MOTIVATION: Leucine-aspartic acid (LD) motifs are short linear interaction motifs (SLiMs) that link paxillin family proteins to factors controlling cell adhesion, motility and survival. The existence and importance of LD motifs beyond the paxillin family is poorly understood. RESULTS: To enable a proteome-wide assessment of LD motifs, we developed an active learning based framework (LD motif finder; LDMF) that iteratively integrates computational predictions with experimental validation. Our analysis of the human proteome revealed a dozen new proteins containing LD motifs. We found that LD motif signalling evolved in unicellular eukaryotes more than 800 Myr ago, with paxillin and vinculin as core constituents, and nuclear export signal as a likely source of de novo LD motifs. We show that LD motif proteins form a functionally homogenous group, all being involved in cell morphogenesis and adhesion. This functional focus is recapitulated in cells by GFP-fused LD motifs, suggesting that it is intrinsic to the LD motif sequence, possibly through their effect on binding partners. Our approach elucidated the origin and dynamic adaptations of an ancestral SLiM, and can serve as a guide for the identification of other SLiMs for which only few representatives are known. AVAILABILITY AND IMPLEMENTATION: LDMF is freely available online at www.cbrc.kaust.edu.sa/ldmf; Source code is available at https://github.com/tanviralambd/LD/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recognition of different genomic signals and regions (GSRs) in DNA is crucial for understanding genome organization, gene regulation, and gene function, which in turn generate better genome and gene annotations. Although many methods have been developed to recognize GSRs, their pure computational identification remains challenging. Moreover, various GSRs usually require a specialized set of features for developing robust recognition models. Recently, deep-learning (DL) methods have been shown to generate more accurate prediction models than 'shallow' methods without the need to develop specialized features for the problems in question. Here, we explore the potential use of DL for the recognition of GSRs. RESULTS: We developed DeepGSR, an optimized DL architecture for the prediction of different types of GSRs. The performance of the DeepGSR structure is evaluated on the recognition of polyadenylation signals (PAS) and translation initiation sites (TIS) of different organisms: human, mouse, bovine and fruit fly. The results show that DeepGSR outperformed the state-of-the-art methods, reducing the classification error rate of the PAS and TIS prediction in the human genome by up to 29% and 86%, respectively. Moreover, the cross-organisms and genome-wide analyses we performed, confirmed the robustness of DeepGSR and provided new insights into the conservation of examined GSRs across species. AVAILABILITY AND IMPLEMENTATION: DeepGSR is implemented in Python using Keras API; it is available as open-source software and can be obtained at https://doi.org/10.5281/zenodo.1117159. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The significance of long non-coding RNAs (lncRNAs) in many biological processes and diseases has gained intense interests over the past several years. However, computational identification of lncRNAs in a wide range of species remains challenging; it requires prior knowledge of well-established sequences and annotations or species-specific training data, but the reality is that only a limited number of species have high-quality sequences and annotations. RESULTS: Here we first characterize lncRNAs in contrast to protein-coding RNAs based on feature relationship and find that the feature relationship between open reading frame length and guanine-cytosine (GC) content presents universally substantial divergence in lncRNAs and protein-coding RNAs, as observed in a broad variety of species. Based on the feature relationship, accordingly, we further present LGC, a novel algorithm for identifying lncRNAs that is able to accurately distinguish lncRNAs from protein-coding RNAs in a cross-species manner without any prior knowledge. As validated on large-scale empirical datasets, comparative results show that LGC outperforms existing algorithms by achieving higher accuracy, well-balanced sensitivity and specificity, and is robustly effective (>90% accuracy) in discriminating lncRNAs from protein-coding RNAs across diverse species that range from plants to mammals. To our knowledge, this study, for the first time, differentially characterizes lncRNAs and protein-coding RNAs based on feature relationship, which is further applied in computational identification of lncRNAs. Taken together, our study represents a significant advance in characterization and identification of lncRNAs and LGC thus bears broad potential utility for computational analysis of lncRNAs in a wide range of species. AVAILABILITY AND IMPLEMENTATION: LGC web server is publicly available at http://bigd.big.ac.cn/lgc/calculator. The scripts and data can be downloaded at http://bigd.big.ac.cn/biocode/tools/BT000004. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Finding computationally drug-target interactions (DTIs) is a convenient strategy to identify new DTIs at low cost with reasonable accuracy. However, the current DTI prediction methods suffer the high false positive prediction rate. Results: We developed DDR, a novel method that improves the DTI prediction accuracy. DDR is based on the use of a heterogeneous graph that contains known DTIs with multiple similarities between drugs and multiple similarities between target proteins. DDR applies non-linear similarity fusion method to combine different similarities. Before fusion, DDR performs a pre-processing step where a subset of similarities is selected in a heuristic process to obtain an optimized combination of similarities. Then, DDR applies a random forest model using different graph-based features extracted from the DTI heterogeneous graph. Using 5-repeats of 10-fold cross-validation, three testing setups, and the weighted average of area under the precision-recall curve (AUPR) scores, we show that DDR significantly reduces the AUPR score error relative to the next best start-of-the-art method for predicting DTIs by 34% when the drugs are new, by 23% when targets are new and by 34% when the drugs and the targets are known but not all DTIs between them are not known. Using independent sources of evidence, we verify as correct 22 out of the top 25 DDR novel predictions. This suggests that DDR can be used as an efficient method to identify correct DTIs. Availability and implementation: The data and code are provided at https://bitbucket.org/RSO24/ddr/. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Genetic variants underlying complex traits, including disease susceptibility, are enriched within the transcriptional regulatory elements, promoters and enhancers. There is emerging evidence that regulatory elements associated with particular traits or diseases share similar patterns of transcriptional activity. Accordingly, shared transcriptional activity (coexpression) may help prioritise loci associated with a given trait, and help to identify underlying biological processes. Using cap analysis of gene expression (CAGE) profiles of promoter- and enhancer-derived RNAs across 1824 human samples, we have analysed coexpression of RNAs originating from trait-associated regulatory regions using a novel quantitative method (network density analysis; NDA). For most traits studied, phenotype-associated variants in regulatory regions were linked to tightly-coexpressed networks that are likely to share important functional characteristics. Coexpression provides a new signal, independent of phenotype association, to enable fine mapping of causative variants. The NDA coexpression approach identifies new genetic variants associated with specific traits, including an association between the regulation of the OCT1 cation transporter and genetic variants underlying circulating cholesterol levels. NDA strongly implicates particular cell types and tissues in disease pathogenesis. For example, distinct groupings of disease-associated regulatory regions implicate two distinct biological processes in the pathogenesis of ulcerative colitis; a further two separate processes are implicated in Crohn's disease. Thus, our functional analysis of genetic predisposition to disease defines new distinct disease endotypes. We predict that patients with a preponderance of susceptibility variants in each group are likely to respond differently to pharmacological therapy. Together, these findings enable a deeper biological understanding of the causal basis of complex traits.

Motivation: The computational search for promoters in prokaryotes remains an attractive problem in bioinformatics. Despite the attention it has received for many years, the problem has not been addressed satisfactorily. In any bacterial genome, the transcription start site is chosen mostly by the sigma (σ) factor proteins, which control the gene activation. The majority of published bacterial promoter prediction tools target σ 70 promoters in Escherichia coli . Moreover, no σ-specific classification of promoters is available for prokaryotes other than for E. coli . Results: Here, we introduce bTSSfinder, a novel tool that predicts putative promoters for five classes of σ factors in Cyanobacteria (σ A , σ C , σ H , σ G and σ F ) and for five classes of sigma factors in E. coli (σ 70 , σ 38 , σ 32 , σ 28 and σ 24 ). Comparing to currently available tools, bTSSfinder achieves higher accuracy (MCC = 0.86, F 1 -score = 0.93) compared to the next best tool with MCC = 0.59, F 1 -score = 0.79) and covers multiple classes of promoters. Availability and Implementation: bTSSfinder is available standalone and online at http://www.cbrc.kaust.edu.sa/btssfinder . Contacts: [email protected] or [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Discriminating the causative disease variant(s) for individuals with inherited or de novo mutations presents one of the main challenges faced by the clinical genetics community today. Computational approaches for variant prioritization include machine learning methods utilizing a large number of features, including molecular information, interaction networks, or phenotypes. Here, we demonstrate the PhenomeNET Variant Predictor (PVP) system that exploits semantic technologies and automated reasoning over genotype-phenotype relations to filter and prioritize variants in whole exome and whole genome sequencing datasets. We demonstrate the performance of PVP in identifying causative variants on a large number of synthetic whole exome and whole genome sequences, covering a wide range of diseases and syndromes. In a retrospective study, we further illustrate the application of PVP for the interpretation of whole exome sequencing data in patients suffering from congenital hypothyroidism. We find that PVP accurately identifies causative variants in whole exome and whole genome sequencing datasets and provides a powerful resource for the discovery of causal variants.

Enhancers are cis-acting DNA elements that play critical roles in distal regulation of gene expression. Identifying enhancers is an important step for understanding distinct gene expression programs that may reflect normal and pathogenic cellular conditions. Experimental identification of enhancers is constrained by the set of conditions used in the experiment. This requires multiple experiments to identify enhancers, as they can be active under specific cellular conditions but not in different cell types/tissues or cellular states. This has opened prospects for computational prediction methods that can be used for high-throughput identification of putative enhancers to complement experimental approaches. Potential functions and properties of predicted enhancers have been catalogued and summarized in several enhancer-oriented databases. Because the current methods for the computational prediction of enhancers produce significantly different enhancer predictions, it will be beneficial for the research community to have an overview of the strategies and solutions developed in this field. In this review, we focus on the identification and analysis of enhancers by bioinformatics approaches. First, we describe a general framework for computational identification of enhancers, present relevant data types and discuss possible computational solutions. Next, we cover over 30 existing computational enhancer identification methods that were developed since 2000. Our review highlights advantages, limitations and potentials, while suggesting pragmatic guidelines for development of more efficient computational enhancer prediction methods. Finally, we discuss challenges and open problems of this topic, which require further consideration.

MOTIVATION: The increased prevalence of multi-drug resistant (MDR) pathogens heightens the need to design new antimicrobial agents. Antimicrobial peptides (AMPs) exhibit broad-spectrum potent activity against MDR pathogens and kills rapidly, thus giving rise to AMPs being recognized as a potential substitute for conventional antibiotics. Designing new AMPs using current in-silico approaches is, however, challenging due to the absence of suitable models, large number of design parameters, testing cycles, production time and cost. To date, AMPs have merely been categorized into families according to their primary sequences, structures and functions. The ability to computationally determine the properties that discriminate AMP families from each other could help in exploring the key characteristics of these families and facilitate the in-silico design of synthetic AMPs. RESULTS: Here we studied 14 AMP families and sub-families. We selected a specific description of AMP amino acid sequence and identified compositional and physicochemical properties of amino acids that accurately distinguish each AMP family from all other AMPs with an average sensitivity, specificity and precision of 92.88%, 99.86% and 95.96%, respectively. Many of our identified discriminative properties have been shown to be compositional or functional characteristics of the corresponding AMP family in literature. We suggest that these properties could serve as guides for in-silico methods in design of novel synthetic AMPs. The methodology we developed is generic and has a potential to be applied for characterization of any protein family.

MOTIVATION: Cancer cells are often characterized by epigenetic changes, which include aberrant histone modifications. In particular, local or regional epigenetic silencing is a common mechanism in cancer for silencing expression of tumor suppressor genes. Though several tools have been created to enable detection of histone marks in ChIP-seq data from normal samples, it is unclear whether these tools can be efficiently applied to ChIP-seq data generated from cancer samples. Indeed, cancer genomes are often characterized by frequent copy number alterations: gains and losses of large regions of chromosomal material. Copy number alterations may create a substantial statistical bias in the evaluation of histone mark signal enrichment and result in underdetection of the signal in the regions of loss and overdetection of the signal in the regions of gain. RESULTS: We present HMCan (Histone modifications in cancer), a tool specially designed to analyze histone modification ChIP-seq data produced from cancer genomes. HMCan corrects for the GC-content and copy number bias and then applies Hidden Markov Models to detect the signal from the corrected data. On simulated data, HMCan outperformed several commonly used tools developed to analyze histone modification data produced from genomes without copy number alterations. HMCan also showed superior results on a ChIP-seq dataset generated for the repressive histone mark H3K27me3 in a bladder cancer cell line. HMCan predictions matched well with experimental data (qPCR validated regions) and included, for example, the previously detected H3K27me3 mark in the promoter of the DLEC1 gene, missed by other tools we tested.

Abstract Contact: [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

SUMMARY: In higher eukaryotes, the identification of translation initiation sites (TISs) has been focused on finding these signals in cDNA or mRNA sequences. Using Arabidopsis thaliana (A.t.) information, we developed a prediction tool for signals within genomic sequences of plants that correspond to TISs. Our tool requires only genome sequence, not expressed sequences. Its sensitivity/specificity is for A.t. (90.75%/92.2%), for Vitis vinifera (66.8%/94.4%) and for Populus trichocarpa (81.6%/94.4%), which suggests that our tool can be used in annotation of different plant genomes. We provide a list of features used in our model. Further study of these features may improve our understanding of mechanisms of the translation initiation. AVAILABILITY AND IMPLEMENTATION: Our tool is implemented as an artificial neural network. It is available as a web-based tool and, together with the source code, the list of features, and data used for model development, is accessible at http://cbrc.kaust.edu.sa/dts.

MOTIVATION: Polyadenylation is the addition of a poly(A) tail to an RNA molecule. Identifying DNA sequence motifs that signal the addition of poly(A) tails is essential to improved genome annotation and better understanding of the regulatory mechanisms and stability of mRNA. Existing poly(A) motif predictors demonstrate that information extracted from the surrounding nucleotide sequences of candidate poly(A) motifs can differentiate true motifs from the false ones to a great extent. A variety of sophisticated features has been explored, including sequential, structural, statistical, thermodynamic and evolutionary properties. However, most of these methods involve extensive manual feature engineering, which can be time-consuming and can require in-depth domain knowledge. RESULTS: We propose a novel machine-learning method for poly(A) motif prediction by marrying generative learning (hidden Markov models) and discriminative learning (support vector machines). Generative learning provides a rich palette on which the uncertainty and diversity of sequence information can be handled, while discriminative learning allows the performance of the classification task to be directly optimized. Here, we used hidden Markov models for fitting the DNA sequence dynamics, and developed an efficient spectral algorithm for extracting latent variable information from these models. These spectral latent features were then fed into support vector machines to fine-tune the classification performance. We evaluated our proposed method on a comprehensive human poly(A) dataset that consists of 14 740 samples from 12 of the most abundant variants of human poly(A) motifs. Compared with one of the previous state-of-the-art methods in the literature (the random forest model with expert-crafted features), our method reduces the average error rate, false-negative rate and false-positive rate by 26, 15 and 35%, respectively. Meanwhile, our method makes ~30% fewer error predictions relative to the other string kernels. Furthermore, our method can be used to visualize the importance of oligomers and positions in predicting poly(A) motifs, from which we can observe a number of characteristics in the surrounding regions of true and false motifs that have not been reported before. AVAILABILITY: http://sfb.kaust.edu.sa/Pages/Software.aspx. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recognition of poly(A) signals in mRNA is relatively straightforward due to the presence of easily recognizable polyadenylic acid tail. However, the task of identifying poly(A) motifs in the primary genomic DNA sequence that correspond to poly(A) signals in mRNA is a far more challenging problem. Recognition of poly(A) signals is important for better gene annotation and understanding of the gene regulation mechanisms. In this work, we present one such poly(A) motif prediction method based on properties of human genomic DNA sequence surrounding a poly(A) motif. These properties include thermodynamic, physico-chemical and statistical characteristics. For predictions, we developed Artificial Neural Network and Random Forest models. These models are trained to recognize 12 most common poly(A) motifs in human DNA. Our predictors are available as a free web-based tool accessible at http://cbrc.kaust.edu.sa/dps. Compared with other reported predictors, our models achieve higher sensitivity and specificity and furthermore provide a consistent level of accuracy for 12 poly(A) motif variants. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Burgeoning sequencing technologies have generated massive amounts of genomic and proteomic data. Annotating the functions of proteins identified in this data has become a big and crucial problem. Various computational methods have been developed to infer the protein functions based on either the sequences or domains of proteins. The existing methods, however, ignore the recurrence and the order of the protein domains in this function inference. RESULTS: We developed two new methods to infer protein functions based on protein domain recurrence and domain order. Our first method, DRDO, calculates the posterior probability of the Gene Ontology terms based on domain recurrence and domain order information, whereas our second method, DRDO-NB, relies on the naïve Bayes methodology using the same domain architecture information. Our large-scale benchmark comparisons show strong improvements in the accuracy of the protein function inference achieved by our new methods, demonstrating that domain recurrence and order can provide important information for inference of protein functions. AVAILABILITY: The new models are provided as open source programs at http://sfb.kaust.edu.sa/Pages/Software.aspx. CONTACT: [email protected], [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics Online.

We present results of scaling an ab initio motif family identification system, Dragon Motif Finder (DMF), to 65,536 processor cores of IBM Blue Gene/P. DMF seeks groups of mutually similar polynucleotide patterns within a set of genomic sequences and builds various motif families from them. Such information is of relevance to many problems in life sciences. Prior attempts to scale such ab initio motif-finding algorithms achieved limited success. We solve the scalability issues using a combination of mixed-mode MPI-OpenMP parallel programming, master-slave work assignment, multi-level workload distribution, multi-level MPI collectives, and serial optimizations. While the scalability of our algorithm was excellent (94% parallel efficiency on 65,536 cores relative to 256 cores on a modest-size problem), the final speedup with respect to the original serial code exceeded 250,000 when serial optimizations are included. This enabled us to carry out many large-scale ab initio motif-finding simulations in a few hours while the original serial code would have needed decades of execution time.

10.1109/IJCNN.2008.4633821

UNLABELLED: Dragon Promoter Mapper (DPM) is a tool to model promoter structure of co-regulated genes using methodology of Bayesian networks. DPM exploits an exhaustive set of motif features (such as motif, its strand, the order of motif occurrence and mutual distance between the adjacent motifs) and generates models from the target promoter sequences, which may be used to (1) detect regions in a genomic sequence which are similar to the target promoters or (2) to classify other promoters as similar or not to the target promoter group. DPM can also be used for modelling of enhancers and silencers. AVAILABILITY: http://defiant.i2r.a-star.edu.sg/projects/BayesPromoter/ CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Manual for using DPM web server is provided at http://defiant.i2r.a-star.edu.sg/projects/BayesPromoter/html/manual/manual.htm.

BACKGROUND: Mammalian antimicrobial peptides (AMPs) are effectors of the innate immune response. A multitude of signals coming from pathways of mammalian pathogen/pattern recognition receptors and other proteins affect the expression of AMP-coding genes (AMPcgs). For many AMPcgs the promoter elements and transcription factors that control their tissue cell-specific expression have yet to be fully identified and characterized. RESULTS: Based upon the RIKEN full-length cDNA and public sequence data derived from human, mouse and rat, we identified 178 candidate AMP transcripts derived from 61 genes belonging to 29 AMP families. However, only for 31 mouse genes belonging to 22 AMP families we were able to determine true orthologous relationships with 30 human and 15 rat sequences. We screened the promoter regions of AMPcgs in the three species for motifs by an ab initio motif finding method and analyzed the derived promoter characteristics. Promoter models were developed for alpha-defensins, penk and zap AMP families. The results suggest a core set of transcription factors (TFs) that regulate the transcription of AMPcg families in mouse, rat and human. The three most frequent core TFs groups include liver-, nervous system-specific and nuclear hormone receptors (NHRs). Out of 440 motifs analyzed, we found that three represent potentially novel TF-binding motifs enriched in promoters of AMPcgs, while the other four motifs appear to be species-specific. CONCLUSION: Our large-scale computational analysis of promoters of 22 families of AMPcgs across three mammalian species suggests that their key transcriptional regulators are likely to be TFs of the liver-, nervous system-specific and NHR groups. The computationally inferred promoter elements and potential TF binding motifs provide a rich resource for targeted experimental validation of TF binding and signaling studies that aim at the regulation of mouse, rat or human AMPcgs.

MOTIVATION: Histone proteins play important roles in chromosomal functions. They are significantly evolutionarily conserved across species, which suggests similarity in their transcription regulation. The abundance of experimental data on histone promoters provides an excellent background for the evaluation of computational methods. Our study addresses the issue of how well computational analysis can contribute to unveiling the biologically relevant content of promoter regions for a large number of mammalian histone genes taken across several species, and suggests the consensus promoter models of different histone groups. RESULTS: This is the first study to unveil the detailed promoter structures of all five mammalian histone groups and their subgroups. This is also the most comprehensive computational analysis of histone promoters performed to date. The most exciting fact is that the results correlate very well with the biologically known facts and experimental data. Our analysis convincingly demonstrates that computational approach can significantly contribute to elucidation of promoter content (identification of biologically relevant signals) complementing tedious wet-lab experiments. We believe that this type of analysis can be easily applied to other functional gene classes, thus providing a general framework for modelling promoter groups. These results also provide the basis to hunt for genes co-regulated with histone genes across mammalian genomes.

Prediction using linear interpolation works well in systems where the destabilizing effects of long dead-times are not dominant. When the process contains a long dead-time, prediction using linear derivative control will not work because the measured signal will not contain sufficient information about any future changes that may occur in the loop. Under these conditions, the anticipatory nature of the derivative controller fails to ensure proper control of deadtime dominant processes. This paper proposes a fuzzy logic tuned, polynomial based nonlinear predictor to improve the control of plants experiencing instability due to long dead-times. The proposed predictor replaces the derivative controller in a PID controller, and contributes towards a general improvement of the control performance in systems having long dead-times.

Abstract Summary: Dragon Promoter Finder (DPF) locates RNA polymerase II promoters in DNA sequences of vertebrates by predicting Transcription Start Site (TSS) positions. DPF’s algorithm uses sensors for three functional regions (promoters, exons and introns) and an Artificial Neural Network (ANN). Results on a large and diverse evaluation set indicate that DPF exhibits a superior predicting ability for TSS location compared to three other promoter-finding programs. Availability: http://sdmc.krdl.org.sg:8080/promoter/ Contact: [email protected] * To whom correspondence should be addressed.

The abundance of computer software for different types of prediction in DNA and protein sequence analyses raises the problem of adequate ranking of prediction program quality. A single measure of success of predictor software, which adequately ranks the predictors, does not exist. A typical example of such an incomplete measure is the so-called correlation coefficient. This paper provides an overview and short analysis of several different measures of prediction quality. Frequently, some of these measures give results contradictory to each other even when they relate to the same prediction scores. This may lead to confusion. In order to overcome some of the problems, a few new measures are proposed including some variants of a 'generalised distance from the ideal predictor score'; these are based on topological properties, rather than on statistics. In order to provide a sort of a balanced ranking, the averaged score measure (ASM) is introduced. The ASM provides a possibility for the selection of the predictor that probably has the best overall performance. The method presented in the paper applies to the ranking problem of any prediction software whose results can be properly represented in a true positive-false positive framework, thus providing a natural set-up for linear biological sequence analysis.