Deep Learning for Taxonomic Classification of Biological Bacterial Sequences

Biological sequence data mining is hot spot in bioinformatics. A biological sequence can be regarded as a set of characters. Time series is similar to biological sequences in terms of both representation and mechanism. Therefore, in the article, biological sequences are represented with time series to obtain biological time sequence (BTS). Hybrid ensemble learning framework (SaPt-CNN-LSTM-AR-EA) for BTS is proposed. Single-sequence and multi-sequence models are respectively constructed with self-adaption pre-training one-dimensional convolutional recurrent neural network and autoregressive fractional integrated moving average fused evolutionary algorithm. In DNA sequence experiments with six viruses, SaPt-CNN-LSTM-AR-EA realized the good overall prediction performance and the prediction accuracy and correlation respectively reached 1.7073 and 0.9186. SaPt-CNN-LSTM-AR-EA was compared with other five benchmark models so as to verify its effectiveness and stability. SaPt-CNN-LSTM-AR-EA increased the average accuracy by about 30%. The framework proposed in this article is significant in biology, biomedicine, and computer science, and can be widely applied in sequence splicing, computational biology, bioinformation, and other fields.

BackgroundSimilarity of sequences is a key mathematical notion for Classification and Phylogenetic studies in Biology. It is currently primarily handled using alignments. However, the alignment methods seem inadequate for post-genomic studies since they do not scale well with data set size and they seem to be confined only to genomic and proteomic sequences. Therefore, alignment-free similarity measures are actively pursued. Among those, USM (Universal Similarity Metric) has gained prominence. It is based on the deep theory of Kolmogorov Complexity and universality is its most novel striking feature. Since it can only be approximated via data compression, USM is a methodology rather than a formula quantifying the similarity of two strings. Three approximations of USM are available, namely UCD (Universal Compression Dissimilarity), NCD (Normalized Compression Dissimilarity) and CD (Compression Dissimilarity). Their applicability and robustness is tested on various data sets yielding a first massive quantitative estimate that the USM methodology and its approximations are of value. Despite the rich theory developed around USM, its experimental assessment has limitations: only a few data compressors have been tested in conjunction with USM and mostly at a qualitative level, no comparison among UCD, NCD and CD is available and no comparison of USM with existing methods, both based on alignments and not, seems to be available.ResultsWe experimentally test the USM methodology by using 25 compressors, all three of its known approximations and six data sets of relevance to Molecular Biology. This offers the first systematic and quantitative experimental assessment of this methodology, that naturally complements the many theoretical and the preliminary experimental results available. Moreover, we compare the USM methodology both with methods based on alignments and not. We may group our experiments into two sets. The first one, performed via ROC (Receiver Operating Curve) analysis, aims at assessing the intrinsic ability of the methodology to discriminate and classify biological sequences and structures. A second set of experiments aims at assessing how well two commonly available classification algorithms, UPGMA (Unweighted Pair Group Method with Arithmetic Mean) and NJ (Neighbor Joining), can use the methodology to perform their task, their performance being evaluated against gold standards and with the use of well known statistical indexes, i.e., the F-measure and the partition distance. Based on the experiments, several conclusions can be drawn and, from them, novel valuable guidelines for the use of USM on biological data. The main ones are reported next.ConclusionUCD and NCD are indistinguishable, i.e., they yield nearly the same values of the statistical indexes we have used, accross experiments and data sets, while CD is almost always worse than both. UPGMA seems to yield better classification results with respect to NJ, i.e., better values of the statistical indexes (10% difference or above), on a substantial fraction of experiments, compressors and USM approximation choices. The compression program PPMd, based on PPM (Prediction by Partial Matching), for generic data and Gencompress for DNA, are the best performers among the compression algorithms we have used, although the difference in performance, as measured by statistical indexes, between them and the other algorithms depends critically on the data set and may not be as large as expected. PPMd used with UCD or NCD and UPGMA, on sequence data is very close, although worse, in performance with the alignment methods (less than 2% difference on the F-measure). Yet, it scales well with data set size and it can work on data other than sequences. In summary, our quantitative analysis naturally complements the rich theory behind USM and supports the conclusion that the methodology is worth using because of its robustness, flexibility, scalability, and competitiveness with existing techniques. In particular, the methodology applies to all biological data in textual format. The software and data sets are available under the GNU GPL at the supplementary material web page.

Deep learning (DL) has become a powerful tool for the recognition and classification of biological sequences. However, conventional single-architecture models often struggle with suboptimal predictive performance and high computational costs. To address these challenges, we present EnsembleDL-Lipo, an innovative ensemble deep learning framework that combines Convolutional Neural Networks (CNNs) and Deep Neural Networks (DNNs) to enhance the identification of lipocalin sequences. Lipocalins are multifunctional extracellular proteins involved in various diseases and stress responses, and their low sequence similarity and occurrence in the 'twilight zone' of sequence alignment present significant hurdles for accurate classification. These challenges necessitate efficient computational methods to complement traditional, labor-intensive experimental approaches. EnsembleDL-Lipo overcomes these issues by leveraging a set of PSSM-based features to train a large ensemble of deep learning models. The framework integrates multiple feature representations derived from position-specific scoring matrices (PSSMs), optimizing classification performance across diverse sequence patterns. The model achieved superior results on the training dataset, with an accuracy (ACC) of 97.65%, recall of 97.10%, Matthews correlation coefficient (MCC) of 0.95, and area under the curve (AUC) of 0.99. Validation on an independent test set further confirmed the robustness of the model, yielding an ACC of 95.79%, recall of 90.48%, MCC of 0.92, and AUC of 0.97. These results demonstrate that EnsembleDL-Lipo is a highly effective and computationally efficient tool for lipocalin sequence identification, significantly outperforming existing methods and offering strong potential for applications in biomarker discovery.

BackgroundMany open problems in bioinformatics involve elucidating underlying functional signals in biological sequences. DNA sequences, in particular, are characterized by rich architectures in which functional signals are increasingly found to combine local and distal interactions at the nucleotide level. Problems of interest include detection of regulatory regions, splice sites, exons, hypersensitive sites, and more. These problems naturally lend themselves to formulation as classification problems in machine learning. When classification is based on features extracted from the sequences under investigation, success is critically dependent on the chosen set of features.MethodologyWe present an algorithmic framework (EFFECT) for automated detection of functional signals in biological sequences. We focus here on classification problems involving DNA sequences which state-of-the-art work in machine learning shows to be challenging and involve complex combinations of local and distal features. EFFECT uses a two-stage process to first construct a set of candidate sequence-based features and then select a most effective subset for the classification task at hand. Both stages make heavy use of evolutionary algorithms to efficiently guide the search towards informative features capable of discriminating between sequences that contain a particular functional signal and those that do not.ResultsTo demonstrate its generality, EFFECT is applied to three separate problems of importance in DNA research: the recognition of hypersensitive sites, splice sites, and ALU sites. Comparisons with state-of-the-art algorithms show that the framework is both general and powerful. In addition, a detailed analysis of the constructed features shows that they contain valuable biological information about DNA architecture, allowing biologists and other researchers to directly inspect the features and potentially use the insights obtained to assist wet-laboratory studies on retainment or modification of a specific signal. Code, documentation, and all data for the applications presented here are provided for the community at http://www.cs.gmu.edu/~ashehu/?q=OurTools.

Sequences occur naturally in many domains such as biology, engineering, finance and scientific research. Since humans have the inherent ability to comprehend and utilize sequences in day to day cognitive tasks such as speech, vision and motor control; biologically inspired sequence learning techniques are used for explanatory data analysis in these domains. Identifying the common substrings which exist in sequences helps in determining the underlying structure and calculating the similarity between sequences. The suffix trie, suffix tree and suffix array are data structures which are used in many solutions to sequence based problems. However, these are static data structures and not flexible tools which can be used for sequence learning. In this paper we present the Adaptive Suffix Trie algorithm, a sequence learning algorithm which can be used for identifying substrings of different lengths and frequencies from a given set of sequences. In contrast to suffix data structures which store all suffixes, the adaptive suffix trie only captures the frequent substrings that occur in the given dataset, resulting in a less complex structure with only the relevant or useful information. We show how the algorithms' learning parameters can be adapted for extracting substrings with the required characteristics and then demonstrate it's application in the classification of biological sequences.

layerUMAP: A tool for visualizing and understanding deep learning models in biological sequence classification using UMAP.

In this paper, we propose a new image super-resolution (SR) approach based on a convolutional neural network (CNN), which jointly learns the feature extraction, upsampling, and high-resolution (HR) reconstruction modules, yielding a completely end-to-end trainable deep CNN. However, directly training such a deep network in an end-to-end fashion is challenging, which takes a longer time to converge and may lead to sub-optimal results. To address this issue, we propose to jointly train an ensemble of deep and shallow networks. The shallow network with weaker learning capability restores the main structure of the image content, while the deep network with stronger representation power captures the high-frequency details. Since the shallow network is much easier to optimize, it significantly lowers the difficulty of deep network optimization during joint training. To further ensure more accurate restoration of HR images, the high-frequency details are reconstructed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information. The proposed method is extensively evaluated on widely adopted data sets and compares favorably against state-of-the-art methods. In-depth ablation studies are conducted to verify the contributions of different network designs to image SR, providing additional insights for future research.

In order to solve the problem of low detection efficiency of remote sensing image using convolutional neural network. a faster detection algorithm based on the three levels cascade convolutional densely connected network model is established to target detection in high resolution remote sensing images. Firstly, the shallow full convolutional network is used as the first layer of cascaded network. The shallow layer network runs fast, and it can quickly filter the incorrect window in the remote sensing image. The full convolutional network can build the sliding window into the network and improve the efficiency. Secondly, the shallow network is used as the second layer network to filter the windows again after the first layer network detected. Thirdly, the third layer network uses a small densely connected network (DenseNet). Densely connected network have fewer parameters and are more accurate. It can identify the reserved windows of second layer network. The data used in the test are No.2 High resolution satellite remote sensing images. The experiment shows that for the same size picture, in the case of little difference in the correct rate, the computation time of convolutional neural network is about 1.3-1.8 times of the computing time of cascaded network.

BackgroundWhile multiple alignment is the first step of usual classification schemes for biological sequences, alignment-free methods are being increasingly used as alternatives when multiple alignments fail. Subword-based combinatorial methods are popular for their low algorithmic complexity (suffix trees ...) or exhaustivity (motif search), in general with fixed length word and/or number of mismatches. We developed previously a method to detect local similarities (the N-local decoding) based on the occurrences of repeated subwords of fixed length, which does not impose a fixed number of mismatches. The resulting similarities are, for some "good" values of N, sufficiently relevant to form the basis of a reliable alignment-free classification. The aim of this paper is to develop a method that uses the similarities detected by N-local decoding while not imposing a fixed value of N. We present a procedure that selects for every position in the sequences an adaptive value of N, and we implement it as the MS4 classification tool.ResultsAmong the equivalence classes produced by the N-local decodings for all N, we select a (relatively) small number of "relevant" classes corresponding to variable length subwords that carry enough information to perform the classification. The parameter N, for which correct values are data-dependent and thus hard to guess, is here replaced by the average repetitivity κ of the sequences. We show that our approach yields classifications of several sets of HIV/SIV sequences that agree with the accepted taxonomy, even on usually discarded repetitive regions (like the non-coding part of LTR).ConclusionsThe method MS4 satisfactorily classifies a set of sequences that are notoriously hard to align. This suggests that our approach forms the basis of a reliable alignment-free classification tool. The only parameter κ of MS4 seems to give reasonable results even for its default value, which can be a great advantage for sequence sets for which little information is available.

This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDNI) and Dynamic Depth Motion Normal Images (DDMNI). These dynamic images are constructed from a sequence of depth maps using bidirectional rank pooling to effectively capture the spatial-temporal information. Such image-based representations enable us to fine-tune the existing ConvNets models trained on image data for classification of depth sequences, without introducing large parameters to learn. Upon the proposed representations, a convolutional Neural networks (ConvNets) based method is developed for gesture recognition and evaluated on the Large-scale Isolated Gesture Recognition at the ChaLearn Looking at People (LAP) challenge 2016. The method achieved 55.57% classification accuracy and ranked 2nd place in this challenge but was very close to the best performance even though we only used depth data.

Efficient biological sequence (proteins or DNA) alignment is an important and challenging task in bioinformatics. It is similar to string matching in the context of biological data and is used to infer the evolutionary relationship between a set of protein or DNA sequences. An accurate alignment can provide valuable information for experimentation on the newly found sequences. It is indispensable in basic research as well as in practical applications such as pharmaceutical development, drug discovery, disease prevention and criminal forensics. Many algorithms and methods, such as, dot plot (Gibbs & McIntyre, 1970),Needleman-Wunsch (N-W) (Needleman & Wunsch, 1970), Smith-Waterman (S-W) (Smith & Waterman, 1981), FASTA (Pearson & Lipman, 1985), BLAST (Altschul et al., 1990), HMMER (Eddy, 1998) and ClustalW (Thompson et al., 1994) have been proposed to perform and accelerate sequence alignment activities. An overview of these methods is given in (Hasan et al., 2007). Out of these, S-W algorithm is an optimal sequence alignment method, but its computational cost makes it inappropriate for practical purposes. To develop efficient and optimal sequence alignment solutions, the S-W algorithm has recently been implemented on emerging accelerator platforms such as Field Programmable Gate Arrays (FPGAs), Cell Broadband Engine (Cell/B.E.) and Graphics Processing Units (GPUs) (Buyukkur & Najjar, 2008; Hasan et al., 2010; Liu et al., 2009; 2010; Lu et al., 2008). This chapter aims at providing a broad overview of sequence alignment in general with particular emphasis on the classification and discussion of available methods and their comparison. Further, it reviews in detail the acceleration approaches based on implementations on different platforms and provides a comparison considering different parameters. This chapter is organized as follows: The remainder of this section gives a classification, discussion and comparison of the available methods and their hardware acceleration. Section 2 introduces the S-W algorithm which is the focus of discussion in the succeeding sections. Section 3 reviews CPU-based acceleration. Section 4 provides a review of FPGA-based acceleration. Section 5 overviews GPU-based acceleration. Section 6 presents a comparison of accelerations on different platforms, whereas Section 7 concludes the chapter.

This paper shows how the newly developed paradigm of General Fuzzy Automata (GFA) can be used as a biological sequence predictor. We consider the positional correlations of amino acids in a protein family as the basic criteria for prediction and classification of unknown sequences. It will be shown how the GFA formalism can be used as an efficient tool for classification of protein sequences. The results show that this approach predicts the membership of an unknown sequence in a protein family better than profile Hidden Markov Models (HMMs) which are now a popular and putative approach in biological sequence analysis.

BackgroundDeep learning has emerged as a powerful tool in the analysis of biological data, including the analysis of large metagenome data. However, its application remains limited due to high computational costs, model complexity, and difficulty extracting biological insights from these artificial neural networks (ANNs). In this study, we applied a transfer learning approach using the ESM-2 protein structure prediction model and our own smaller ANN to classify proteins containing the domain of unknown function 3494 (DUF3494) by their source environments. DUF3494 is found in a diverse group of putative ice-binding and substrate-binding proteins across a range of environments in prokaryotic and eukaryotic microorganisms. They present a compelling test case for exploring the balance between prediction accuracy and interpretability in sequence classification.ResultsOur ANN analysed 50,669 DUF3494 sequences from publicly available metagenomes, and successfully classified a large proportion of sequences by source environment (polar marine, glacier ice, frozen sediment, rock, subsurface). We identified environment-specific features that appear to drive classification. Our best-performing ANN was able to classify between 75.9 and 97.8% of sequences correctly. To enhance biological interpretability of these predictions, we compared this model with a genetic algorithm (GA), which, although it had lower predictive ability, provided transparent classification rules and predictors. Further in silico mutagenesis of key residues uncovered a vertically aligned column of amino acids on the b-face of the protein which was important for environmental differentiation, suggesting that both methods captured distinct evolutionary and ecological aspects of the sequences. Feature importance analysis identified that steric and electronic properties of the protein were associated with predictive ability.ConclusionsOur findings highlight the utility of deep learning for classification of diverse biological sequences and provide a framework for combining methods to improve model interpretability and ecological insights.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12915-025-02361-1.

BackgroundSingular value decomposition (SVD) is a powerful technique for information retrieval; it helps uncover relationships between elements that are not prima facie related. SVD was initially developed to reduce the time needed for information retrieval and analysis of very large data sets in the complex internet environment. Since information retrieval from large-scale genome and proteome data sets has a similar level of complexity, SVD-based methods could also facilitate data analysis in this research area.ResultsWe found that SVD applied to amino acid sequences demonstrates relationships and provides a basis for producing clusters and cladograms, demonstrating evolutionary relatedness of species that correlates well with Linnaean taxonomy. The choice of a reasonable number of singular values is crucial for SVD-based studies. We found that fewer singular values are needed to produce biologically significant clusters when SVD is employed. Subsequently, we developed a method to determine the lowest number of singular values and fewest clusters needed to guarantee biological significance; this system was developed and validated by comparison with Linnaean taxonomic classification.ConclusionsBy using SVD, we can reduce uncertainty concerning the appropriate rank value necessary to perform accurate information retrieval analyses. In tests, clusters that we developed with SVD perfectly matched what was expected based on Linnaean taxonomy.

Sequence comparison i.e., The assessment of how similar two biological sequences are to each other, is a fundamental and routine task in Computational Biology and Bioinformatics. Classically, alignment methods are the de facto standard for such an assessment. In fact, considerable research efforts for the development of efficient algorithms, both on classic and parallel architectures, has been carried out in the past 50 years. Due to the growing amount of sequence data being produced, a new class of methods has emerged: Alignment-free methods. Research in this ares has become very intense in the past few years, stimulated by the advent of Next Generation Sequencing technologies, since those new methods are very appealing in terms of computational resources needed and biological relevance. Despite such an effort and in contrast with sequence alignment methods, no systematic investigation of how to take advantage of distributed architectures to speed up alignment-free methods, has taken place. We provide a contribution of that kind, by evaluating the possibility of using the Hadoop distributed framework to speed up the running times of these methods, compared to their original sequential formulation.