Representation Of DNA Sequences Research Articles

Using a hybrid neural network architecture for DNA sequence representation: A study on [formula omitted]-methylcytosine sites

N4-methylcytosine (4mC) is a modified form of cytosine found in DNA, contributing to epigenetic regulation. It exists in various genomes, including the Rosaceae family encompassing significant fruit crops like apples, cherries, and roses. Previous investigations have examined the distribution and functional implications of 4mC sites within the Rosaceae genome, focusing on their potential roles in gene expression regulation, environmental adaptation, and evolution. This research aims to improve the accuracy of predicting 4mC sites within the genome of Fragaria vesca, a Rosaceae plant species. Building upon the original 4mc-w2vec method, which combines word embedding processing and a convolutional neural network (CNN), we have incorporated additional feature encoding techniques and leveraged pre-trained natural language processing (NLP) models with different deep learning architectures including different forms of CNN, recurrent neural networks (RNN) and long short-term memory (LSTM). Our assessments have shown that the best model is derived from a CNN model using fastText encoding. This model demonstrates enhanced performance, achieving a sensitivity of 0.909, specificity of 0.77, and accuracy of 0.879 on an independent dataset. Furthermore, our model surpasses previously published works on the same dataset, thus showcasing its superior predictive capabilities.

The complex polyploid genome architecture of sugarcane

Sugarcane, the world’s most harvested crop by tonnage, has shaped global history, trade and geopolitics, and is currently responsible for 80% of sugar production worldwide1. While traditional sugarcane breeding methods have effectively generated cultivars adapted to new environments and pathogens, sugar yield improvements have recently plateaued2. The cessation of yield gains may be due to limited genetic diversity within breeding populations, long breeding cycles and the complexity of its genome, the latter preventing breeders from taking advantage of the recent explosion of whole-genome sequencing that has benefited many other crops. Thus, modern sugarcane hybrids are the last remaining major crop without a reference-quality genome. Here we take a major step towards advancing sugarcane biotechnology by generating a polyploid reference genome for R570, a typical modern cultivar derived from interspecific hybridization between the domesticated species (Saccharum officinarum) and the wild species (Saccharum spontaneum). In contrast to the existing single haplotype (‘monoploid’) representation of R570, our 8.7 billion base assembly contains a complete representation of unique DNA sequences across the approximately 12 chromosome copies in this polyploid genome. Using this highly contiguous genome assembly, we filled a previously unsized gap within an R570 physical genetic map to describe the likely causal genes underlying the single-copy Bru1 brown rust resistance locus. This polyploid genome assembly with fine-grain descriptions of genome architecture and molecular targets for biotechnology will help accelerate molecular and transgenic breeding and adaptation of sugarcane to future environmental conditions.

Discovering genomic islands in unannotated bacterial genomes using sequence embedding.

Genomic islands (GEIs) are clusters of genes in bacterial genomes that are typically acquired by horizontal gene transfer. GEIs play a crucial role in the evolution of bacteria by rapidly introducing genetic diversity and thus helping them adapt to changing environments. Specifically of interest to human health, many GEIs contain pathogenicity and antimicrobial resistance genes. Detecting GEIs is, therefore, an important problem in biomedical and environmental research. There have been many previous studies for computationally identifying GEIs. Still, most of these studies rely on detecting anomalies in the unannotated nucleotide sequences or on a fixed set of known features on annotated nucleotide sequences. Here, we present TreasureIsland, which uses a new unsupervised representation of DNA sequences to predict GEIs. We developed a high-precision boundary detection method featuring an incremental fine-tuning of GEI borders, and we evaluated the accuracy of this framework using a new comprehensive reference dataset, Benbow. We show that TreasureIsland's accuracy rivals other GEI predictors, enabling efficient and faster identification of GEIs in unannotated bacterial genomes. TreasureIsland is available under an MIT license at: https://github.com/FriedbergLab/GenomicIslandPrediction.

SoftVoting6mA: An improved ensemble-based method for predicting DNA N6-methyladenine sites in cross-species genomes.

The DNA N6-methyladenine (6mA) is an epigenetic modification, which plays a pivotal role in biological processes encompassing gene expression, DNA replication, repair, and recombination. Therefore, the precise identification of 6mA sites is fundamental for better understanding its function, but challenging. We proposed an improved ensemble-based method for predicting DNA N6-methyladenine sites in cross-species genomes called SoftVoting6mA. The SoftVoting6mA selected four (electron-ion-interaction pseudo potential, One-hot encoding, Kmer, and pseudo dinucleotide composition) codes from 15 types of encoding to represent DNA sequences by comparing their performances. Similarly, the SoftVoting6mA combined four learning algorithms using the soft voting strategy. The 5-fold cross-validation and the independent tests showed that SoftVoting6mA reached the state-of-the-art performance. To enhance accessibility, a user-friendly web server is provided at http://www.biolscience.cn/SoftVoting6mA/.

Classification of DNA Sequence Based on a Non-gradient Algorithm: Pseudoinverse Learners.

This chapter proposes a prototype-based classification approach for analyzing DNA barcodes that uses a spectral representation of DNA sequences and a non-gradient neural network. Biological sequences can be viewed as data components with higher non-fixed dimensions, which correspond to the length of the sequences. Through computational procedures such as one-hot encoding, numerical encoding plays an important role in DNA sequence evaluation (OHE). However, the OHE method has some disadvantages: (1) It does not add any details that could result in an additional predictive variable, and (2) if the variable has many classes, OHE significantly expands the feature space. To address these shortcomings, this chapter proposes a computationally efficient framework for classifying DNA sequences of living organisms in the image domain. A multilayer perceptron trained by a pseudoinverse learning autoencoder (PILAE) algorithm is used in the proposed strategy. The learning control parameters and the number of hidden layers do not have to be specified during the PILAE training process. As a result, the PILAE classifier outperforms other deep neural network (DNN) strategies such as the VGG-16 and Xception models.

PanKmer: k-mer-based and reference-free pangenome analysis.

Pangenomes are replacing single reference genomes as the definitive representation of DNA sequence within a species or clade. Pangenome analysis predominantly leverages graph-based methods that require computationally intensive multiple genome alignments, do not scale to highly complex eukaryotic genomes, limit their scope to identifying structural variants (SVs), or incur bias by relying on a reference genome. Here, we present PanKmer, a toolkit designed for reference-free analysis of pangenome datasets consisting of dozens to thousands of individual genomes. PanKmer decomposes a set of input genomes into a table of observed k-mers and their presence-absence values in each genome. These are stored in an efficient k-mer index data format that encodes SNPs, INDELs, and SVs. It also includes functions for downstream analysis of the k-mer index, such as calculating sequence similarity statistics between individuals at whole-genome or local scales. For example, k-mers can be "anchored" in any individual genome to quantify sequence variability or conservation at a specific locus. This facilitates workflows with various biological applications, e.g. identifying cases of hybridization between plant species. PanKmer provides researchers with a valuable and convenient means to explore the full scope of genetic variation in a population, without reference bias. PanKmer is implemented as a Python package with components written in Rust, released under a BSD license. The source code is available from the Python Package Index (PyPI) at https://pypi.org/project/pankmer/ as well as Gitlab at https://gitlab.com/salk-tm/pankmer. Full documentation is available at https://salk-tm.gitlab.io/pankmer/.

Compact and automated eDNA sampler for in situ monitoring of marine environments

Using environmental DNA (eDNA) to monitor biodiversity in aquatic environments is becoming an efficient and cost-effective alternative to other methods such as visual and acoustic identification. Until recently, eDNA sampling was accomplished primarily through manual sampling methods; however, with technological advances, automated samplers are being developed to make sampling easier and more accessible. This paper describes a new eDNA sampler capable of self-cleaning and multi-sample capture and preservation, all within a single unit capable of being deployed by a single person. The first in-field test of this sampler took place in the Bedford Basin, Nova Scotia, Canada alongside parallel samples taken using the typical Niskin bottle collection and post-collection filtration method. Both methods were able to capture the same aquatic microbial community and counts of representative DNA sequences were well correlated between methods with R^{2} values ranging from 0.71–0.93. The two collection methods returned the same top 10 families in near identical relative abundance, demonstrating that the sampler was able to capture the same community composition of common microbes as the Niskin. The presented eDNA sampler provides a robust alternative to manual sampling methods, is amenable to autonomous vehicle payload constraints, and will facilitate persistent monitoring of remote and inaccessible sites.

A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application

BackgroundUsing visual, biological, and electronic health records data as the sole input source, pretrained convolutional neural networks and conventional machine learning methods have been heavily employed for the identification of various malignancies. Initially, a series of preprocessing steps and image segmentation steps are performed to extract region of interest features from noisy features. Then, the extracted features are applied to several machine learning and deep learning methods for the detection of cancer.MethodsIn this work, a review of all the methods that have been applied to develop machine learning algorithms that detect cancer is provided. With more than 100 types of cancer, this study only examines research on the four most common and prevalent cancers worldwide: lung, breast, prostate, and colorectal cancer. Next, by using state-of-the-art sentence transformers namely: SBERT (2019) and the unsupervised SimCSE (2021), this study proposes a new methodology for detecting cancer. This method requires raw DNA sequences of matched tumor/normal pair as the only input. The learnt DNA representations retrieved from SBERT and SimCSE will then be sent to machine learning algorithms (XGBoost, Random Forest, LightGBM, and CNNs) for classification. As far as we are aware, SBERT and SimCSE transformers have not been applied to represent DNA sequences in cancer detection settings.ResultsThe XGBoost model, which had the highest overall accuracy of 73 ± 0.13 % using SBERT embeddings and 75 ± 0.12 % using SimCSE embeddings, was the best performing classifier. In light of these findings, it can be concluded that incorporating sentence representations from SimCSE’s sentence transformer only marginally improved the performance of machine learning models.

I-DNAN6mA: Accurate Identification of DNA N6-Methyladenine Sites Using the Base-Pairing Map and Deep Learning.

The recent discovery of numerous DNA N6-methyladenine (6mA) sites has transformed our perception about the roles of 6mA in living organisms. However, our ability to understand them is hampered by our inability to identify 6mA sites rapidly and cost-efficiently by existing experimental methods. Developing a novel method to quickly and accurately identify 6mA sites is critical for speeding up the progress of its function detection and understanding. In this study, we propose a novel computational method, called I-DNAN6mA, to identify 6mA sites and complement experimental methods well, by leveraging the base-pairing rules and a well-designed three-stage deep learning model with pairwise inputs. The performance of our proposed method is benchmarked and evaluated on four species, i.e., Arabidopsis thaliana, Drosophila melanogaster, Rice, and Rosaceae. The experimental results demonstrate that I-DNAN6mA achieves area under the receiver operating characteristic curve values of 0.967, 0.963, 0.947, 0.976, and 0.990, accuracies of 91.5, 92.7, 88.2, 0.938, and 96.2%, and Mathew's correlation coefficient values of 0.855, 0.831, 0.763, 0.877, and 0.924 on five benchmark data sets, respectively, and outperforms several existing state-of-the-art methods. To our knowledge, I-DNAN6mA is the first approach to identify 6mA sites using a novel image-like representation of DNA sequences and a deep learning model with pairwise inputs. I-DNAN6mA is expected to be useful for locating functional regions of DNA.

Predicting In-Vitro DNA-Protein Binding With a Spatially Aligned Fusion of Sequence and Shape.

Discovery of transcription factor binding sites (TFBSs) is of primary importance for understanding the underlying binding mechanic and gene regulation process. Growing evidence indicates that apart from the primary DNA sequences, DNA shape landscape has a significant influence on transcription factor binding preference. To effectively model the co-influence of sequence and shape features, we emphasize the importance of position information of sequence motif and shape pattern. In this paper, we propose a novel deep learning-based architecture, named hybridShape eDeepCNN, for TFBS prediction which integrates DNA sequence and shape information in a spatially aligned manner. Our model utilizes the power of the multi-layer convolutional neural network and constructs an independent subnetwork to adapt for the distinct data distribution of heterogeneous features. Besides, we explore the usage of continuous embedding vectors as the representation of DNA sequences. Based on the experiments on 20 in-vitro datasets derived from universal protein binding microarrays (uPBMs), we demonstrate the superiority of our proposed method and validate the underlying design logic.

Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence.

DNA can stabilize silver nanoclusters (AgN-DNAs) whose atomic sizes and diverse fluorescence colors are selected by nucleobase sequence. These programmable nanoclusters hold promise for sensing, bioimaging, and nanophononics. However, DNA's vast sequence space challenges the design and discovery of AgN-DNAs with tailored properties. In particular, AgN-DNAs with bright near-infrared luminescence above 800 nm remain rare, placing limits on their applications for bioimaging in the tissue transparency windows. Here, we present a design method for near-infrared emissive AgN-DNAs. By combining high-throughput experimentation and machine learning with fundamental information from AgN-DNA crystal structures, we distill the salient DNA sequence features that determine AgN-DNA color, for the entire known spectral range of these nanoclusters. A succinct set of nucleobase staple features are predictive of AgN-DNA color. By representing DNA sequences in terms of these motifs, our machine learning models increase the design success for near-infrared emissive AgN-DNAs by 12.3 times as compared to training data, nearly doubling the number of known AgN-DNAs with bright near-infrared luminescence above 800 nm. These results demonstrate how incorporating known structure-property relationships into machine learning models can enhance materials study and design, even for sparse and imbalanced training data.

BERT contextual embeddings for taxonomic classification of bacterial DNA sequences

Biological taxonomic classification is an important task needed for the identification and discovery of organisms, as well as the inference of their evolutionary relationships. The order and structure of biological sequence components has an essential and primary role in what the sequence’s identity and function is. In order to be able to efficiently differentiate between different bacterial categories, interactions and positions of the biological components in sequences must be known — which is an essential challenge in biological sequence classification. In this light, a considerable amount of recent research has been made to explore efficient representations of biological sequences such as spectral k-mer representation, one-hot encoding, Hilbert space curves and classical word embeddings such as Word2Vec. This paper identifies the taxonomic classification of bacterial 16S rRNA genes at five resolutions mapping hierarchical taxonomic ranks. A Bidirectional Encoder Representations from Transformers (BERT) model is pretrained using biological sequences, which to the best of our knowledge is the first time BERT has been trained with such sequences. A complete prediction model is then proposed – BioSeqBERT-CNN – that initially extracts contextual embeddings representations of DNA sequences using the pretrained BERT model. Extracted representations are further used for taxonomic classification through a Convolutional Neural Network (CNN). For boosting the deep learning classification performance, a data augmentation step is applied. Classification with the original dataset on the most fine-grained rank produced an accuracy of 93.5%, which surpasses that of recent works by 1.5–24.3%. Using data augmentation, an accuracy of 99.9% is achieved, which exceeds values of recent works by a minimum and maximum of 7.9% and 30.7%, respectively on the most fine-grained taxonomic rank. This exhibits promising performance promoting the study of using contextual embeddings to represent biological sequences, with Deep Learning networks.

Nucleosome positioning based on DNA sequence embedding and deep learning

BackgroundNucleosome positioning is the precise determination of the location of nucleosomes on DNA sequence. With the continuous advancement of biotechnology and computer technology, biological data is showing explosive growth. It is of practical significance to develop an efficient nucleosome positioning algorithm. Indeed, convolutional neural networks (CNN) can capture local features in DNA sequences, but ignore the order of bases. While the bidirectional recurrent neural network can make up for CNN's shortcomings in this regard and extract the long-term dependent features of DNA sequence.ResultsIn this work, we use word vectors to represent DNA sequences and propose three new deep learning models for nucleosome positioning, and the integrative model NP_CBiR reaches a better prediction performance. The overall accuracies of NP_CBiR on H. sapiens, C. elegans, and D. melanogaster datasets are 86.18%, 89.39%, and 85.55% respectively.ConclusionsBenefited by different network structures, NP_CBiR can effectively extract local features and bases order features of DNA sequences, thus can be considered as a complementary tool for nucleosome positioning.

Numerical Characterization of DNA Sequences for Alignment-free Sequence Comparison - A Review.

Biological macromolecules, namely, DNA, RNA, and protein, have their building blocks organized in a particular sequence and the sequential arrangement encodes the evolutionary history of the organism (species). Hence, biological sequences have been used for studying evolutionary relationships among the species. This is usually carried out by Multiple Sequence Algorithms (MSA). Due to certain limitations of MSA, alignment-free sequence comparison methods were developed. The present review is on alignment-free sequence comparison methods carried out using the numerical characterization of DNA sequences. The graphical representation of DNA sequences by chaos game representation and other 2-dimensional and 3-dimensional methods are discussed. The evolution of numerical characterization from the various graphical representations and the application of the DNA invariants thus computed in phylogenetic analysis are presented. The extension of computing molecular descriptors in chemometrics to the calculation of a new set of DNA invariants and their use in alignment-free sequence comparison in an N-dimensional space and construction of phylogenetic trees are also reviewed. The phylogenetic tress constructed by the alignment-free sequence comparison methods using DNA invariants were found to be better than those constructed using alignment-based tools such as PHLYIP and ClustalW. One of the graphical representation methods is now extended to study viral sequences of infectious diseases for the identification of conserved regions to design peptidebased vaccines by combining numerical characterization and graphical representation.

DeLUCS: Deep learning for unsupervised clustering of DNA sequences.

We present a novel Deep Learning method for the Unsupervised Clustering of DNA Sequences (DeLUCS) that does not require sequence alignment, sequence homology, or (taxonomic) identifiers. DeLUCS uses Frequency Chaos Game Representations (FCGR) of primary DNA sequences, and generates “mimic” sequence FCGRs to self-learn data patterns (genomic signatures) through the optimization of multiple neural networks. A majority voting scheme is then used to determine the final cluster assignment for each sequence. The clusters learned by DeLUCS match true taxonomic groups for large and diverse datasets, with accuracies ranging from 77% to 100%: 2,500 complete vertebrate mitochondrial genomes, at taxonomic levels from sub-phylum to genera; 3,200 randomly selected 400 kbp-long bacterial genome segments, into clusters corresponding to bacterial families; three viral genome and gene datasets, averaging 1,300 sequences each, into clusters corresponding to virus subtypes. DeLUCS significantly outperforms two classic clustering methods (K-means++ and Gaussian Mixture Models) for unlabelled data, by as much as 47%. DeLUCS is highly effective, it is able to cluster datasets of unlabelled primary DNA sequences totalling over 1 billion bp of data, and it bypasses common limitations to classification resulting from the lack of sequence homology, variation in sequence length, and the absence or instability of sequence annotations and taxonomic identifiers. Thus, DeLUCS offers fast and accurate DNA sequence clustering for previously intractable datasets.

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

DNA sequence classification is one of the major challenges in biological data processing. The identification and classification of novel viral genome sequences drastically help in reducing the dangers of a viral outbreak like COVID-19. The more accurate the classification of these viruses, the faster a vaccine can be produced to counter them. Thus, more accurate methods should be utilized to classify the viral DNA. This research proposes a hybrid deep learning model for efficient viral DNA sequence classification. A genetic algorithm (GA) was utilized for weight optimization with Convolutional Neural Networks (CNN) architecture. Furthermore, Long Short-Term Memory (LSTM) as well as Bidirectional CNN-LSTM model architectures are employed. Encoding methods are needed to transform the DNA into numeric format for the proposed model. Three different encoding methods to represent DNA sequences as input to the proposed model were experimented: k-mer, label encoding, and one hot vector encoding. Furthermore, an efficient oversampling method was applied to overcome the imbalanced dataset issues. The performance of the proposed GA optimized CNN hybrid model using label encoding achieved the highest classification accuracy of 94.88% compared with other encoding methods.

DeePhage: distinguishing virulent and temperate phage-derived sequences in metavirome data with a deep learning approach.

BackgroundProkaryotic viruses referred to as phages can be divided into virulent and temperate phages. Distinguishing virulent and temperate phage–derived sequences in metavirome data is important for elucidating their different roles in interactions with bacterial hosts and regulation of microbial communities. However, there is no experimental or computational approach to effectively classify their sequences in culture-independent metavirome. We present a new computational method, DeePhage, which can directly and rapidly judge each read or contig as a virulent or temperate phage–derived fragment.FindingsDeePhage uses a “one-hot” encoding form to represent DNA sequences in detail. Sequence signatures are detected via a convolutional neural network to obtain valuable local features. The accuracy of DeePhage on 5-fold cross-validation reaches as high as 89%, nearly 10% and 30% higher than that of 2 similar tools, PhagePred and PHACTS. On real metavirome, DeePhage correctly predicts the highest proportion of contigs when using BLAST as annotation, without apparent preferences. Besides, DeePhage reduces running time vs PhagePred and PHACTS by 245 and 810 times, respectively, under the same computational configuration. By direct detection of the temperate viral fragments from metagenome and metavirome, we furthermore propose a new strategy to explore phage transformations in the microbial community. The ability to detect such transformations provides us a new insight into the potential treatment for human disease.ConclusionsDeePhage is a novel tool developed to rapidly and efficiently identify 2 kinds of phage fragments especially for metagenomics analysis. DeePhage is freely available via http://cqb.pku.edu.cn/ZhuLab/DeePhage or https://github.com/shufangwu/DeePhage.

Covid-19 diagnosis by combining RT-PCR and pseudo-convolutional machines to characterize virus sequences

The Covid-19 pandemic, a disease transmitted by the SARS-CoV-2 virus, has already caused the infection of more than 120 million people, of which 70 million have been recovered, while 3 million people have died. The high speed of infection has led to the rapid depletion of public health resources in most countries. RT-PCR is Covid-19’s reference diagnostic method. In this work we propose a new technique for representing DNA sequences: they are divided into smaller sequences with overlap in a pseudo-convolutional approach and represented by co-occurrence matrices. This technique eliminates multiple sequence alignment. Through the proposed method, it is possible to identify virus sequences from a large database: 347,363 virus DNA sequences from 24 virus families and SARS-CoV-2. When comparing SARS-CoV-2 with virus families with similar symptoms, we obtained 0.97 pm 0.03 for sensitivity and 0.9919 pm 0.0005 for specificity with MLP classifier and 30% overlap. When SARS-CoV-2 is compared to other coronaviruses and healthy human DNA sequences, we obtained 0.99 pm 0.01 for sensitivity and 0.9986 pm 0.0002 for specificity with MLP and 50% overlap. Therefore, the molecular diagnosis of Covid-19 can be optimized by combining RT-PCR and our pseudo-convolutional method to identify DNA sequences for SARS-CoV-2 with greater specificity and sensitivity.

Comparative analysis and prediction of nucleosome positioning using integrative feature representation and machine learning algorithms

BackgroundNucleosome plays an important role in the process of genome expression, DNA replication, DNA repair and transcription. Therefore, the research of nucleosome positioning has invariably received extensive attention. Considering the diversity of DNA sequence representation methods, we tried to integrate multiple features to analyze its effect in the process of nucleosome positioning analysis. This process can also deepen our understanding of the theoretical analysis of nucleosome positioning.ResultsHere, we not only used frequency chaos game representation (FCGR) to construct DNA sequence features, but also integrated it with other features and adopted the principal component analysis (PCA) algorithm. Simultaneously, support vector machine (SVM), extreme learning machine (ELM), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and convolutional neural networks (CNN) are used as predictors for nucleosome positioning prediction analysis, respectively. The integrated feature vector prediction quality is significantly superior to a single feature. After using principal component analysis (PCA) to reduce the feature dimension, the prediction quality of H. sapiens dataset has been significantly improved.ConclusionsComparative analysis and prediction on H. sapiens, C. elegans, D. melanogaster and S. cerevisiae datasets, demonstrate that the application of FCGR to nucleosome positioning is feasible, and we also found that integrative feature representation would be better.

Transcription factor binding site detection using convolutional neural networks with a functional group-based data representation

Transcription factors (TFs) play an essential role in molecular biology by regulating gene expression. The binding sites of TFs can vary by a large amount and the numerous possible binding locations make their detection a challenging issue. Recently, several machine learning approaches using nucleotide sequence data were applied to classify DNA sequences regarding Transcription Factor Binding Sites (TFBS). We propose a novel training strategy without the traditional 1D nucleotide-based DNA sequence representation by instead using a 2D topological matrix of sub-nucleotide chemical functional groups substantially defining the protein binding ability of DNA fragments. We train convolutional neural networks using this novel Functional Group DNA Representation (FGDR) to solve a TFBS classification task. We compare our results with the efficiency of previous nucleotide-based training approaches and show that learning from an FGDR data sequence has several benefits regarding TFBS classification. Moreover, we reason that learning deep neural networks from the FGDR representation produces competitive results while only introducing a pre-processing conversion step. Finally, we show that employing an ensemble of models from the nucleotide and FGDR representations for network training results in higher classification performance than any of the single input approaches.