Sequence Clustering Algorithm Research Articles

AptamerRunner: An accessible aptamer structure prediction and clustering algorithm for visualization of selected aptamers

Aptamers are short single-stranded DNA or RNA molecules with high affinity and specificity for targets and are generated using the iterative Systematic Evolution of Ligands by EXponential enrichment (SELEX) process. Next-generation sequencing (NGS) revolutionized aptamer selections by allowing a more comprehensive analysis of SELEX-enriched aptamers as compared to Sanger sequencing. The current challenge with aptamer NGS datasets is identifying a diverse cohort of candidate aptamers with the highest likelihood of successful experimental validation. Herein we present AptamerRunner, an aptamer sequence and/or structure clustering algorithm that synergistically integrates computational analysis with visualization and expertise-directed decision making. The visual integration of networked aptamers with ranking data, such as fold enrichment or scoring algorithm results, represents a significant advancement over existing clustering tools by providing a natural context to depict groups of aptamers from which ranked or scored candidates can be chosen for experimental validation. The inherent flexibility, user-friendly design, and prospects for future enhancements with AptamerRunner has broad-reaching implications for aptamer researchers across a wide range of disciplines.

Interpretable sequence clustering

Categorical sequence clustering is vital across various domains; however, the interpretability of cluster assignments presents considerable challenges. Sequences inherently lack explicit features, and existing sequence clustering algorithms heavily rely on complex representations, which complicates the explanation of their outcomes. To address this issue, we propose a method called Interpretable Sequence Clustering Tree (ISCT), which combines sequential patterns with a concise and interpretable tree structure. ISCT leverages k−1 patterns to generate k leaf nodes, corresponding to k clusters, which provides an intuitive explanation on how each cluster is formed. More precisely, ISCT first projects sequences into random subspaces and then utilizes the k-means algorithm to obtain high-quality initial cluster assignments. Subsequently, it constructs a pattern-based decision tree using a boosting strategy in which sequences are re-projected and re-clustered at each node before mining the top-1 discriminative splitting pattern. Experimental results on 14 real-world data sets demonstrate that our proposed method provides an interpretable tree structure while delivering fast and accurate cluster assignments.

Random forest clustering for discrete sequences

As one of the most popular machine learning methods, random forests have been successfully applied to different data analysis tasks such as classification, regression and cluster analysis. Recently, the random forest clustering method has received much attention due to its simplicity, accuracy and robustness. However, we cannot directly employ the random forest clustering algorithm to solve the discrete sequence clustering problem because of the lack of explicit features and “negative” sequences. In this paper, we propose a new random forest clustering algorithm for discrete sequences. The proposed method firstly injects a set of decoy sequences and then constructs the random forest in a supervised and adaptive manner by generating features on the fly. Experimental results on real data sets show that the proposed method can achieve better performance than those state-of-the-art discrete sequence clustering algorithms.

A New Method of Time-Series Event Prediction Based on Sequence Labeling

In the existing research on time-series event prediction (TSEP) methods, most of the work is focused on improving the algorithm for classifying subsequence sets (sets composed of multiple adjacent subsequences). However, these prediction methods ignore the timing dependence between the subsequence sets, nor do they capture the mutual transition relationship between events, the prediction effect on a small sample data set is very poor. Meanwhile, the sequence labeling problem is one of the common problems in natural language processing and image segmentation. To solve this problem, this paper proposed a new framework for time-series event prediction, which transforms the event prediction problem into a labeling problem, to better capture the timing relationship between the subsequence sets. Specifically, the framework used a sequence clustering algorithm for the first time to identify representative patterns in the time series, then represented the set of subsequences as a weighted combination of patterns, and used the eXtreme gradient boosting algorithm (XGBoost) for feature selection. After that, the selected pattern feature was used as the input of the long-term short-term memory model (LSTM) to obtain the preliminary prediction value. Furthermore, the fully-linked conditional random field (CRF) was used to smooth and refine the preliminary prediction value to obtain the final prediction result. Finally, the experimental results of event prediction on five real data sets show that the CX-LC method has a certain improvement in prediction accuracy compared with the other six models.

SCRAPT: an iterative algorithm for clustering large 16S rRNA gene data sets.

16S rRNA gene sequence clustering is an important tool in characterizing the diversity of microbial communities. As 16S rRNA gene data sets are growing in size, existing sequence clustering algorithms increasingly become an analytical bottleneck. Part of this bottleneck is due to the substantial computational cost expended on small clusters and singleton sequences. We propose an iterative sampling-based 16S rRNA gene sequence clustering approach that targets the largest clusters in the data set, allowing users to stop the clustering process when sufficient clusters are available for the specific analysis being targeted. We describe a probabilistic analysis of the iterative clustering process that supports the intuition that the clustering process identifies the larger clusters in the data set first. Using real data sets of 16S rRNA gene sequences, we show that the iterative algorithm, coupled with an adaptive sampling process and a mode-shifting strategy for identifying cluster representatives, substantially speeds up the clustering process while being effective at capturing the large clusters in the data set. The experiments also show thatSCRAPT(Sample, Cluster, Recruit, AdaPt and iTerate) is able to produce operational taxonomic units that are less fragmented than popular tools: UCLUST, CD-HIT and DNACLUST. The algorithm is implemented in the open-source package SCRAPT. The source code used to generate the results presented in this paper is available at https://github.com/hsmurali/SCRAPT.

LotuS2: an ultrafast and highly accurate tool for amplicon sequencing analysis

BackgroundAmplicon sequencing is an established and cost-efficient method for profiling microbiomes. However, many available tools to process this data require both bioinformatics skills and high computational power to process big datasets. Furthermore, there are only few tools that allow for long read amplicon data analysis. To bridge this gap, we developed the LotuS2 (less OTU scripts 2) pipeline, enabling user-friendly, resource friendly, and versatile analysis of raw amplicon sequences.ResultsIn LotuS2, six different sequence clustering algorithms as well as extensive pre- and post-processing options allow for flexible data analysis by both experts, where parameters can be fully adjusted, and novices, where defaults are provided for different scenarios.We benchmarked three independent gut and soil datasets, where LotuS2 was on average 29 times faster compared to other pipelines, yet could better reproduce the alpha- and beta-diversity of technical replicate samples. Further benchmarking a mock community with known taxon composition showed that, compared to the other pipelines, LotuS2 recovered a higher fraction of correctly identified taxa and a higher fraction of reads assigned to true taxa (48% and 57% at species; 83% and 98% at genus level, respectively). At ASV/OTU level, precision and F-score were highest for LotuS2, as was the fraction of correctly reported 16S sequences.ConclusionLotuS2 is a lightweight and user-friendly pipeline that is fast, precise, and streamlined, using extensive pre- and post-ASV/OTU clustering steps to further increase data quality. High data usage rates and reliability enable high-throughput microbiome analysis in minutes.AvailabilityLotuS2 is available from GitHub, conda, or via a Galaxy web interface, documented at http://lotus2.earlham.ac.uk/.6hTcPpJ8wvT9bQx45qQZLRVideo

Hybrid CNN-LSTM and modified wild horse herd Model-based prediction of genome sequences for genetic disorders

Structural genomic rearrangements are a major source of genetic disorders. The main objective of the proposed work is the detection of changes or mutations that occur in a single gene of the Deoxyribonucleic acid (DNA) sequence in the human genome. More specifically, autosomal dominant inheritance from either parent causes Monogenetic or Single-gene disorders. The proposed work of prediction of monogenetic disorders uses two different approaches. The first approach is the clustering method that uses the Microsoft sequence clustering algorithm and Needleman–Wunsch algorithm for sequence alignment. The second one is the formulation of the hybrid Convolution Neural Network (CNN) and Long short-term memory (LSTM) architecture for accurate genetic disorder prediction. The modified wild horse herd optimization (MWHHO) technique is used to enhance the weight function of the hybrid CNN-LSTM architecture. The MWHHO algorithm is formed by integrating the operations of horse herd optimization and the wild horse algorithm. Experimental findings employing the NCBI dataset demonstrate that the proposed approach has a high-performance accuracy when compared to the previous technique in the prediction of monogenetic disorders such as Marfan syndrome, Prader-Willi syndrome, and Angelman syndromes. The proposed CNN-LSTM-based MWHHO algorithm is compared to several baseline techniques in terms of AUC and error rate, including COBRA, Deep Learning, Ensemble methodology, WHISTLE, Network-based classification, LVQ-CGA, and DNN. When evaluated with the F-Score, the proposed model obtains a value of 94.83%, 90.69%, and 91.53% for the NCBI SARS-COV-2, ENCPP, and UBE3A datasets respectively. In summary, the proposed model offers improved accuracies of 98.25%, 97.89%, and 96.53% for the SARC-CoV-2, ENCPP, and UBE3A datasets.

NGIA: A novel Greedy Incremental Alignment based algorithm for gene sequence clustering

Gene sequence clustering is very basic and important in computational biology and bioinformatics for the study of phylogenetic relationships and gene function prediction, etc. With the rapid growth of the amount of biological data (gene/protein sequences), gene sequence clustering algorithms face more challenges in low precision and efficiency. The growing redundant sequences in gene sequence databases usually contribute to the increasing memory and computing demand for most clustering methods. For example, the original greedy incremental alignment-based (GIA) clustering algorithm obtains high precision clustering results, but with very poor efficiency. Efficient greedy incremental clustering algorithms have been developed with a cost of precision reduction, which usually trade clustering precision off for speed improvement. Algorithms with a better balance between precision and speed are needed. This paper proposes a novel Greedy Incremental Alignment-based algorithm called nGIA for gene clustering with high efficiency and precision. nGIA consists of a pre-filter, a modified short word filter, a new data packing strategy, a modified greedy incremental method, and is parallelized via GPU. The experimental evaluations on four independent datasets show that the proposed tool can cluster datasets with high precisions of 99.99%. Compared with the results of CD-HIT, Vsearch, and Uclust, nGIA is on average 13.6x, 6.2x, and 1.7x faster. In addition, we have developed a multi-node version to handle large data sets. The strong scalability test shows that the multi-node version of nGIA can scale up to 32 threads with a 31% parallel efficiency. The software is available at https://github.com/SIAT-HPCC/gene-sequence-clustering.

An accurate and exact clustering algorithm for next generation sequencing metagenomic sequences

Clustering algorithms are the essential tools in the target metagenomics, used to perform the taxonomic profiling of microbial communities. In the present study, an algorithmic tool called hash‐based exact alignment (HBEA) clustering algorithm is presented, which uses exact pairwise global alignment algorithm to improve the cluster quality and creates a hash table for extraction of cluster representatives. The algorithm is de novo based and uses the general de facto 97% sequence similarity score to cluster the sequences. Our experimental investigation on various types of datasets with distinct parameters and attributes showed that HBEA produces better operational taxonomic unit (OTU) clusters and computational complexity than other algorithms.

An Approach of Leading Sequence Clustering (LSC) Algorithm based Scheduling and Agglomerative Mean Shift Clustering for Load Balancing in Cloud

An Approach of Leading Sequence Clustering (LSC) Algorithm based Scheduling and Agglomerative Mean Shift Clustering for Load Balancing in Cloud

Novel Approach to Task Scheduling and Load Balancing Using the Dominant Sequence Clustering and Mean Shift Clustering Algorithms

Cloud computing (CC) is fast-growing and frequently adopted in information technology (IT) environments due to the benefits it offers. Task scheduling and load balancing are amongst the hot topics in the realm of CC. To overcome the shortcomings of the existing task scheduling and load balancing approaches, we propose a novel approach that uses dominant sequence clustering (DSC) for task scheduling and a weighted least connection (WLC) algorithm for load balancing. First, users’ tasks are clustered using the DSC algorithm, which represents user tasks as graph of one or more clusters. After task clustering, each task is ranked using Modified Heterogeneous Earliest Finish Time (MHEFT) algorithm. where the highest priority task is scheduled first. Afterwards, virtual machines (VM) are clustered using a mean shift clustering (MSC) algorithm using kernel functions. Load balancing is subsequently performed using a WLC algorithm, which distributes the load based on server weight and capacity as well as client connectivity to server. A highly weighted or least connected server is selected for task allocation, which in turn increases the response time. Finally, we evaluate the proposed architecture using metrics such as response time, makespan, resource utilization, and service reliability.

A mixed‐integer programming approach for clustering demand data for multiscale mathematical programming applications

AbstractAcross all sectors within the energy and process industry, tremendous efforts have been devoted toward the development and operation of agile manufacturing techniques to respond to customer needs and volatile markets while at the same time control costs, improve efficiency, and reduce pollution. This has created a demand for systems to solve complex integrated planning and scheduling problems that bridge the gap between the different functional and strategic decision‐making levels. Integration across supply chain decision levels is key to improving investment returns. Different approaches have been proposed to tackle this problem. However, most of them are problem‐specific or applicable only to short time horizons. Clustering has the potential to handle such problems by grouping similar input parameters together and considerably reduce the model size while not compromising solution accuracy. This work presents a new class of clustering algorithms to support the integration of planning applications of different time scales. The clustering algorithms were formulated using integer programming with integral absolute error as similarity measure. The algorithms were successfully applied to clustering electricity demand data and applied to the unit commitment problem. The computational performances of the proposed normal and sequence clustering algorithms were compared against a full planning model that does not employ clustering. The results show a clear advantage in terms of solution time compared to the full‐scale case while maintaining solution accuracy.

A Scalable Feature Based Clustering Algorithm for Sequences with Many Distinct Items

A Scalable Feature Based Clustering Algorithm for Sequences with Many Distinct Items

Small-variance asymptotics for non-parametric online robot learning

Small-variance asymptotics is emerging as a useful technique for inference in large-scale Bayesian non-parametric mixture models. This paper analyzes the online learning of robot manipulation tasks with Bayesian non-parametric mixture models under small-variance asymptotics. The analysis yields a scalable online sequence clustering (SOSC) algorithm that is non-parametric in the number of clusters and the subspace dimension of each cluster. SOSC groups the new datapoint in low-dimensional subspaces by online inference in a non-parametric mixture of probabilistic principal component analyzers (MPPCA) based on a Dirichlet process, and captures the state transition and state duration information online in a hidden semi-Markov model (HSMM) based on a hierarchical Dirichlet process. A task-parameterized formulation of our approach autonomously adapts the model to changing environmental situations during manipulation. We apply the algorithm in a teleoperation setting to recognize the intention of the operator and remotely adjust the movement of the robot using the learned model. The generative model is used to synthesize both time-independent and time-dependent behaviors by relying on the principles of shared and autonomous control. Experiments with the Baxter robot yield parsimonious clusters that adapt online with new demonstrations and assist the operator in performing remote manipulation tasks.

Metagenome sequence clustering with hash-based canopies.

Metagenomics is the collective sequencing of co-existing microbial communities which are ubiquitous across various clinical and ecological environments. Due to the large volume and random short sequences (reads) obtained from community sequences, analysis of diversity, abundance and functions of different organisms within these communities are challenging tasks. We present a fast and scalable clustering algorithm for analyzing large-scale metagenome sequence data. Our approach achieves efficiency by partitioning the large number of sequence reads into groups (called canopies) using hashing. These canopies are then refined by using state-of-the-art sequence clustering algorithms. This canopy-clustering (CC) algorithm can be used as a pre-processing phase for computationally expensive clustering algorithms. We use and compare three hashing schemes for canopy construction with five popular and state-of-the-art sequence clustering methods. We evaluate our clustering algorithm on synthetic and real-world 16S and whole metagenome benchmarks. We demonstrate the ability of our proposed approach to determine meaningful Operational Taxonomic Units (OTU) and observe significant speedup with regards to run time when compared to different clustering algorithms. We also make our source code publicly available on Github. a.

Phenotype Prediction from Metagenomic Data Using Clustering and Assembly with Multiple Instance Learning (CAMIL).

The recent advent of Metagenome Wide Association Studies (MGWAS) provides insight into the role of microbes on human health and disease. However, the studies present several computational challenges. In this paper, we demonstrate a novel, efficient, and effective Multiple Instance Learning (MIL) based computational pipeline to predict patient phenotype from metagenomic data. MIL methods have the advantage that besides predicting the clinical phenotype, we can infer the instance level label or role of microbial sequence reads in the specific disease. Specifically, we use a Bag of Words method, which has been shown to be one of the most effective and efficient MIL methods. This involves assembly of the metagenomic sequence data, clustering of the assembled contigs, extracting features from the contigs, and using an SVM classifier to predict patient labels and identify the most relevant sequence clusters. With the exception of the given labels for the patients, this entire process is de novo (unsupervised). We call our pipeline "CAMIL", which stands for Clustering and Assembly with Multiple Instance Learning. We use multiple state-of-the-art clustering methods for feature extraction, evaluation, and comparison of the performance of our proposed approach for each of these clustering methods. We also present a fast and scalable pre-clustering algorithm as a preprocessing step for our proposed pipeline. Our approach achieves efficiency by partitioning the large number of sequence reads into groups (called canopies) using locality sensitive hashing (LSH). These canopies are then refined by using state-of-the-art sequence clustering algorithms. We use data from a well-known MGWAS study of patients with Type-2 Diabetes and show that our pipeline significantly outperforms the classifier used in that paper, as well as other common MIL methods.

A segmentation method for lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise.

The fast and accurate segmentation of lung nodule image sequences is the basis of subsequent processing and diagnostic analyses. However, previous research investigating nodule segmentation algorithms cannot entirely segment cavitary nodules, and the segmentation of juxta-vascular nodules is inaccurate and inefficient. To solve these problems, we propose a new method for the segmentation of lung nodule image sequences based on superpixels and density-based spatial clustering of applications with noise (DBSCAN). First, our method uses three-dimensional computed tomography image features of the average intensity projection combined with multi-scale dot enhancement for preprocessing. Hexagonal clustering and morphological optimized sequential linear iterative clustering (HMSLIC) for sequence image oversegmentation is then proposed to obtain superpixel blocks. The adaptive weight coefficient is then constructed to calculate the distance required between superpixels to achieve precise lung nodules positioning and to obtain the subsequent clustering starting block. Moreover, by fitting the distance and detecting the change in slope, an accurate clustering threshold is obtained. Thereafter, a fast DBSCAN superpixel sequence clustering algorithm, which is optimized by the strategy of only clustering the lung nodules and adaptive threshold, is then used to obtain lung nodule mask sequences. Finally, the lung nodule image sequences are obtained. The experimental results show that our method rapidly, completely and accurately segments various types of lung nodule image sequences.

Representative Points and Cluster Attributes Based Incremental Sequence Clustering Algorithm

In order to improve the execution time and clustering quality of sequence clustering algorithm in large-scale dynamic dataset, a novel algorithm RPCAISC (Representative Points and Cluster Attributes Based Incremental Sequence Clustering) was presented. In this paper, density factor is defined. The primary representative point that has a density factor less than the prescribed threshold will be deleted directly. New representative points can be reselected from non-representative points. Moreover, the representative points of each cluster are modeled using the K-nearest neighbor method. The definition of the relevant degree (RD) between clusters was also proposed. The RD is computed by comprehensively considering the correlations of objects within a cluster and between different clusters. Then, whether the two clusters need to merge is determined. Additionally, the cluster attributes of the initial clustering are retained with this process. By calculating the matching degree between the incremental sequence and the existing cluster attributes, dynamic sequence clustering can be achieved. The theoretic experimental results and analysis prove that RPCAISC has better correct rate of clustering results and execution efficiency.

New Hierarchical Clustering Algorithm for Protein Sequences Based on Hellinger Distance

New Hierarchical Clustering Algorithm for Protein Sequences Based on Hellinger Distance

Sequence clustering algorithm based on weighted vector identification

Sequence clustering has become an important topic that experts in data mining are currently investigating. However, clustering quality is typically significantly affected by both the selection of initial centers and the mean sequences. In this study, the sequence clustering algorithm based on weighted vector identification (SCAWVI) algorithm is developed based on sequence element composite similarity and the weight of a sequence in its corresponding cluster. Based on the weighted sequence element, all sequences in the sequence database are preprocessed into M-dimensional weighted vector identifications. Then, using Huffman-based initial clustering centers optimization algorithm, the initial clustering centers are optimized. In addition, the weighted vector identification and the weight of a sequence in its corresponding cluster are used to update the clustering centers. The theoretical experimental results and the analysis results in this study show that the SCAWVI algorithm has a higher rate of accurate results in its clustering results and higher execution efficiency.