Annotation Quality Research Articles

PathoCoder: Rethinking the Flaws of Patch-Based Learning for Multi-Class Classification in Computational Pathology.

Pathology-based decision support systems in clinical settings have faced impediments from data preparation beforehand, large-scale manual annotations, and poor domain generalization. We report a unified hybrid framework with only raw, slide-level label images. The method, which we termed PathoCoder, comprises core feature extractors, a feature combiner/reduction, and a supervised classifier. It is trained (through 5-fold cross-validation) on 2452 SurePath cervical liquid-based whole-slide captures, provided from Mendeley repository. Tests resulted in 98.37%, 98.37%, 98.41%, and 98.37% in accuracy, precision, recall, and F1, respectively. Extensive experiments validate the proposed scheme and versatility enough to accommodate epithelial ovarian tumor histotypes. Our method paves the way for more accelerated advancements in pathology AI by reducing patch/pixel-based annotation and good tissue quality dependency. Its applicability spans diverse classification tasks with varying tissue content and holds potential for real-world implementation.

The role of SASP in ischemic stroke: a deep dive into cellular mechanisms

BackgroundThe escalating incidence of ischemic stroke (IS) exerts a heavy toll on global health. Aging, a prominent risk factor, implicates the senescence-associated secretory phenotype (SASP) in IS pathogenesis. We postulated that alterations in SASP-related factor expression during IS correlate with remodeling of intercellular interaction networks and disease advancement. The present study endeavored to preliminarily dissect the SASP-IS nexus via combined bulk and single-cell transcriptome analysis.MethodsAggregated expression profiles from human peripheral blood bulk chips and MCAO mouse single-cell sequencing data, followed by SASP gene analysis. Executed protein interaction network and enrichment assays. Investigated immune infiltration in stroke patients, managed quality control and annotation of single-cell data, cherry-picked central cells based on SASP scores, unearthed essential genes via enrichment analysis, conducted pseudo-time and intercellular communication studies, and prognosticated drugs for hub genes. Finally, authenticated core gene expression in serum of MCAO and Sham rats using real-time fluorescent polymerase chain reaction (RT-qPCR).ResultsFourteen hub genes were discerned. Seven cell types were annotated in MCAO mouse peripheral blood single-cell data. Basophils exhibited the highest SASP scores, with Lcp1 upregulated and Ccl3 downregulated in basophils of the MCAO group. Enrichment analysis divulged a significant association of Ccl3 with the cell apoptosis pathway and Lcp1 with immune responses. The Ccl3 gene is pivotal in basophils and basophil-neutrophil crosstalk. Additionally, we forecasted nagrestipen’s regulatory function on Ccl3. RT-qPCR demonstrated a marked elevation in Lcp1 mRNA and a pronounced reduction in Ccl3 in the MCAO group relative to the Sham group.ConclusionThe Ccl3 gene in basophils and its immune cell interaction is a linchpin in the IS immune microenvironment. Ccl3 and Lcp1 might potentially modulate IS progression by influencing SASP, proffering novel prospects for IS clinical diagnosis and treatment.

Novel Surveillance View: A Novel Benchmark and View-Optimized Framework for Pedestrian Detection from UAV Perspectives

To address the issues of insufficient samples, limited scene diversity, missing perspectives, and low resolution in existing UAV-based pedestrian detection datasets, this paper proposes a novel UAV-based pedestrian detection benchmark dataset named the Novel Surveillance View (NSV). This dataset encompasses diverse scenes and pedestrian information captured from multiple perspectives, and introduces an innovative data mining approach that leverages tracking and optical flow information. This approach significantly improves data acquisition efficiency while ensuring annotation quality. Furthermore, an improved pedestrian detection method is proposed to overcome the performance degradation caused by significant perspective changes in top-down UAV views. Firstly, the View-Agnostic Decomposition (VAD) module decouples features into perspective-dependent and perspective-independent branches to enhance the model’s generalization ability to perspective variations. Secondly, the Deformable Conv-BN-SiLU (DCBS) module dynamically adjusts the receptive field shape to better adapt to the geometric deformations of pedestrians. Finally, the Context-Aware Pyramid Spatial Attention (CPSA) module integrates multi-scale features with attention mechanisms to address the challenge of drastic target scale variations. The experimental results demonstrate that the proposed method improves the mean Average Precision (mAP) by 9% on the NSV dataset, thereby validating that the approach effectively enhances pedestrian detection accuracy from UAV perspectives by optimizing perspective features.

Regional Image Quality Scoring for 2-D Echocardiography Using Deep Learning.

To develop and compare methods to automatically estimate regional ultrasound image quality for echocardiography separate from view correctness. Three methods for estimating image quality were developed: (i) classic pixel-based metric: the generalized contrast-to-noise ratio (gCNR), computed on myocardial segments (region of interest) and left ventricle lumen (background), extracted by a U-Net segmentation model; (ii) local image coherence: the average local coherence as predicted by a U-Net model that predicts image coherence from B-mode ultrasound images at the pixel level; (iii) deep convolutional network: an end-to-end deep-learning model that predicts the quality of each region in the image directly. These methods were evaluated against manual regional quality annotations provided by three experienced cardiologists. The results indicated poor performance of the gCNR metric, with Spearman correlation to annotations of ρ = 0.24. The end-to-end learning model obtained the best result, ρ = 0.69, comparable to the inter-observer correlation, ρ = 0.63. Finally, the coherence-based method, with ρ = 0.58, out-performed the classical metrics and was more generic than the end-to-end approach. The deep convolutional network provided the most accurate regional quality prediction, while the coherence-based method offered a more generalizable solution. gCNR showed limited effectiveness in this study. The image quality prediction tool is available as an open-source Python library at https://github.com/GillesVanDeVyver/arqee.

How to Efficiently Annotate Images for Best-Performing Deep Learning-Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model.

Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically requires pixel-level annotations for each object of interest. To mitigate this challenge, alternative approaches such as using weak labels (e.g., bounding boxes or scribbles) or less precise (noisy) annotations can be employed. Noisy and weak labels are significantly quicker to generate, allowing for more annotated images within the same time frame. However, the potential decrease in annotation quality may adversely impact the segmentation performance of the resulting model. In this study, we conducted a comprehensive cost-effectiveness evaluation on six variants of annotation strategies (9 10 sub-variants in total) across 4 datasets and conclude that the common practice of precisely outlining objects of interest is virtually never the optimal approach when annotation budget is limited. Both noisy and weak annotations showed usage cases that yield similar performance to the perfectly annotated counterpart, yet had significantly better cost-effectiveness. We hope our findings will help researchers be aware of the different available options and use their annotation budgets more efficiently, especially in cases where accurately acquiring labels for target objects is particularly costly. Our code will be made available on https://github.com/yzluka/AnnotationEfficiency2D .

Enhancing Coffee Leaf Rust Detection Using DenseNet201: A Comprehensive Analysis of the Mbozi and Public Datasets in Songwe, Tanzania

Coffee Leaf Rust (CLR) is a worldwide devastating fungal disease that threatens coffee production, upsetting economic and farmers' livelihoods. Traditional methods of detecting CLR heavily rely on using machine-learning (ML) models trained through weakly collected datasets and physical inspection which is tedious, time-consuming, and subject to human error. This study explores the performance of the DenseNet201 model using three datasets: Mbozi, Public, and Combined (a merger of Mbozi and Public datasets). Machine Learning Theory guided this research. The study objective is to assess the influence of dataset quality on CLR detection, analyze Mbozi and Public datasets using DenseNet201, and enhance robustness by merging the two datasets. A study on coffee leaf rot (CLR) severity was conducted using systematic sampling techniques. Leaves from multiple coffee farms were collected, representing different levels of infection. The Mbozi dataset, sourced from high-resolution images captured from Tanzania's Songwe coffee plantations, was analyzed for quality under controlled conditions, including environmental factors, image clarity, resolution, labeling consistency, and class balance, based on data completeness, image quality score, visual inspection, and model performance. DenseNet201 was trained and validated on each dataset achieving its highest accuracy with the Mbozi dataset at 98.72% and a validation accuracy of 97.65%, demonstrating the importance of consistent image quality and accurate annotations. In contrast, the public dataset suffered from inconsistencies in resolution and labeling, resulting in a lower training and validation accuracy of 96.86% and 96.42% respectively. The Combined dataset, which integrated the strengths of both datasets, exhibited a stronger generalization with an accuracy of 97.48% and validation accuracy of 97.49%, balancing the need for high-quality images with environmental variability. The study shows improved CLR detection speed and accuracy due to high-quality and consistently labeled images from the Mbozi dataset. It recommends future models integrate regionally relevant and high-resolution datasets for robust performance in real-world agricultural conditions, providing coffee farmers with timely disease intervention tools for better production management and economic stability in coffee-growing regions.

CrowdBA: A Low-Cost Quality-Driven Crowdsourcing Architecture for Bounding Box Annotation Based on Blockchain

Many blockchain-based crowdsourcing frameworks currently struggle to address the high costs associated with on-chain storage and computation effectively, and they lack a quality-driven incentive mechanism tailored to bounding box annotation scenarios. To address these challenges, this paper proposes CrowdBA: A low-cost, quality-driven crowdsourcing architecture. The CrowdBA utilizes the Ethereum public blockchain as the foundational architecture and develops corresponding smart contracts. First, by integrating Ethereum with the InterPlanetary File System (IPFS), storage and computation processes are shifted off-chain, effectively addressing the high costs associated with data storage and computation on public blockchains. Additionally, the CrowdBA introduces a Dynamic Intersection over the union-weighted bounding box fusion (DWBF) algorithm, which assigns dynamic weights based on IoU to infer true bounding boxes, thereby assessing each worker’s annotation quality. Annotation quality then serves as a key criterion for incentive distribution, ensuring fair and appropriate compensation for all contributors. Experimental results demonstrate that the operational costs of each smart contract function remain within reasonable limits; the off-chain storage and computation approach significantly reduces storage and computation expenses, and the DWBF algorithm shows marked improvements in accuracy and robustness over other bounding box fusion methods.

PSAURON: a tool for assessing protein annotation across a broad range of species.

Evaluating the accuracy of protein-coding sequences in genome annotations is a challenging problemfor which there is no broadly applicable solution. In this manuscript,we introduce PSAURON (Protein Sequence Assessment Using a Reference ORF Network), a novel software tool developed to help assess the quality of protein-coding gene annotations. Utilizing a machine learning model trained on a diverse dataset from over 1000 plant and animal genomes, PSAURON assigns a score to coding DNA or protein sequence that reflects the likelihood that the sequence is a genuine protein-coding region. PSAURON scores can be used for genome-wide protein annotation assessment as well as the rapid identification of potentially spurious annotated proteins. Validation against established benchmarks demonstrates PSAURON's effectiveness and correlation with recognized measures of protein quality, highlighting its potential use as a widelyapplicable method to evaluate precision in gene annotation. PSAURON is open source and freely available at https://github.com/salzberg-lab/PSAURON.

Sphae: an automated toolkit for predicting phage therapy candidates from sequencing data.

Phage therapy offers a viable alternative for bacterial infections amid rising antimicrobial resistance. Its success relies on selecting safe and effective phage candidates that require comprehensive genomic screening to identify potential risks. However, this process is often labor intensive and time-consuming, hindering rapid clinical deployment. We developed Sphae, an automated bioinformatics pipeline designed to streamline the therapeutic potential of a phage in under 10 minutes. Using Snakemake workflow manager, Sphae integrates tools for quality control, assembly, genome assessment, and annotation tailored specifically for phage biology. Sphae automates the detection of key genomic markers, including virulence factors, antimicrobial resistance genes, and lysogeny indicators such as integrase, recombinase, and transposase, which could preclude therapeutic use. Among the 65 phage sequences analyzed, 28 showed therapeutic potential, 8 failed due to low sequencing depth, 22 contained prophage or virulent markers, and 23 had multiple phage genomes. This workflow produces a report to assess phage safety and therapy suitability quickly. Sphae is scalable and portable, facilitating efficient deployment across most high-performance computing and cloud platforms, accelerating the genomic evaluation process. Sphae source code is freely available at https://github.com/linsalrob/sphae, with installation supported on Conda, PyPi, Docker containers.

Cultivated genome references for protein database construction and high-resolution taxonomic annotation in metaproteomics.

Metaproteomics offers a profound understanding of the functional dynamics of the gut microbiome, which is crucial for personalized healthcare strategies. The selection of an appropriate database is a critical step for the identification of peptides and proteins, as well as for the provision of accurate taxonomic and functional annotations. The matched metagenomic-derived database is considered to be the best, but its limitations include the identification of low-abundance organisms and taxonomic resolution. Herein, we constructed a protein database (DBCGR2) based on Cultivated Genome Reference 2 (CGR2) and developed a complete peptide-centric analysis workflow for database searching and for the annotation of taxonomy and function. This workflow was subsequently appraised in comparison with metagenomics-derived databases for the analysis of metaproteomic data. Our findings suggested that the performance of DBCGR2 in identification was comparable with metagenomics-derived databases with improvement in identification rates of peptides from low-abundance species. The database searching results could be fully annotated using the pepTaxa taxonomic annotation approach developed in this study, and the taxonomic resolution was enhanced to strain level. Additionally, the results demonstrated that the sensitivity of functional annotation could be enhanced by employing DBCGR2. Overall, the DBCGR2 combined with pepTaxa can be considered an alternative for metaproteomic data analysis with superior analysis performances.IMPORTANCEMass spectrometry-based metaproteomics offers a profound understanding of the gut microbial taxonomy and functionality. The databases utilized in the analysis of metaproteomic data are crucial, as they determine the identification of proteins that can be recognized and linked to overall human health, in addition to the quality of taxonomic and functional annotation. Among the most effective approaches for constructing protein databases is the utilization of metagenomic sequencing to create matched databases. However, the database, derived from isolated genomes, has yet to undergo rigorous testing for their efficacy and accuracy in protein identification and taxonomic and functional annotation. Here, we constructed a protein database DBCGR2 derived from Cultivated Genome Reference 2 (CGR2) and a complete workflow for data analysis. We compared the performances of DBCGR2 and metagenomics-derived databases. Our results indicated that DBCGR2 can be regarded as an alternative to metagenomics-derived databases, which contribute to metaproteomic data analysis.

Magnetic Resonance Imaging Liver Segmentation Protocol Enables More Consistent and Robust Annotations, Paving the Way for Advanced Computer-Assisted Analysis

Background/Objectives: Recent advancements in artificial intelligence (AI) have spurred interest in developing computer-assisted analysis for imaging examinations. However, the lack of high-quality datasets remains a significant bottleneck. Labeling instructions are critical for improving dataset quality but are often lacking. This study aimed to establish a liver MRI segmentation protocol and assess its impact on annotation quality and inter-reader agreement. Methods: This retrospective study included 20 patients with chronic liver disease. Manual liver segmentations were performed by a radiologist in training and a radiology technician on T2-weighted imaging (wi) and T1wi at the portal venous phase. Based on the inter-reader discrepancies identified after the first segmentation round, a segmentation protocol was established, guiding the second round of segmentation, resulting in a total of 160 segmentations. The Dice Similarity Coefficient (DSC) assessed inter-reader agreement pre- and post-protocol, with a Wilcoxon signed-rank test for per-volume analysis and an Aligned-Rank Transform (ART) for repeated measures analyses of variance (ANOVA) for per-slice analysis. Slice selection at extreme cranial or caudal liver positions was evaluated using the McNemar test. Results: The per-volume DSC significantly increased after protocol implementation for both T2wi (p < 0.001) and T1wi (p = 0.03). Per-slice DSC also improved significantly for both T2wi and T1wi (p < 0.001). The protocol reduced the number of liver segmentations with a non-annotated slice on T1wi (p = 0.04), but the change was not significant on T2wi (p = 0.16). Conclusions: Establishing a liver MRI segmentation protocol improves annotation robustness and reproducibility, paving the way for advanced computer-assisted analysis. Moreover, segmentation protocols could be extended to other organs and lesions and incorporated into guidelines, thereby expanding the potential applications of AI in daily clinical practice.

Whombat: An open‐source audio annotation tool for machine learning assisted bioacoustics

Abstract Automated analysis of bioacoustic recordings using machine learning (ML) methods has the potential to greatly scale biodiversity monitoring efforts. The use of ML for high‐stakes applications, such as conservation and scientific research, demands a data‐centric approach with a focus on selecting and utilizing carefully annotated and curated evaluation and training data that are relevant and representative. Creating annotated bioacoustic datasets presents a number of challenges, such as managing large collections of recordings with associated metadata, developing flexible annotation tools that can accommodate the diverse range of vocalization profiles of different organisms and addressing the scarcity of expert annotators. We present Whombat, a user‐friendly, browser‐based interface for managing audio recordings and annotation projects, with several visualization, exploration and annotation tools. It enables users to quickly annotate, review, and share annotations, as well as visualize and evaluate a set of machine learning predictions on a dataset. The tool facilitates an iterative workflow where user annotations and machine learning predictions feedback to enhance model performance and annotation quality. We demonstrate the flexibility of Whombat by showcasing two distinct use cases: (1) a project aimed at enhancing automated UK bat call identification at the Bat Conservation Trust (BCT), and (2) a collaborative effort among the USDA Forest Service and Oregon State University researchers exploring bioacoustic applications and extending automated avian classification models in the Pacific Northwest, USA. Whombat is a flexible tool that can effectively address the challenges of annotation for bioacoustic research. It can be used for individual and collaborative work, hosted on a shared server or accessed remotely, or run on a personal computer without the need for coding skills. The code is open‐source, and we provide a user guide.

ADSP Whole Genome Sequencing (WGS) Release 5 data update from Genome Center for Alzheimer’s Disease

AbstractBackgroundThe Genome Center for Alzheimer’s Disease (GCAD) coordinates the integration and meta‐analysis of all available Alzheimer’s disease (AD) relevant whole genome sequencing (WGS) data to facilitate the goal of identifying AD risk or protective genetic variants and eventual therapeutic targets. The WGS datasets are generated via the collaboration of scientists from the Alzheimer’s Disease Sequencing Project (ADSP) and GCAD. To minimize data heterogeneity introduced by different sequencing protocols and machines, GCAD processes all samples using identical pipelines.MethodsThe raw sequencing data are first mapped to GRCh38/hg38 and variants (SNVs and indels) are called using GATK. Additionally, compact VCF and GDS formatted files are generated to facilitate researchers who want to use smaller pVCFs. SNVs and indels are annotated using the ADSP annotation pipeline. Lastly, structural variants (SV) are called using Smoove and Manta and joint genotyped using GraphTyper2.ResultsThe dataset (ADSP Release 5, R5, 2024) includes ∼60,000 genomes from >50 diverse cohorts with 4 major ancestries: 47% Non‐Hispanic White, 29% Hispanic or Latino, 16% Black or African American and 8% Asian. Data are deeply sequenced (average genome coverage: >30x). CRAMs, gVCFs from GATK, and SV VCFs of a subset of the R5 samples (n = 36,361) were deposited into NIAGADS Data Sharing Service (DSS) (https://dss.niagads.org/) for public distribution in 2022, and similarly, the new samples in R5 will be released after the joint call is complete. In addition, joint‐genotype VCFs on SNVs, indels, and SVs will be available. These will undergo full quality control and annotation process.ConclusionThe ADSP and GCAD generate high quality genotype and SV calls. Currently the project is processing ∼60,000 WGS samples sequenced primarily through the ADSP Follow‐Up Study, which will contain a more ancestrally diverse set of populations. We anticipate this 2024 release will continue to benefit the research community studying AD genetics.

Phage therapy candidates from Sphae: An automated toolkit for predicting sequencing data.

Phage therapy is a viable alternative for treating bacterial infections amidst the escalating threat of antimicrobial resistance. However, the therapeutic success of phage therapy depends on selecting safe and effective phage candidates. While experimental methods focus on isolating phages and determining their lifecycle and host range, comprehensive genomic screening is critical to identify markers that indicate potential risks, such as toxins, antimicrobial resistance, or temperate lifecycle traits. These analyses are often labor-intensive and time-consuming, limiting the rapid deployment of phage in clinical settings. We developed Sphae, an automated bioinformatics pipeline designed to streamline therapeutic potential of a phage in under ten minutes. Using Snakemake workflow manager, Sphae integrates tools for quality control, assembly, genome assessment, and annotation tailored specifically for phage biology. Sphae automates the detection of key genomic markers, including virulence factors, antimicrobial resistance genes, and lysogeny indicators like integrase, recombinase, and transposase, which could preclude therapeutic use. Benchmarked on 65 phage sequences, 28 phage samples showed therapeutic potential, 8 failed during assembly due to low sequencing depth, 22 samples included prophage or virulent markers, and the remaining 23 samples included multiple phage genomes per sample. This workflow outputs a comprehensive report, enabling rapid assessment of phage safety and suitability for phage therapy under these criteria. Sphae is scalable, portable, facilitating efficient deployment across most high-performance computing (HPC) and cloud platforms, expediting the genomic evaluation process. Sphae is source code and freely available at https://github.com/linsalrob/sphae, with installation supported on Conda, PyPi, Docker containers.

Rfam 15: RNA families database in 2025.

The Rfam database, a widely used repository of non-coding RNA families, has undergone significant updates in release 15.0. This paper introduces major improvements, including the expansion of Rfamseq to 26 106 genomes, a 76% increase, incorporating the latest UniProt reference proteomes and additional viral genomes. Sixty-five RNA families were enhanced using experimentally determined 3D structures, improving the accuracy of consensus secondary structures and annotations. R-scape covariation analysis was used to refine structural predictions in 26 families. Gene Ontology (GO) and Sequence Ontology annotations were comprehensively updated, increasing GO term coverage to 75% of families. The release adds 14 new Hepatitis C Virus RNA families and completes microRNA family synchronization with miRBase, resulting in 1603 microRNA families. New data types, including FULL alignments, have been implemented. Integration with APICURON for improved curator attribution and multiple website enhancements further improve user experience. These updates significantly expand Rfam's coverage and improve annotation quality, reinforcing its critical role in RNA research, genome annotation and the development of machine learning models. Rfam is freely available at https://rfam.org.

Advancements in deep learning for visual object tracking

Abstract. Since contemporary information-retrieval systems rely heavily on the content of titles and abstracts to identify relevant articles in literature searches, great care should be taken in constructing both. This comprehensive review delves into the transformative impact of deep learning on the domain of visual object tracking. Since the inception of AlexNet in 2012, deep learning has revolutionized feature extraction, leading to significant advancements in tracking accuracy and robustness. The article explores the integration of deep learning with various tracking algorithms, including deep correlation filters, classification-based approaches, Siamese networks, gradient-based methods, and the innovative application of Transformer architectures. Moreover, the role of tracking datasets in fostering algorithm development and innovation is highlighted, with an emphasis on the expansion in scale, diversity, and annotation quality. Furthermore, the article also examines the multifaceted evaluation metrics for tracking algorithms, encompassing precision, robustness, efficiency, generalization, and real-time capabilities. Looking ahead, the review outlines future research directions, such as algorithm optimization for lightweight and accelerated performance, enhancing generalizability, leveraging multimodal data fusion, and refining Transformer models for improved temporal information processing. The challenges of long-term tracking and the growing importance of algorithm interpretability and transparency are also discussed. In summary, the article underscores the promising trajectory of deep learning in visual object tracking, with ongoing research poised to make tracking technologies smarter, more efficient, and robust, catering to a wide array of practical applications and environments.

A method for improving the quality of image annotation in semantic monitoring gis of business processes

A method for improving the quality of image annotation in semantic monitoring gis of business processes

A comprehensive review of existing corpora and methods for creating annotated corpora for event extraction tasks

Abstract Purpose The purpose of this study is to serve as a comprehensive review of the existing annotated corpora. This review study aims to provide information on the existing annotated corpora for event extraction, which are limited but essential for training and improving the existing event extraction algorithms. In addition to the primary goal of this study, it provides guidelines for preparing an annotated corpus and suggests suitable tools for the annotation task. Design/methodology/approach This study employs an analytical approach to examine available corpus that is suitable for event extraction tasks. It offers an in-depth analysis of existing event extraction corpora and provides systematic guidelines for researchers to develop accurate, high-quality corpora. This ensures the reliability of the created corpus and its suitability for training machine learning algorithms. Findings Our exploration reveals a scarcity of annotated corpora for event extraction tasks. In particular, the English corpora are mainly focused on the biomedical and general domains. Despite the issue of annotated corpora scarcity, there are several high-quality corpora available and widely used as benchmark datasets. However, access to some of these corpora might be limited owing to closed-access policies or discontinued maintenance after being initially released, rendering them inaccessible owing to broken links. Therefore, this study documents the available corpora for event extraction tasks. Research limitations Our study focuses only on well-known corpora available in English and Chinese. Nevertheless, this study places a strong emphasis on the English corpora due to its status as a global lingua franca, making it widely understood compared to other languages. Practical implications We genuinely believe that this study provides valuable knowledge that can serve as a guiding framework for preparing and accurately annotating events from text corpora. It provides comprehensive guidelines for researchers to improve the quality of corpus annotations, especially for event extraction tasks across various domains. Originality/value This study comprehensively compiled information on the existing annotated corpora for event extraction tasks and provided preparation guidelines.

Proteome-scale structural prediction of the giant Marseillevirus reveals conserved folds and putative homologs of the hypothetical proteins.

A significant proportion of the highly divergent and novel proteins of giant viruses are termed "hypothetical" due to the absence of detectable homologous sequences in the existing databases. The quality of genome and proteome annotations often relies on the identification of signature sequences and motifs in order to assign putative functions to the gene products. These annotations serve as the first set of information for researchers to develop workable hypotheses for further experimental research. The structure-function relationship of proteins suggests that proteins with similar functions may also exhibit similar folding patterns. Here, we report the first proteome-wide structure prediction of the giant Marseillevirus. We use AlphaFold-predicted structures and their comparative analysis with the experimental structures in the PDB database to preliminarily annotate the viral proteins. Our work highlights the conservation of structural folds in proteins with highly divergent sequences and reveals potentially paralogous relationships among them. We also provide evidence for gene duplication and fusion as contributing factors to giant viral genome expansion and evolution. With the easily accessible AlphaFold and other advanced bioinformatics tools for high-confidence de novo structure prediction, we propose a combined sequence and predicted-structure-based proteome annotation approach for the initial characterization of novel and complex organisms or viruses.

Chromosome-level genome assembly of the sacoglossan sea slug Elysia timida (Risso, 1818)

BackgroundSequencing and annotating genomes of non-model organisms helps to understand genome architecture, the genetic processes underlying species traits, and how these genes have evolved in closely-related taxa, among many other biological processes. However, many metazoan groups, such as the extremely diverse molluscs, are still underrepresented in the number of sequenced and annotated genomes. Although sequencing techniques have recently improved in quality and quantity, molluscs are still neglected due to difficulties in applying standardized protocols for obtaining genomic data.ResultsIn this study, we present the chromosome-level genome assembly and annotation of the sacoglossan sea slug species Elysia timida, known for its ability to store the chloroplasts of its food algae. In particular, by optimizing the long-read and chromosome conformation capture library preparations, the genome assembly was performed using PacBio HiFi and Arima HiC data. The scaffold and contig N50s, at 41.8 Mb and 1.92 Mb, respectively, are approximately 30-fold and fourfold higher compared to other published sacoglossan genome assemblies. Structural annotation resulted in 19,904 protein-coding genes, which are more contiguous and complete compared to publicly available annotations of Sacoglossa with respect to metazoan BUSCOs. We found no evidence for horizontal gene transfer (HGT), i.e. no photosynthetic genes encoded in the sacoglossan nucleus genome. However, we detected genes encoding polyketide synthases in E. timida, indicating that polypropionates are produced. HPLC–MS/MS analysis confirmed the presence of a large number of polypropionates, including known and yet uncharacterised compounds.ConclusionsWe can show that our methodological approach helps to obtain a high-quality genome assembly even for a "difficult-to-sequence" organism, which may facilitate genome sequencing in molluscs. This will enable a better understanding of complex biological processes in molluscs, such as functional kleptoplasty in Sacoglossa, by significantly improving the quality of genome assemblies and annotations.