Search

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased. [ABSTRACT FROM AUTHOR]

Functional annotation of open reading frames in microbial genomes remains substantially incomplete. Enzymes constitute the most prevalent functional gene class in microbial genomes and can be described by their specific catalytic functions using the Enzyme Commission (EC) number. Consequently, the ability to predict EC numbers could substantially reduce the number of un-annotated genes. Here we present a deep learning model, DeepECtransformer, which utilizes transformer layers as a neural network architecture to predict EC numbers. Using the extensively studied Escherichia coli K-12 MG1655 genome, DeepECtransformer predicted EC numbers for 464 un-annotated genes. We experimentally validated the enzymatic activities predicted for three proteins (YgfF, YciO, and YjdM). Further examination of the neural network's reasoning process revealed that the trained neural network relies on functional motifs of enzymes to predict EC numbers. Thus, DeepECtransformer is a method that facilitates the functional annotation of uncharacterized genes. Functional annotation of open reading frames in microbial genomes remains substantially incomplete. Here, Kim et al. present a deep learning model that utilizes transformer layers as a neural network architecture to predict specific catalytic functions for enzyme-encoding genes of unknown function. [ABSTRACT FROM AUTHOR]

Recent developments in deep learning have shown success in accurately predicting the location of biological markers in Optical Coherence Tomography (OCT) volumes of patients with Age-Related Macular Degeneration (AMD) and Diabetic Retinopathy (DR). We propose a method that automatically locates biological markers to the Early Treatment Diabetic Retinopathy Study (ETDRS) rings, only requiring B-scan-level presence annotations. We trained a neural network using 22,723 OCT B-Scans of 460 eyes (433 patients) with AMD and DR, annotated with slice-level labels for Intraretinal Fluid (IRF) and Subretinal Fluid (SRF). The neural network outputs were mapped into the corresponding ETDRS rings. We incorporated the class annotations and domain knowledge into a loss function to constrain the output with biologically plausible solutions. The method was tested on a set of OCT volumes with 322 eyes (189 patients) with Diabetic Macular Edema, with slice-level SRF and IRF presence annotations for the ETDRS rings. Our method accurately predicted the presence of IRF and SRF in each ETDRS ring, outperforming previous baselines even in the most challenging scenarios. Our model was also successfully applied to en-face marker segmentation and showed consistency within C-scans, despite not incorporating volume information in the training process. We achieved a correlation coefficient of 0.946 for the prediction of the IRF area. [ABSTRACT FROM AUTHOR]

Previous work on plant disease detection demonstrated that object detectors generally suffer from degraded training data, and annotations with noise may cause the training task to fail. Well-annotated datasets are therefore crucial to build a robust detector. However, a good label set generally requires much expert knowledge and meticulous work, which is expensive and timeconsuming. This paper aims to learn robust feature representations with inaccurate bounding boxes, thereby reducing the model requirements for annotation quality. Specifically, we analyze the distribution of noisy annotations in the real world. A teacher-student learning paradigm is proposed to correct inaccurate bounding boxes. The teacher model is used to rectify the degraded bounding boxes, and the student model extracts more robust feature representations from the corrected bounding boxes. Furthermore, the method can be easily generalized to semi-supervised learning paradigms and autolabeling techniques. Experimental results show that applying our method to the Faster-RCNN detector achieves a 26% performance improvement on the noisy dataset. Besides, our method achieves approximately 75% of the performance of a fully supervised object detector when 1% of the labels are available. Overall, this work provides a robust solution to real-world location noise. It alleviates the challenges posed by noisy data to precision agriculture, optimizes data labeling technology, and encourages practitioners to further investigate plant disease detection and intelligent agriculture at a lower cost. The code will be released at https://github.com/JiuqingDong/TS_OAMIL-for-Plant-disease-detection. [ABSTRACT FROM AUTHOR]

Background: The advancement of single-cell sequencing has progressed our ability to solve biological questions. Cell type annotation is of vital importance to this process, allowing for the analysis and interpretation of enormous single-cell datasets. At present, however, manual cell annotation which is the predominant approach remains limited by both speed and the requirement of expert knowledge. Methods: To address these challenges, we constructed a hierarchically organized marker map through manually curating over 26,000 cell marker entries from about 7000 publications. We then developed WISE, a weighted and integrated gene set enrichment method, to integrate the prevalence of canonical markers and ordered differentially expressed genes of specific cell types in the marker map. Benchmarking analysis suggested that our method outperformed state-of-the-art methods. Results: By integrating the marker map and WISE, we developed a user-friendly and convenient web server, ACT (http://xteam.xbio.top/ACT/ or http://biocc.hrbmu.edu.cn/ACT/), which only takes a simple list of upregulated genes as input and provides interactive hierarchy maps, together with well-designed charts and statistical information, to accelerate the assignment of cell identities and made the results comparable to expert manual annotation. Besides, a pan-tissue marker map was constructed to assist in cell assignments in less-studied tissues. Applying ACT to three case studies showed that all cell clusters were quickly and accurately annotated, and multi-level and more refined cell types were identified. Conclusions: We developed a knowledge-based resource and a corresponding method, together with an intuitive graphical web interface, for cell type annotation. We believe that ACT, emerging as a powerful tool for cell type annotation, would be widely used in single-cell research and considerably accelerate the process of cell type identification. [ABSTRACT FROM AUTHOR]

Zicaitai is a seasonal vegetable known for its high anthocyanin content in both stalks and leaves, yet its reference genome has not been published to date. Here, we generated the first chromosome-level genome assembly of Zicaitai using a combination of PacBio long-reads, Illumina short-reads, and Hi-C sequencing techniques. The final genome length is 474.12 Mb with a scaffold N50 length of 43.82 Mb, a BUSCO score of 99.30% and the LAI score of 10.14. Repetitive elements accounted for 60.89% (288.72 Mb) of the genome, and Hi-C data enabled the allocation of 430.87 Mb of genome sequences to ten pseudochromosomes. A total of 42,051 protein-coding genes were successfully predicted using multiple methods, of which 99.74% were functionally annotated. Notably, comparing the genome of Zicaitai with seven other species in the Cruciferae family revealed strong conservation in terms of gene numbers and structures. Overall, the high-quality genome assembly provides a critical resource for studying the genetic basis of important agronomic traits in Zicaitai. [ABSTRACT FROM AUTHOR]

Motivation Annotations of biochemical models provide details of chemical species, documentation of chemical reactions, and other essential information. Unfortunately, the vast majority of biochemical models have few, if any, annotations, or the annotations provide insufficient detail to understand the limitations of the model. The quality and quantity of annotations can be improved by developing tools that recommend annotations. For example, recommender tools have been developed for annotations of genes. Although annotating genes is conceptually similar to annotating biochemical models, there are important technical differences that make it difficult to directly apply this prior work. Results We present AMAS , a system that predicts annotations for elements of models represented in the Systems Biology Markup Language (SBML) community standard. We provide a general framework for predicting model annotations for a query element based on a database of annotated reference elements and a match score function that calculates the similarity between the query element and reference elements. The framework is instantiated to specific element types (e.g. species, reactions) by specifying the reference database (e.g. ChEBI for species) and the match score function (e.g. string similarity). We analyze the computational efficiency and prediction quality of AMAS for species and reactions in BiGG and BioModels and find that it has subsecond response times and accuracy between 80% and 95% depending on specifics of what is predicted. We have incorporated AMAS into an open-source, pip-installable Python package that can run as a command-line tool that predicts and adds annotations to species and reactions to an SBML model. Availability and implementation Our project is hosted at https://github.com/sys-bio/AMAS , where we provide examples, documentation, and source code files. Our source code is licensed under the MIT open-source license. [ABSTRACT FROM AUTHOR]

This article traces the evidence left by early modern readers who marked their Bibles' annotations—both by taking attentive notice of them and by leaving their own inky traces on them. Among the burgeoning critical interest in both printed and manuscript marginalia there has been little interrogation of the intersection between the two. This article traces the evidence of what the readerly marginalia of biblical annotations can tell us about their readers. It argues that literacy formed and fostered by reading annotated Bibles was likely to be skillful and attuned to issues of interpretation and meaning-making. [ABSTRACT FROM AUTHOR]

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively. [Display omitted] • A consistency training framework for efficient learning from sparse semantic labels. • Propose to probe and well exploit super-points to promote the pseudo-label quality. • Extensive experiments validate the effectiveness and superiority of PointMatch. [ABSTRACT FROM AUTHOR]

Facial analysis models are increasingly applied in real-world applications that significantly impact people's lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic discrimination behavior concerning protected groups, potentially negatively impacting individuals and society. It is, therefore, critical to develop techniques that can mitigate unintended biases in facial classifiers. Hence, this work introduces a novel learning method combining subjective human-based labels and objective annotations based on mathematical definitions of facial traits. Specifically, we generate new objective annotations from two large-scale human-annotated datasets, each capturing a different perspective of the analyzed facial trait. We then propose an ensemble learning method, which combines individual models trained on different types of annotations. We provide an in-depth analysis of the annotation procedure as well as the datasets distribution. We next show how much each individual model, each trained on a different set of annotations, contributes to the final ensemble. Finally, we empirically show that, by incorporating label diversity in the model pipeline, our method successfully mitigates unintended biases while maintaining significant accuracy on the downstream tasks. Our method is generic and can be applied to different types of facial tasks. [Display omitted] • Central hypothesis: Introducing unbiased math concepts in labels reduces biases. • We included mathematical and unbiased notions to improve facial analysis. • This is the first time a debiasing method combines objective and subjective annotations. • We generate new "objective" annotations to the dataset CelebA. • Subjective annotations are the human-based annotations to the dataset. • We show that our model achieves a better fairness metric compared to the literature. • We improved the fairness metric and kept the accuracy levels. [ABSTRACT FROM AUTHOR]

The article reports on the use of social annotation with high school students, featuring educators Johnny B. Allred, Jami Reed, and Christian Z. Goering. They discuss how social annotation fosters meaningful engagement with texts, encouraging students to ask questions and speculate about characters and plot, ultimately enhancing critical thinking and reading skills.

The blackstripe livebearer Poeciliopsis prolifica is a live-bearing fish belonging to the family Poeciliidae with high level of postfertilization maternal investment (matrotrophy). This viviparous matrotrophic species has evolved a structure similarly to the mammalian placenta. Placentas have independently evolved multiple times in Poeciliidae from nonplacental ancestors, which provide an opportunity to study the placental evolution. However, there is a lack of high-quality reference genomes for the placental species in Poeciliidae. In this study, we present a 674 Mb assembly of P. prolifica in 504 contigs with excellent continuity (contig N50 7.7 Mb) and completeness (97.2% Benchmarking Universal Single-Copy Orthologs [BUSCO] completeness score, including 92.6% single-copy and 4.6% duplicated BUSCO score). A total of 27,227 protein-coding genes were annotated from the merged datasets based on bioinformatic prediction, RNA sequencing and homology evidence. Phylogenomic analyses revealed that P. prolifica diverged from the guppy (Poecilia reticulata) ∼19 Ma. Our research provides the necessary resources and the genomic toolkit for investigating the genetic underpinning of placentation. [ABSTRACT FROM AUTHOR]

With continuous progress in science and technology, a large amount of data are produced in all fields of the world at anytime and anywhere. These data are unmarked and lack marking information, while manual marking is time-consuming and laborious. Herein, this paper introduces a distributed semi-supervised labeling framework. This framework addresses the issue of missing data by proposing an attribute-filling method based on subspace learning. Furthermore, this paper presents a distributed semi-supervised learning strategy that trains sub-models (private models) within each sub-system. Finally, this paper develops a distributed graph convolutional neural network fusion technique with enhanced interpretability grounded on the attention mechanism. This paper assigns weights of importance to the edges of each layer in the graph neural network based on sub-models and public data, thereby enabling distributed and interpretable graph convolutional attention. Extensive experimentation using public datasets demonstrates the superiority of the proposed scheme over other state-of-the-art baselines, achieving a reduction in loss of 50% compared to the original approach. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to propose a methodology for the enrichment and tailoring of a knowledge organization system (KOS), in order to support the information extraction (IE) task for the analysis of documents in the tourism domain. In particular, the KOS is used to develop a named entity recognition (NER) system. Design/methodology/approach: A method to improve and customize an available thesaurus by leveraging documents related to the tourism in Italy is firstly presented. Then, the obtained thesaurus is used to create an annotated NER corpus, exploiting both distant supervision, deep learning and a light human supervision. Findings: The study shows that a customized KOS can effectively support IE tasks when applied to documents belonging to the same domains and types used for its construction. Moreover, it is very useful to support and ease the annotation task using the proposed methodology, allowing to annotate a corpus with a fraction of the effort required for a manual annotation. Originality/value: The paper explores an alternative use of a KOS, proposing an innovative NER corpus annotation methodology. Moreover, the KOS and the annotated NER data set will be made publicly available. [ABSTRACT FROM AUTHOR]

Metagenomics provides a tool to assess the functional potential of environmental and host‐associated microbiomes based on the analysis of environmental DNA: assembly, gene prediction and annotation. While gene prediction is straightforward for most bacterial and archaeal taxa, it has limited applicability in the majority of eukaryotic organisms, including fungi that contain introns in gene coding sequences. As a consequence, eukaryotic genes are underrepresented in metagenomics datasets and our understanding of the contribution of fungi and other eukaryotes to microbiome functioning is limited. Here, we developed a machine intelligence‐based algorithm that predicts fungal introns in environmental DNA with reasonable precision and used it to improve the annotation of environmental metagenomes. Intron removal increased the number of predicted genes by up to 9.1% and improved the annotation of several others. The proportion of newly predicted genes increased with the share of eukaryotic genes in the metagenome and—within fungal taxa—increased with the number of introns per gene. Our approach provides a tool named SVMmycointron for improved metagenome annotation, especially of microbiomes with a high proportion of eukaryotes. The scripts described in the paper are made publicly available and can be readily utilized by microbiome researchers analysing metagenomics data. [ABSTRACT FROM AUTHOR]

Human activities can be recognized in sensor data using supervised machine learning algorithms. In this approach, human annotators must annotate events in the sensor data which are used as input to supervised learning algorithms. Annotating events directly in time series graphs of data streams is difficult. Video is often collected and synchronized to the sensor data to aid human annotators in identifying events in the data. Other work in human activity recognition (HAR) minimizes the cost of annotation by using unsupervised or semi-supervised machine learning algorithms or using algorithms that are more tolerant of human annotation errors. Rather than adjusting algorithms, we focus on the performance of the human annotators themselves. Understanding how human annotators perform annotation may lead to annotation interfaces and data collection schemes that better support annotators. We investigate the accuracy and efficiency of human annotators in the context of four HAR tasks when using video, data, or both to annotate events. After a training period, we found that annotators were more efficient when using data alone on three of four tasks and more accurate when marking event types when using video alone on all four tasks. Annotators were more accurate when marking event boundaries using data alone on two tasks and more accurate using video alone on the other two tasks. Our results suggest that data and video collected for annotation of HAR tasks play different roles in the annotation process and these roles may vary with the HAR task. [ABSTRACT FROM AUTHOR]

【Objective】The characteristics of differential proteins of maize at nine-leaf stage under long sunshine condition were investigated, so as to provide biological basis for revealing the molecular mechanism of maize.【Method】LP light sensitive (NT32) and light insensitive (NQR273) maize inbred lines were used as experimental materials. The experimental materials were treated with artificial control of long sunshine (16 h light /8 h dark). Young leaves of maized were collected at the nine-leaf stage, and proteomic analysis of different light-sensitive inbred lines was analyzed by TMT technique. At the same time, bioinformatics analysis was used to study the expression characteristics of differential proteins under long sunshine condition.【Result】A total of 191 differential proteins were detected, of which 107 were up-regulated and 84 were down-regulated. GO enrichment analysis showed that differential proteins were mainly involved in biological processes such as ribosome structure, cysteine-type peptidase activity and manganese ion binding process. Proteolysis and translation processes were important molecular functional classes. Differential proteins were mainly enriched with secondary metabolite biosynthesis, glutathione metabolism, porphyrin and chlorophyll metabolism and other pathways. Amino acid synthesis and ribosome metabolism were identified as key pathways. There were 79 differential proteins with functional annotation, which were involved in ROS homeostasis (19), storage protection (7), amino acid metabolism (8), and other functional genes (45).【Conclusion】 The ROS clearance ability of light-sensitive NT32 corn was enhanced under long sunshine condition, while the storage protection ability and amino acid metabolism decreased, and other functional genes played their roles in different ways, which meant that the regulatory system of amino acid synthesis and ribosome metabolism in the leaves of light-sensitive NT32 maize maintained the stable growth of corn under long sunshine condition. [ABSTRACT FROM AUTHOR]

With the increase of user-generated content on social media, the detection of abusive language has become crucial and is therefore reflected in several shared tasks that have been performed in recent years. The development of automatic detection systems is desirable, and the classification of abusive social media content can be solved with the help of machine learning. The basis for successful development of machine learning models is the availability of consistently labeled training data. But a diversity of terms and definitions of abusive language is a crucial barrier. In this work, we analyze a total of nine datasets—five English and four German datasets—designed for detecting abusive online content. We provide a detailed description of the datasets, that is, for which tasks the dataset was created, how the data were collected, and its annotation guidelines. Our analysis shows that there is no standard definition of abusive language, which often leads to inconsistent annotations. As a consequence, it is difficult to draw cross-domain conclusions, share datasets, or use models for other abusive social media language tasks. Furthermore, our manual inspection of a random sample of each dataset revealed controversial examples. We highlight challenges in data annotation by discussing those examples, and present common problems in the annotation process, such as contradictory annotations and missing context information. Finally, to complement our theoretical work, we conduct generalization experiments on three German datasets. [ABSTRACT FROM AUTHOR]

The quality of annotations in manually annotated hate speech datasets is crucial for automatic hate speech detection. This contribution focuses on the positive effects of manually annotating online comments for hate speech within the context in which the comments occur. We quantify the impact of context availability by meticulously designing an experiment: Two annotation rounds are performed, one in-context and one out-of-context, on the same English YouTube data (more than 10,000 comments), by using the same annotation schema and platform, the same highly trained annotators, and quantifying annotation quality through inter-annotator agreement. Our results show that the presence of context has a significant positive impact on the quality of the manual annotations. This positive impact is more noticeable among replies than among comments, although the former is harder to consistently annotate overall. Previous research reporting that out-of-context annotations favour assigning non-hate-speech labels is also corroborated, showing further that this tendency is especially present among comments inciting violence, a highly relevant category for hate speech research and society overall. We believe that this work will improve future annotation campaigns even beyond hate speech and motivate further research on the highly relevant questions of data annotation methodology in natural language processing, especially in the light of the current expansion of its scope of application. [ABSTRACT FROM AUTHOR]

This paper introduces Semantic Knowledge Advanced Tool for Extraction Browsing Organisation Annotation Retrieval and Discovery (SKATEBOARD), a tool designed to facilitate knowledge exploration through the application of semantic technologies. The demand for advanced solutions that streamline Knowledge Extraction, management, and visualisation, characterised by abundant information, has grown substantially in the current era. Graph-based representations have emerged as a robust approach for uncovering intricate data relationships, complementing the capabilities offered by AI models. Acknowledging the transparency and user control challenges faced by AI-driven solutions, SKATEBOARD offers a comprehensive framework encompassing Knowledge Extraction, ontology development, management, and interactive exploration. By adhering to Linked Data principles and adopting graph-based exploration, SKATEBOARD provides users with a clear view of data relationships and dependencies. Furthermore, it integrates recommendation systems and reasoning capabilities to augment the knowledge discovery process, thus introducing a serendipity effect generated by the SKATEBOARD interface exploration. This paper elucidates SKATEBOARD's functionalities while emphasising its user-centric design. After reviewing related research, we provide an overview of the SKATEBOARD pipeline, demonstrating its capacity to bridge RDF and LPG representations. Subsequent sections delve into Knowledge Extraction and exploration, culminating in the evaluation of the tool. SKATEBOARD empowers users to make informed decisions and uncover valuable insights within their data domains, with the added dimension of serendipitous discoveries facilitated by its interface exploration capabilities. [ABSTRACT FROM AUTHOR]

Public proteomics data often lack essential metadata, limiting its potential. To address this, we present lesSDRF, a tool to simplify the process of metadata annotation, thereby ensuring that data leave a lasting, impactful legacy well beyond its initial publication. Public proteomics data often lack essential metadata, limiting their potential. To address this, the authors developed lesSDRF, a tool to simplify the process of metadata annotation, thereby ensuring that data leave a lasting, impactful legacy well beyond their initial publication. [ABSTRACT FROM AUTHOR]

Background: Single-cell RNA-sequencing (scRNA-seq) has become a widely used tool for both basic and translational biomedical research. In scRNA-seq data analysis, cell type annotation is an essential but challenging step. In the past few years, several annotation tools have been developed. These methods require either labeled training/reference datasets, which are not always available, or a list of predefined cell subset markers, which are subject to biases. Thus, a user-friendly and precise annotation tool is still critically needed. Results: We curated a comprehensive cell marker database named scMayoMapDatabase and developed a companion R package scMayoMap, an easy-to-use single-cell annotation tool, to provide fast and accurate cell type annotation. The effectiveness of scMayoMap was demonstrated in 48 independent scRNA-seq datasets across different platforms and tissues. Additionally, the scMayoMapDatabase can be integrated with other tools and further improve their performance. Conclusions: scMayoMap and scMayoMapDatabase will help investigators to define the cell types in their scRNA-seq data in a streamlined and user-friendly way. [ABSTRACT FROM AUTHOR]

The recent development of high-throughput workflows in genomics and transcriptomics revealed that efficient annotation of such results is essential for researchers to draw conclusions from obtained results. Although some tools are available, their functionality is limited. Here, we present AGouTI–a universal tool for flexible annotation of any genomic or transcriptomic coordinates using known genomic features deposited in different publicly available databases in the form of GTF or GFF files. In contrast to currently available tools, AGouTI is designed to provide a flexible selection of genomic features overlapping or adjacent to annotated intervals and can be used on custom column-based text files obtained from different data analysis pipelines. Although providing many unique options, AGouTI is straightforward in installation and usage, enabling effortless integration into existing data analysis workflows. [ABSTRACT FROM AUTHOR]

A long tradition of research in theoretical, experimental and computational pragmatics has investigated over-specification and under-specification in referring expressions. Along broadly Gricean lines, these studies compare the amount of information expressed by a referring expression against the amount of information that is required. Often, however, these studies offer no formal definition of what "required" means, and how the comparison should be performed. In this paper, we use a simple set-theoretic perspective to define some communicatively important types of over-/under-specification. We argue that our perspective enables an enhanced understanding of reference phenomena that can pay important dividends for the analysis of reference in corpora and for the evaluation of computational models of referring. To illustrate and substantiate our claims, we analyse two corpora, containing Chinese and English referring expressions respectively, using the new perspective. The results show that interesting new monolingual and cross-linguistic insights can be obtained from our perspective. • A new prospective on reference is proposed; • Referring Expressions are sub-categorised; • An annotation scheme is proposed based on the new perspective; • Using the scheme, a enhanced analysis is conducted on two reference corpora (in English and Chinese, respectively). [ABSTRACT FROM AUTHOR]

Digital imaging has become an essential element in every medical institution. Therefore, medical image retrieval such as chest X-ray (CXR) must be improved via novel feature extraction and annotation activities before they are stored into image databases. To date, many methods have been introduced to annotate medical images using spatial relationships after these features are extracted. However, the annotation performance for each method is inconsistent and does not show promising achievement to retrieve images. It is noticed that each method is still struggling with at least two big problems. Firstly, the recommended annotation model is weak because the method does not consider the object shape and rely on gross object shape estimation. Secondly, the suggested annotation model can only be functional for simple object placement. As a result, it is difficult to determine the spatial relationship feature after they are extracted to annotate images accurately. Hence, this study aims to propose a new model to annotate nodule location within lung zone for CXR image with extracted spatial relationship feature to improve image retrieval. In order to achieve the aim, a methodology that consists of six phases of CXR image annotation using the extracted spatial relationship features is introduced. This comprehensive methodology covers all cycles for image annotation tasks starting from image pre-processing until determination of spatial relationship features for the lung zone in the CXR. The outcome from applying the methodology also enables us to produce a new semi-automatic annotation system named CHEXRIARS which acts as a tool to annotate the extracted spatial relationship features in CXR images. The CHEXRIARS performance is tested using a retrieval test with two common tests namely the precision and recall (PNR). Apart from CHEXRIARS, three other annotation methods that are object slope, object projection and comparison of region boundaries are also included in the retrieval performance test. Overall, the CHEXRIARS interpolated PNR curve shows the best shape because it is the closest curve approaching the value of 1 on the X-axis and Y-axis. Meanwhile the value of area under curve for CHEXRIARS also revealed that this system attained the highest score at 0.856 as compared to the other three annotation methods. The outcome from the retrieval performance test indicated that the proposed annotation model has produced outstanding outcome and improved the image retrieval. [ABSTRACT FROM AUTHOR]

Detecting and tracking multiple moving objects in a video is a challenging task. For living cells, the task becomes even more arduous as cells change their morphology over time, can partially overlap, and mitosis leads to new cells. Differently from fluorescence microscopy, label-free techniques can be easily applied to almost all cell lines, reducing sample preparation complexity and phototoxicity. In this study, we present ALFI, a dataset of images and annotations for label-free microscopy, made publicly available to the scientific community, that notably extends the current panorama of expertly labeled data for detection and tracking of cultured living nontransformed and cancer human cells. It consists of 29 time-lapse image sequences from HeLa, U2OS, and hTERT RPE-1 cells under different experimental conditions, acquired by differential interference contrast microscopy, for a total of 237.9 hours. It contains various annotations (pixel-wise segmentation masks, object-wise bounding boxes, tracking information). The dataset is useful for testing and comparing methods for identifying interphase and mitotic events and reconstructing their lineage, and for discriminating different cellular phenotypes. [ABSTRACT FROM AUTHOR]

Event extraction(EE) is a challenging task of information extraction, which aims to extract structured event information from text. Existing methods usually achieve state-of-the-art performance based on pre-trained language models(PLMs) that exploit the semantic information of triggers and arguments. However, these methods struggle in extraction due to their lack of two intrinsic considerations: (a) the complexity of event structure; (b) the impact of exact event type on event extraction. In this paper, we propose an event annotation enhanced BERT framework, termed EABERT. Specifically,event annotations are predefined and can be considered as a complete event structure. We inject additional event knowledge into the model by incorporating event annotations into the model input. Furthermore, to incorporate appropriate event annotations into the model, we employ the bilateral-branch BERT network to train the event type classifier for better accuracy of event annotations. Experiments on the event extraction benchmark dataset (ACE 2005, MAVEN) significantly improved our proposed framework compared to previous approaches. [ABSTRACT FROM AUTHOR]

Motivation Evaluating the gene completeness is critical to measuring the quality of a genome assembly. An incomplete assembly can lead to errors in gene predictions, annotation, and other downstream analyses. Benchmarking Universal Single-Copy Orthologs (BUSCO) is a widely used tool for assessing the completeness of genome assembly by testing the presence of a set of single-copy orthologs conserved across a wide range of taxa. However, BUSCO is slow particularly for large genome assemblies. It is cumbersome to apply BUSCO to a large number of assemblies. Results Here, we present compleasm, an efficient tool for assessing the completeness of genome assemblies. Compleasm utilizes the miniprot protein-to-genome aligner and the conserved orthologous genes from BUSCO. It is 14 times faster than BUSCO for human assemblies and reports a more accurate completeness of 99.6% than BUSCO's 95.7%, which is in close agreement with the annotation completeness of 99.5% for T2T-CHM13. Availability and implementation https://github.com/huangnengCSU/compleasm. [ABSTRACT FROM AUTHOR]

This article provides edition, translation, and annotation of a Greek excerpt dealing with the christological issue of "whether there is an anhypostatos nature." Until now unedited and recently catalogued as one of the fragments of Cyril of Alexandria's Contra Synousiastas , it in fact contains a close parallel to a famous passage from Leontius of Byzantium's Contra Nestorianos et Eutychianos concerning the distinction between hypostasis and enhypostaton. It is argued that the fragment was written in the aftermath of the Tritheist controversy and, more specifically, that it faces the doctrines of John Philoponus. [ABSTRACT FROM AUTHOR]

In the entity extraction task, there are some complex extraction problems, such as nested entity, entity boundary recognition, context ambiguity, and multi-instance entity recognition. Entity nesting is an important challenge in relational extraction. The main reason of entity nesting problem is that the boundary information between entities is not clear. In order to solve the entity nesting problem at the fragment level, while preserving the relationship between fragments with the same characteristics and improving efficiency, we proposed a brand new fragment annotation method. On the basis of traditional fragment annotation method, combined with pointer annotation method, we designed an annotation method of "ergodic enumeration + group mapping". On the basis of this method, an entity extraction model is designed: Span-Extraction Based Entity Extraction Model (LMA). Our model underwent a series of validations in the English data sets New York Times(NYT) and WEBNLG, showing significant improvements over the baseline model F1. It can effectively alleviate the above problems. [ABSTRACT FROM AUTHOR]

Disorder prediction methods that can discriminate between ordered and disordered regions have contributed fundamentally to our understanding of the properties and prevalence of intrinsically disordered proteins (IDPs) in proteomes as well as their functional roles. However, a recent large-scale assessment of the performance of these methods indicated that there is still room for further improvements, necessitating novel approaches to understand the strengths and weaknesses of individual methods. In this study, we compared two methods, IUPred and disorder prediction, based on the pLDDT scores derived from AlphaFold2 (AF2) models. We evaluated these methods using a dataset from the DisProt database, consisting of experimentally characterized disordered regions and subsets associated with diverse experimental methods and functions. IUPred and AF2 provided consistent predictions in 79% of cases for long disordered regions; however, for 15% of these cases, they both suggested order in disagreement with annotations. These discrepancies arose primarily due to weak experimental support, the presence of intermediate states, or context-dependent behavior, such as binding-induced transitions. Furthermore, AF2 tended to predict helical regions with high pLDDT scores within disordered segments, while IUPred had limitations in identifying linker regions. These results provide valuable insights into the inherent limitations and potential biases of disorder prediction methods. [ABSTRACT FROM AUTHOR]

This paper explores the potential of self-supervised learning as an alternative to supervised learning in the context of geometry-based 3D object retrieval. With the ongoing digitalization of many industries, an exponentially increasing number of 3D objects are processed by retrieval systems. In order to support new shapes, modern deep learning-based retrieval systems require retraining. The dominant paradigm for optimizing neural networks in this field is supervised classification training. Supervised learning requires time-consuming and expensive data annotation. Moreover, training neural networks for classification introduces a bias towards the classes in the training data, which is undesirable for retrieval systems encountering unseen object types in the wild. Through extensive experiments, we make a direct comparison between supervised and self-supervised learning on four datasets from three different domains (household, manufacturing and medical). For object classes seen during training, self-supervised and supervised learning are competitive. For unseen classes, self-supervised learning outperforms supervised learning in many cases. We conclude that self-supervised learning provides a powerful tool for circumventing labeling costs and providing more robust retrieval systems. [Display omitted] • Self-supervised learning is on par with supervised learning for 3D object retrieval. • Self-supervised object retrieval outperforms supervised learning out-of-distribution. • Object alignment is highly impactful on the performance of retrieval systems. • Non-contrastive siamese networks are a practical option in 3D deep learning. [ABSTRACT FROM AUTHOR]

This article examines the efforts of Matthew Parker and his scholarly circle to understand the medieval books that he collected as archbishop of Canterbury. It argues that Parker made sense of his books by connecting them to what amounted to an emerging history of the book. That is, Parker began to piece together the formal features of different medieval books into a rough but increasingly refined timeline of the history of book production in order to contextualize any given manuscript. The evidence can be found scattered throughout Parker's library, in the form of annotations, transcripts of passages, copied illustrations, and printed books that offer a wealth of information about how Parker's team understood the books they handled. This documentation reveals how they combined scribal knowledge with textual information, to powerful ends. By connecting Parker's practices to contemporary developments in other areas of knowledge production, from alchemy to conjectural emendation, this article offers a new way forward for scholarly analysis of the early modern study of older books, especially for our analysis of early modern practices and paradigms that do not fit modern definitions of paleography and codicology. [ABSTRACT FROM AUTHOR]

Holistic scene understanding is a challenging problem in computer vision. Most recent researches in this field were focusing on the object detection, the semantic segmentation and the relationship detection tasks. The attribute can provide meaningful information for the object instance, thus the object instance can be expressed more detail in the scene understanding. However, most researches in this field have been limited to several special conditions. Such as, several researches were just focusing on the attribute of special object class, because their solutions were aimed at a limited-scenarios, their methods are hardly to generalize in other scenarios. We also find that most of the research for multi-attribute detection task were only regarding each attribute as binary class and simply use the multi-binary-classifier method for the attribute detection. But these strategies above not consider the relation between each pair of the attributes, they will fall into trouble in the "imperfect" attribute dataset (which is labeled with the missing and incomplete annotations), and they will have low performance in the long-tail attribute class (which has lower rank of annotation and more missing labels). In this paper, we focus on the multi-attribute detection for a variant of object classes and take the relation between attributes into consideration. We propose a GRU-based model to detect a variable-length attribute sequence with a customized loss compute method to solve the "imperfect" attribute dataset problem. Furthermore, we perform ablative studies to prove the effectiveness of each part of our method. Finally, we compare our model with several existed multi-attribute detection methods on VG (Visual Genome) and CUB200 bird datasets to prove the superior performance of the proposed model. [ABSTRACT FROM AUTHOR]

The evolution of single-cell technology is ongoing, continually generating massive amounts of data that reveal many mysteries surrounding intricate diseases. However, their drawbacks continue to constrain us. Among these, annotating cell types in single-cell gene expressions pose a substantial challenge, despite the myriad of tools at our disposal. The rapid growth in data, resources, and tools has consequently brought about significant alterations in this area over the years. In our study, we spotlight all note-worthy cell type annotation techniques developed over the past four years. We provide an overview of the latest trends in this field, showcasing the most advanced methods in taxonomy. Our research underscores the demand for additional tools that incorporate a biological context and also predicts that the rising trend of graph neural network approaches will likely lead this research field in the coming years. [ABSTRACT FROM AUTHOR]

One of a map's fundamental elements is its annotations, and extracting these annotations is an important step in enabling machine intelligence to understand scanned map data. Due to the complexity of the characters and lines, extracting annotations from scanned Chinese maps is difficult, and there is currently little research in this area. A deep-learning-based framework for extracting annotations from scanned Chinese maps is presented in the paper. Improved the EAST annotation detection model and CRNN annotation recognition model based on transfer learning make up the two primary parts of this framework. Several sets of the comparative tests for annotation detection and recognition were created in order to assess the efficacy of this method for extracting annotations from scanned Chinese maps. The experimental findings show the following: (i) The suggested annotation detection approach in this study revealed precision, recall, and h-mean values of 0.8990, 0.8389, and 0.8635, respectively. These measures demonstrate improvements over the currently popular models of −0.0354 to 0.0907, 0.0131 to 0.2735, and 0.0467 to 0.1919, respectively. (ii) The proposed annotation recognition method in this study revealed precision, recall, and h-mean values of 0.9320, 0.8956, and 0.9134, respectively. These measurements demonstrate improvements over the currently popular models of 0.0294 to 0.1049, 0.0498 to 0.1975, and 0.0402 to 0.1582, respectively. [ABSTRACT FROM AUTHOR]

The research deals with an evolutionary-based mutation with functional annotation to identify protein complexes within PPI networks. An important field of research in computational biology is the difficult and fundamental challenge of revealing complexes in protein interaction networks. The complex detection models that have been developed to tackle challenges are mostly dependent on topological properties and rarely use the biological properties of PPI networks. This research aims to push the evolutionary algorithm to its maximum by employing gene ontology (GO) to communicate across proteins based on biological information similarity for direct genes. The outcomes show that the suggested method can be utilized to improve the predictability of the complexes identified. The GO functional annotation of proteins as a heuristic guide is injected into the framework of single-objective evolutionary algorithms (EAs), while the complex detection community score (CS) model works as a fitness function in EAs. In the experiments, we analyzed the performance of our proposed algorithm when applied to the publicly accessible yeast protein networks. The results show a considerable improvement in the detection ability of complexes in the PPI network. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (Re-ID) has better scalability and usability in real-world deployments due to the lack of annotations, which is more challenging than supervised methods. State-of-the-art approaches mainly employ clustering algorithms to generate pseudo-labels for transferring the process into a supervised operation. However, the clustering algorithm depends on discriminative pedestrian features. Only using the clustering algorithm produces low-quality labels and hinders the performance of the Re-ID model. In the paper, we propose the hybrid feature constraint network (HFCN) to adequately restrict the pedestrian feature distribution for unsupervised person Re-ID. Specifically, we first define a feature constraint loss to restrict the feature distribution so that different pedestrians can be clearly distinguished at the first step. And then, we design a multi-task operation with the iterative update for clustering algorithm to further implement the feature constraint. This can adequately utilize predicted label information and identify complex samples. Finally, we integrate the feature constraint loss and multi-task operation to optimize the Re-ID model, which could promote the clustering to generate high-quality labels and learn valuable information. Extensive experiments prove that the proposed HFCN is effective and outperforms the state-of-the-art. [ABSTRACT FROM AUTHOR]

This paper introduced a novel approach for image retrieval, the scene-aware object saliency ranking algorithm（SASR）,which addressed the issue of traditional image retrieval techniques relying on semantic similarity and neglecting the crucial importance of object relationships within a scene. SASR consisted of two stages. In the first stage, this paper proposed a viewpoint data-based method called the “combined threshold” to annotate true value labels for object-level saliency ranking, simplifying the annotation of ranking labels. In the second stage, this paper presented an object-level saliency ranking network based on graph convolutional networks that resolved several specific difficulties encountered in sorting objects. The proposed algorithm improved on the current saliency ranking label generation methods and was tested via a large number of comparative experiments. The experimental results on the SALICON dataset show that the SASR algorithm enhances saliency ranking perfor-mance significantly. Moreover, the results from the NUS-WIDE dataset indicate that, when supported by the proposed algorithm, image retrieval performance increases by an average of 2%,which solidifies the efficacy of the proposed algorithm [ABSTRACT FROM AUTHOR]

Copyright of Palíndromo is the property of Universidade do Estado de Santa Catarina 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.)

Copyright of Coal Geology & Exploration is the property of Xian Research Institute of China Coal Research Institute 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.)

Sensing the mental state induced by different task contexts, where cognition is a focus, is as important as sensing the affective state where emotion is induced in the foreground of consciousness, because completing tasks is part of every waking moment of life. However, few datasets are publicly available to advance mental state analysis, especially those using the eye as the sensing modality with detailed ground truth for eye behaviors. In this study, we contribute a high-quality publicly accessible eye video dataset, IREye4Task, where the eyelid, pupil and iris boundary are annotated for each frame to obtain eye behaviors as responses to four different task contexts and two load levels of tasks, over more than a million frames. Meanwhile, we propose a series of eye behavior representations to provide insights into how the eye behaves during different mental states. Finally, we benchmark three mental-state recognition tasks for this dataset to demonstrate the effectiveness of the eye behavior representations. This is the first public wearable eye video dataset for mental state analysis with high quality eye landmarks and a variety of mental states, and is the first study analyzing comprehensive eye behaviors far beyond using pupil size and blink in previous studies. [ABSTRACT FROM AUTHOR]

The quality of daily spontaneous conversations is of importance towards both our well-being as well as the development of interactive social agents. Prior research directly studying the quality of social conversations has operationalized it in narrow terms, associating greater quality to less small talk. Other works taking a broader perspective of interaction experience have indirectly studied quality through one of the several overlapping constructs such as rapport or engagement, in isolation. In this work we bridge this gap by proposing a holistic conceptualization of conversation quality, building upon the collaborative attributes of cooperative conversation floors. Taking a multilevel perspective of conversation, we develop and validate two instruments for perceived conversation quality (PCQ) at the individual and group levels. Specifically, we motivate capturing external raters’ gestalt impressions of participant experiences from thin slices of behavior, and collect annotations of PCQ on the publicly available MatchNMingle dataset of in-the-wild mingling conversations. Finally, we present an analysis of behavioral features that are predictive of PCQ. We find that for the conversations in MatchNMingle, raters tend to associate smaller group sizes, equitable speaking turns with fewer interruptions, and time taken for synchronous bodily coordination with higher PCQ. [ABSTRACT FROM AUTHOR]

Facial Expression Recognition (FER) suffers from misrecognition due to the similarities between expressions. To address this issue, popular works replace original annotations with soft labels to reflect expression similarities. However, existing soft label learning (SLL) modules are independent of FER modules. In this article, inspired by automatic control theory, we propose a bias-based soft label learning network for FER named EC-Net. For optimizing FER and SLL modules jointly, EC-Net constitutes the closed-loop feedback between the two modules by designing a module measuring and transmitting the bias between FER module predictions and target labels. Specifically, EC-Net contains three modules: E-subNet, C-subNet, and L-Transmitter. First, E-subNet, i.e., the FER module, attempts to converge to target labels under the supervision of soft labels, acting as the executor. Then, L-Transmitter measures the bias between E-subNet predictions and target labels. It converts multiple discrete biases to the bias-based label through spectral clustering and transmits it to C-subNet. Finally, C-SubNet, i.e., the SLL module, generates soft labels from the bias-based label with a cascaded learner and progressively distinguishes similar expressions. It updates the learned soft labels for E-subNet, performing like the controller. Supervised by the bias-based soft label, E-subNet effectively reduces the dominant bias caused by similar expressions. We conduct extensive experiments on four popular benchmarks, demonstrating the effectiveness of applying closed-loop feedback in the FER task. [ABSTRACT FROM AUTHOR]

With the increasing use of social media with its ability for users to share comments immediately, the extent of a system to identify offensive content has become a necessity in all languages. Due to the lack of publicly available resources on offensive language identification for Farsi, which has more than 110 million speakers, we present Pars-OFF, a three-layered annotated corpus for offensive language detection in Farsi to fill the existing gap. The introduced corpus contains 10,563 data samples. The tweets have been collected with a combination of similarity-based and keyword-based data selection techniques to avoid severe unbalancedness. Additionally, as a baseline, this article reports the performance of the traditional machine learning approaches and Transformer based models over the Pars-OFF dataset. The best performance was obtained by the BERT+fastText model, yielding the F1-Macro score of 89.57. [ABSTRACT FROM AUTHOR]

Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model's attention are within expert annotations, whereas 36.03% of the two dimensional model's attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.