Automatic prediction of non-coding RNA genes in prokaryotes based on compositional statistics

Although non-coding RNA (ncRNA) genes do not encode proteins, they play vital roles in cells by producing functionally important RNAs. In this paper, we present a novel method for predicting ncRNA genes based on compositional features extracted directly from gene sequences. Our method consists of two Support Vector Machine (SVM) models--Codon model which uses codon usage features derived from ncRNA genes and protein-coding genes and Kmer model which utilizes features of nucleotide and dinucleotide frequency extracted respectively from ncRNA genes and randomly chosen genome sequences. The 10-fold cross-validation accuracy for the two models is found to be 92% and 91%, respectively. Thus, we could make an automatic prediction of ncRNA genes in one genome without manual filtration of protein-coding genes. After applying our method in Sulfolobus solfataricus genome, 25 prediction results have been generated according to 25 cut-off pairs. We have also applied the approach in E. coli and found our results comparable to those of previous studies. In general, our method enables automatic identification of ncRNA genes in newly sequenced prokaryotic genomes.     

PSoL: a positive sample only learning algorithm for finding non-coding RNA genes

MOTIVATION: Small non-coding RNA (ncRNA) genes play important regulatory roles in a variety of cellular processes. However, detection of ncRNA genes is a great challenge to both experimental and computational approaches. In this study, we describe a new approach called positive sample only learning (PSoL) to predict ncRNA genes in the Escherichia coli genome. Although PSoL is a machine learning method for classification, it requires no negative training data, which, in general, is hard to define properly and affects the performance of machine learning dramatically. In addition, using the support vector machine (SVM) as the core learning algorithm, PSoL can integrate many different kinds of information to improve the accuracy of prediction. Besides the application of PSoL for predicting ncRNAs, PSoL is applicable to many other bioinformatics problems as well. RESULTS: The PSoL method is assessed by 5-fold cross-validation experiments which show that PSoL can achieve about 80% accuracy in recovery of known ncRNAs. We compared PSoL predictions with five previously published results. The PSoL method has the highest percentage of predictions overlapping with those from other methods.     

Sequence-based heuristics for faster annotation of non-coding RNA families

MOTIVATION: Non-coding RNAs (ncRNAs) are functional RNA molecules that do not code for proteins. Covariance Models (CMs) are a useful statistical tool to find new members of an ncRNA gene family in a large genome database, using both sequence and, importantly, RNA secondary structure information. Unfortunately, CM searches are extremely slow. Previously, we created rigorous filters, which provably sacrifice none of a CM's accuracy, while making searches significantly faster for virtually all ncRNA families. However, these rigorous filters make searches slower than heuristics could be. RESULTS: In this paper we introduce profile HMM-based heuristic filters. We show that their accuracy is usually superior to heuristics based on BLAST. Moreover, we compared our heuristics with those used in tRNAscan-SE, whose heuristics incorporate a significant amount of work specific to tRNAs, where our heuristics are generic to any ncRNA. Performance was roughly comparable, so we expect that our heuristics provide a high-quality solution that--unlike family-specific solutions--can scale to hundreds of ncRNA families. AVAILABILITY: The source code is available under GNU Public License at the supplementary web site.     

Designing filters for fast-known NcRNA identification

Detecting members of known noncoding RNA (ncRNA) families in genomic DNA is an important part of sequence annotation. However, the most widely used tool for modeling ncRNA families, the covariance model (CM), incurs a high-computational cost when used for genome-wide search. This cost can be reduced by using a filter to exclude sequences that are unlikely to contain the ncRNA of interest, applying the CM only where it is likely to match strongly. Despite recent advances, designing an efficient filter that can detect ncRNA instances lacking strong conservation while excluding most irrelevant sequences remains challenging. In this work, we design three types of filters based on multiple secondary structure profiles (SSPs). An SSP augments a regular profile (i.e., a position weight matrix) with secondary structure information but can still be efficiently scanned against long sequences. Multi-SSPbased filters combine evidence from multiple SSP matches and can achieve high sensitivity and specificity. Our SSP-based filters are extensively tested in BRAliBase III data set, Rfam 9.0, and a published soil metagenomic data set. In addition, we compare the SSPbased filters with several other ncRNA search tools including Infernal (with profile HMMs as filters), ERPIN, and tRNAscan-SE. Our experiments demonstrate that carefully designed SSP filters can achieve significant speedup over unfiltered CM search while maintaining high sensitivity for various ncRNA families. The designed filters and filter-scanning programs are available at our website: www.cse.msu.edu/~yannisun/ssp/.     

Deep Learning and Its Applications in Biomedicine

Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of human health and disease. Developed from artificial neural networks, deep learning-based algorithms show great promise in extracting features and learning patterns from complex data. The aim of this paper is to provide an overview of deep learning techniques and some of the state-of-the-art applications in the biomedical field. We first introduce the development of artificial neural network and deep learning. We then describe two main components of deep learning, i.e., deep learning architectures and model optimization. Subsequently, some examples are demonstrated for deep learning applications, including medical image classification, genomic sequence analysis, as well as protein structure classification and prediction. Finally, we offer our perspectives for the future directions in the field of deep learning.     

利用不同G+C含量细菌基因组评估细菌ncRNA基因预测工具

【目的】为识别已完成全测序细菌基因组中的ncRNA基因,对3个常用ncRNA预测工具s RNAPredict、PORTRAIT和s RNAscanner进行评估。【方法】选择了细菌ncRNA数据库BSRD收录的含有已知ncRNA基因数目大于30的9个细菌基因组,并按基因组G+C含量进行分类,比较s RNAPredict和PORTRAIT工具的预测准确性。提取不同G+C含量基因组中ncRNA基因转录起始和终止区的序列特征,对s RNAscanner预测结果进行评估。【结果】s RNAPredict对细菌ncRNA基因的预测特异性和阳性检出率均高于PORTRAIT,而敏感性则较差;两种工具预测效果均随基因组G+C含量不同而产生明显变化。在不同G+C含量的细菌基因组中,ncRNA基因启动子和终止子区域的序列特征有明显差异。利用这些序列特征能提高s RNAscanner预测ncRNA基因的平均水平。【结论】3种ncRNA基因工具预测效果随基因组G+C含量变化而不同。不同G+C含量基因组中ncRNA基因的转录起始和终止区特征可作为ncRNA基因预测的重要参数之一。     

Decoding microRNA drivers in atherosclerosis

An estimated 97% of the human genome consists of non-protein-coding sequences. As our understanding of genome regulation improves, this has led to the characterization of a diverse array of non-coding RNAs (ncRNA). Among these, micro-RNAs (miRNAs) belong to the short ncRNA class (22–25 nucleotides in length), with approximately 2500 miRNA genes encoded within the human genome. From a therapeutic perspective, there is interest in exploiting miRNA as biomarkers of disease progression and response to treatments, as well as miRNA mimics/repressors as novel medicines. miRNA have emerged as an important class of RNA master regulators with important roles identified in the pathogenesis of atherosclerotic cardiovascular disease. Atherosclerosis is characterized by a chronic inflammatory build-up, driven largely by low-density lipoprotein cholesterol accumulation within the artery wall and vascular injury, including endothelial dysfunction, leukocyte recruitment and vascular remodelling. Conventional therapy focuses on lifestyle interventions, blood pressure-lowering medications, high-intensity statin therapy and antiplatelet agents. However, a significant proportion of patients remain at increased risk of cardiovascular disease. This continued cardiovascular risk is referred to as residual risk. Hence, a new drug class targeting atherosclerosis could synergise with existing therapies to optimise outcomes. Here, we review our current understanding of the role of ncRNA, with a focus on miRNA, in the development and progression of atherosclerosis, highlighting novel biological mechanisms and therapeutic avenues.     

Bistability in gene transcription: interplay of messenger RNA, protein, and nonprotein coding RNA

The author proposes a kinetic model describing the interplay of messenger ribonucleic acid (mRNA), protein, produced via translation of this RNA, and nonprotein coding RNA (ncRNA). The model includes association of mRNA and ncRNA and regulation of the ncRNA production by protein. In the case of positive feedback between the production of protein and ncRNA, the steady state of the system is found to be unique. For negative feedback, the model predicts in the mean-field case either unique steady state or bistable kinetics. With incorporation of fluctuations, the bistability is manifested in the form of kinetic bursts provided that the number of reactants is low. Basically, the model describes the simplest biological switch operating with participation of ncRNA. Although the results obtained are applicable to ncRNSs in general, the presentation is focused primarily on microRNAs (miRNAs) which form a large important subclass of ncRNAs and are thought to regulate up to one third of all human genes.     

Evolutionary Modeling and Prediction of Non-Coding RNAs in Drosophila

We performed benchmarks of phylogenetic grammar-based ncRNA gene prediction, experimenting with eight different models of structural evolution and two different programs for genome alignment. We evaluated our models using alignments of twelve Drosophila genomes. We find that ncRNA prediction performance can vary greatly between different gene predictors and subfamilies of ncRNA gene. Our estimates for false positive rates are based on simulations which preserve local islands of conservation; using these simulations, we predict a higher rate of false positives than previous computational ncRNA screens have reported. Using one of the tested prediction grammars, we provide an updated set of ncRNA predictions for D. melanogaster and compare them to previously-published predictions and experimental data. Many of our predictions show correlations with protein-coding genes. We found significant depletion of intergenic predictions near the 3′ end of coding regions and furthermore depletion of predictions in the first intron of protein-coding genes. Some of our predictions are colocated with larger putative unannotated genes: for example, 17 of our predictions showing homology to the RFAM family snoR28 appear in a tandem array on the X chromosome; the 4.5 Kbp spanned by the predicted tandem array is contained within a FlyBase-annotated cDNA.     

Deep learning for computational biology

Technological advances in genomics and imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples. This rapid increase in biological data dimension and acquisition rate is challenging conventional analysis strategies. Modern machine learning methods, such as deep learning, promise to leverage very large data sets for finding hidden structure within them, and for making accurate predictions. In this review, we discuss applications of this new breed of analysis approaches in regulatory genomics and cellular imaging. We provide background of what deep learning is, and the settings in which it can be successfully applied to derive biological insights. In addition to presenting specific applications and providing tips for practical use, we also highlight possible pitfalls and limitations to guide computational biologists when and how to make the most use of this new technology.     

生物医学数据分析中的深度学习方法应用

生物医学数据的积累速度史无前例,为生物医学研究带来机遇的同时,也让传统数据分析技术面临巨大挑战.本文综述了深度学习方法应用在生物医学数据分析中的最新研究进展.首先阐述了深度学习方法,列举深度学习方法的主要实现模型,随后总结了目前生物医学数据分析中的深度学习方法应用情况,分析了在数据处理、模型构建和训练方法等方面共有问题的解决方法,最后给出了深度学习方法应用于生物医学数据分析时可能存在的问题及建议.