Search

Archival DNA samples collected and analysed for a range of research and applied questions have accumulated in the laboratories of universities, government agencies and commercial service providers for decades. These DNA archives represent a valuable, yet largely un‐tapped repository of genomic information. With lowering costs of, and increasing access to, high‐throughput sequencing, we predict an increase in retrospective research to explore the wealth of information that resides in these archival samples. However, for this to occur, we need confidence in the integrity of the DNA samples, often stored under suboptimal conditions and their fitness of purpose for downstream genomic analysis.Here, we borrow from a well‐established concept in ancient DNA to evaluate sample integrity, defined as loss of information content in recovered amplicons, of frozen DNA samples and based on the ratio of ⍺‐diversity of short‐ and long‐read 16S rRNA gene sequences.The 16S rRNA variable region of 87 stored DNA samples, extracted from soil, collected from western and southern agricultural regions of Australia between 2001 and 2021 were sequenced using both PacBio full length reads (V1–V9, 1.5 kbp) and Illumina short‐reads (V3–V4, 200–450 bp). When ⍺‐diversity ratios were calculated between the long and short reads to assess DNA degradation, the ratio of ⍺‐diversity did not decrease in older samples versus younger samples.We suggest this as a novel method to confirm integrity of DNA before embarking on large‐scale diversity profiling projects using archival DNA. [ABSTRACT FROM AUTHOR]

Abstract Archival DNA samples collected and analysed for a range of research and applied questions have accumulated in the laboratories of universities, government agencies and commercial service providers for decades. These DNA archives represent a valuable, yet largely un‐tapped repository of genomic information. With lowering costs of, and increasing access to, high‐throughput sequencing, we predict an increase in retrospective research to explore the wealth of information that resides in these archival samples. However, for this to occur, we need confidence in the integrity of the DNA samples, often stored under suboptimal conditions and their fitness of purpose for downstream genomic analysis. Here, we borrow from a well‐established concept in ancient DNA to evaluate sample integrity, defined as loss of information content in recovered amplicons, of frozen DNA samples and based on the ratio of ⍺‐diversity of short‐ and long‐read 16S rRNA gene sequences. The 16S rRNA variable region of 87 stored DNA samples, extracted from soil, collected from western and southern agricultural regions of Australia between 2001 and 2021 were sequenced using both PacBio full length reads (V1–V9, 1.5 kbp) and Illumina short‐reads (V3–V4, 200–450 bp). When ⍺‐diversity ratios were calculated between the long and short reads to assess DNA degradation, the ratio of ⍺‐diversity did not decrease in older samples versus younger samples. We suggest this as a novel method to confirm integrity of DNA before embarking on large‐scale diversity profiling projects using archival DNA.

The precise classification of DNA sequences is pivotal in genomics, holding significant implications for personalized medicine. The stakes are particularly high when classifying key genetic markers such as BRAC, related to breast cancer susceptibility; BRAF, associated with various malignancies; and KRAS, a recognized oncogene. Conventional machine learning techniques often necessitate intricate feature engineering and may not capture the full spectrum of sequence dependencies. To ameliorate these limitations, this study employs an adapted U-Net architecture, originally designed for biomedical image segmentation, to classify DNA sequences.The attention mechanism was also tested LONG WITH u-Net architecture to precisely classify DNA sequences into BRAC, BRAF, and KRAS categories. Our comprehensive methodology includes rigorous data preprocessing, model training, and a multi-faceted evaluation approach. The adapted U-Net model exhibited exceptional performance, achieving an overall accuracy of 0.96. The model also achieved high precision and recall rates across the classes, with precision ranging from 0.93 to 1.00 and recall between 0.95 and 0.97 for the key markers BRAC, BRAF, and KRAS. The F1-score for these critical markers ranged from 0.95 to 0.98. These empirical results substantiate the architecture's capability to capture local and global features in DNA sequences, affirming its applicability for critical, sequence-based bioinformatics challenges.

DNA viruses that produce persistent infections have been proposed as potential causes for the extinction of Neanderthals, and, therefore, the identification of viral genome remnants in Neanderthal sequence reads is an initial step to address this hypothesis. Here, as proof of concept, we searched for viral remnants in sequence reads of Neanderthal genome data by mapping to adenovirus, herpesvirus and papillomavirus, which are double-stranded DNA viruses that may establish lifelong latency and can produce persistent infections. The reconstructed ancient viral genomes of adenovirus, herpesvirus and papillomavirus revealed conserved segments, with nucleotide identity to extant viral genomes and variable regions in coding regions with substantial divergence to extant close relatives. Sequence reads mapped to extant viral genomes showed deamination patterns of ancient DNA, and these ancient viral genomes showed divergence consistent with the age of these samples (≈50,000 years) and viral evolutionary rates (10−5 to 10−8 substitutions/site/year). Analysis of random effects showed that the Neanderthal mapping to genomes of extant persistent viruses is above what is expected by random similarities of short reads. Also, negative control with a nonpersistent DNA virus does not yield statistically significant assemblies. This work demonstrates the feasibility of identifying viral genome remnants in archaeological samples with signal-to-noise assessment. [ABSTRACT FROM AUTHOR]

The precise classification of DNA sequences is pivotal in genomics, holding significant implications for personalized medicine. The stakes are particularly high when classifying key genetic markers such as BRAC, related to breast cancer susceptibility; BRAF, associated with various malignancies; and KRAS, a recognized oncogene. Conventional machine learning techniques often necessitate intricate feature engineering and may not capture the full spectrum of sequence dependencies. To ameliorate these limitations, this study employs an adapted U-Net architecture, originally designed for biomedical image segmentation, to classify DNA sequences.The attention mechanism was also tested LONG WITH u-Net architecture to precisely classify DNA sequences into BRAC, BRAF, and KRAS categories. Our comprehensive methodology includes rigorous data preprocessing, model training, and a multi-faceted evaluation approach. The adapted U-Net model exhibited exceptional performance, achieving an overall accuracy of 0.96. The model also achieved high precision and recall rates across the classes, with precision ranging from 0.93 to 1.00 and recall between 0.95 and 0.97 for the key markers BRAC, BRAF, and KRAS. The F1-score for these critical markers ranged from 0.95 to 0.98. These empirical results substantiate the architecture's capability to capture local and global features in DNA sequences, affirming its applicability for critical, sequence-based bioinformatics challenges. [ABSTRACT FROM AUTHOR]

Prey metabarcoding has become a popular tool in molecular ecology for resolving trophic interactions at high resolution, from various sample types and animals. To date, most predator–prey studies of small‐sized animals (<1 mm) have met the problem of overabundant predator DNA in dietary samples by adding blocking primers/peptide nucleic acids. These primers aim to limit the PCR amplification and detection of the predator DNA but may introduce bias to the prey composition identified by interacting with sequences that are similar to those of the predator. Here we demonstrate the use of an alternative method to explore the prey of small marine copepods using whole‐body DNA extracts and deep, brute force metabarcoding of an 18S rDNA fragment. After processing and curating raw data from two sequencing runs of varying depths (0.4 and 5.4 billion raw reads), we isolated 1.3 and 52.2 million prey reads, with average depths of ~15,900 and ~120,000 prey reads per copepod individual, respectively. While data from both sequencing runs were sufficient to distinguish dietary compositions from disparate seasons, locations, and copepod species, greater sequencing depth led to better separation of clusters. As computation and sequencing are becoming ever more powerful and affordable, we expect the brute force approach to become a general standard for prey metabarcoding, as it offers a simple and affordable solution to consumers that is impractical to dissect or unknown to science. [ABSTRACT FROM AUTHOR]

Lithology identification is the research basis in oil and gas reservoir exploration and is critical for the formation characterization and reservoir development. Traditional lithofacies identification methods rely on the knowledge and experience of geologists and are usually done manually. With the development of deep learning technology and its application in the field of geophysics, lithofacies identification based on deep-learning approach has attracted great attention in recent years. Well logging data have obvious sequence characteristics. Therefore, we propose to use a bidirectional long and short-term memory (BiLSTM) neural network to learn long-term information for more effective lithology facies classification. In addition, we also perform correlation analysis on the input well logging curves and conduct median filter at different scales according to the correlation degree to extract the geological features within data itself and discard the interference of noise. The raw data-based lithofacies identification can reflect the noise resistance of the neural network model to some extent, while the filtered data are more beneficial for the model to extract the geological features correlated with lithofacies and provide accurate classification results. We validate our proposed framework by applying it to a case study from the Council Grove gas reservoir located in Kansas. Furthermore, we compare the effect of input data and network model on the identification results. The experimental results show that the proposed lithofacies identification method has higher classification accuracy. [ABSTRACT FROM AUTHOR]

High-utility sequential pattern mining (HUSPM) has emerged as an important topic due to its wide application and considerable popularity. However, due to the combinatorial explosion of the search space when the HUSPM problem encounters a low-utility threshold or large-scale data, it may be time-consuming and memory-costly to address the HUSPM problem. Several algorithms have been proposed for addressing this problem, but they still cost a lot in terms of running time and memory usage. In this article, to further solve this problem efficiently, we design a compact structure called sequence projection (seqPro) and propose an efficient algorithm, namely, discovering high-utility sequential patterns with the seqPro structure (HUSPSP). HUSP-SP utilizes the compact seq-array to store the necessary information in a sequence database. The seqPro structure is designed to efficiently calculate candidate patterns' utilities and upper-bound values. Furthermore, a new upper bound on utility, namely, tighter reduced sequence utility and two pruning strategies in search space, are utilized to improve the mining performance of HUSP-SP. Experimental results on both synthetic and real-life datasets show that HUSP-SP can significantly outperform the state-of-the-art algorithms in terms of running time, memory usage, search space pruning efficiency, and scalability. [ABSTRACT FROM AUTHOR]

Abstract Prey metabarcoding has become a popular tool in molecular ecology for resolving trophic interactions at high resolution, from various sample types and animals. To date, most predator–prey studies of small‐sized animals (

Cemetery soils most likely contain degradative bacteria which possibly have beneficial potencies. However, the bacterial exploration in these potencies is still limitedly conducted in Indonesia. The raw sequence data of total bacteria in the cemetery soils through metagenomic analysis have been revealed. The data were obtained by collecting soil samples from six spots of two major Cemetery areas, which were Pracimaloyo (P) and Bonoloyo (B), in Surakarta City, Central Java, Indonesia. The six sample spots consisted of two samples from P area with respectively 20 cm and 140 cm depths and four samples of each two samples from B area with 20 and 40 cm depths. The total DNA was subsequently extracted from the collected soils using ZymoBIOMICS DNA Miniprep Kit. The total DNA then was amplified using a couple of 16S rRNA primers through Illumina HiSeq 2500 PE250 (Novogen, Korea) environment system. The raw sequence data has been submitted to the National Center for Biotechnology Information (NCBI) with project ID PRJNA997385. The archived sequence can be accessed in the NCBI website with the following URLs https://www.ncbi.nlm.nih.gov/sra/PRJNA997385. A brief analysis of the sequence data showed that the most common phyla in 20 cm-depths were Proteobacteria (29.5%), Actinobacteria (21.6%), and Firmicutes (19.2%), while Actinobacteria were the most found in 140 cm-depths with 34.2% followed by Proteobacteria (21.9%) and Firmicutes (16.6%). This data would be the first report of total bacterial sequence from cemetery soils in Indonesia.

Big data analytics has become a significant trend for many businesses as a result of the daily acquisition of enormous volumes of data. This information has been gathered because it may be important for dealing with complicated problems including fraud, marketing, healthcare, and cyber security. Analytics are used by big businesses like Facebook and Google to analyse and make decisions about their massive volumes of collected data. Such analyses and decisions impact both the present and the future of technology. The inherent non-linear properties in huge data may be captured by deep learning (DL) algorithms using automated feature extraction techniques. In order to estimate renewable energy, energy consumption, demand, and supply, among other things, over the short, medium, and long term, a complete and in-depth investigation of generative, hybrid, and discriminative DL models is being conducted. This article examines the benefits and drawbacks of DL that depends on a variety of deep neural networks, including recurrent neural networks, multilayer neural networks, auto encoders and long short-term memory. [ABSTRACT FROM AUTHOR]

Metagenomic data compression is very important as metagenomic projects are facing the challenges of larger data volumes per sample and more samples nowadays. Reference-based compression is a promising method to obtain a high compression ratio. However, existing microbial reference genome databases are not suitable to be directly used as references for compression due to their large size and redundancy, and different metagenomic cohorts often have various microbial compositions. We present a novel pipeline that generated simplified and tailored reference genomes for large metagenomic cohorts, enabling the reference-based compression of metagenomic data. We constructed customized reference genomes, ranging from 2.4 to 3.9 GB, for 29 real metagenomic datasets and evaluated their compression performance. Reference-based compression achieved an impressive compression ratio of over 20 for human whole-genome data and up to 33.8 for all samples, demonstrating a remarkable 4.5 times improvement than the standard Gzip compression. Our method provides new insights into reference-based metagenomic data compression and has a broad application potential for faster and cheaper data transfer, storage, and analysis. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic continues to impact daily life worldwide. It would be helpful and valuable if we could obtain valid information from the COVID-19 pandemic sequential data itself for characterizing the pandemic. Here, we aim to demonstrate that it is feasible to analyze the patterns of the pandemic using a time-series clustering approach. In this work, we use dynamic time warping distance and hierarchical clustering to cluster time series of daily new cases and deaths from different countries into four patterns. It is found that geographic factors have a large but not decisive influence on the pattern of pandemic development. Moreover, the age structure of the population may also influence the formation of cluster patterns. Our proven valid method may provide a different but very useful perspective for other scholars and researchers.

DNA viruses that produce persistent infections have been proposed as potential causes for the extinction of Neanderthals, and, therefore, the identification of viral genome remnants in Neanderthal sequence reads is an initial step to address this hypothesis. Here, as proof of concept, we searched for viral remnants in sequence reads of Neanderthal genome data by mapping to adenovirus, herpesvirus and papillomavirus, which are double-stranded DNA viruses that may establish lifelong latency and can produce persistent infections. The reconstructed ancient viral genomes of adenovirus, herpesvirus and papillomavirus revealed conserved segments, with nucleotide identity to extant viral genomes and variable regions in coding regions with substantial divergence to extant close relatives. Sequence reads mapped to extant viral genomes showed deamination patterns of ancient DNA, and these ancient viral genomes showed divergence consistent with the age of these samples (≈50,000 years) and viral evolutionary rates (10−5 to 10−8 substitutions/site/year). Analysis of random effects showed that the Neanderthal mapping to genomes of extant persistent viruses is above what is expected by random similarities of short reads. Also, negative control with a nonpersistent DNA virus does not yield statistically significant assemblies. This work demonstrates the feasibility of identifying viral genome remnants in archaeological samples with signal-to-noise assessment.

The surface electromyography (sEMG) signal is a complex interference pattern resulting from the electrical activity of contracting muscles, which directly correlates with muscle activity and exercise level. Patellofemoral osteoarthritis (PF OA) refers to the softening and destruction of the articular cartilage of the knee cap, which is important to diagnose in the early phase. The aim of this study is to develop a predictive model, called the Enhanced Sequencing Deep Learning (PESDL) Algorithm, to detect PF OA from the sEMG signal. The algorithm consists of four main modules: (i) Data Acquisition Module (DAM), (ii) Signal Preprocessing Module (SPM), (iii) Data Augmentation and Concatenation Module (DACM), and (iv) Lower Limb Classification (LLC). The sEMG signals from five core muscles of the lower limb were acquired during stepping stairs up and down, and machine learning was used to obtain the muscle activation data signals. The acquired data was preprocessed, augmented, concatenated, and shuffled. Three feedforward deep networks (RNN, LSTM, and GRU) were used to classify the lower limb sEMG time-sequence data, with the GRU network showing better performance than the other two. The model's performance was evaluated using seven performance measures and 10-fold cross-validation. The maximum values of feedforward deep networks (RNN), LSTM, and GRU for the five muscles (RF, BF, VM, ST, and FX) using seven performance measures were as follows: RNN (0.961, 0.154, 0.943, 0.244, 1.0, 1.0, 0.899), LSTM (0.967, 0.147, 0.945, 0.217, 0.997, 1.0, 0.927), and GRU (0.976, 0.111, 0.949, 0.212, 0.996, 0.998, 0.938), respectively, listed in the order of accuracy, loss, validation accuracy, validation loss, recall, precision, and F1-score. Comparisons with other state-of-the-art models using the same datasets demonstrated the effective performance of the predictive model. The results suggest that RNN models, particularly GRU and LSTM, can be effective for detecting PF OA, and the specific RNN architecture used can have a significant impact on performance.

Research from a range of disciplines highlights the need to adopt a life course perspective that considers earlier life courses to explain outcomes in later life (e.g. later life health, cognitive ageing or retirement behaviour). This includes a more comprehensive assessment of earlier life courses over time and of how they are shaped by societal and political contexts. But quantitative data with detailed information on life courses that allow to address these questions are rare. Or, in case the data are available, the data are rather difficult to handle and appears to be underused. This contribution introduces the harmonized life history data from the gateway to global ageing data platform from two European Surveys, SHARE and ELSA, with data from 30 European countries. Besides providing some details on the collection of life history data in the two surveys, we also describe the way how raw data were rearranged in a user-friendly state sequence format and additionally give some examples based on the resulting data. This illustrates the potential of collected life history data from SHARE and ELSA, clearly going beyond the description of single aspects of the life course. By providing harmonized data of two prominent studies on ageing in Europe in a user-friendly format, the gateway to global ageing data platform provides a unique data source that is easily accessible for research, and permits to study life course and their links to later life in a cross-national perspective. [ABSTRACT FROM AUTHOR]

Metagenomic data compression is very important as metagenomic projects are facing the challenges of larger data volumes per sample and more samples nowadays. Reference-based compression is a promising method to obtain a high compression ratio. However, existing microbial reference genome databases are not suitable to be directly used as references for compression due to their large size and redundancy, and different metagenomic cohorts often have various microbial compositions. We present a novel pipeline that generated simplified and tailored reference genomes for large metagenomic cohorts, enabling the reference-based compression of metagenomic data. We constructed customized reference genomes, ranging from 2.4 to 3.9 GB, for 29 real metagenomic datasets and evaluated their compression performance. Reference-based compression achieved an impressive compression ratio of over 20 for human whole-genome data and up to 33.8 for all samples, demonstrating a remarkable 4.5 times improvement than the standard Gzip compression. Our method provides new insights into reference-based metagenomic data compression and has a broad application potential for faster and cheaper data transfer, storage, and analysis.

The hyperspectral image (HSI) has nearly continuous spectral information; thus, the target of interest can be accurately identified by the subtle details of spectral properties. Spectral resolution at different scales can capture different levels of spectral features: Small-scale spectral bands are beneficial for extracting global details in vision transformers, while large-scale spectral bands are more effective for local features. Transformer shows advantages in global information extraction with self-attention module and even surpasses convolutional neural network (CNNs) in various tasks. Some works based on the vision transformer have performed surprisingly in HSI classification. However, single-scale vision transformers are insufficient to balance the extraction of local details and redundancy on different scales. The recent work, a multiscale vision transformer, has provided a solution with spatial patch-wise features in image classification. Inspired by this, we propose the cross-spectral vision transformer (CSiT) with two branches to extract pixel-wise multiscale features and further design a multiscale spectral embedding module to enhance local details between neighboring spectral bands. Moreover, based on the cross-attention operation, a single token for each branch is recognized as a query and used to exchange information with other branches. We evaluate the classification performance of the proposed CSiT in three classic HSI datasets with extensive experiments, showing the multiscale vision transformer architecture has a promising result for HSI classification with 1-D spectral bands.

In recent years, DNA barcoding has rapidly developed as a powerful tool in taxonomy, demonstrating its value in species identification and discovery of cryptic diversity. The number of barcoding sequences of various species continues to grow in the GenBank and BOLD databases; however, the accuracy of sequences and related raw information in public repositories is often questionable. In the present study, based on a dataset of 68,089 Hemiptera COI barcode sequences covering 3,064 species, 1,072 genera, and 48 families, we analyzed genetic differences within and between species and evaluated possible data errors in the insect barcodes. The results showed that errors in the barcode data are not rare, and most of them are due to human errors, such as specimen misidentification, sample confusion, and contamination. A significant portion of these errors can be attributed to inappropriate and imprecise practices in the DNA barcoding workflow. Herein, suggestions are provided to improve the practical operations and workflow of DNA barcoding to reduce human errors.

Here we developed KARAJ, a fast and flexible Linux command-line tool to automate the end-to-end process of querying and downloading a wide range of genomic and transcriptomic sequence data types. The input to KARAJ is a list of PMCIDs or publication URLs or various types of accession numbers to automate four tasks as follows; firstly, it provides a summary list of accessible datasets generated by or used in these scientific articles, enabling users to select appropriate datasets; secondly, KARAJ calculates the size of files that users want to download and confirms the availability of adequate space on the local disk; thirdly, it generates a metadata table containing sample information and the experimental design of the corresponding study; and lastly, it enables users to download supplementary data tables attached to publications. Further, KARAJ provides a parallel downloading framework powered by Aspera connect which reduces the downloading time significantly. [ABSTRACT FROM AUTHOR]

To avoid environmental pollution caused by oil tank leakage of integrated bulldozer, it is necessary to realize automatic real-time monitoring of hydraulic oil tank leakage during construction of integrated bulldozer. Therefore, on the premise of considering environmental pollution, the paper proposed an automatic monitoring method of hydraulic oil tank leakage of integrated bulldozer. The real-time data of the hydraulic oil tank of the integrated bulldozer is collected through the optical fiber element, and the sequence data is processed and input into the echo state network model. The model initializes the full connection matrix and initial vector through the data, updates the state vector of the reserve pool layer, collects each vector and training samples to form the state vector and the state of the output matrix, solves the output weight matrix, completes the model training, and determines the leakage point of the hydraulic oil tank. The test results show that this method can obtain the real-time data of the hydraulic oil tank. Under the determination of the optimal parameters, it can accurately monitor the leakage times of the oil tank under different working conditions without noise interference. The monitoring can be completed in the early stage of leakage, and a large amount of oil leakage can be effectively avoided and can reduce the pollution degree of oil tank leakage to the ecological environment such as air and soil. [ABSTRACT FROM AUTHOR]

Sequence data can be used in genomic selection (GS), genome-wide association studies (GWAS) and the analysis of recessive lethal defects instead of, or complementary to, SNP array genotypes and increase the power of those applications in various ways. Because sequencing large study cohorts is still expensive, genotype imputation - the prediction of missing genotypes - is a cost-effective alternative to generate sequence-level genotypes for a large number of animals. These genotypes can then be used in subsequent studies and, for example, facilitate the identification of causative mutations. In this context, it is important to consider the accuracy of imputation and to know the factors affecting it. As the availability of sequence data from (warmblood) horses is limited, for this species, imputation is a good possibility to generate sequence level genotypes, which can boost the power of GWAS and the identification of recessive lethal defects. [ABSTRACT FROM AUTHOR]

Event sequence data is increasingly available in various application domains, such as business process management, software engineering, or medical pathways. Processes in these domains are typically represented as process diagrams or flow charts. So far, various techniques have been developed for automatically generating such diagrams from event sequence data. An open challenge is the visual analysis of drift phenomena when processes change over time. In this article, we address this research gap. Our contribution is a system for fine-granular process drift detection and corresponding visualizations for event logs of executed business processes. We evaluated our system both on synthetic and real-world data. On synthetic logs, we achieved an average F-score of 0.96 and outperformed all the state-of-the-art methods. On real-world logs, we identified all types of process drifts in a comprehensive manner. Finally, we conducted a user study highlighting that our visualizations are easy to use and useful as perceived by process mining experts. In this way, our work contributes to research on process mining, event sequence analysis, and visualization of temporal data. [ABSTRACT FROM AUTHOR]

Copyright of Journal of South China Agricultural University is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To pursue higher accuracy, the structure of deep learning model is getting more and more complex, with deeper and deeper network. The increase in the number of parameters means that more data are needed to train the model. However, manually labeling data is costly, and it is not easy to collect data in some specific fields limited by objective reasons. As a result, data insufficiency is a very common problem. Data augmentation is here to alleviate the problem by artificially generating new data. The success of data augmentation in the field of computer vision leads people to consider using similar methods on sequence data. In this paper, not only the time-domain methods such as flipping and cropping but also some augmentation methods in frequency domain are described. In addition to experience-based or knowledge-based methods, detailed descriptions on machine learning models used for automatic data generation such as GAN are also included. Methods that have been widely applied to various sequence data such as text, audio and time series are mentioned with their satisfactory performance in issues like medical diagnosis and emotion classification. Despite the difference in data type, these methods are designed with similar ideas. Using these ideas as a clue, various data augmentation methods applied to different types of sequence data are introduced, and some discussions and prospects are made.

In this paper, we present a novel face-based random walk method aimed at addressing the 3D semantic segmentation issue. Our method utilizes a one-dimensional convolutional neural network for detailed feature extraction from sequences of triangular faces and employs a stacked gated recurrent unit to gather information along the sequence during training. This approach allows us to effectively handle irregular meshes and utilize the inherent feature extraction potential present in mesh geometry. Our study's results show that the proposed method achieves competitive results compared to the state-of-the-art methods in mesh segmentation. Importantly, it requires fewer training iterations and demonstrates versatility by applying to a wide range of objects without the need for the mesh to adhere to manifold or watertight topology requirements. • Segment 3D meshes using a hybrid architecture, gated recurrent units, and 1D convolutional neural networks. • Extraction of geometric features from 3D mesh faces using mathematical algorithms; random walks. • Apply deep learning algorithms to irregular 3D data without considering whether each mesh is a manifold or closed. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) contains hundreds of contiguous spectral bands compared with red green blue (RGB) image, making the precise identification of materials possible by capturing subtle spectral and spatial features. Owing to the special advantage in image processing, convolutional neural networks (CNNs) have been proven to be a successful architecture in HSI classification. However, due to the limitation of receptive field of fixed convolution kernel, CNNs can only extract local features of hyperspectral image. Besides, CNNs fail to mine and represent the sequence attributes of spectral bands because of the limitations of its inherent network backbone. With the emergence of vision transformer, the network can break through the limitation of receptive field and obtain the global correlation of the whole image, but it only focuses on the global information of the object and ignores the local information existing in the sequence and images. Moreover, the correlation of spectral information will be destroyed if traditional methods are directly used to convert hyperspectral images into sequence. To solve this issue, a novel convolution and vision transformer fusion network called CAVFN is devised which contains a new cube-embedding module that can reduce the loss of spectral information effectively by dividing the large HSI cube into several small cubes and encoding them into sequences. More significantly, this paper also combines 1D-CNN and 2D-CNN with vision transformer to extract the local features of sequences and patches, and combines them with global features to obtain better classification results. Finally, this paper evaluates the classification results of the proposed network on three HSI datasets by conducting extensive experiments, showing that our network outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Here we introduce a MIxS extension to facilitate the recording and cataloguing of metadata from samples related to hydrocarbon resources. The proposed MIxS-HCR package incorporates the core features of the MIxS standard for marker gene (MIMARKS) and metagenomic (MIMS) sequences along with a hydrocarbon resources customized environmental package. Adoption of the MIxS-HCR standard will enable the comparison and better contextualization of investigations related to hydrocarbon rich environments. The insights from such standardized way of reporting could be highly beneficial for the successful development and optimization of hydrocarbon recovery processes and management of microbiological issues in petroleum production systems.

Deep learning models have been successfully applied in a wide range of fields. The creation of a deep learning framework for analyzing high-performance sequence data have piqued the research community's interest. N4 acetylcytidine (ac4C) is a post-transcriptional modification in mRNA, is an mRNA component that plays an important role in mRNA stability control and translation. The ac4C method of mRNA changes is still not simple, time consuming, or cost effective for conventional laboratory experiments. As a result, we developed DL-ac4C, a CNN-based deep learning model for ac4C recognition. In the alternative scenario, the model families are well-suited to working in large datasets with a large number of available samples, especially in biological domains. In this study, the DL-ac4C method (deep learning) is compared to non-deep learning (machine learning) methods, regression, and support vector machine. The results show that DL-ac4C is more advanced than previously used approaches. The proposed model improves the accuracy recall area by 9.6 percent and 9.8 percent, respectively, for cross-validation and independent tests. More nuanced methods of incorporating prior bio-logical knowledge into the estimation procedure of deep learning models are required to achieve better results in terms of predictive efficiency and cost-effectiveness. Based on an experiment's acetylated dataset, the DL-ac4C sequence-based predictor for acetylation sites in mRNA can predict whether query sequences have potential acetylation motifs. [ABSTRACT FROM AUTHOR]

Background: The mammalian immune system is able to generate antibodies against a huge variety of antigens, including bacteria, viruses, and toxins. The ultradeep DNA sequencing of rearranged immunoglobulin genes has considerable potential in furthering our understanding of the immune response, but it is limited by the lack of a high-throughput, sequence-based method for predicting the antigen(s) that a given immunoglobulin recognizes. Objective: As a step toward the prediction of antibody-antigen binding from sequence data alone, we aimed to compare a range of machine learning approaches that were applied to a collated data set of antibody-antigen pairs in order to predict antibody-antigen binding from sequence data. Methods: Data for training and testing were extracted from the Protein Data Bank and the Coronavirus Antibody Database, and additional antibody-antigen pair data were generated by using a molecular docking protocol. Several machine learning methods, including the weighted nearest neighbor method, the nearest neighbor method with the BLOSUM62 matrix, and the random forest method, were applied to the problem. Results: The final data set contained 1157 antibodies and 57 antigens that were combined in 5041 antibody-antigen pairs. The best performance for the prediction of interactions was obtained by using the nearest neighbor method with the BLOSUM62 matrix, which resulted in around 82% accuracy on the full data set. These results provide a useful frame of reference, as well as protocols and considerations, for machine learning and data set creation in the prediction of antibody-antigen binding. Conclusions: Several machine learning approaches were compared to predict antibody-antigen interaction from protein sequences. Both the data set (in CSV format) and the machine learning program (coded in Python) are freely available for download on GitHub. [ABSTRACT FROM AUTHOR]

Abstract Background Goats were domesticated 10,500 years ago to supply humans with useful resources. Since then, specialized breeds that are adapted to their local environment have been developed and display specific genetic profiles. The VarGoats project is a 1000 genomes resequencing program designed to cover the genetic diversity of the Capra genus. In this study, our main objective was to assess the use of sequence data to detect genomic regions associated with traits of interest in French Alpine and Saanen breeds. Results Direct imputation from the GoatSNP50 BeadChip genotypes to sequence level was investigated in these breeds using FImpute and different reference panels: within-breed, all Capra hircus sequenced individuals, European goats and French mainland goats. The best results were obtained with the French goat panel with allele and genotype concordance rates reaching 0.86 and 0.75 in the Alpine and 0.86 and 0.73 in the Saanen breed respectively. Mean correlations tended to be low in both breeds due to the high proportion of variants with low frequencies. For association analysis, imputation was performed using FImpute for 1129 French Alpine and Saanen males using within-breed and French panels on 23,338,436 filtered variants. The association results of both imputation scenarios were then compared. In Saanen goats, a large region on chromosome 19 was significantly linked to semen volume and milk yield in both scenarios. Significant variants for milk yield were annotated for 91 genes on chromosome 19 in Saanen goats. For semen volume, the annotated genes include YBOX2 which is related to azoospermia or oligospermia in other species. New signals for milk yield were detected on chromosome 2 in Alpine goats and on chromosome 5 in Saanen goats when using a multi-breed panel. Conclusion Even with very small reference populations, an acceptable imputation quality can be achieved in French dairy goats. GWAS on imputed sequences confirmed the existence of QTLs and identified new regions of interest in dairy goats. Adding identified candidates to a genotyping array and sequencing more individuals might corroborate the involvement of identified regions while removing potential imputation errors.

Utility mining has emerged as an important and interesting topic owing to its wide application and considerable popularity. However, conventional utility mining methods have a bias toward items that have longer on-shelf time as they have a greater chance to generate a high utility. To eliminate the bias, the problem of on-shelf utility mining (OSUM) is introduced. In this article, we focus on the task of OSUM of sequence data, where the sequential database is divided into several partitions according to time periods and items are associated with utilities and several on-shelf time periods. To address the problem, we propose two methods, OSUM of sequence data (OSUMS) and OSUMS+, to extract on-shelf high-utility sequential patterns. For further efficiency, we also design several strategies to reduce the search space and avoid redundant calculation with two upper bounds time prefix extension utility (TPEU) and time reduced sequence utility (TRSU). In addition, two novel data structures are developed for facilitating the calculation of upper bounds and utilities. Substantial experimental results on certain real and synthetic datasets show that the two methods outperform the state-of-the-art algorithm. In conclusion, OSUMS may consume a large amount of memory and is unsuitable for cases with limited memory, while OSUMS+ has wider real-life applications owing to its high efficiency. [ABSTRACT FROM AUTHOR]

Rail surface defect (RSD) inspection is an essential routine maintenance task. Computer vision testing is suitable for RSD inspection with its intuitiveness and rapidity. Deep learning techniques, which can extract deep semantic features, have been applied to inspect RSDs in recent years. However, these methods demand thousands of samples. And sample collection requires hard-working and costs high. To address the issue, a novel inspection scheme for RSDs is presented for limited samples with a line-level label, which regards defect images as sequence data and classifies pixel lines. Thousands of pixel lines are easy to be collected and labeling line-level is a simple task in labeling works. Then two methods OC-IAN and OC-TD are designed for inspecting express rail defects and common/heavy rail defects, respectively. OC-IAN and OC-TD both employ one-dimensional convolutional neural network (ODCNN) to extract features and long- and short-term memory (LSTM) network to extract context information. The main differences between OC-IAN and OC-TD are that OC-TD applies a double-branch structure and removes the attention module. Experimental results on RSDDs dataset demonstrate that our methods are effective and outperform the state-of-the-art methods on defect-level metrics (Type-I: Rec-0.9314, Pre-0.8421, F1-0.8845; Type-II: Rec-0.9427, Pre-0.9176, F1-0.9300). [ABSTRACT FROM AUTHOR]

Real or imputed high-density SNP genotypes are routinely used for genomic prediction and genome-wide association studies. Many researchers are moving toward the use of actual or imputed next-generation sequence data in whole-genome analyses. Simulation studies are useful to mimic complex scenarios and test different analytical methods. We have developed the software tool XSim to efficiently simulate sequence data in descendants in arbitrary pedigrees. In this software, a strategy to drop-down origins and positions of chromosomal segments rather than every allele state is implemented to simulate sequence data and to accommodate complicated pedigree structures across multiple generations. Both C++ and Julia versions of XSim have been developed.

Introduction: Advance planning of vaccine trials conducted during outbreaks increases our ability to rapidly define the efficacy and potential impact of a vaccine. Vaccine efficacy against infectiousness (VEI) is an important measure for understanding a vaccine's full impact, yet it is currently not identifiable in many trial designs because it requires knowledge of infectors' vaccination status. Recent advances in genomics have improved our ability to reconstruct transmission networks. We aim to assess if augmenting trials with pathogen sequence and contact tracing data can permit them to estimate VEI.Methods: We develop a transmission model with a vaccine trial in an outbreak setting, incorporate pathogen sequence data and contact tracing data, and assign probabilities to likely infectors. We then propose and evaluate the performance of an estimator of VEI.Results: We find that under perfect knowledge of infector-infectee pairs, we are able to accurately estimate VEI. Use of sequence data results in imperfect reconstruction of transmission networks, biasing estimates of VEI towards the null, with approaches using deep sequence data performing better than approaches using consensus sequence data. Inclusion of contact tracing data reduces the bias.Conclusion: Pathogen genomics enhance identifiability of VEI, but imperfect transmission network reconstruction biases estimate toward the null and limits our ability to detect VEI. Given the consistent direction of the bias, estimates obtained from trials using these methods will provide lower bounds on the true VEI. A combination of sequence and epidemiologic data results in the most accurate estimates, underscoring the importance of contact tracing. [ABSTRACT FROM AUTHOR]