Problem In Bioinformatics Research Articles

A systematic review of the application of machine learning in the detection and classification of transposable elements.

BackgroundTransposable elements (TEs) constitute the most common repeated sequences in eukaryotic genomes. Recent studies demonstrated their deep impact on species diversity, adaptation to the environment and diseases. Although there are many conventional bioinformatics algorithms for detecting and classifying TEs, none have achieved reliable results on different types of TEs. Machine learning (ML) techniques can automatically extract hidden patterns and novel information from labeled or non-labeled data and have been applied to solving several scientific problems.MethodologyWe followed the Systematic Literature Review (SLR) process, applying the six stages of the review protocol from it, but added a previous stage, which aims to detect the need for a review. Then search equations were formulated and executed in several literature databases. Relevant publications were scanned and used to extract evidence to answer research questions.ResultsSeveral ML approaches have already been tested on other bioinformatics problems with promising results, yet there are few algorithms and architectures available in literature focused specifically on TEs, despite representing the majority of the nuclear DNA of many organisms. Only 35 articles were found and categorized as relevant in TE or related fields.ConclusionsML is a powerful tool that can be used to address many problems. Although ML techniques have been used widely in other biological tasks, their utilization in TE analyses is still limited. Following the SLR, it was possible to notice that the use of ML for TE analyses (detection and classification) is an open problem, and this new field of research is growing in interest.

Parameterized Algorithms in Bioinformatics: An Overview

Bioinformatics regularly poses new challenges to algorithm engineers and theoretical computer scientists. This work surveys recent developments of parameterized algorithms and complexity for important NP-hard problems in bioinformatics. We cover sequence assembly and analysis, genome comparison and completion, and haplotyping and phylogenetics. Aside from reporting the state of the art, we give challenges and open problems for each topic.

STS-NLSP: A Network-Based Label Space Partition Method for Predicting the Specificity of Membrane Transporter Substrates Using a Hybrid Feature of Structural and Semantic Similarity.

Membrane transport proteins play crucial roles in the pharmacokinetics of substrate drugs, the drug resistance in cancer and are vital to the process of drug discovery, development and anti-cancer therapeutics. However, experimental methods to profile a substrate drug against a panel of transporters to determine its specificity are labor intensive and time consuming. In this article, we aim to develop an in silico multi-label classification approach to predict whether a substrate can specifically recognize one of the 13 categories of drug transporters ranging from ATP-binding cassette to solute carrier families using both structural fingerprints and chemical ontologies information of substrates. The data-driven network-based label space partition (NLSP) method was utilized to construct the model based on a hybrid of similarity-based feature by the integration of 2D fingerprint and semantic similarity. This method builds predictors for each label cluster (possibly intersecting) detected by community detection algorithms and takes union of label sets for a compound as final prediction. NLSP lies into the ensembles of multi-label classifier category in multi-label learning field. We utilized Cramér's V statistics to quantify the label correlations and depicted them via a heatmap. The jackknife tests and iterative stratification based cross-validation method were adopted on a benchmark dataset to evaluate the prediction performance of the proposed models both in multi-label and label-wise manner. Compared with other powerful multi-label methods, ML-kNN, MTSVM, and RAkELd, our multi-label classification model of NLPS-RF (random forest-based NLSP) has proven to be a feasible and effective model, and performed satisfactorily in the predictive task of transporter-substrate specificity. The idea behind NLSP method is intriguing and the power of NLSP remains to be explored for the multi-label learning problems in bioinformatics. The benchmark dataset, intermediate results and python code which can fully reproduce our experiments and results are available at https://github.com/dqwei-lab/STS.

GenSeq+: A Scalable High-Performance Accelerator for Genome Sequencing.

Genome sequencing is one of the most challenging problems in computational biology and bioinformatics. As a traditional algorithm, the string match meets a challenge with the development of the massive volume of data because of gene sequencing. Surveys show that there will be a huge amount of short read segments during the process of gene sequencing and the need for a highly efficient is urgent. As a classic fast and exact single pattern matching algorithm, Knuth-Morris-Pratt (KMP) algorithm has been demonstrated in network security and computational biology. However, with the increasing amount of data in the modern society, it becomes increasingly important and essential to provide a High-performance implementation of KMP algorithm. In this article, we implement a scalable KMP accelerator based on FPGA, named GeneKMP. The accelerator is composed of different computing units to achieve a pipelined organization for higher throughput with satisfying scalability. A novel programming model is provided to alleviate the burden of the high-level programmers. We provide a greedy-based partitioning algorithm for the software/hardware design paradigms. Experimental results on the state-of-the-art Xilinx FPGA hardware prototype show that our accelerator can achieve up to a promising speedup with insignificant hardware cost and power consumption.

Recent developments in deep learning applied to protein structure prediction.

Although many structural bioinformatics tools have been using neural network models for a long time, deep neural network (DNN) models have attracted considerable interest in recent years. Methods employing DNNs have had a significant impact in recent CASP experiments, notably in CASP12 and especially CASP13. In this article, we offer a brief introduction to some of the key principles and properties of DNN models and discuss why they are naturally suited to certain problems in structural bioinformatics. We also briefly discuss methodological improvements that have enabled these successes. Using the contact prediction task as an example, we also speculate why DNN models are able to produce reasonably accurate predictions even in the absence of many homologues for a given target sequence, a result that can at first glance appear surprising given the lack of input information. We end on some thoughts about how and why these types of models can be so effective, as well as a discussion on potential pitfalls.

Feature selection may improve deep neural networks for the bioinformatics problems.

Deep neural network (DNN) algorithms were utilized in predicting various biomedical phenotypes recently, and demonstrated very good prediction performances without selecting features. This study proposed a hypothesis that the DNN models may be further improved by feature selection algorithms. A comprehensive comparative study was carried out by evaluating 11 feature selection algorithms on three conventional DNN algorithms, i.e. convolution neural network (CNN), deep belief network (DBN) and recurrent neural network (RNN), and three recent DNNs, i.e. MobilenetV2, ShufflenetV2 and Squeezenet. Five binary classification methylomic datasets were chosen to calculate the prediction performances of CNN/DBN/RNN models using feature selected by the 11 feature selection algorithms. Seventeen binary classification transcriptome and two multi-class transcriptome datasets were also utilized to evaluate how the hypothesis may generalize to different data types. The experimental data supported our hypothesis that feature selection algorithms may improve DNN models, and the DBN models using features selected by SVM-RFE usually achieved the best prediction accuracies on the five methylomic datasets. All the algorithms were implemented and tested under the programming environment Python version 3.6.6. Supplementary data are available at Bioinformatics online.

RNAknot: A new algorithm for RNA secondary structure prediction based on genetic algorithm and GRASP method.

The prediction of the optimal secondary structure for a given RNA sequence represents a challenging computational problem in bioinformatics. This challenge becomes harder especially with the discovery of different pseudoknot classes, which is a complex topology that plays diverse roles in biological processes. Many recent studies have been proposed to predict RNA secondary structure with some pseudoknot classes, but only a few of them have reached satisfying results in terms of both complexity and accuracy. Here we present RNAknot, a new method for predicting RNA secondary structure that contains the following components: stems, hairpin loops, multi-branched loops or multi-loops, bulge loops, and internal loops, in addition to two types of pseudoknots, H-type pseudoknot and Hairpin kissing. RNAknot is based on a genetic algorithm and Greedy Randomized Adaptive Search Procedure (GRASP), and it uses the free energy as fitness function to evaluate the obtained structures. In order to validate the performance of the presented method 131 tests have been performed using two datasets of 26 and 105 RNA sequences, which have been taken from the two data bases RNAstrand and Pseudobase respectively. The obtained results are compared with those of some RNA secondary structure prediction programs such as Vs_subopt, CyloFold, IPknot, Kinefold, RNAstructure, and Sfold. The results of this comparative study show that the prediction accuracy of our proposed approach is significantly improved compared to those obtained by the other programs. For the first dataset, RNAknot has the highest specificity (SP) (71.23%) and sensitivity (SN) (72.15%) averages compared to the other programs. Concerning the second dataset, the RNA secondary structure predictions obtained by the RNAknot correspond to the highest averages of SP (85.49%) and F-measure (79.97%) compared to the other programs. The program is available as a jar file in the link: www.bachmek.umi.ac.ma/wp-content/uploads/RNAknot.0.0.2.rar.

Iron Hack - A symposium/hackathon focused on porphyrias, Friedreich’s ataxia, and other rare iron-related diseases

Background: Basic and clinical scientific research at the University of South Florida (USF) have intersected to support a multi-faceted approach around a common focus on rare iron-related diseases. We proposed a modified version of the National Center for Biotechnology Information’s (NCBI) Hackathon-model to take full advantage of local expertise in building “Iron Hack”, a rare disease-focused hackathon. As the collaborative, problem-solving nature of hackathons tends to attract participants of highly-diverse backgrounds, organizers facilitated a symposium on rare iron-related diseases, specifically porphyrias and Friedreich’s ataxia, pitched at general audiences. Methods: The hackathon was structured to begin each day with presentations by expert clinicians, genetic counselors, researchers focused on molecular and cellular biology, public health/global health, genetics/genomics, computational biology, bioinformatics, biomolecular science, bioengineering, and computer science, as well as guest speakers from the American Porphyria Foundation (APF) and Friedreich’s Ataxia Research Alliance (FARA) to inform participants as to the human impact of these diseases. Results: As a result of this hackathon, we developed resources that are relevant not only to these specific disease-models, but also to other rare diseases and general bioinformatics problems. Within two and a half days, “Iron Hack” participants successfully built collaborative projects to visualize data, build databases, improve rare disease diagnosis, and study rare-disease inheritance. Conclusions: The purpose of this manuscript is to demonstrate the utility of a hackathon model to generate prototypes of generalizable tools for a given disease and train clinicians and data scientists to interact more effectively.

Prediction of FMN Binding Sites in Electron Transport Chains Based on 2-D CNN and PSSM Profiles.

Flavin mono-nucleotides (FMNs) are cofactors that hold responsibility for carrying and transferring electrons in the electron transport chain stage of cellular respiration. Without being facilitated by FMNs, energy production is stagnant due to the interruption in most of the cellular processes. Investigation on FMN's functions, therefore, can gain holistic understanding about human diseases and molecular information on drug targets. We proposed a deep learning model using a two-dimensional convolutional neural network and position specific scoring matrices that could identify FMN interacting residues with the sensitivity of 83.7 percent, specificity of 99.2 percent, accuracy of 98.2 percent, and Matthews correlation coefficients of 0.85 for an independent dataset containing 141 FMN binding sites and 1,920 non-FMN binding sites. The proposed method outperformed other previous studies using similar evaluation metrics. Our positive outcome can also promote the utilization of deep learning in dealing with various problems in bioinformatics and computational biology.

Iron Hack - A symposium/hackathon focused on porphyrias, Friedreich's ataxia, and other rare iron-related diseases.

Background: Basic and clinical scientific research at the University of South Florida (USF) have intersected to support a multi-faceted approach around a common focus on rare iron-related diseases. We proposed a modified version of the National Center for Biotechnology Information's (NCBI) Hackathon-model to take full advantage of local expertise in building "Iron Hack", a rare disease-focused hackathon. As the collaborative, problem-solving nature of hackathons tends to attract participants of highly-diverse backgrounds, organizers facilitated a symposium on rare iron-related diseases, specifically porphyrias and Friedreich's ataxia, pitched at general audiences. Methods: The hackathon was structured to begin each day with presentations by expert clinicians, genetic counselors, researchers focused on molecular and cellular biology, public health/global health, genetics/genomics, computational biology, bioinformatics, biomolecular science, bioengineering, and computer science, as well as guest speakers from the American Porphyria Foundation (APF) and Friedreich's Ataxia Research Alliance (FARA) to inform participants as to the human impact of these diseases. Results: As a result of this hackathon, we developed resources that are relevant not only to these specific disease-models, but also to other rare diseases and general bioinformatics problems. Within two and a half days, "Iron Hack" participants successfully built collaborative projects to visualize data, build databases, improve rare disease diagnosis, and study rare-disease inheritance. Conclusions: The purpose of this manuscript is to demonstrate the utility of a hackathon model to generate prototypes of generalizable tools for a given disease and train clinicians and data scientists to interact more effectively.

Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks

BackgroundAlkaloids, a class of organic compounds that contain nitrogen bases, are mainly synthesized as secondary metabolites in plants and fungi, and they have a wide range of bioactivities. Although there are thousands of compounds in this class, few of their biosynthesis pathways are fully identified. In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network. Molecular similarity is a crucial metric in the analysis of qualitative structure–activity relationships. However, it is sometimes difficult for current fingerprint representations to emphasize specific features for the target problems efficiently. It is advantageous to allow the model to select the appropriate features according to data-driven decisions for extracting more useful information, which influences a classification or regression problem substantially.ResultsIn this study, we applied a neural network architecture for undirected graph representation of molecules. By encoding a molecule as an abstract graph and applying "convolution" on the graph and training the weight of the neural network framework, the neural network can optimize feature selection for the training problem. By incorporating the effects from adjacent atoms recursively, graph convolutional neural networks can extract the features of latent atoms that represent chemical features of a molecule efficiently. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%.ConclusionWe have showed that our model can predict more accurately compared to the random forest and general neural network when the variables and fingerprints are not selected, while the performance is comparable when we carefully select 507 variables from 18000 dimensions of descriptors. The prediction of pathways contributes to understanding of alkaloid synthesis mechanisms and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 12000 alkaloids found in various organisms and found power-low-like distribution.

Protein Subcellular Localization Prediction based on PSI-BLAST Profile and Principal Component Analysis

Background: Prediction of protein subcellular location is a meaningful task which attracts much attention in recent years. Particularly, the number of new protein sequences yielded by the highthroughput sequencing technology in the post genomic era has increased explosively. Objective: Protein subcellular localization prediction based solely on sequence data remains to be a challenging problem of computational biology. Methods: In this paper, three sets of evolutionary features are derived from the position-specific scoring matrix, which has shown great potential in other bioinformatics problems. A fusion model is built up by the optimal parameters combination. Finally, principal component analysis and support vector machine classifier is applied to predict protein subcellular localization on NNPSL dataset and Cell- PLoc 2.0 dataset. Results: Our experimental results show that the proposed method remarkably improved the prediction accuracy, and the features derived from PSI-BLAST profile only are appropriate for protein subcellular localization prediction.

ProteinNet: a standardized data set for machine learning of protein structure

BackgroundRapid progress in deep learning has spurred its application to bioinformatics problems including protein structure prediction and design. In classic machine learning problems like computer vision, progress has been driven by standardized data sets that facilitate fair assessment of new methods and lower the barrier to entry for non-domain experts. While data sets of protein sequence and structure exist, they lack certain components critical for machine learning, including high-quality multiple sequence alignments and insulated training/validation splits that account for deep but only weakly detectable homology across protein space.ResultsWe created the ProteinNet series of data sets to provide a standardized mechanism for training and assessing data-driven models of protein sequence-structure relationships. ProteinNet integrates sequence, structure, and evolutionary information in programmatically accessible file formats tailored for machine learning frameworks. Multiple sequence alignments of all structurally characterized proteins were created using substantial high-performance computing resources. Standardized data splits were also generated to emulate the difficulty of past CASP (Critical Assessment of protein Structure Prediction) experiments by resetting protein sequence and structure space to the historical states that preceded six prior CASPs. Utilizing sensitive evolution-based distance metrics to segregate distantly related proteins, we have additionally created validation sets distinct from the official CASP sets that faithfully mimic their difficulty.ConclusionProteinNet represents a comprehensive and accessible resource for training and assessing machine-learned models of protein structure.

Deep Neural Architectures for Highly Imbalanced Data in Bioinformatics.

In the postgenome era, many problems in bioinformatics have arisen due to the generation of large amounts of imbalanced data. In particular, the computational classification of precursor microRNA (pre-miRNA) involves a high imbalance in the classes. For this task, a classifier is trained to identify RNA sequences having the highest chance of being miRNA precursors. The big issue is that well-known pre-miRNAs are usually just a few in comparison to the hundreds of thousands of candidate sequences in a genome, which results in highly imbalanced data. This imbalance has a strong influence on most standard classifiers and, if not properly addressed, the classifier is not able to work properly in a real-life scenario. This work provides a comparative assessment of recent deep neural architectures for dealing with the large imbalanced data issue in the classification of pre-miRNAs. We present and analyze recent architectures in a benchmark framework with genomes of animals and plants, with increasing imbalance ratios up to 1:2000. We also propose a new graphical way for comparing classifiers performance in the context of high-class imbalance. The comparative results obtained show that, at a very high imbalance, deep belief neural networks can provide the best performance.

Using Probabilistic Neural Networks to Predict the Localization of Proteins in Cell Compartments

This paper describes the use of probabilistic neural networks to solve problems of bioinformatics by the example of determining the localization of proteins according to their primary structure. The data used are sets of characteristics of amino acid sequences of proteins, obtained by various software tools aimed at finding specific signal sequences, as well as data on where these proteins are localized in cells of two microorganisms — E. coli and S. cerevisiae. The data source is the UCI Machine Learning Repository (http://archive.ics.uci.edu/ml/datasets). The possibility of using probabilistic neural networks to solve this problem is shown, since the classification accuracy of 57.5% and 85.0% for yeast and for bacterial cells is obtained, respectively. The obtained indicators of the accuracy of the classification of the data used exceed those that, according to the literature, were achieved with the use of other recognition methods. It is noted that a high learning rate and the possibility of modification make probabilistic neural networks a promising tool for analyzing bioinformatics data. In silico

Using deep reinforcement learning approach for solving the multiple sequence alignment problem

In the present paper, we use a deep reinforcement learning (DRL) approach for solving the multiple sequence alignment problem which is an NP-complete problem. Multiple Sequence Alignment problem simply refers to the process of arranging initial sequences of DNA, RNA or proteins in order to maximize their regions of similarity. Multiple Sequence Alignment is the first step in solving many bioinformatics problems such as constructing phylogenetic trees. In this study, our proposed approach models the Multiple Sequence Alignment problem as a DRL problem and utilizes long short-term memory networks for estimation phase in the reinforcement learning algorithm. Furthermore, the actor-critic algorithm with experience-replay method is used for much quicker convergence process. Using deep Q-learning (an RL approach) and Q-network overcomes the complexity of other approaches. The experimental evaluation is performed on 8 different real-life datasets and in every used dataset our approach outperforms other well-known approaches and tools such as MAFFT, ClustalW, and other heuristic approaches in case of scoring in solving the MSA problem.

DNA short read alignment on apache spark

The evolution of technologies has unleashed a wealth of challenges by generating massive amount of data. Recently, biological data has increased exponentially, which has introduced several computational challenges. DNA short read alignment is an important problem in bioinformatics. The exponential growth in the number of short reads has increased the need for an ideal platform to accelerate the alignment process. Apache Spark is a cluster-computing framework that involves data parallelism and fault tolerance. In this article, we proposed a Spark-based algorithm to accelerate DNA short reads alignment problem, and it is called Spark-DNAligning. Spark-DNAligning exploits Apache Spark’s performance optimizations such as broadcast variable, join after partitioning, caching, and in-memory computations. Spark-DNAligning is evaluated in term of performance by comparing it with SparkBWA tool and a MapReduce based algorithm called CloudBurst. All the experiments are conducted on Amazon Web Services (AWS). Results demonstrate that Spark-DNAligning outperforms both tools by providing a speedup in the range of 101–702 in aligning gigabytes of short reads to the human genome. Empirical evaluation reveals that Apache Spark offers promising solutions to DNA short reads alignment problem.

ILearn: an integrated platform and meta-learner for feature engineering, machine-learning analysis and modeling of DNA, RNA and protein sequence data.

With the explosive growth of biological sequences generated in the post-genomic era, one of the most challenging problems in bioinformatics and computational biology is to computationally characterize sequences, structures and functions in an efficient, accurate and high-throughput manner. A number of online web servers and stand-alone tools have been developed to address this to date; however, all these tools have their limitations and drawbacks in terms of their effectiveness, user-friendliness and capacity. Here, we present iLearn, a comprehensive and versatile Python-based toolkit, integrating the functionality of feature extraction, clustering, normalization, selection, dimensionality reduction, predictor construction, best descriptor/model selection, ensemble learning and results visualization for DNA, RNA and protein sequences. iLearn was designed for users that only want to upload their data set and select the functions they need calculated from it, while all necessary procedures and optimal settings are completed automatically by the software. iLearn includes a variety of descriptors for DNA, RNA and proteins, and four feature output formats are supported so as to facilitate direct output usage or communication with other computational tools. In total, iLearn encompasses 16 different types of feature clustering, selection, normalization and dimensionality reduction algorithms, and five commonly used machine-learning algorithms, thereby greatly facilitating feature analysis and predictor construction. iLearn is made freely available via an online web server and a stand-alone toolkit.

A high-performance approach for predicting donor splice sites based on short window size and imbalanced large samples

BackgroundSplice sites prediction has been a long-standing problem in bioinformatics. Although many computational approaches developed for splice site prediction have achieved satisfactory accuracy, further improvement in predictive accuracy is significant, for it is contributing to predict gene structure more accurately. Determining a proper window size before prediction is necessary. Overly long window size may introduce some irrelevant features, which would reduce predictive accuracy, while the use of short window size with maximum information may performs better in terms of predictive accuracy and time cost. Furthermore, the number of false splice sites following the GT–AG rule far exceeds that of true splice sites, accurate and rapid prediction of splice sites using imbalanced large samples has always been a challenge. Therefore, based on the short window size and imbalanced large samples, we developed a new computational method named chi-square decision table (χ2-DT) for donor splice site prediction.ResultsUsing a short window size of 11 bp, χ2-DT extracts the improved positional features and compositional features based on chi-square test, then introduces features one by one based on information gain, and constructs a balanced decision table aimed at implementing imbalanced pattern classification. With a 2000:271,132 (true sites:false sites) training set, χ2-DT achieves the highest independent test accuracy (93.34%) when compared with three classifiers (random forest, artificial neural network, and relaxed variable kernel density estimator) and takes a short computation time (89 s). χ2-DT also exhibits good independent test accuracy (92.40%), when validated with BG-570 mutated sequences with frameshift errors (nucleotide insertions and deletions). Moreover, χ2-DT is compared with the long-window size-based methods and the short-window size-based methods, and is found to perform better than all of them in terms of predictive accuracy.ConclusionsBased on short window size and imbalanced large samples, the proposed method not only achieves higher predictive accuracy than some existing methods, but also has high computational speed and good robustness against nucleotide insertions and deletions.ReviewersThis article was reviewed by Ryan McGinty, Ph.D. and Dirk Walther.

Recent Advances of Deep Learning in Bioinformatics and Computational Biology.

Extracting inherent valuable knowledge from omics big data remains as a daunting problem in bioinformatics and computational biology. Deep learning, as an emerging branch from machine learning, has exhibited unprecedented performance in quite a few applications from academia and industry. We highlight the difference and similarity in widely utilized models in deep learning studies, through discussing their basic structures, and reviewing diverse applications and disadvantages. We anticipate the work can serve as a meaningful perspective for further development of its theory, algorithm and application in bioinformatic and computational biology.