Annotation Method Research Articles

A spatiotemporal chaos based deep learning model watermarking scheme

With deep learning techniques achieving great results in modern industry, the intellectual property (IP) protection for deep learning models has attracted the attention of academics and engineers. However, training a commercially viable deep learning model usually needs professional resources and time. Once a malicious user clones, illegally distributes and uses the model, it can infringe on the model owner's IP and even steal its market share. Among the existing IP protection methods, scholars prefer the black-box watermarking approaches, of which the content of the trigger set and the label are the key part of the watermarking technique. However, most schemes do not consider the security and invisibility of the trigger set, which allows attackers to easily trigger the model by creating a fake trigger set, thereby committing a fraudulent ownership claim attack and claiming the ownership belongs to themselves. To overcome these drawbacks, we proposed a spatiotemporal chaotic data annotation method. Firstly, the unpredictability and acyclicity of chaos make the model resistant to fraudulent ownership claim attacks, statistical inference and other common machine learning attacks; Secondly, the trigger set and parameters are independent of each other, guaranteeing the security of the key; Thirdly, the spatiotemporal chaotic system provides a large key space, which meets the commercialization needs of deep learning models. Theoretical analysis and experimental results show that our scheme has security, practicality and robustness. To further validate the superiority of the proposed method, we also compare it with the Logistic chaotic annotation watermarking-based method, and the results show that our method performs better in terms of robustness, effectiveness, completeness, fidelity, security and practicality.

Development of a deep-learning phenotyping tool for analyzing image-based strawberry phenotypes.

In strawberry farming, phenotypic traits (such as crown diameter, petiole length, plant height, flower, leaf, and fruit size) measurement is essential as it serves as a decision-making tool for plant monitoring and management. To date, strawberry plant phenotyping has relied on traditional approaches. In this study, an image-based Strawberry Phenotyping Tool (SPT) was developed using two deep-learning (DL) architectures, namely "YOLOv4" and "U-net" integrated into a single system. We aimed to create the most suitable DL-based tool with enhanced robustness to facilitate digital strawberry plant phenotyping directly at the natural scene or indirectly using captured and stored images. Our SPT was developed primarily through two steps (subsequently called versions) using image data with different backgrounds captured with simple smartphone cameras. The two versions (V1 and V2) were developed using the same DL networks but differed by the amount of image data and annotation method used during their development. For V1, 7,116 images were annotated using the single-target non-labeling method, whereas for V2, 7,850 images were annotated using the multitarget labeling method. The results of the held-out dataset revealed that the developed SPT facilitates strawberry phenotype measurements. By increasing the dataset size combined with multitarget labeling annotation, the detection accuracy of our system changed from 60.24% in V1 to 82.28% in V2. During the validation process, the system was evaluated using 70 images per phenotype and their corresponding actual values. The correlation coefficients and detection frequencies were higher for V2 than for V1, confirming the superiority of V2. Furthermore, an image-based regression model was developed to predict the fresh weight of strawberries based on the fruit size (R2 = 0.92). The results demonstrate the efficiency of our system in recognizing the aforementioned six strawberry phenotypic traits regardless of the complex scenario of the environment of the strawberry plant. This tool could help farmers and researchers make accurate and efficient decisions related to strawberry plant management, possibly causing increased productivity and yield potential.

SPA: Annotating Small Object with a Single Point in Remote Sensing Images

Detecting oriented small objects is a critical task in remote sensing, but the development of high-performance deep learning-based detectors is hindered by the need for large-scale and well-annotated datasets. The high cost of creating these datasets, due to the dense and numerous distribution of small objects, significantly limits the application and development of such detectors. To address this problem, we propose a single-point-based annotation approach (SPA) based on the graph cut method. In this framework, user annotations act as the origin of positive sample points, and a similarity matrix, computed from feature maps extracted by deep learning networks, facilitates an intuitive and efficient annotation process for building graph elements. Utilizing the Maximum Flow algorithm, SPA derives positive sample regions from these points and generates oriented bounding boxes (OBBOXs). Experimental results demonstrate the effectiveness of SPA, with at least a 50% improvement in annotation efficiency. Furthermore, the intersection-over-union (IoU) metric of our OBBOX is 3.6% higher than existing methods such as the “Segment Anything Model”. When applied in training, the model annotated with SPA shows a 4.7% higher mean average precision (mAP) compared to models using traditional annotation methods. These results confirm the technical advantages and practical impact of SPA in advancing small object detection in remote sensing.

HiTE: a fast and accurate dynamic boundary adjustment approach for full-length transposable element detection and annotation

Recent advancements in genome assembly have greatly improved the prospects for comprehensive annotation of Transposable Elements (TEs). However, existing methods for TE annotation using genome assemblies suffer from limited accuracy and robustness, requiring extensive manual editing. In addition, the currently available gold-standard TE databases are not comprehensive, even for extensively studied species, highlighting the critical need for an automated TE detection method to supplement existing repositories. In this study, we introduce HiTE, a fast and accurate dynamic boundary adjustment approach designed to detect full-length TEs. The experimental results demonstrate that HiTE outperforms RepeatModeler2, the state-of-the-art tool, across various species. Furthermore, HiTE has identified numerous novel transposons with well-defined structures containing protein-coding domains, some of which are directly inserted within crucial genes, leading to direct alterations in gene expression. A Nextflow version of HiTE is also available, with enhanced parallelism, reproducibility, and portability.

ScATAcat: cell-type annotation for scATAC-seq data.

Cells whose accessibility landscape has been profiled with scATAC-seq cannot readily be annotated to a particular cell type. In fact, annotating cell-types in scATAC-seq data is a challenging task since, unlike in scRNA-seq data, we lack knowledge of 'marker regions' which could be used for cell-type annotation. Current annotation methods typically translate accessibility to expression space and rely on gene expression patterns. We propose a novel approach, scATAcat, that leverages characterized bulk ATAC-seq data as prototypes to annotate scATAC-seq data. To mitigate the inherent sparsity of single-cell data, we aggregate cells that belong to the same cluster and create pseudobulk. To demonstrate the feasibility of our approach we collected a number of datasets with respective annotations to quantify the results and evaluate performance for scATAcat. scATAcat is available as a python package at https://github.com/aybugealtay/scATAcat.

A gene regulatory network-aware graph learning method for cell identity annotation in single-cell RNA-seq data.

Cell identity annotation for single-cell transcriptome data is a crucial process for constructing cell atlases, unraveling pathogenesis, and inspiring therapeutic approaches. Currently, the efficacy of existing methodologies is contingent upon specific data sets. Nevertheless, such data are often sourced from various batches, sequencing technologies, tissues, and even species. Notably, the gene regulatory relationship remains unaffected by the aforementioned factors, highlighting the extensive gene interactions within organisms. Therefore, we propose scHGR, an automated annotation tool designed to leverage gene regulatory relationships in constructing gene-mediated cell communication graphs for single-cell transcriptome data. This strategy helps reduce noise from diverse data sources while establishing distant cellular connections, yielding valuable biological insights. Experiments involving 22 scenarios demonstrate that scHGR precisely and consistently annotates cell identities, benchmarked against state-of-the-art methods. Crucially, scHGR uncovers novel subtypes within peripheral blood mononuclear cells, specifically from CD4+ T cells and cytotoxic T cells. Furthermore, by characterizing a cell atlas comprising 56 cell types for COVID-19 patients, scHGR identifies vital factors like IL1 and calcium ions, offering insights for targeted therapeutic interventions.

Monocular visual anti-collision method based on residual mixed attention for storage and retrieval machines

In the traditional manufacturing industry, the safe operation of storage and retrieval (S/R) machines is vital for efficient automated warehouse management. Recently, deep learning-based monocular vision approaches have emerged as a promising solution for collision avoidance in automated storage and retrieval systems (AS/RS). However, the scarcity of specific datasets and the need for high-performance, lightweight neural network models pose challenges in the AS/RS domain. To address these challenges, this paper introduces a novel workflow for implementing a monocular anti-collision system for S/R machines. A semi-supervised annotation method leveraging a pretrained clustering model is proposed to expedite image collection and classification, resulting in a tailored dataset. Furthermore, the NightMix technique is introduced, combining Grayscale Enhancement and Floating Grid Mix method to enhance dataset diversity and capacity. Notably, a residual attention awareness module is integrated into MobileNet V3 to enhance its feature processing capabilities. Finally, the proposed approaches are validated through extensive experiments involving various design choices. The experimental results demonstrate that our methods are not only computationally efficient but also highly competitive in terms of learning performance.

ScType enables fast and accurate cell type identification from spatial transcriptomics data.

The limited resolution of spatial transcriptomics (ST) assays in the past has led to the development of cell type annotation methods that separate the convolved signal based on available external atlas data. In light of the rapidly increasing resolution of the ST assay technologies, we made available and investigated the performance of a deconvolution-free marker-based cell annotation method called scType. In contrast to existing methods, the spatial application of scType does not require computationally strenuous deconvolution, nor large single-cell reference atlases. We show that scType enables ultra-fast and accurate identification of abundant cell types from ST data, especially when a large enough panel of genes is detected. Examples of such assays are Visium and Slide-seq, which currently offer the best trade-off between high resolution and number of genes detected by the assay for cell type annotation. scType source R and python codes for spatial data are openly available in GitHub (https://github.com/kris-nader/sp-type or https://github.com/kris-nader/sc-type-py). Step-by-step tutorials for R and python spatial data analysis can be found in https://github.com/kris-nader/sp-type and https://github.com/kris-nader/sc-type-py/blob/main/spatial_tutorial.md, respectively.

Could this be next for corpus linguistics? Methods of semi-automatic data annotation with contextualized word embeddings

Abstract This paper explores how linguistic data annotation can be made (semi-)automatic by means of machine learning. More specifically, we focus on the use of “contextualized word embeddings” (i.e. vectorized representations of the meaning of word tokens based on the sentential context in which they appear) extracted by large language models (LLMs). In three example case studies, we assess how the contextualized embeddings generated by LLMs can be combined with different machine learning approaches to serve as a flexible, adaptable semi-automated data annotation tool for corpus linguists. Subsequently, to evaluate which approach is most reliable across the different case studies, we use a Bayesian framework for model comparison, which estimates the probability that the performance of a given classification approach is stronger than that of an alternative approach. Our results indicate that combining contextualized word embeddings with metric fine-tuning yield highly accurate automatic annotations.

Satellite Image Cloud Automatic Annotator with Uncertainty Estimation

In satellite imagery, clouds obstruct the ground information, directly impacting various downstream applications. Thus, cloud annotation/cloud detection serves as the initial preprocessing step in remote sensing image analysis. Recently, deep learning methods have significantly improved in the field of cloud detection, but training these methods necessitates abundant annotated data, which requires experts with professional domain knowledge. Moreover, the influx of remote sensing data from new satellites has further led to an increase in the cost of cloud annotation. To address the dependence on labeled datasets and professional domain knowledge, this paper proposes an automatic cloud annotation method for satellite remote sensing images, CloudAUE. Unlike traditional approaches, CloudAUE does not rely on labeled training datasets and can be operated by users without domain expertise. To handle the irregular shapes of clouds, CloudAUE firstly employs a convex hull algorithm for selecting cloud and non-cloud regions by polygons. When selecting convex hulls, the cloud region is first selected, and points at the edges of the cloud region are sequentially selected as polygon vertices to form a polygon that includes the cloud region. Then, the same selection is performed on non-cloud regions. Subsequently, the fast KD-Tree algorithm is used for pixel classification. Finally, an uncertainty method is proposed to evaluate the quality of annotation. When the confidence value of the image exceeds a preset threshold, the annotation process terminates and achieves satisfactory results. When the value falls below the threshold, the image needs to undergo a subsequent round of annotation. Through experiments on two labeled datasets, HRC and Landsat 8, CloudAUE demonstrates comparable or superior accuracy to deep learning algorithms, and requires only one to two annotations to obtain ideal results. An unlabeled self-built Google Earth dataset is utilized to validate the effectiveness and generalizability of CloudAUE. To show the extension capabilities in various fields, CloudAUE also achieves desirable results on a forest fire dataset. Finally, some suggestions are provided to improve annotation performance and reduce the number of annotations.

Exploring motivations for algorithm mention in the domain of natural language processing: A deep learning approach

With the formation of the fourth paradigm of scientific research, algorithms have become increasingly important in scientific research. In academic papers, algorithms may be mentioned by scholars with various motivations, using, comparing, or improving algorithms to solve complex research tasks. Identifying these motivations can help scholars discover the relationships between algorithms and further assess their roles and values. Therefore, taking the field of natural language processing (NLP) as an example, this article proposes a complete method to conduct the identification, distribution, and evolution of motivations for mentioning algorithms at the sentence level. Specifically, using manual annotation and machine learning methods, we identify algorithm entities and sentences in the full text of papers, classify motivations for mentioning algorithms by pre-training models and data augmentation techniques, and finally analyze the distribution and evolution of motivations. The results show that the deep learning models trained with the augmented data outperform the traditional machine learning models in the classification task. In academic papers, more than half of the sentences show the direct use of algorithms, while the lowest percentage of motivations are improving algorithms, and the diversity of motivations has been increasing with time. For specific algorithms, grammatical algorithms are mentioned more by the motivation of “description,” while more motivations of “use” are found in the machine learning algorithms category. As time passed, the “use” motivations gradually replaced the “description” motivations for different algorithms, and the number of motivation types decreased significantly. Our research explores the identification, distribution, and evolution of authors’ motivations for mentioning algorithm entities, which could provide a basis for future algorithm relationship identification and influence evaluation using motivations.

Research on the generation and annotation method of thin section images of tight oil reservoir based on deep learning

The cast thin sections of tight oil reservoirs contain important parameters such as rock mineral composition and content, porosity, permeability and stratigraphic characteristics, which are of great significance for reservoir evaluation. The use of deep learning technology for intelligent identification of thin section images is a development trend of mineral identification. However, the difficulty of making cast thin sections, the complexity of the making process and the high cost of thin section annotation have led to a lack of cast thin section images, which cannot meet the training requirements of deep learning image recognition models. In order to increase the sample size and improve the training effect of deep learning model, we proposed a generation and annotation method of thin section images of tight oil reservoir based on deep learning, by taking Fuyu reservoir in Sanzhao Sag as the target area. Firstly, the Augmentor strategy space was used to preliminarily augment the original images while preserving the original image features to meet the requirements of the model. Secondly, the category attention mechanism was added to the original StyleGAN network to avoid the influence of the uneven number of components in thin sections on the quality of the generated images. Then, the SALM annotation module was designed to achieve semi-automatic annotation of the generated images. Finally, experiments on image sharpness, distortion, standard accuracy and annotation efficiency were designed to verify the advantages of the method in image quality and annotation efficiency.

IMA Genome – F19

The pace at which Next Generation Sequence data is being produced continues to accelerate as technology improves. As a result, such data are increasingly becoming accessible to biologists outside of the field of bioinformatics. In contrast, access to training in the methods of genome assembly and annotation are not growing at a similar rate. In this issue, we report on a Genome Assembly Workshop for Mycologists that was held at the Forestry and Agricultural Biotechnology Institute (FABI) at the University of Pretoria, South Africa and make available the 12 draft genome sequences emanating from the event. With the aim of making the process of genome assembly and annotation more accessible to biologists, we provide a step-by-step guide to both genome assembly and annotation, intended to encourage and empower mycologists to use genome data in their research.

DiffuPrompter: Pixel-Level Automatic Annotation for High-Resolution Remote Sensing Images with Foundation Models

Instance segmentation is pivotal in remote sensing image (RSI) analysis, aiding in many downstream tasks. However, annotating images with pixel-wise annotations is time-consuming and laborious. Despite some progress in automatic annotation, the performance of existing methods still needs improvement due to the high precision requirements for pixel-level annotation and the complexity of RSIs. With the support of large-scale data, some foundational models have made significant progress in semantic understanding and generalization capabilities. In this paper, we delve deep into the potential of the foundational models in automatic annotation and propose a training-free automatic annotation method called DiffuPrompter, achieving pixel-level automatic annotation of RSIs. Extensive experimental results indicate that the proposed method can provide reliable pseudo-labels, significantly reducing the annotation costs of the segmentation task. Additionally, the cross-domain validation experiments confirm the powerful effectiveness of large-scale pseudo-data in improving model generalization performance.

SAFPred: synteny-aware gene function prediction for bacteria using protein embeddings.

Today, we know the function of only a small fraction of the protein sequences predicted from genomic data. This problem is even more salient for bacteria, which represent some of the most phylogenetically and metabolically diverse taxa on Earth. This low rate of bacterial gene annotation is compounded by the fact that most function prediction algorithms have focused on eukaryotes, and conventional annotation approaches rely on the presence of similar sequences in existing databases. However, often there are no such sequences for novel bacterial proteins. Thus, we need improved gene function prediction methods tailored for bacteria. Recently, transformer-based language models-adopted from the natural language processing field-have been used to obtain new representations of proteins, to replace amino acid sequences. These representations, referred to as protein embeddings, have shown promise for improving annotation of eukaryotes, but there have been only limited applications on bacterial genomes. To predict gene functions in bacteria, we developed SAFPred, a novel synteny-aware gene function prediction tool based on protein embeddings from state-of-the-art protein language models. SAFpred also leverages the unique operon structure of bacteria through conserved synteny. SAFPred outperformed both conventional sequence-based annotation methods and state-of-the-art methods on multiple bacterial species, including for distant homolog detection, where the sequence similarity to the proteins in the training set was as low as 40%. Using SAFPred to identify gene functions across diverse enterococci, of which some species are major clinical threats, we identified 11 previously unrecognized putative novel toxins, with potential significance to human and animal health. https://github.com/AbeelLab/safpred.

Construction and Implementation of Content-Based National Music Retrieval Model Under Deep Learning

This research mainly studies the construction and implementation of the content-based folk music retrieval model. Firstly, it studies the music automatic annotation method based on deep learning, and then proposes the tag conditional random field music automatic annotation method, and then constructs the music annotation depth neural network model combining a variety of music representation and attention mechanism. Finally, it analyzes the proposed folk music retrieval model the effectiveness of the cable model is verified and its performance is evaluated. The results show that in Glu module, Glu blocks had better performance in music annotation, and the music annotation results of each index in music hierarchical sequence modeling are better, which ensures the effectiveness of music annotation. Compared with other algorithms, the AUC tag score of the proposed method is the highest, which is 0.913; it can better model the mapping relationship between the audio features of music input to the text tag and has higher scores on all evaluation indicators.

Advanced high-resolution chromatographic strategies for efficient isolation of natural products from complex biological matrices: from metabolite profiling to pure chemical entities

AbstractThe isolation of pure compounds from extracts represents a key step common to all investigations of natural product (NP) research. Isolation methods have gone through a remarkable evolution. Current approaches combine powerful metabolite profiling methods for compounds annotation with omics mining results and/or bioassay for bioactive NPs/biomarkers priorisation. Targeted isolation of prioritized NPs is performed using high-resolution chromatographic methods that closely match those used for analytical profiling. Considerable progress has been made by the introduction of innovative stationary phases providing remarkable selectivity for efficient NPs isolation. Today, efficient separation conditions determined at the analytical scale using high- or ultra-high-performance liquid chromatography can be optimized via HPLC modelling software and efficiently transferred to the semi-preparative scale by chromatographic calculation. This ensures similar selectivity at both the analytical and preparative scales and provides a precise separation prediction. High-resolution conditions at the preparative scale can notably be granted using optimized sample preparation and dry load sample introduction. Monitoring by ultraviolet, mass spectrometry, and or universal systems such as evaporative light scattering detectors and nuclear magnetic resonance allows to precisely guide the isolation or trigger the collection of specific NPs with different structural scaffolds. Such approaches can be applied at different scales depending on the amounts of NPs to be isolated. This review will showcase recent research to highlight both the potential and constraints of using these cutting-edge technologies for the isolation of plant and microorganism metabolites. Several strategies involving their application will be examined and critically discussed. Graphical abstract

Impact of pre-knowledge and engagement in robot-supported collaborative learning through using the ICAPB model

Several challenges exist in computer-supported collaborative learning environments, such as the potential for distraction and student boredom and isolation, which may adversely affect the quality of collaborative learning and knowledge construction. On the other hand, as an innovative learning tool, physical robots are seen as successful collaborative learning facilitators that can raise student engagement, strengthen social presence, and boost learning results. Meanwhile, tasks designed based on Bloom's taxonomy further ensure students' attention and cognitive growth in robot-supported collaborative learning (RSCL) environments. Although some researchers have explored how to maintain engagement in previous studies on robots, it is still difficult due to the lack of a commonly employed annotation method for evaluating engagement. Therefore, this study proposed the interactive, constructive, active, passive, and behavioral (ICAPB) engagement coding model, combining cognitive and behavioral engagement, to comprehensively analyze the relationship between pre-knowledge, student engagement, and learning achievement in the RSCL environment. An experiment was conducted in a first-aid course at a university to evaluate the effectiveness of this approach. The study involved a total of 36 students using a collaborative robotic system with Bloom's taxonomy. The results showed that pre-knowledge, whether at a high or low level, did not significantly affect students' posttest scores. Instead, student engagement significantly positively impacted their learning achievement.

EML: Emotion-Aware Meta Learning for Cross-Event False Information Detection

Modern social media’s development has dramatically changed how people obtain information. However, the wide dissemination of various false information has severely detrimental effects. Accordingly, many deep learning-based methods have been proposed to detect false information and achieve promising results. However, these methods are unsuitable for new events due to the extremely limited labeled data and their discrepant data distribution to existing events. Domain adaptation methods have been proposed to mitigate these problems. However, their performance is suboptimal because they are not sensitive to new events due to they aim to align the domain information between existing events, and they hardly capture the fine-grained difference between real and fake claims by only using semantic information. Therefore, we propose a novel Emotion-aware Meta Learning (EML) approach for cross-event false information early detection, which deeply integrates emotions in meta learning to find event-sensitive initialization parameters that quickly adapt to new events. Emotion-aware meta learning is non-trivial and faces three challenges: 1) How to effectively model semantic and emotional features to capture fine-grained differences. 2) How to reduce the impact of noise in meta learning based on semantic and emotional features. 3) How to detect the false information in a zero-shot detection scenario, i.e., no labeled data for new events. To tackle these challenges, firstly, we construct the emotion-aware meta tasks by selecting claims with similar and opposite emotions to the target claim other than usually used random sampling. Secondly, we propose a task weighting method and event-adaptation meta tasks to further improve the model’s robustness and generalization ability for detecting new events. Finally, we propose a weak label annotation method to extend EML to zero-shot detection according to the calculated labels’ confidence. Extensive experiments on real-world datasets show that the EML achieves superior performances on false information detection for new events.

GeneMark-ETP significantly improves the accuracy of automatic annotation of large eukaryotic genomes.

Large-scale genomic initiatives, such as the Earth BioGenome Project, require efficient methods for eukaryotic genome annotation. Here we present an automatic gene finder, GeneMark-ETP, integrating genomic-, transcriptomic-, and protein-derived evidence that has been developed with a focus on large plant and animal genomes. GeneMark-ETP first identifies genomic loci where extrinsic data are sufficient for making gene predictions with "high confidence." The genes situated in the genomic space between the high-confidence genes are predicted in the next stage. The set of high-confidence genes serves as an initial training set for the statistical model. Further on, the model parameters are iteratively updated in the rounds of gene prediction and parameter re-estimation. Upon reaching convergence, GeneMark-ETP makes the final predictions and delivers the whole complement of predicted genes. GeneMark-ETP outperforms gene finders using a single type of extrinsic evidence. Comparisons with gene finders MAKER2 and TSEBRA, those that use both transcript- and protein-derived extrinsic evidence, show that GeneMark-ETP delivers state-of-the-art gene-prediction accuracy, with the margin of outperforming existing approaches increasing in its application to larger and more complex eukaryotic genomes.