A genetic algorithm-based weighted ensemble method for predicting transposon-derived piRNAs

Databases and computational methods for the identification of piRNA-related molecules: A survey

Piwi-interacting RNAs (piRNAs) are a class of small non-coding RNAs (ncRNAs) that plays important roles in many biological processes and major cancer diagnosis and treatment, thus becoming a hot research topic. This study aims to provide an in-depth review of computational piRNA-related research, including databases and computational models. Herein, we perform literature analysis and use comparative evaluation methods to summarize and analyze three aspects of computational piRNA-related research: (i) computational models for piRNA-related molecular identification tasks, (ii) computational models for piRNA-disease association prediction tasks, and (iii) computational resources and evaluation metrics for these tasks. This study shows that computational piRNA-related research has significantly progressed, exhibiting promising performance in recent years, whereas they also suffer from the emerging challenges of inconsistent naming systems and the lack of data. Different from other reviews on piRNA-related identification tasks that focus on the organization of datasets and computational methods, we pay more attention to the analysis of computational models, algorithms, and performances that aim to provide valuable references for computational piRNA-related identification tasks. This study will benefit the theoretical development and practical application of piRNAs by better understanding computational models and resources to investigate the biological functions and clinical implications of piRNA.

Guided optimization of ToxPi model weights using a Semi-Automated approach

The Toxicological Prioritization Index (ToxPi) is a visual analysis and decision support tool for dimension reduction and visualization of high throughput, multi-dimensional feature data. ToxPi was originally developed for assessing the relative toxicity of multiple chemicals or stressors by synthesizing complex toxicological data to provide a single comprehensive view of the potential health effects. It continues to be used for profiling chemicals and has since been applied to other types of "sample" entities, including geospatial (e.g. county-level Covid-19 risk and sites of historical PFAS exposure) and other profiling applications. For any set of features (data collected on a set of sample entities), ToxPi integrates the data into a set of weighted slices that provide a visual profile and a score metric for comparison. This scoring system is highly dependent on user-provided feature weights, yet users often lack knowledge of how to define these feature weights. Common methods for predicting feature weights are generally unusable due to inappropriate statistical assumptions and lack of global distributional expectation. However, users often have an inherent understanding of expected results for a small subset of samples. For example, in chemical toxicity, prior knowledge can often place subsets of chemicals into categories of low, moderate or high toxicity (reference chemicals). Ordinal regression can be used to predict weights based on these response levels that are applicable to the entire feature set, analogous to using positive and negative controls to contextualize an empirical distribution. We propose a semi-supervised method utilizing ordinal regression to predict a set of feature weights that produces the best fit for the known response ("reference") data and subsequently fine-tunes the weights via a customized genetic algorithm. We conduct a simulation study to show when this method can improve the results of ordinal regression, allowing for accurate feature weight prediction and sample ranking in scenarios with minimal response data. To ground-truth the guided weight optimization, we test this method on published data to build a ToxPi model for comparison against expert-knowledge-driven weight assignments.

Stacking-ac4C: an ensemble model using mixed features for identifying n4-acetylcytidine in mRNA

N4-acetylcytidine (ac4C) is a modification of cytidine at the nitrogen-4 position, playing a significant role in the translation process of mRNA. However, the precise mechanism and details of how ac4C modifies translated mRNA remain unclear. Since identifying ac4C sites using conventional experimental methods is both labor-intensive and time-consuming, there is an urgent need for a method that can promptly recognize ac4C sites. In this paper, we propose a comprehensive ensemble learning model, the Stacking-based heterogeneous integrated ac4C model, engineered explicitly to identify ac4C sites. This innovative model integrates three distinct feature extraction methodologies: Kmer, electron-ion interaction pseudo-potential values (PseEIIP), and pseudo-K-tuple nucleotide composition (PseKNC). The model also incorporates the robust Cluster Centroids algorithm to enhance its performance in dealing with imbalanced data and alleviate underfitting issues. Our independent testing experiments indicate that our proposed model improves the Mcc by 15.61% and the ROC by 5.97% compared to existing models. To test our model's adaptability, we also utilized a balanced dataset assembled by the authors of iRNA-ac4C. Our model showed an increase in Sn of 4.1%, an increase in Acc of nearly 1%, and ROC improvement of 0.35% on this balanced dataset. The code for our model is freely accessible at https://github.com/louliliang/ST-ac4C.git, allowing users to quickly build their model without dealing with complicated mathematical equations.

LSTM4piRNA: Efficient piRNA Detection in Large-Scale Genome Databases Using a Deep Learning-Based LSTM Network

Piwi-interacting RNAs (piRNAs) are a new class of small, non-coding RNAs, crucial in the regulation of gene expression. Recent research has revealed links between piRNAs, viral defense mechanisms, and certain human cancers. Due to their clinical potential, there is a great interest in identifying piRNAs from large genome databases through efficient computational methods. However, piRNAs lack conserved structure and sequence homology across species, which makes piRNA detection challenging. Current detection algorithms heavily rely on manually crafted features, which may overlook or improperly use certain features. Furthermore, there is a lack of suitable computational tools for analyzing large-scale databases and accurately identifying piRNAs. To address these issues, we propose LSTM4piRNA, a highly efficient deep learning-based method for predicting piRNAs in large-scale genome databases. LSTM4piRNA utilizes a compact LSTM network that can effectively analyze RNA sequences from extensive datasets to detect piRNAs. It can automatically learn the dependencies among RNA sequences, and regularization is further integrated to reduce the generalization error. Comprehensive performance evaluations based on piRNAs from the piRBase database demonstrate that LSTM4piRNA outperforms current advanced methods and is well-suited for analysis with large-scale databases.

MiSiPi-Rna: an integrated tool for characterizing small regulatory RNA processing

RNA interference (RNAi) is mediated by small (20-30 nucleotide) RNAs that are produced by complex processing pathways. In animals, three main classes are recognized: microRNAs (miRNAs), small-interfering RNAs (siRNAs) and piwi-interacting RNAs (piRNAs). Understanding of small RNA pathways has benefited from genetic models where key enzymatic events were identified that lead to stereotypical positioning of small RNAs relative to precursor transcripts. Increasingly there is interest in using RNAi in non-model systems due to ease of generating synthetic small RNA precursors for research and biotechnology. Unfortunately, small RNAs are often rapidly evolving, requiring investigation of a species' endogenous small RNAs prior to deploying an RNAi approach. This can be accomplished through small non-coding RNA sequencing followed by applying various computational tools; however, the complexity and separately maintained packages lead to significant challenges for annotating global small RNA populations. To address this need, we developed a simple and efficient R package (MiSiPi-Rna) which can be used to characterize pre-selected loci with plots and statistics, aiding researchers understanding RNAi biology specific to their target species. Additionally, MiSiPi-Rna pioneers several computational approaches to identifying Dicer processing to assist annotation of miRNA and siRNA.

COVID-19 mortality prediction using ensemble learning and grey wolf optimization

COVID-19 is now often moderate and self-recovering, but in a significant proportion of individuals, it is severe and deadly. Determining whether individuals are at high risk for serious disease or death is crucial for making appropriate treatment decisions. We propose a computational method to estimate the mortality risk for patients with COVID-19. To develop the model, 4,711 reported cases confirmed as SARS-CoV-2 infections were used for model development. Our computational method was developed using ensemble learning in combination with a genetic algorithm. The best-performing ensemble model achieves an AUCROC (area under the receiver operating characteristic curve) value of 0.7802. The best ensemble model was developed using only 10 features, which means it requires less medical information so that the diagnostic cost may be reduced while the prognostic time may be improved. The results demonstrate the robustness of the used method as well as the efficiency of the combination of machine learning and genetic algorithms in developing the ensemble model.

Implementation of ensemble machine learning algorithms on exome datasets for predicting early diagnosis of cancers

Classification of different cancer types is an essential step in designing a decision support model for early cancer predictions. Using various machine learning (ML) techniques with ensemble learning is one such method used for classifications. In the present study, various ML algorithms were explored on twenty exome datasets, belonging to 5 cancer types. Initially, a data clean-up was carried out on 4181 variants of cancer with 88 features, and a derivative dataset was obtained using natural language processing and probabilistic distribution. An exploratory dataset analysis using principal component analysis was then performed in 1 and 2D axes to reduce the high-dimensionality of the data. To significantly reduce the imbalance in the derivative dataset, oversampling was carried out using SMOTE. Further, classification algorithms such as K-nearest neighbour and support vector machine were used initially on the oversampled dataset. A 4-layer artificial neural network model with 1D batch normalization was also designed to improve the model accuracy. Ensemble ML techniques such as bagging along with using KNN, SVM and MLPs as base classifiers to improve the weighted average performance metrics of the model. However, due to small sample size, model improvement was challenging. Therefore, a novel method to augment the sample size using generative adversarial network (GAN) and triplet based variational auto encoder (TVAE) was employed that reconstructed the features and labels generating the data. The results showed that from initial scrutiny, KNN showed a weighted average of 0.74 and SVM 0.76. Oversampling ensured that the accuracy of the derivative dataset improved significantly and the ensemble classifier augmented the accuracy to 82.91%, when the data was divided into 70:15:15 ratio (training, test and holdout datasets). The overall evaluation metric value when GAN and TVAE increased the sample size was found to be 0.92 with an overall comparison model of 0.66. Therefore, the present study designed an effective model for classifying cancers which when implemented to real world samples, will play a major role in early cancer diagnosis.

PIWI-interacting RNAs in human diseases: databases and computational models

PIWI-interacting RNAs (piRNAs) are short 21-35 nucleotide molecules that comprise the largest class of non-coding RNAs and found in a large diversity of species including yeast, worms, flies, plants and mammals including humans. The most well-understood function of piRNAs is to monitor and protect the genome from transposons particularly in germline cells. Recent data suggest that piRNAs may have additional functions in somatic cells although they are expressed there in far lower abundance. Compared with microRNAs (miRNAs), piRNAs have more limited bioinformatics resources available. This review collates 39 piRNA specific and non-specific databases and bioinformatics resources, describes and compares their utility and attributes and provides an overview of their place in the field. In addition, we review 33 computational models based upon function: piRNA prediction, transposon element and mRNA-related piRNA prediction, cluster prediction, signature detection, target prediction and disease association. Based on the collection of databases and computational models, we identify trends and potential gaps in tool development. We further analyze the breadth and depth of piRNA data available in public sources, their contribution to specific human diseases, particularly in cancer and neurodegenerative conditions, and highlight a few specific piRNAs that appear to be associated with these diseases. This briefing presents the most recent and comprehensive mapping of piRNA bioinformatics resources including databases, models and tools for disease associations to date. Such a mapping should facilitate and stimulate further research on piRNAs.

Identification of Functional piRNAs Using a Convolutional Neural Network

Piwi-interacting RNAs (piRNAs) are a distinct sub-class of small non-coding RNAs that are mainly responsible for germline stem cell maintenance, gene stability, and maintaining genome integrity by repression of transposable elements. piRNAs are also expressed aberrantly and associated with various kinds of cancers. To identify piRNAs and their role in guiding target mRNA deadenylation, the currently available computational methods require urgent improvements in performance. To facilitate this, we propose a robust predictor based on a lightweight and simplified deep learning architecture using a convolutional neural network (CNN) to extract significant features from raw RNA sequences without the need for more customized features. The proposed model's performance is comprehensively evaluated using k-fold cross-validation on a benchmark dataset. The proposed model significantly outperforms existing computational methods in the prediction of piRNAs and their role in target mRNA deadenylation. In addition, a user-friendly and publicly-accessible web server is available at http://nsclbio.jbnu.ac.kr/tools/2S-piRCNN/.

A Review of Discovery Profiling of PIWI-Interacting RNAs and Their Diverse Functions in Metazoans

PIWI-interacting RNAs (piRNAs) are a class of small non-coding RNAs (sncRNAs) that perform crucial biological functions in metazoans and defend against transposable elements (TEs) in germ lines. Recently, ubiquitously expressed piRNAs were discovered in soma and germ lines using small RNA sequencing (sRNA-seq) in humans and animals, providing new insights into the diverse functions of piRNAs. However, the role of piRNAs has not yet been fully elucidated, and sRNA-seq studies continue to reveal different piRNA activities in the genome. In this review, we summarize a set of simplified processes for piRNA analysis in order to provide a useful guide for researchers to perform piRNA research suitable for their study objectives. These processes can help expand the functional research on piRNAs from previously reported sRNA-seq results in metazoans. Ubiquitously expressed piRNAs have been discovered in the soma and germ lines in Annelida, Cnidaria, Echinodermata, Crustacea, Arthropoda, and Mollusca, but they are limited to germ lines in Chordata. The roles of piRNAs in TE silencing, gene expression regulation, epigenetic regulation, embryonic development, immune response, and associated diseases will continue to be discovered via sRNA-seq.

Bioinformatics and Machine Learning Approaches to Understand the Regulation of Mobile Genetic Elements

Simple Summary

Transposable elements (TEs) are DNA sequences that are, or were, able to move (transpose) within the genome of a single cell. They were first discovered by Barbara McClintock while working on maize, and they make up a large fraction of the genome. Transpositions can result in mutations and they can alter the genome size. Cells regulate the activity of TEs using a variety of mechanisms, such as chemical modifications of DNA and small RNAs. Machine learning (ML) is an interdisciplinary subject that studies computer algorithms that can improve through experience and by the use of data. ML has been successfully applied to a variety of problems in bioinformatics and has exhibited favorable precision and speed. Here, we provide a systematic and guided review on the ML and bioinformatic methods and tools that are used for the analysis of the regulation of TEs.

Abstract

Transposable elements (TEs, or mobile genetic elements, MGEs) are ubiquitous genetic elements that make up a substantial proportion of the genome of many species. The recent growing interest in understanding the evolution and function of TEs has revealed that TEs play a dual role in genome evolution, development, disease, and drug resistance. Cells regulate TE expression against uncontrolled activity that can lead to developmental defects and disease, using multiple strategies, such as DNA chemical modification, small RNA (sRNA) silencing, chromatin modification, as well as sequence-specific repressors. Advancements in bioinformatics and machine learning approaches are increasingly contributing to the analysis of the regulation mechanisms. A plethora of tools and machine learning approaches have been developed for prediction, annotation, and expression profiling of sRNAs, for methylation analysis of TEs, as well as for genome-wide methylation analysis through bisulfite sequencing data. In this review, we provide a guided overview of the bioinformatic and machine learning state of the art of fields closely associated with TE regulation and function.

Advances in Computational Methodologies for Classification and Sub-Cellular Locality Prediction of Non-Coding RNAs

Apart from protein-coding Ribonucleic acids (RNAs), there exists a variety of non-coding RNAs (ncRNAs) which regulate complex cellular and molecular processes. High-throughput sequencing technologies and bioinformatics approaches have largely promoted the exploration of ncRNAs which revealed their crucial roles in gene regulation, miRNA binding, protein interactions, and splicing. Furthermore, ncRNAs are involved in the development of complicated diseases like cancer. Categorization of ncRNAs is essential to understand the mechanisms of diseases and to develop effective treatments. Sub-cellular localization information of ncRNAs demystifies diverse functionalities of ncRNAs. To date, several computational methodologies have been proposed to precisely identify the class as well as sub-cellular localization patterns of RNAs). This paper discusses different types of ncRNAs, reviews computational approaches proposed in the last 10 years to distinguish coding-RNA from ncRNA, to identify sub-types of ncRNAs such as piwi-associated RNA, micro RNA, long ncRNA, and circular RNA, and to determine sub-cellular localization of distinct ncRNAs and RNAs. Furthermore, it summarizes diverse ncRNA classification and sub-cellular localization determination datasets along with benchmark performance to aid the development and evaluation of novel computational methodologies. It identifies research gaps, heterogeneity, and challenges in the development of computational approaches for RNA sequence analysis. We consider that our expert analysis will assist Artificial Intelligence researchers with knowing state-of-the-art performance, model selection for various tasks on one platform, dominantly used sequence descriptors, neural architectures, and interpreting inter-species and intra-species performance deviation.

The biogenesis and biological function of PIWI-interacting RNA in cancer

Small non-coding RNAs (ncRNAs) are vital regulators of biological activities, and aberrant levels of small ncRNAs are commonly found in precancerous lesions and cancer. PIWI-interacting RNAs (piRNAs) are a novel type of small ncRNA initially discovered in germ cells that have a specific length (24-31 nucleotides), bind to PIWI proteins, and show 2'-O-methyl modification at the 3'-end. Numerous studies have revealed that piRNAs can play important roles in tumorigenesis via multiple biological regulatory mechanisms, including silencing transcriptional and posttranscriptional gene processes and accelerating multiprotein interactions. piRNAs are emerging players in the malignant transformation of normal cells and participate in the regulation of cancer hallmarks. Most of the specific cancer hallmarks regulated by piRNAs are involved in sustaining proliferative signaling, resistance to cell death or apoptosis, and activation of invasion and metastasis. Additionally, piRNAs have been used as biomarkers for cancer diagnosis and prognosis and have great potential for clinical utility. However, research on the underlying mechanisms of piRNAs in cancer is limited. Here, we systematically reviewed recent advances in the biogenesis and biological functions of piRNAs and relevant bioinformatics databases with the aim of providing insights into cancer diagnosis and clinical applications. We also focused on some cancer hallmarks rarely reported to be related to piRNAs, which can promote in-depth research of piRNAs in molecular biology and facilitate their clinical translation into cancer treatment.

Quantitative Toxicity Prediction via Meta Ensembling of Multitask Deep Learning Models

Toxicity prediction using quantitative structure-activity relationship has achieved significant progress in recent years. However, most existing machine learning methods in toxicity prediction utilize only one type of feature representation and one type of neural network, which essentially restricts their performance. Moreover, methods that use more than one type of feature representation struggle with the aggregation of information captured within the features since they use predetermined aggregation formulas. In this paper, we propose a deep learning framework for quantitative toxicity prediction using five individual base deep learning models and their own base feature representations. We then propose to adopt a meta ensemble approach using another separate deep learning model to perform aggregation of the outputs of the individual base deep learning models. We train our deep learning models in a weighted multitask fashion combining four quantitative toxicity data sets of LD50, IGC50, LC50, and LC50-DM and minimizing the root-mean-square errors. Compared to the current state-of-the-art toxicity prediction method TopTox on LD50, IGC50, and LC50-DM, that is, three out of four data sets, our method, respectively, obtains 5.46, 16.67, and 6.34% better root-mean-square errors, 6.41, 11.80, and 12.16% better mean absolute errors, and 5.21, 7.36, and 2.54% better coefficients of determination. We named our method QuantitativeTox, and our implementation is available from the GitHub repository https://github.com/Abdulk084/QuantitativeTox.

Emerging Classes of Small Non-Coding RNAs With Potential Implications in Diabetes and Associated Metabolic Disorders

Most of the sequences in the human genome do not code for proteins but generate thousands of non-coding RNAs (ncRNAs) with regulatory functions. High-throughput sequencing technologies and bioinformatic tools significantly expanded our knowledge about ncRNAs, highlighting their key role in gene regulatory networks, through their capacity to interact with coding and non-coding RNAs, DNAs and proteins. NcRNAs comprise diverse RNA species, including amongst others PIWI-interacting RNAs (piRNAs), involved in transposon silencing, and small nucleolar RNAs (snoRNAs), which participate in the modification of other RNAs such as ribosomal RNAs and transfer RNAs. Recently, a novel class of small ncRNAs generated from the cleavage of tRNAs or pre-tRNAs, called tRNA-derived small RNAs (tRFs) has been identified. tRFs have been suggested to regulate protein translation, RNA silencing and cell survival. While for other ncRNAs an implication in several pathologies is now well established, the potential involvement of piRNAs, snoRNAs and tRFs in human diseases, including diabetes, is only beginning to emerge. In this review, we summarize fundamental aspects of piRNAs, snoRNAs and tRFs biology. We discuss their biogenesis while emphasizing on novel sequencing technologies that allow ncRNA discovery and annotation. Moreover, we give an overview of genomic approaches to decrypt their mechanisms of action and to study their functional relevance. The review will provide a comprehensive landscape of the regulatory roles of these three types of ncRNAs in metabolic disorders by reporting their differential expression in endocrine pancreatic tissue as well as their contribution to diabetes incidence and diabetes-underlying conditions such as inflammation. Based on these discoveries we discuss the potential use of piRNAs, snoRNAs and tRFs as promising therapeutic targets in metabolic disorders.

Computational Methods and Online Resources for Identification of piRNA-Related Molecules

piRNAs are a class of small non-coding RNA molecules, which interact with the PIWI family and have many important and diverse biological functions. The present review is aimed to provide guidelines and contribute to piRNA research. We focused on the four types of identification models on piRNA-related molecules, including piRNA, piRNA cluster, piRNA target, and disease-related piRNA. We evaluated the types of tools for the identification of piRNAs based on five aspects: datasets, features, classifiers, performance, and usability. We found the precision of 2lpiRNApred was the highest in datasets of model organisms, piRNN had a better performance of datasets of non-model organisms, and 2L-piRNA had the fastest recognition speed of all tools. In addition, we presented an overview of piRNA databases. The databases were divided into six categories: basic annotation, comprehensive annotation, isoform, cluster, target, and disease. We found that piRNA data of non-model organisms, piRNA target data, and piRNA-disease-associated data should be strengthened. Our review might assist researchers in selecting appropriate tools or datasets for their studies, reveal potential problems and shed light on future bioinformatics studies.

Roles of Noncoding RNAs in Islet Biology

The discovery that most mammalian genome sequences are transcribed to ribonucleic acids (RNA) has revolutionized our understanding of the mechanisms governing key cellular processes and of the causes of human diseases, including diabetes mellitus. Pancreatic islet cells were found to contain thousands of noncoding RNAs (ncRNAs), including micro-RNAs (miRNAs), PIWI-associated RNAs, small nucleolar RNAs, tRNA-derived fragments, long non-coding RNAs, and circular RNAs. While the involvement of miRNAs in islet function and in the etiology of diabetes is now well documented, there is emerging evidence indicating that other classes of ncRNAs are also participating in different aspects of islet physiology. The aim of this article will be to provide a comprehensive and updated view of the studies carried out in human samples and rodent models over the past 15 years on the role of ncRNAs in the control of α- and β-cell development and function and to highlight the recent discoveries in the field. We not only describe the role of ncRNAs in the control of insulin and glucagon secretion but also address the contribution of these regulatory molecules in the proliferation and survival of islet cells under physiological and pathological conditions. It is now well established that most cells release part of their ncRNAs inside small extracellular vesicles, allowing the delivery of genetic material to neighboring or distantly located target cells. The role of these secreted RNAs in cell-to-cell communication between β-cells and other metabolic tissues as well as their potential use as diabetes biomarkers will be discussed. © 2020 American Physiological Society. Compr Physiol 10:893-932, 2020.

2lpiRNApred: a two-layered integrated algorithm for identifying piRNAs and their functions based on LFE-GM feature selection

Piwi-interacting RNAs (piRNAs) are indispensable in the transposon silencing, including in germ cell formation, germline stem cell maintenance, spermatogenesis, and oogenesis. piRNA pathways are amongst the major genome defence mechanisms, which maintain genome integrity. They also have important functions in tumorigenesis, as indicated by aberrantly expressed piRNAs being recently shown to play roles in the process of cancer development. A number of computational methods for this have recently been proposed, but they still have not yielded satisfactory predictive performance. Moreover, only one computational method that identifies whether piRNAs function in inducting target mRNA deadenylation been reported in the literature. In this study, we developed a two-layered integrated classifier algorithm, 2lpiRNApred. It identifies piRNAs in the first layer and determines whether they function in inducting target mRNA deadenylation in the second layer. A new feature selection algorithm, which was based on Luca fuzzy entropy and Gaussian membership function (LFE-GM), was proposed to reduce the dimensionality of the features. Five feature extraction strategies, namely, Kmer, General parallel correlation pseudo-dinucleotide composition, General series correlation pseudo-dinucleotide composition, Normalized Moreau-Broto autocorrelation, and Geary autocorrelation, and two types of classifier, Sparse Representation Classifier (SRC) and support vector machine with Mahalanobis distance-based radial basis function (SVMMDRBF), were used to construct a two-layered integrated classifier algorithm, 2lpiRNApred. The results indicate that 2lpiRNApred performs significantly better than six other existing prediction tools.

A comprehensive comparison and analysis of computational predictors for RNA N6-methyladenosine sites of Saccharomyces cerevisiae

N6-methyladenosine (m6A) modification, as one of the commonest post-transcription modifications in RNAs, has been reported to be highly related to many biological processes. Over the past decade, several tools for m6A sites prediction of Saccharomyces cerevisiae have been developed and are freely available online. However, the quality of predictions by these tools is difficult to quantify and compare. In this study, an independent dataset M6Atest6540 was compiled to systematically evaluate nine publicly available m6A prediction tools for S. cerevisiae. The experimental results indicate that RAM-ESVM achieved the best performance on M6Atest6540; however, most models performed substantially worse than their performances reported in the original papers. The benchmark dataset Met2614, which was used as the training dataset for the nine methods, were further analyzed by using a position bias index. The results demonstrated the significantly different bias of dataset Met2614 compared with the RNA segments around m6A sites recorded in RMBase. Moreover, newMet2614 was collected by randomly selecting RNA segments from non-redundant data recorded in RMBase, and three different kinds of features were extracted. The performances of the models built on Met2614 and newMet2614 with the features were compared, which shows the better generalization of models built on newMet2614. Our results also indicate the position-specific propensity-based features outperform other features, although they are also easily over-fitted on a biased dataset.

Mobile genomics: tools and techniques for tackling transposons

Next-generation sequencing approaches have fundamentally changed the types of questions that can be asked about gene function and regulation. With the goal of approaching truly genome-wide quantifications of all the interaction partners and downstream effects of particular genes, these quantitative assays have allowed for an unprecedented level of detail in exploring biological interactions. However, many challenges remain in our ability to accurately describe and quantify the interactions that take place in those hard to reach and extremely repetitive regions of our genome comprised mostly of transposable elements (TEs). Tools dedicated to TE-derived sequences have lagged behind, making the inclusion of these sequences in genome-wide analyses difficult. Recent improvements, both computational and experimental, allow for the better inclusion of TE sequences in genomic assays and a renewed appreciation for the importance of TE biology. This review will discuss the recent improvements that have been made in the computational analysis of TE-derived sequences as well as the areas where such analysis still proves difficult. This article is part of a discussion meeting issue 'Crossroads between transposons and gene regulation'.

Is There Any Sequence Feature in the RNA Pseudouridine Modification Prediction Problem?

Pseudouridine (Ψ) is the most abundant RNA modification and has been found in many kinds of RNAs, including snRNA, rRNA, tRNA, mRNA, and snoRNA. Thus, Ψ sites play a significant role in basic research and drug development. Although some experimental techniques have been developed to identify Ψ sites, they are expensive and time consuming, especially in the post-genomic era with the explosive growth of known RNA sequences. Thus, highly accurate computational methods are urgently required to quickly detect the Ψ sites on uncharacterized RNA sequences. Several predictors have been proposed using multifarious features, but their evaluated performances are still unsatisfactory. In this study, we first identified Ψ sites for H. sapiens, S. cerevisiae, and M. musculus using the sequence features from the bi-profile Bayes (BPB) method based on the random forest (RF) and support vector machine (SVM) algorithms, where the performances were evaluated using 5-fold cross-validation and independent tests. It was found that the SVM-based accuracies were 3.55% and 5.09% lower than the iPseU-CUU predictor for the H_990 and S_628 datasets, respectively. Almost the same-level results were obtained for M_994 and an independent H_200 dataset, even showing a 5.0% improvement for S_200. Then, three different kinds of features, including basic Kmer, general parallel correlation pseudo-dinucleotide composition (PC-PseDNC-General), and nucleotide chemical property (NCP) and nucleotide density (ND) from the iRNA-PseU method, were combined with BPB to show their comprehensive performances, where the effective features are selected by the max-relevance-max-distance (MRMD) method. The best evaluated accuracies of the combined features for the S_628 and M_994 datasets were achieved at 70.54% and 72.45%, which were 2.39% and 0.65% higher than iPseU-CUU. For the S_200 dataset, it was also improved 8% from 69% to 77%. However, there was no obvious improvement for H. sapiens, which was evaluated as approximately 63.23% and 72.0% for the H_990 and H_200 datasets, respectively. The overall performances for Ψ identification using BPB features as well as the combined features were not obviously improved. Although some kinds of feature extraction methods based on the RNA sequence information have been applied to construct the predictors in previous studies, the corresponding accuracies are generally in the range of 60%-70%. Thus, researchers need to reconsider whether there is any sequence feature in the RNA Ψ modification prediction problem.

Computational Identification of piRNAs Using Features Based on RNA Sequence, Structure, Thermodynamic and Physicochemical Properties

Rationale

PIWI-interacting RNAs (piRNAs) are a recently-discovered class of small non-coding RNAs (ncRNAs) with a length of 21-35 nucleotides. They play a role in gene expression regulation, transposon silencing, and viral infection inhibition. Once considered as "dark matter" of ncRNAs, piRNAs emerged as important players in multiple cellular functions in different organisms. However, our knowledge of piRNAs is still very limited as many piRNAs have not been yet identified due to lack of robust computational predictive tools.

Methods

To identify novel piRNAs, we developed piRNAPred, an integrated framework for piRNA prediction employing hybrid features like k-mer nucleotide composition, secondary structure, thermodynamic and physicochemical properties. A non-redundant dataset (D³³⁴⁹ or D^1684p+1665n) comprising 1684 experimentally verified piRNAs and 1665 non-piRNA sequences was obtained from piRBase and NONCODE, respectively. These sequences were subjected to the computation of various sequence-structure based features in binary format and trained using different machine learning techniques, of which support vector machine (SVM) performed the best.

Results

During the ten-fold cross-validation approach (10-CV), piRNAPred achieved an overall accuracy of 98.60% with Mathews correlation coefficient (MCC) of 0.97 and receiver operating characteristic (ROC) of 0.99. Furthermore, we achieved a dimensionality reduction of feature space using an attribute selected classifier.

Conclusion

We obtained the highest performance in accurately predicting piRNAs as compared to the current state-of-the-art piRNA predictors. In conclusion, piRNAPred would be helpful to expand the piRNA repertoire, and provide new insights on piRNA functions.

LncRNA-miRNA interaction prediction through sequence-derived linear neighborhood propagation method with information combination

BACKGROUND

Researchers discover lncRNAs can act as decoys or sponges to regulate the behavior of miRNAs. Identification of lncRNA-miRNA interactions helps to understand the functions of lncRNAs, especially their roles in complicated diseases. Computational methods can save time and reduce cost in identifying lncRNA-miRNA interactions, but there have been only a few computational methods.

RESULTS

In this paper, we propose a sequence-derived linear neighborhood propagation method (SLNPM) to predict lncRNA-miRNA interactions. First, we calculate the integrated lncRNA-lncRNA similarity and the integrated miRNA-miRNA similarity by combining known lncRNA-miRNA interactions, lncRNA sequences and miRNA sequences. We consider two similarity calculation strategies respectively, namely similarity-based information combination (SC) and interaction profile-based information combination (PC). Second, the integrated lncRNA similarity-based graph and the integrated miRNA similarity-based graph are respectively constructed, and the label propagation processes are implemented on two graphs to score lncRNA-miRNA pairs. Finally, the weighted averages of their outputs are adopted as final predictions. Therefore, we construct two editions of SLNPM: sequence-derived linear neighborhood propagation method based on similarity information combination (SLNPM-SC) and sequence-derived linear neighborhood propagation method based on interaction profile information combination (SLNPM-PC). The experimental results show that SLNPM-SC and SLNPM-PC predict lncRNA-miRNA interactions with higher accuracy compared with other state-of-the-art methods. The case studies demonstrate that SLNPM-SC and SLNPM-PC help to find novel lncRNA-miRNA interactions for given lncRNAs or miRNAs.

CONCLUSION

The study reveals that known interactions bring the most important information for lncRNA-miRNA interaction prediction, and sequences of lncRNAs (miRNAs) also provide useful information. In conclusion, SLNPM-SC and SLNPM-PC are promising for lncRNA-miRNA interaction prediction.

Recent Advances in the Machine Learning-Based Drug-Target Interaction Prediction

BACKGROUND

The identification of drug-target interactions is a crucial issue in drug discovery. In recent years, researchers have made great efforts on the drug-target interaction predictions, and developed databases, software and computational methods.

RESULTS

In the paper, we review the recent advances in machine learning-based drug-target interaction prediction. First, we briefly introduce the datasets and data, and summarize features for drugs and targets which can be extracted from different data. Since drug-drug similarity and target-target similarity are important for many machine learning prediction models, we introduce how to calculate similarities based on data or features. Different machine learningbased drug-target interaction prediction methods can be proposed by using different features or information. Thus, we summarize, analyze and compare different machine learning-based prediction methods.

CONCLUSION

This study provides the guide to the development of computational methods for the drug-target interaction prediction.

A Random Forest Sub-Golgi Protein Classifier Optimized via Dipeptide and Amino Acid Composition Features

To gain insight into the malfunction of the Golgi apparatus and its relationship to various genetic and neurodegenerative diseases, the identification of sub-Golgi proteins, both cis-Golgi and trans-Golgi proteins, is of great significance. In this study, a state-of-art random forests sub-Golgi protein classifier, rfGPT, was developed. The rfGPT used 2-gap dipeptide and split amino acid composition for the feature vectors and was combined with the synthetic minority over-sampling technique (SMOTE) and an analysis of variance (ANOVA) feature selection method. The rfGPT was trained on a sub-Golgi protein sequence data set (137 sequences), with sequence identity less than 25%. For the optimal rfGPT classifier with 93 features, the accuracy (ACC) was 90.5%; the Matthews correlation coefficient (MCC) was 0.811; the sensitivity (Sn) was 92.6%; and the specificity (Sp) was 88.4%. The independent testing scores for the rfGPT were ACC = 90.6%; MCC = 0.696; Sn = 96.1%; and Sp = 69.2%. Although the independent testing accuracy was 4.4% lower than that for the best reported sub-Golgi classifier trained on a data set with 40% sequence identity (304 sequences), the rfGPT is currently the top sub-Golgi protein predictor utilizing feature vectors without any position-specific scoring matrix and its derivative features. Therefore, the rfGPT is a more practical tool, because no sequence alignment is required with tens of millions of protein sequences. To date, the rfGPT is the Golgi classifier with the best independent testing scores, optimized by training on smaller benchmark data sets. Feature importance analysis proves that the non-polar and aliphatic residues composition, the (aromatic residues) + (non-polar, aliphatic residues) dipeptide and aromatic residues composition between NH2-termial and COOH-terminal of protein sequences are the three top biological features for distinguishing the sub-Golgi proteins.

PredLnc-GFStack: A Global Sequence Feature Based on a Stacked Ensemble Learning Method for Predicting lncRNAs from Transcripts

Long non-coding RNAs (lncRNAs) are a class of RNAs with the length exceeding 200 base pairs (bps), which do not encode proteins, nevertheless, lncRNAs have many vital biological functions. A large number of novel transcripts were discovered as a result of the development of high-throughput sequencing technology. Under this circumstance, computational methods for lncRNA prediction are in great demand. In this paper, we consider global sequence features and propose a stacked ensemble learning-based method to predict lncRNAs from transcripts, abbreviated as PredLnc-GFStack. We extract the critical features from the candidate feature list using the genetic algorithm (GA) and then employ the stacked ensemble learning method to construct PredLnc-GFStack model. Computational experimental results show that PredLnc-GFStack outperforms several state-of-the-art methods for lncRNA prediction. Furthermore, PredLnc-GFStack demonstrates an outstanding ability for cross-species ncRNA prediction.

Identifying Plant Pentatricopeptide Repeat Coding Gene/Protein Using Mixed Feature Extraction Methods

Motivation: Pentatricopeptide repeat (PPR) is a triangular pentapeptide repeat domain that plays a vital role in plant growth. In this study, we seek to identify PPR coding genes and proteins using a mixture of feature extraction methods. We use four single feature extraction methods focusing on the sequence, physical, and chemical properties as well as the amino acid composition, and mix the features. The Max-Relevant-Max-Distance (MRMD) technique is applied to reduce the feature dimension. Classification uses the random forest, J48, and naïve Bayes with 10-fold cross-validation. Results: Combining two of the feature extraction methods with the random forest classifier produces the highest area under the curve of 0.9848. Using MRMD to reduce the dimension improves this metric for J48 and naïve Bayes, but has little effect on the random forest results. Availability and Implementation: The webserver is available at: http://server.malab.cn/MixedPPR/index.jsp.

Sequence-based bacterial small RNAs prediction using ensemble learning strategies

Background

Bacterial small non-coding RNAs (sRNAs) have emerged as important elements in diverse physiological processes, including growth, development, cell proliferation, differentiation, metabolic reactions and carbon metabolism, and attract great attention. Accurate prediction of sRNAs is important and challenging, and helps to explore functions and mechanism of sRNAs.

Results

In this paper, we utilize a variety of sRNA sequence-derived features to develop ensemble learning methods for the sRNA prediction. First, we compile a balanced dataset and four imbalanced datasets. Then, we investigate various sRNA sequence-derived features, such as spectrum profile, mismatch profile, reverse compliment k-mer and pseudo nucleotide composition. Finally, we consider two ensemble learning strategies to integrate all features for building ensemble learning models for the sRNA prediction. One is the weighted average ensemble method (WAEM), which uses the linear weighted sum of outputs from the individual feature-based predictors to predict sRNAs. The other is the neural network ensemble method (NNEM), which trains a deep neural network by combining diverse features. In the computational experiments, we evaluate our methods on these five datasets by using 5-fold cross validation. WAEM and NNEM can produce better results than existing state-of-the-art sRNA prediction methods.

Conclusions

WAEM and NNEM have great potential for the sRNA prediction, and are helpful for understanding the biological mechanism of bacteria.

SFPEL-LPI: Sequence-based feature projection ensemble learning for predicting LncRNA-protein interactions

LncRNA-protein interactions play important roles in post-transcriptional gene regulation, poly-adenylation, splicing and translation. Identification of lncRNA-protein interactions helps to understand lncRNA-related activities. Existing computational methods utilize multiple lncRNA features or multiple protein features to predict lncRNA-protein interactions, but features are not available for all lncRNAs or proteins; most of existing methods are not capable of predicting interacting proteins (or lncRNAs) for new lncRNAs (or proteins), which don’t have known interactions. In this paper, we propose the sequence-based feature projection ensemble learning method, “SFPEL-LPI”, to predict lncRNA-protein interactions. First, SFPEL-LPI extracts lncRNA sequence-based features and protein sequence-based features. Second, SFPEL-LPI calculates multiple lncRNA-lncRNA similarities and protein-protein similarities by using lncRNA sequences, protein sequences and known lncRNA-protein interactions. Then, SFPEL-LPI combines multiple similarities and multiple features with a feature projection ensemble learning frame. In computational experiments, SFPEL-LPI accurately predicts lncRNA-protein associations and outperforms other state-of-the-art methods. More importantly, SFPEL-LPI can be applied to new lncRNAs (or proteins). The case studies demonstrate that our method can find out novel lncRNA-protein interactions, which are confirmed by literature. Finally, we construct a user-friendly web server, available at http://www.bioinfotech.cn/SFPEL-LPI/.

LncRNA-protein interactions play important roles in post-transcriptional gene regulation, poly-adenylation, splicing and translation. Identification of lncRNA-protein interactions helps to understand lncRNA-related activities. In this paper, we propose a novel computational method “SFPEL-LPI” to predict lncRNA-protein interactions. SFPEL-LPI makes use of lncRNA sequences, protein sequences and known lncRNA-protein associations to extract features and calculate similarities for lncRNAs and proteins, and then combines them with a feature projection ensemble learning frame. SFPEL-LPI can predict unobserved interactions between lncRNAs and proteins, and also can make predictions for new lncRNAs (or proteins), which have no interactions with any proteins (or lncRNAs). SFPEL-LPI produces high-accuracy performances on the benchmark dataset when evaluated by five-fold cross validation, and outperforms state-of-the-art methods. The case studies demonstrate that SFPEL-LPI can find out novel associations, which are confirmed by literature. To facilitate the lncRNA-protein interaction prediction, we develop a user-friendly web server, available at http://www.bioinfotech.cn/SFPEL-LPI/.

Support Vector Machine Classifier for Accurate Identification of piRNA

Piwi-interacting RNA (piRNA) is a newly identified class of small non-coding RNAs. It can combine with PIWI proteins to regulate the transcriptional gene silencing process, heterochromatin modifications, and to maintain germline and stem cell function in animals. To better understand the function of piRNA, it is imperative to improve the accuracy of identifying piRNAs. In this study, the sequence information included the single nucleotide composition, and 16 dinucleotides compositions, six physicochemical properties in RNA, the position specificities of nucleotides both in N-terminal and C-terminal, and the proportions of the similar peptide sequence of both N-terminal and C-terminal in positive and negative samples, which were used to construct the feature vector. Then, the F-Score was applied to choose an optimal single type of features. By combining these selected features, we achieved the best results on the jackknife and the 5-fold cross-validation running 10 times based on the support vector machine algorithm. Moreover, we further evaluated the stability and robustness of our new method.

PredT4SE-Stack: Prediction of Bacterial Type IV Secreted Effectors From Protein Sequences Using a Stacked Ensemble Method

Gram-negative bacteria use various secretion systems to deliver their secreted effectors. Among them, type IV secretion system exists widely in a variety of bacterial species, and secretes type IV secreted effectors (T4SEs), which play vital roles in host-pathogen interactions. However, experimental approaches to identify T4SEs are time- and resource-consuming. In the present study, we aim to develop an in silico stacked ensemble method to predict whether a protein is an effector of type IV secretion system or not based on its sequence information. The protein sequences were encoded by the feature of position specific scoring matrix (PSSM)-composition by summing rows that correspond to the same amino acid residues in PSSM profiles. Based on the PSSM-composition features, we develop a stacked ensemble model PredT4SE-Stack to predict T4SEs, which utilized an ensemble of base-classifiers implemented by various machine learning algorithms, such as support vector machine, gradient boosting machine, and extremely randomized trees, to generate outputs for the meta-classifier in the classification system. Our results demonstrated that the framework of PredT4SE-Stack was a feasible and effective way to accurately identify T4SEs based on protein sequence information. The datasets and source code of PredT4SE-Stack are freely available at http://xbioinfo.sjtu.edu.cn/PredT4SE_Stack/index.php.

iNuc-ext-PseTNC: an efficient ensemble model for identification of nucleosome positioning by extending the concept of Chou's PseAAC to pseudo-tri-nucleotide composition

Nucleosome is a central element of eukaryotic chromatin, which composes of histone proteins and DNA molecules. It performs vital roles in many eukaryotic intra-nuclear processes, for instance, chromatin structure and transcriptional regulation formation. Identification of nucleosome positioning via wet lab is difficult; so, the attention is diverted towards the accurate intelligent automated prediction. In this regard, a novel intelligent automated model "iNuc-ext-PseTNC" is developed to identify the nucleosome positioning in genomes accurately. In this predictor, the sequences of DNA are mathematically represented by two different discrete feature extraction techniques, namely pseudo-tri-nucleotide composition (PseTNC) and pseudo-di-nucleotide composition. Several contemporary machine learning algorithms were examined. Further, the predictions of individual classifiers were integrated through an evolutionary genetic algorithm. The success rates of the ensemble model are higher than individual classifiers. After analyzing the prediction results, it is noticed that iNuc-ext-PseTNC model has achieved better performance in combination with PseTNC feature space, which are 94.3%, 93.14%, and 88.60% of accuracies using six-fold cross-validation test for the three benchmark datasets S₁, S₂, and S₃, respectively. The achieved outcomes exposed that the results of iNuc-ext-PseTNC model are prominent compared to the existing methods so far notifiable in the literature. It is ascertained that the proposed model might be more fruitful and a practical tool for rudimentary academia and research.

Sc-ncDNAPred: A Sequence-Based Predictor for Identifying Non-coding DNA in Saccharomyces cerevisiae

With the rapid development of high-speed sequencing technologies and the implementation of many whole genome sequencing project, research in the genomics is advancing from genome sequencing to genome synthesis. Synthetic biology technologies such as DNA-based molecular assemblies, genome editing technology, directional evolution technology and DNA storage technology, and other cutting-edge technologies emerge in succession. Especially the rapid growth and development of DNA assembly technology may greatly push forward the success of artificial life. Meanwhile, DNA assembly technology needs a large number of target sequences of known information as data support. Non-coding DNA (ncDNA) sequences occupy most of the organism genomes, thus accurate recognizing of them is necessary. Although experimental methods have been proposed to detect ncDNA sequences, they are expensive for performing genome wide detections. Thus, it is necessary to develop machine-learning methods for predicting non-coding DNA sequences. In this study, we collected the ncDNA benchmark dataset of Saccharomyces cerevisiae and reported a support vector machine-based predictor, called Sc-ncDNAPred, for predicting ncDNA sequences. The optimal feature extraction strategy was selected from a group included mononucleotide, dimer, trimer, tetramer, pentamer, and hexamer, using support vector machine learning method. Sc-ncDNAPred achieved an overall accuracy of 0.98. For the convenience of users, an online web-server has been built at: http://server.malab.cn/Sc_ncDNAPred/index.jsp.

piRNN: deep learning algorithm for piRNA prediction

Piwi-interacting RNAs (piRNAs) are the largest class of small non-coding RNAs discovered in germ cells. Identifying piRNAs from small RNA data is a challenging task due to the lack of conserved sequences and structural features of piRNAs. Many programs have been developed to identify piRNA from small RNA data. However, these programs have limitations. They either rely on extracting complicated features, or only demonstrate strong performance on transposon related piRNAs. Here we proposed a new program called piRNN for piRNA identification. For our software, we applied a convolutional neural network classifier that was trained on the datasets from four different species (Caenorhabditis elegans, Drosophila melanogaster, rat and human). A matrix of k-mer frequency values was used to represent each sequence. piRNN has great usability and shows better performance in comparison with other programs. It is freely available at https://github.com/bioinfolabmu/piRNN.

RFAmyloid: A Web Server for Predicting Amyloid Proteins

Amyloid is an insoluble fibrous protein and its mis-aggregation can lead to some diseases, such as Alzheimer’s disease and Creutzfeldt–Jakob’s disease. Therefore, the identification of amyloid is essential for the discovery and understanding of disease. We established a novel predictor called RFAmy based on random forest to identify amyloid, and it employed SVMProt 188-D feature extraction method based on protein composition and physicochemical properties and pse-in-one feature extraction method based on amino acid composition, autocorrelation pseudo acid composition, profile-based features and predicted structures features. In the ten-fold cross-validation test, RFAmy’s overall accuracy was 89.19% and F-measure was 0.891. Results were obtained by comparison experiments with other feature, classifiers, and existing methods. This shows the effectiveness of RFAmy in predicting amyloid protein. The RFAmy proposed in this paper can be accessed through the URL http://server.malab.cn/RFAmyloid/.

M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning

N6-methyladenosine (m⁶A) modification is the most abundant RNA methylation modification and involves various biological processes, such as RNA splicing and degradation. Recent studies have demonstrated the feasibility of identifying m⁶A peaks using high-throughput sequencing techniques. However, such techniques cannot accurately identify specific methylated sites, which is important for a better understanding of m⁶A functions. In this study, we develop a novel machine learning-based predictor called M6APred-EL for the identification of m⁶A sites. To predict m⁶A sites accurately within genomic sequences, we trained an ensemble of three support vector machine classifiers that explore the position-specific information and physical chemical information from position-specific k-mer nucleotide propensity, physical-chemical properties, and ring-function-hydrogen-chemical properties. We examined and compared the performance of our predictor with other state-of-the-art methods of benchmarking datasets. Comparative results showed that the proposed M6APred-EL performed more accurately for m⁶A site identification. Moreover, a user-friendly web server that implements the proposed M6APred-EL is well established and is currently available at http://server.malab.cn/M6APred-EL/. It is expected to be a practical and effective tool for the investigation of m⁶A functional mechanisms.

Predicting drug-disease associations by using similarity constrained matrix factorization

Background

Drug-disease associations provide important information for the drug discovery. Wet experiments that identify drug-disease associations are time-consuming and expensive. However, many drug-disease associations are still unobserved or unknown. The development of computational methods for predicting unobserved drug-disease associations is an important and urgent task.

Results

In this paper, we proposed a similarity constrained matrix factorization method for the drug-disease association prediction (SCMFDD), which makes use of known drug-disease associations, drug features and disease semantic information. SCMFDD projects the drug-disease association relationship into two low-rank spaces, which uncover latent features for drugs and diseases, and then introduces drug feature-based similarities and disease semantic similarity as constraints for drugs and diseases in low-rank spaces. Different from the classic matrix factorization technique, SCMFDD takes the biological context of the problem into account. In computational experiments, the proposed method can produce high-accuracy performances on benchmark datasets, and outperform existing state-of-the-art prediction methods when evaluated by five-fold cross validation and independent testing.

Conclusion

We developed a user-friendly web server by using known associations collected from the CTD database, available at http://www.bioinfotech.cn/SCMFDD/. The case studies show that the server can find out novel associations, which are not included in the CTD database.

A unified frame of predicting side effects of drugs by using linear neighborhood similarity

BACKGROUND

Drug side effects are one of main concerns in the drug discovery, which gains wide attentions. Investigating drug side effects is of great importance, and the computational prediction can help to guide wet experiments. As far as we known, a great number of computational methods have been proposed for the side effect predictions. The assumption that similar drugs may induce same side effects is usually employed for modeling, and how to calculate the drug-drug similarity is critical in the side effect predictions.

RESULTS

In this paper, we present a novel measure of drug-drug similarity named "linear neighborhood similarity", which is calculated in a drug feature space by exploring linear neighborhood relationship. Then, we transfer the similarity from the feature space into the side effect space, and predict drug side effects by propagating known side effect information through a similarity-based graph. Under a unified frame based on the linear neighborhood similarity, we propose method "LNSM" and its extension "LNSM-SMI" to predict side effects of new drugs, and propose the method "LNSM-MSE" to predict unobserved side effect of approved drugs.

CONCLUSIONS

We evaluate the performances of LNSM and LNSM-SMI in predicting side effects of new drugs, and evaluate the performances of LNSM-MSE in predicting missing side effects of approved drugs. The results demonstrate that the linear neighborhood similarity can improve the performances of side effect prediction, and the linear neighborhood similarity-based methods can outperform existing side effect prediction methods. More importantly, the proposed methods can predict side effects of new drugs as well as unobserved side effects of approved drugs under a unified frame.

Predicting human splicing branchpoints by combining sequence-derived features and multi-label learning methods

Background

Alternative splicing is the critical process in a single gene coding, which removes introns and joins exons, and splicing branchpoints are indicators for the alternative splicing. Wet experiments have identified a great number of human splicing branchpoints, but many branchpoints are still unknown. In order to guide wet experiments, we develop computational methods to predict human splicing branchpoints.

Results

Considering the fact that an intron may have multiple branchpoints, we transform the branchpoint prediction as the multi-label learning problem, and attempt to predict branchpoint sites from intron sequences. First, we investigate a variety of intron sequence-derived features, such as sparse profile, dinucleotide profile, position weight matrix profile, Markov motif profile and polypyrimidine tract profile. Second, we consider several multi-label learning methods: partial least squares regression, canonical correlation analysis and regularized canonical correlation analysis, and use them as the basic classification engines. Third, we propose two ensemble learning schemes which integrate different features and different classifiers to build ensemble learning systems for the branchpoint prediction. One is the genetic algorithm-based weighted average ensemble method; the other is the logistic regression-based ensemble method.

Conclusions

In the computational experiments, two ensemble learning methods outperform benchmark branchpoint prediction methods, and can produce high-accuracy results on the benchmark dataset.