Annotation System Research Articles

Parallel Bidirectionally Pretrained Taggers as Feature Generators

In a setting where multiple automatic annotation approaches coexist and advance separately but none completely solve a specific problem, the key might be in their combination and integration. This paper outlines a scalable architecture for Part-of-Speech tagging using multiple standalone annotation systems as feature generators for a stacked classifier. It also explores automatic resource expansion via dataset augmentation and bidirectional training in order to increase the number of taggers and to maximize the impact of the composite system, which is especially viable for low-resource languages. We demonstrate the approach on a preannotated dataset for Serbian using nested cross-validation to test and compare standalone and composite taggers. Based on the results, we conclude that given a limited training dataset, there is a payoff from cutting a percentage of the initial training set and using it to fine-tune a machine-learning-based stacked classifier, especially if it is trained bidirectionally. Moreover, we found a measurable impact on the usage of multiple tagsets to scale-up the architecture further through transfer learning methods.

Deep phenotyping: symptom annotation made simple with SAMS.

Precision medicine needs precise phenotypes. The Human Phenotype Ontology (HPO) uses clinical signs instead of diagnoses and has become the standard annotation for patients’ phenotypes when describing single gene disorders. Use of the HPO beyond human genetics is however still limited. With SAMS (Symptom Annotation Made Simple), we want to bring sign-based phenotyping to routine clinical care, to hospital patients as well as to outpatients. Our web-based application provides access to three widely used annotation systems: HPO, OMIM, Orphanet. Whilst data can be stored in our database, phenotypes can also be imported and exported as Global Alliance for Genomics and Health (GA4GH) Phenopackets without using the database. The web interface can easily be integrated into local databases, e.g. clinical information systems. SAMS offers users to share their data with others, empowering patients to record their own signs and symptoms (or those of their children) and thus provide their doctors with additional information. We think that our approach will lead to better characterised patients which is not only helpful for finding disease mutations but also to better understand the pathophysiology of diseases and to recruit patients for studies and clinical trials. SAMS is freely available at https://www.genecascade.org/SAMS/.

한국어 말하기 자동평가를 위한 발음 오류 분석 - 중국어, 베트남어, 태국어 화자를 중심으로 -

This study aims to propose a phonetic transcription and annotation system for automated speaking assessment of Korean. We analyzed the pronunciation errors discovered in the speech data of 2,250 sentences (32,610 words) read by 30 speakers of Chinese, Vietnamese, and Thai. We were able to predict the observed errors based on the comparative analyses between the phonetic and phonological system of Korean and those of the native languages of the learners, and thus suggested using the frequency of errors for the assessment of segmental accuracy. These results are expected to contribute to the on-going discussions of automated assessment of Korean speaking tests and the future development of automated tools for Korean language education.

Application of Rough Concept Lattice Model in Construction of Ontology and Semantic Annotation in Semantic Web of Things

In order to solve the problem of interoperability in Internet of Things, the Semantic Web technology is introduced into the Internet of Things to form Semantic Web of Things. Ontology construction is the core of Semantic Web of Things. Firstly, this paper analyzes the shortcomings of ontology construction methods in the Semantic Web of Things. Then, this paper proposes construction of semantic ontology based on improved rough concept lattice, which provides theoretical basis for semantic annotation of the sensing data attributes. In addition, this paper describes the semantic annotation system for the Internet of Things based on semantic similarity of ontology. The system consists of three steps: ontology mapping integration module, information extraction module, and semantic annotation of sensing data. Finally, the experimental results show that this semantic annotation method effectively improves the flexibility of sensor information and data attributes and effectively enhances the expression ability of sensor information and the use value of data.

Bioinformatics and network-based approaches for determining pathways, signature molecules, and drug substances connected to genetic basis of schizophrenia etiology

Knowledge of heterogeneous etiology and pathophysiology of schizophrenia (SZP) is reasonably inadequate and non-deterministic due to its inherent complexity and underlying vast dynamics related to genetic mechanisms. The evolution of large-scale transcriptome-wide datasets and subsequent development of relevant, robust technologies for their analyses show promises toward elucidating the genetic basis of disease pathogenesis, its early risk prediction, and predicting drug molecule targets for therapeutic intervention. In this research, we have scrutinized the genetic basis of SZP through functional annotation and network-based system biology approaches. We have determined 96 overlapping differentially expressed genes (DEGs) from 2 microarray datasets and subsequently identified their interconnecting networks to reveal transcriptome signatures like hub proteins (FYN, RAD51, SOCS3, XIAP, AKAP13, PIK3C2A, CBX5, GATA3, EIF3K, and CDKN2B), transcription factors and miRNAs. In addition, we have employed gene set enrichment to highlight significant gene ontology (e.g., positive regulation of microglial cell activation) and relevant pathways (such as axon guidance and focal adhesion) interconnected to the genes associated with SZP. Finally, we have suggested candidate drug substances like Luteolin HL60 UP as a possible therapeutic target based on these key molecular signatures.

Phenonizer: A Fine-Grained Phenotypic Named Entity Recognizer for Chinese Clinical Texts.

Biomedical named entity recognition (BioNER) from clinical texts is a fundamental task for clinical data analysis due to the availability of large volume of electronic medical record data, which are mostly in free text format, in real-world clinical settings. Clinical text data incorporates significant phenotypic medical entities (e.g., symptoms, diseases, and laboratory indexes), which could be used for profiling the clinical characteristics of patients in specific disease conditions (e.g., Coronavirus Disease 2019 (COVID-19)). However, general BioNER approaches mostly rely on coarse-grained annotations of phenotypic entities in benchmark text dataset. Owing to the numerous negation expressions of phenotypic entities (e.g., “no fever,” “no cough,” and “no hypertension”) in clinical texts, this could not feed the subsequent data analysis process with well-prepared structured clinical data. In this paper, we developed Human-machine Cooperative Phenotypic Spectrum Annotation System (http://www.tcmai.org/login, HCPSAS) and constructed a fine-grained Chinese clinical corpus. Thereafter, we proposed a phenotypic named entity recognizer: Phenonizer, which utilized BERT to capture character-level global contextual representation, extracted local contextual features combined with bidirectional long short-term memory, and finally obtained the optimal label sequences through conditional random field. The results on COVID-19 dataset show that Phenonizer outperforms those methods based on Word2Vec with an F1-score of 0.896. By comparing character embeddings from different data, it is found that character embeddings trained by clinical corpora can improve F-score by 0.0103. In addition, we evaluated Phenonizer on two kinds of granular datasets and proved that fine-grained dataset can boost methods' F1-score slightly by about 0.005. Furthermore, the fine-grained dataset enables methods to distinguish between negated symptoms and presented symptoms. Finally, we tested the generalization performance of Phenonizer, achieving a superior F1-score of 0.8389. In summary, together with fine-grained annotated benchmark dataset, Phenonizer proposes a feasible approach to effectively extract symptom information from Chinese clinical texts with acceptable performance.

Commentary on Variants in the ABCC6 Gene Implicated in Pseudoxanthoma Elasticum, a Heritable Ectopic Mineralization Disorder

Significant progress has been made in understanding pseudoxanthoma elasticum (PXE), which results from mutations in ABCC6. The low prevalence of PXE and its heterotypic presentation confound genotype-phenotype correlations and the characterization of many identified variants. Kowal etal. (2022) present an invivo model to characterize and annotate ABCC6 variants, establishing a novel system for allele annotation in the patient population.

Fatty acid synthase (Fasn) inhibits the expression levels of immune response genes via alteration of alternative splicing in islet cells

BackgroundIncreasing evidence has shown that fatty acid synthase (Fasn) is associated with diabetes mellitus (DM) and insulin resistance, however, it remains unclear how Fasn upregulation leads to dysregulation of energy homeostasis in islet cells. Consequently, uncovering the function of Fasn in islet cells. Consequently, uncovering the function of FASN in islet cells is immensely important for finding a treatment target. AimIn this study, we elucidated the biological function of Fasn on the target genes in a rat insulinoma INS-1 cell line. MethodsWe created a Fasn overexpressing rat insulinoma cell line (Fasn-OE), and performed bulk RNA-sequencing (RNA-seq) experiments on Fasn-OE and INS-1 (control) cells. We first identified differentially expressed genes (DEGs) using Bioconductor package edgeR, and then discovered enriched gene ontology terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways using the KEGG Orthology Based Annotation System (KOBAS) 2.0 web server. Furthermore, we identified alternative splicing events (ASEs) and regulated alternative splicing events (RASEs) by applying the ABLas pipeline. The reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was used for validation of selected differentially expressed genes (DEGs) and Fasn-regulated alternative splicing genes (RASGs). ResultsIn this study we found that Fasn overexpression led to significant changes of gene expression profiles, including downregulations of mRNA levels of immune related genes, including Bst2, Ddit3, Isg15, Mx2, Oas1a, Oasl, and RT1-S3 in INS-1 cell line. Furthermore, Fasn positively regulated the expression of transcription factors such as Fat1 and Ncl diabetes-related genes. Importantly, Fasn overexpression to result in alternative splicing events including in a metabolism-associated ATP binding protein mRNA Abcc5. In Gene Ontology analysis, the downregulated genes in Fasn-OE cells were mainly enriched in inflammatory response and innate immune response. In Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis, the downregulated genes were mainly enriched in TNF signaling pathway and cytokine-mediated signaling pathways. ConclusionsOur findings showed that upregulation of Fasn may play a critical role in islet cell immunmetabolism via modifications of immune/inflammatory related genes on transcription and alternative splicing level, which provide novel insights into characterizing the function of Fasn in islet cell immunity and for the development of chemo/immune therapies.

Semantic Metadata Annotation Services in the Biomedical Domain—A Literature Review

For all research data collected, data descriptions and information about the corresponding variables are essential for data analysis and reuse. To enable cross-study comparisons and analyses, semantic interoperability of metadata is one of the most important requirements. In the area of clinical and epidemiological studies, data collection instruments such as case report forms (CRFs), data dictionaries and questionnaires are critical for metadata collection. Even though data collection instruments are often created in a digital form, they are mostly not machine readable; i.e., they are not semantically coded. As a result, the comparison between data collection instruments is complex. The German project NFDI4Health is dedicated to the development of national research data infrastructure for personal health data, and as such searches for ways to enhance semantic interoperability. Retrospective integration of semantic codes into study metadata is important, as ongoing or completed studies contain valuable information. However, this is labor intensive and should be eased by software. To understand the market and find out what techniques and technologies support retrospective semantic annotation/enrichment of metadata, we conducted a literature review. In NFDI4Health, we identified basic requirements for semantic metadata annotation software in the biomedical field and in the context of the FAIR principles. Ten relevant software systems were summarized and aligned with those requirements. We concluded that despite active research on semantic annotation systems, no system meets all requirements. Consequently, further research and software development in this area is needed, as interoperability of data dictionaries, questionnaires and data collection tools is key to reusing and combining results from independent research studies.

Creation of a collection of different biological sample types from elderly patients to study the relationship of clinical, systemic, tissue and cellular biomarkers of accumulation of senescent cells during aging

With aging, tissue homeostasis and their effective recovery after damage is violated. It has been shown that this may be due to the excessive accumulation of senescent (SC) cells in various tissues, which leads to the activation of chronic sterile inflammation, tissue dysfunction and, as a result, to the development of age-related diseases. To assess the contribution of SC cells to human body aging and pathogenesis of such diseases, relevant biomarkers are studied. For successful translation into clinical practice of approaches aimed at regulating the SC cell content in various tissues, it is necessary to study the relationship between the established clinical biomarkers of aging and age-related diseases, systemic aging parameters, and SC biomarkers at the tissue and cellular levels.Aim. To develop and describe action algorithms for creating a biobank of samples obtained from patients aged >65 years in order to study biomarkers of SC cell accumulation.Material and methods. To collect samples, an interaction system was built between several research, clinical and infrastructure departments of a multidisciplinary medical center. At the stage of preanalytical training, regulatory legal acts were developed, including informed consent for patients, as well as protocols for each stage of the study.Results. A roadmap was formed with action algorithms for all participants in the study, as well as with a convenient and accessible system of annotations and storage of biological samples. To date, the collection includes biological samples of 7 different types (peripheral blood serum, formalin-fixed tissue samples and formalin fixed paraffin embedded tissue specimens, samples of different cells isolated from peripheral blood, skin and adipose tissue, samples of deoxyribonucleic and ribonucleic acids, cell secretome conditioned media) obtained from 82 patients. We accumulated relevant anamnestic, clinical and laboratory data, as well as the results of experimental studies to assess the SC cell biomarkers. Using the collection, the relationship between clinical, tissue and cellular biomarkers of SC cell accumulation was studied.Conclusion. The creation of a collection of biological samples at the molecular, cellular, tissue and organism levels from one patient provides great opportunities for research in the field of personalized medicine and the study of age-related disease pathogenesis.

The effects of web-based inquiry learning mode with the support of collaborative digital reading annotation system on information literacy instruction

Past studies have indicated that primary schools' students have difficulty in filtering out incorrect or unreliable information from the Internet when facing a large amount of information due to the lack of basic digital literacy and sensitivity. Therefore, the establishment of a mechanism for information judgment and evaluation to promote primary schools' students digital reading skills and information literacy has become a more and more important research issue in recent years. This study thus developed a web-based inquiry learning mode with collaborative digital reading annotation system support (WILM-CDRASS) aiming to provide innovative teaching mode of effectively enhancing information evaluation abilities of primary schools' students. A quasi-experimental design was conducted in this study to examine the learning effectiveness and technology acceptance of using WILM-CDRASS to enhance information evaluation abilities of primary schools' students compared to a web-based inquiry learning mode with general discussion board support (WILM-GDBS). A total of 50 Grade 5 students from two classes of an elementary school in New Taipei City of Taiwan participated in a collaborative inquiry-based learning course, “Internet information judgment and evaluation,” in this study. A total of 25 students from a class was assigned as the experimental group using WILM-CDRASS to enhance their information evaluation abilities, and a total of 25 students from the remaining class was assigned as the control group using WILM-GDBS. The learning outcomes of WILM-CDRASS and WILM-GDBS in the learning effectiveness and technology acceptance were also compared between students with different prior knowledge levels and cognitive styles from both groups. The analytical results revealed that the learning effectiveness and technology acceptance of learners in the experimental group using WILM-CDRASS for an information literacy course are significantly superior to those of learners in the control group using WILM-GDBS. The research findings also showed that the use of WILM-CDRASS was more beneficial to the students with low prior knowledge and field-independent cognitive style than those of using WILM-GDBS. As for technology acceptance, students with low prior knowledge perceived the use of WILM-CDRASS more helpful than WILM-GDBS for their learning. Based on the research results, several suggestions for the implementation of WILM-CDRASS to support information literacy courses were proposed. Besides, it is suggested to investigate students' effective learning behaviors and the relationship between the learning behaviors and learning performance in inquiry-based information literacy courses with WILM-CDRASS support in future study.

A Semi-automated System for Efficient Annotation of 3D Point Clouds

A Semi-automated System for Efficient Annotation of 3D Point Clouds

A semi-automatic system of web videos annotation and retrieval: application to events detection in soccer domain

A semi-automatic system of web videos annotation and retrieval: application to events detection in soccer domain

InSAR Crowdsourcing Annotation System With Volunteers Uploaded Photographs: Toward a Hazard Alerting System

InSAR Crowdsourcing Annotation System With Volunteers Uploaded Photographs: Toward a Hazard Alerting System

An Empirical User-Study of Text-Based Nonverbal Annotation Systems for Human-Human Conversations

the substantial increase in the number of online human-human conversations and the usefulness of multimodal transcripts, there is a rising need for automated multimodal transcription systems to help us better understand the conversations. In this paper, we evaluated three methods to perform multimodal transcription. They were (1) Jefferson -- an existing manual system used widely by the linguistics community, (2) MONAH -- a system that aimed to make multimodal transcripts accessible and automated, (3) MONAH+ -- a system that builds on MONAH that visualizes machine attention. Based on 104 participants responses, we found that (1) all text-based methods significantly reduced the amount of information for the human users, (2) MONAH was found to be more usable than Jefferson, (3) Jefferson's relative strength was in chronemics (pace / delay) and paralinguistics (pitch / volume) annotations, whilst MONAH's relative strength was in kinesics (body language) annotations, (4) enlarging words' font-size based on machine attention was confusing human users as loudness. These results pose considerations for researchers designing a multimodal annotation system for the masses who would like a fully-automated or human-augmented conversational analysis system.

PipaSet and TEAS: A Multimodal Dataset and Annotation Platform for Automatic Music Transcription and Expressive Analysis Dedicated to Chinese Traditional Plucked String Instrument Pipa

Music information retrieval (MIR) is developing these years rapidly. As the fundamental MIR tasks, automatic music transcription (AMT) and expressive analysis (EA) are gaining momentum in both Western and non-European music. However, the annotated datasets for non-Eurogenic instruments remain scarce in terms of quantity and feature diversity so that general evaluations and data-driven models on various tasks cannot be well explored. As one of the most popular traditional plucked string instruments in Asia, which is barely studied in the MIR community, pipa has lots of distinctive national and local characteristics including the fake nails, intrinsic pitch shift, rubato, as well as a high diversity of sophisticated playing techniques that greatly enhance the music expressiveness. Our work aims to systematically clarify a creation procedure of a pipa dataset with audio, musical notation and multiview video modalities for traditional Chinese solos. The use of 4-track string vibration signals captured by optical sensors paves a path for high quality annotations. Furthermore, a transcription and Expressiveness Annotation System (TEAS) was transparently implemented to ensure the scalability of dataset. Three expressive analysis approaches in this system were newly proposed and evaluated in this paper. Finally, two AMT models were investigated and a series of the existing and emerging MIR tasks enabled by this dataset were enumerated for the future exploration.

Using topic modelling for unsupervised annotation of electronic health records to identify an outbreak of disease in UK dogs.

A key goal of disease surveillance is to identify outbreaks of known or novel diseases in a timely manner. Such an outbreak occurred in the UK associated with acute vomiting in dogs between December 2019 and March 2020. We tracked this outbreak using the clinical free text component of anonymised electronic health records (EHRs) collected from a sentinel network of participating veterinary practices. We sourced the free text (narrative) component of each EHR supplemented with one of 10 practitioner-derived main presenting complaints (MPCs), with the 'gastroenteric' MPC identifying cases involved in the disease outbreak. Such clinician-derived annotation systems can suffer from poor compliance requiring retrospective, often manual, coding, thereby limiting real-time usability, especially where an outbreak of a novel disease might not present clinically as a currently recognised syndrome or MPC. Here, we investigate the use of an unsupervised method of EHR annotation using latent Dirichlet allocation topic-modelling to identify topics inherent within the clinical narrative component of EHRs. The model comprised 30 topics which were used to annotate EHRs spanning the natural disease outbreak and investigate whether any given topic might mirror the outbreak time-course. Narratives were annotated using the Gensim Library LdaModel module for the topic best representing the text within them. Counts for narratives labelled with one of the topics significantly matched the disease outbreak based on the practitioner-derived 'gastroenteric' MPC (Spearman correlation 0.978); no other topics showed a similar time course. Using artificially injected outbreaks, it was possible to see other topics that would match other MPCs including respiratory disease. The underlying topics were readily evaluated using simple word-cloud representations and using a freely available package (LDAVis) providing rapid insight into the clinical basis of each topic. This work clearly shows that unsupervised record annotation using topic modelling linked to simple text visualisations can provide an easily interrogable method to identify and characterise outbreaks and other anomalies of known and previously un-characterised diseases based on changes in clinical narratives.

A crowdsourcing open platform for literature curation in UniProt.

The UniProt knowledgebase is a public database for protein sequence and function, covering the tree of life and over 220 million protein entries. Now, the whole community can use a new crowdsourcing annotation system to help scale up UniProt curation and receive proper attribution for their biocuration work.

Prosody and gestures to modelling multimodal interaction: Constructing an Italian pilot corpus

Modeling dialogue implies detecting natural interaction. A pragmatic approach allows to consider the linguistic act composed of several and different features interacting with each other. Data collected for this project comprises three different genres of communication: monological, dialogical and conversational. The project aims to identify and analyze the pragmatic value of multimodal communication spotting the linguistic actions which carry out illocution values. We draw a pragmatic approach to study multimodal interaction combining the L-AcT annotation (Cresti 2000) with the gesture’s architecture designed by Kendon (Kendon 2004). The annotation system is designed to divide the speech units (utterance, intonation units and illocution types) (Hart, Collier, and Cohen 2006) (Cresti 2005) (Moneglia and Raso 2014) from gestural units (Gesture Unit, Gesture Phrase, Gesture Phase). Keeping the Gesture Unit as a superior macro-unit at the other gestural units only for the quantitative purpose, we realize a matching between gesture and speech units. These units work together to form the communicative intention of the speaker that can be recognizable by the Illocution Type. This annotation system leads to understanding how speakers realize multimodal linguistic actions and how different modalities work.

Towards a Standard of Modelling Annotations in the E-Health Domain

A large number of annotation systems in e-health domain have been implemented in the literature. Several factors distinguish these systems from one another. In fact, each of these systems is based on a separate paradigm, resulting in a disorganized and unstructured vision. As part of our research, we attempted to categorize them based on the functionalities provided by each system, and we also proposed a model of annotations that integrates both the health professional and the patient in the process of annotating the medical file.