of genome DNA

The electrostatic properties of genome DNA influence its interactions with different proteins, in particular, the regulation of transcription by RNA-polymerases. DEPPDB--DNA Electrostatic Potential Properties Database--was developed to hold and provide all available information on the electrostatic properties of genome DNA combined with its sequence and annotation of biological and structural properties of genome elements and whole genomes. Genomes in DEPPDB are organized on a taxonomical basis. Currently, the database contains all the completely sequenced bacterial and viral genomes according to NCBI RefSeq. General properties of the genome DNA electrostatic potential profile and principles of its formation are revealed. This potential correlates with the GC content but does not correspond to it exactly and strongly depends on both the sequence arrangement and its context (flanking regions). Analysis of the promoter regions for bacterial and viral RNA polymerases revealed a correspondence between the scale of these proteins' physical properties and electrostatic profile patterns. We also discovered a direct correlation between the potential value and the binding frequency of RNA polymerase to DNA, supporting the idea of the role of electrostatics in these interactions. This matches a pronounced tendency of the promoter regions to possess higher values of the electrostatic potential.

Multiconstrained gene clustering based on generalized projections

Background

Gene clustering for annotating gene functions is one of the fundamental issues in bioinformatics. The best clustering solution is often regularized by multiple constraints such as gene expressions, Gene Ontology (GO) annotations and gene network structures. How to integrate multiple pieces of constraints for an optimal clustering solution still remains an unsolved problem.

Results

We propose a novel multiconstrained gene clustering (MGC) method within the generalized projection onto convex sets (POCS) framework used widely in image reconstruction. Each constraint is formulated as a corresponding set. The generalized projector iteratively projects the clustering solution onto these sets in order to find a consistent solution included in the intersection set that satisfies all constraints. Compared with previous MGC methods, POCS can integrate multiple constraints from different nature without distorting the original constraints. To evaluate the clustering solution, we also propose a new performance measure referred to as Gene Log Likelihood (GLL) that considers genes having more than one function and hence in more than one cluster. Comparative experimental results show that our POCS-based gene clustering method outperforms current state-of-the-art MGC methods.

Conclusions

The POCS-based MGC method can successfully combine multiple constraints from different nature for gene clustering. Also, the proposed GLL is an effective performance measure for the soft clustering solutions.

Finding human promoter groups based on DNA physical properties

DNA rigidity is an important physical property originating from the DNA three-dimensional structure. Although the general DNA rigidity patterns in human promoters have been investigated, their distinct roles in transcription are largely unknown. In this paper, we discover four highly distinct human promoter groups based on similarity of their rigidity profiles. First, we find that all promoter groups conserve relatively rigid DNAs at the canonical TATA box [a consensus TATA(A/T)A(A/T) sequence] position, which are important physical signals in binding transcription factors. Second, we find that the genes activated by each group of promoters share significant biological functions based on their gene ontology annotations. Finally, we find that these human promoter groups correlate with the tissue-specific gene expression.