Applications of alignment-free methods in epigenomics

Alignment-Free Sequence Comparison: A Systematic Survey From a Machine Learning Perspective

The encounter of large amounts of biological sequence data generated during the last decades and the algorithmic and hardware improvements have offered the possibility to apply machine learning techniques in bioinformatics. While the machine learning community is aware of the necessity to rigorously distinguish data transformation from data comparison and adopt reasonable combinations thereof, this awareness is often lacking in the field of comparative sequence analysis. With realization of the disadvantages of alignments for sequence comparison, some typical applications use more and more so-called alignment-free approaches. In light of this development, we present a conceptual framework for alignment-free sequence comparison, which highlights the delineation of: 1) the sequence data transformation comprising of adequate mathematical sequence coding and feature generation, from 2) the subsequent (dis-)similarity evaluation of the transformed data by means of problem-specific but mathematically consistent proximity measures. We consider coding to be an information-loss free data transformation in order to get an appropriate representation, whereas feature generation is inevitably information-lossy with the intention to extract just the task-relevant information. This distinction sheds light on the plethora of methods available and assists in identifying suitable methods in machine learning and data analysis to compare the sequences under these premises.

Mathematical Approach to Protein Sequence Comparison Based on Physiochemical Properties

The difficult aspect of developing new protein sequence comparison techniques is coming up with a method that can quickly and effectively handle huge data sets of various lengths in a timely manner. In this work, we first obtain two numerical representations of protein sequences separately based on one physical property and one chemical property of amino acids. The lengths of all the sequences under comparison are made equal by appending the required number of zeroes. Then, fast Fourier transform is applied to this numerical time series to obtain the corresponding spectrum. Next, the spectrum values are reduced by the standard inter coefficient difference method. Finally, the corresponding normalized values of the reduced spectrum are selected as the descriptors for protein sequence comparison. Using these descriptors, the distance matrices are obtained using Euclidian distance. They are subsequently used to draw the phylogenetic trees using the UPGMA algorithm. Phylogenetic trees are first constructed for 9 ND4, 9 ND5, and 9 ND6 proteins using the polarity value as the chemical property and the molecular weight as the physical property. They are compared, and it is seen that polarity is a better choice than molecular weight in protein sequence comparison. Next, using the polarity property, phylogenetic trees are obtained for 12 baculovirus and 24 transferrin proteins. The results are compared with those obtained earlier on the identical sequences by other methods. Three assessment criteria are considered for comparison of the results-quality based on rationalized perception, quantitative measures based on symmetric distance, and computational speed. In all the cases, the results are found to be more satisfactory.

Convolutional Neural Network Applied to SARS-CoV-2 Sequence Classification

COVID-19, the illness caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus belonging to the Coronaviridade family, a single-strand positive-sense RNA genome, has been spreading around the world and has been declared a pandemic by the World Health Organization. On 17 January 2022, there were more than 329 million cases, with more than 5.5 million deaths. Although COVID-19 has a low mortality rate, its high capacities for contamination, spread, and mutation worry the authorities, especially after the emergence of the Omicron variant, which has a high transmission capacity and can more easily contaminate even vaccinated people. Such outbreaks require elucidation of the taxonomic classification and origin of the virus (SARS-CoV-2) from the genomic sequence for strategic planning, containment, and treatment of the disease. Thus, this work proposes a high-accuracy technique to classify viruses and other organisms from a genome sequence using a deep learning convolutional neural network (CNN). Unlike the other literature, the proposed approach does not limit the length of the genome sequence. The results show that the novel proposal accurately distinguishes SARS-CoV-2 from the sequences of other viruses. The results were obtained from 1557 instances of SARS-CoV-2 from the National Center for Biotechnology Information (NCBI) and 14,684 different viruses from the Virus-Host DB. As a CNN has several changeable parameters, the tests were performed with forty-eight different architectures; the best of these had an accuracy of 91.94 ± 2.62% in classifying viruses into their realms correctly, in addition to 100% accuracy in classifying SARS-CoV-2 into its respective realm, Riboviria. For the subsequent classifications (family, genera, and subgenus), this accuracy increased, which shows that the proposed architecture may be viable in the classification of the virus that causes COVID-19.

Interpreting alignment-free sequence comparison: what makes a score a good score?

Alignment-free methods are alternatives to alignment-based methods when searching sequence data sets. The output from an alignment-free sequence comparison is a similarity score, the interpretation of which is not straightforward. We propose objective functions to interpret and calibrate outputs from alignment-free searches, noting that different objective functions are necessary for different biological contexts. This leads to advantages: visualising and comparing score distributions, including those from true positives, may be a relatively simple method to gain insight into the performance of different metrics. Using an empirical approach with both DNA and protein sequences, we characterise different similarity score distributions generated under different parameters. In particular, we demonstrate how sequence length can affect the scores. We show that scores of true positive sequence pairs may correlate significantly with their mean length; and even if the correlation is weak, the relative difference in length of the sequence pair may significantly reduce the effectiveness of alignment-free metrics. Importantly, we show how objective functions can be used with test data to accurately estimate the probability of true positives. This can significantly increase the utility of alignment-free approaches. Finally, we have developed a general-purpose software tool called KAST for use in high-throughput workflows on Linux clusters.

MIAOME: Human Microbiome Affect The Host Epigenome

Besides the genetic factors having tremendous influences on the regulations of the epigenome, the microenvironmental factors have recently gained extensive attention for their roles in affecting the host epigenome. There are three major types of microenvironmental factors: microbiota-derived metabolites (MDM), microbiota-derived components (MDC) and microbiota-secreted proteins (MSP). These factors can regulate host physiology by modifying host gene expression through the three highly interconnected epigenetic mechanisms (e.g. histone modifications, DNA modifications, and non-coding RNAs). However, no database was available to provide the comprehensive factors of these types. Herein, a database entitled 'Human Microbiome Affect The Host Epigenome (MIAOME)' was constructed. Based on the types of epigenetic modifications confirmed in the literature review, the MIAOME database captures 1068 (63 genus, 281 species, 707 strains, etc.) human microbes, 91 unique microbiota-derived metabolites & components (16 fatty acids, 10 bile acids, 10 phenolic compounds, 10 vitamins, 9 tryptophan metabolites, etc.) derived from 967 microbes; 50 microbes that secreted 40 proteins; 98 microbes that directly influence the host epigenetic modification, and provides 3 classifications of the epigenome, including (1) 4 types of DNA modifications, (2) 20 histone modifications and (3) 490 ncRNAs regulations, involved in 160 human diseases. All in all, MIAOME has compiled the information on the microenvironmental factors influence host epigenome through the scientific literature and biochemical databases, and allows the collective considerations among the different types of factors. It can be freely assessed without login requirement by all users at: http://miaome.idrblab.net/ttd/

A deep bidirectional recurrent neural network for identification of SARS-CoV-2 from viral genome sequences

In this work, Deep Bidirectional Recurrent Neural Networks (BRNNs) models were implemented based on both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) cells in order to distinguish between genome sequence of SARS-CoV-2 and other Corona Virus strains such as SARS-CoV and MERS-CoV, Common Cold and other Acute Respiratory Infection (ARI) viruses. An investigation of the hyper-parameters including the optimizer type and the number of unit cells, was also performed to attain the best performance of the BRNN models. Results showed that the GRU BRNNs model was able to discriminate between SARS-CoV-2 and other classes of viruses with a higher overall classification accuracy of 96.8% as compared to that of the LSTM BRNNs model having a 95.8% overall classification accuracy. The best hyper-parameters producing the highest performance for both models was obtained when applying the SGD optimizer and an optimum number of unit cells of 80 in both models. This study proved that the proposed GRU BRNN model has a better classification ability for SARS-CoV-2 thus providing an efficient tool to help in containing the disease and achieving better clinical decisions with high precision.

Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning

In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from the National Genomics Data Center repository, separating the genome of different virus strains from the Coronavirus family with 98.73% accuracy. The network's behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from the National Center for Biotechnology Information and Global Initiative on Sharing All Influenza Data repositories, and are proven to be able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n = 6 previously tested positive), delivering a sensitivity similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both automatically identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics.

CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification

BACKGROUND

Nucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data.

RESULTS

In this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel levels are devoted to catching both non periodic and periodic DNA string features. A dense layer is devoted to their combination to give a final classification.

CONCLUSIONS

Results computed on public data sets of different organisms show that CORENup is a state of the art methodology for nucleosome positioning identification based on a Deep Neural Network architecture. The comparisons have been carried out using two groups of datasets, currently adopted by the best performing methods, and CORENup has shown top performance both in terms of classification metrics and elapsed computation time.

Data stream dataset of SARS-CoV-2 genome

As of May 25, 2020, the novel coronavirus disease (called COVID-19) spread to more than 185 countries/regions with more than 348,000 deaths and more than 5,550,000 confirmed cases. In the bioinformatics area, one of the crucial points is the analysis of the virus nucleotide sequences using approaches such as data stream techniques and algorithms. However, to make feasible this approach, it is necessary to transform the nucleotide sequences string to numerical stream representation. Thus, the dataset provides four kinds of data stream representation (DSR) of SARS-CoV-2 virus nucleotide sequences. The dataset provides the DSR of 1557 instances of SARS-CoV-2 virus, 11540 other instances of other viruses from the Virus-Host DB dataset, and three instances of Riboviria viruses from NCBI (Betacoronavirus RaTG13, bat-SL-CoVZC45, and bat-SL-CoVZXC21).

A survey and evaluations of histogram-based statistics in alignment-free sequence comparison

Motivation

Since the dawn of the bioinformatics field, sequence alignment scores have been the main method for comparing sequences. However, alignment algorithms are quadratic, requiring long execution time. As alternatives, scientists have developed tens of alignment-free statistics for measuring the similarity between two sequences.

Results

We surveyed tens of alignment-free k-mer statistics. Additionally, we evaluated 33 statistics and multiplicative combinations between the statistics and/or their squares. These statistics are calculated on two k-mer histograms representing two sequences. Our evaluations using global alignment scores revealed that the majority of the statistics are sensitive and capable of finding similar sequences to a query sequence. Therefore, any of these statistics can filter out dissimilar sequences quickly. Further, we observed that multiplicative combinations of the statistics are highly correlated with the identity score. Furthermore, combinations involving sequence length difference or Earth Mover’s distance, which takes the length difference into account, are always among the highest correlated paired statistics with identity scores. Similarly, paired statistics including length difference or Earth Mover’s distance are among the best performers in finding the K-closest sequences. Interestingly, similar performance can be obtained using histograms of shorter words, resulting in reducing the memory requirement and increasing the speed remarkably. Moreover, we found that simple single statistics are sufficient for processing next-generation sequencing reads and for applications relying on local alignment. Finally, we measured the time requirement of each statistic. The survey and the evaluations will help scientists with identifying efficient alternatives to the costly alignment algorithm, saving thousands of computational hours.

Availability

The source code of the benchmarking tool is available as Supplementary Materials.

Deep learning architectures for prediction of nucleosome positioning from sequences data

Background

Nucleosomes are DNA-histone complex, each wrapping about 150 pairs of double-stranded DNA. Their function is fundamental for one of the primary functions of Chromatin i.e. packing the DNA into the nucleus of the Eukaryote cells. Several biological studies have shown that the nucleosome positioning influences the regulation of cell type-specific gene activities. Moreover, computational studies have shown evidence of sequence specificity concerning the DNA fragment wrapped into nucleosomes, clearly underlined by the organization of particular DNA substrings. As the main consequence, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using a sequence features representation.

Results

In this work, we propose a deep learning model for nucleosome identification. Our model stacks convolutional layers and Long Short-term Memories to automatically extract features from short- and long-range dependencies in a sequence. Using this model we are able to avoid the feature extraction and selection steps while improving the classification performances.

Conclusions

Results computed on eleven data sets of five different organisms, from Yeast to Human, show the superiority of the proposed method with respect to the state of the art recently presented in the literature.

Efficient Algorithms for Sequence Analysis with Entropic Profiles

Entropy, being closely related to repetitiveness and compressibility, is a widely used information-related measure to assess the degree of predictability of a sequence. Entropic profiles are based on information theory principles, and can be used to study the under-/over-representation of subwords, by also providing information about the scale of conserved DNA regions. Here, we focus on the algorithmic aspects related to entropic profiles. In particular, we propose linear time algorithms for their computation that rely on suffix-based data structures, more specifically on the truncated suffix tree (TST) and on the enhanced suffix array (ESA). We performed an extensive experimental campaign showing that our algorithms, beside being faster, make it possible the analysis of longer sequences, even for high degrees of resolution, than state of the art algorithms.

Alignment-free sequence comparison: benefits, applications, and tools

Alignment-free sequence analyses have been applied to problems ranging from whole-genome phylogeny to the classification of protein families, identification of horizontally transferred genes, and detection of recombined sequences. The strength of these methods makes them particularly useful for next-generation sequencing data processing and analysis. However, many researchers are unclear about how these methods work, how they compare to alignment-based methods, and what their potential is for use for their research. We address these questions and provide a guide to the currently available alignment-free sequence analysis tools.

The super-n-motifs model: a novel alignment-free approach for representing and comparing RNA secondary structures

Motivation

Comparing ribonucleic acid (RNA) secondary structures of arbitrary size uncovers structural patterns that can provide a better understanding of RNA functions. However, performing fast and accurate secondary structure comparisons is challenging when we take into account the RNA configuration (i.e. linear or circular), the presence of pseudoknot and G-quadruplex (G4) motifs and the increasing number of secondary structures generated by high-throughput probing techniques. To address this challenge, we propose the super-n-motifs model based on a latent analysis of enhanced motifs comprising not only basic motifs but also adjacency relations. The super-n-motifs model computes a vector representation of secondary structures as linear combinations of these motifs.

Results

We demonstrate the accuracy of our model for comparison of secondary structures from linear and circular RNA while also considering pseudoknot and G4 motifs. We show that the super-n-motifs representation effectively captures the most important structural features of secondary structures, as compared to other representations such as ordered tree, arc-annotated and string representations. Finally, we demonstrate the time efficiency of our model, which is alignment free and capable of performing large-scale comparisons of 10 000 secondary structures with an efficiency up to 4 orders of magnitude faster than existing approaches.

Availability and Implementation

The super-n-motifs model was implemented in C ++. Source code and Linux binary are freely available at http://jpsglouzon.github.io/supernmotifs/ .

Contact

Shengrui.Wang@Usherbrooke.ca.

Supplementary information

Supplementary data are available at Bioinformatics o nline.

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.

Set of rules for genomic signal downsampling

Comparison and classification of organisms based on molecular data is an important task of computational biology, since at least parts of DNA sequences for many organisms are available. Unfortunately, methods for comparison are computationally very demanding, suitable only for short sequences. In this paper, we focus on the redundancy of genetic information stored in DNA sequences. We proposed rules for downsampling of DNA signals of cumulated phase. According to the length of an original sequence, we are able to significantly reduce the amount of data with only slight loss of original information. Dyadic wavelet transform was chosen for fast downsampling with minimum influence on signal shape carrying the biological information. We proved the usability of such new short signals by measuring percentage deviation of pairs of original and downsampled signals while maintaining spectral power of signals. Minimal loss of biological information was proved by measuring the Robinson-Foulds distance between pairs of phylogenetic trees reconstructed from the original and downsampled signals. The preservation of inter-species and intra-species information makes these signals suitable for fast sequence identification as well as for more detailed phylogeny reconstruction.

Application of discrete Fourier inter-coefficient difference for assessing genetic sequence similarity

Digital signal processing (DSP) techniques for biological sequence analysis continue to grow in popularity due to the inherent digital nature of these sequences. DSP methods have demonstrated early success for detection of coding regions in a gene. Recently, these methods are being used to establish DNA gene similarity. We present the inter-coefficient difference (ICD) transformation, a novel extension of the discrete Fourier transformation, which can be applied to any DNA sequence. The ICD method is a mathematical, alignment-free DNA comparison method that generates a genetic signature for any DNA sequence that is used to generate relative measures of similarity among DNA sequences. We demonstrate our method on a set of insulin genes obtained from an evolutionarily wide range of species, and on a set of avian influenza viral sequences, which represents a set of highly similar sequences. We compare phylogenetic trees generated using our technique against trees generated using traditional alignment techniques for similarity and demonstrate that the ICD method produces a highly accurate tree without requiring an alignment prior to establishing sequence similarity.