We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes sourced from 112 hospitals across diverse populations, geographies, and facilities. AbdomenAtlas provides 673 K high-quality masks of anatomical structures in the abdominal region annotated by a team of 10 radiologists with the help of AI algorithms. We start by having expert radiologists manually annotate 22 anatomical structures in 5,246 CT volumes. Following this, a semi-automatic annotation procedure is performed for the remaining CT volumes, where radiologists revise the annotations predicted by AI, and in turn, AI improves its predictions by learning from revised annotations. Such a large-scale, detailed-annotated, and multi-center dataset is needed for two reasons. Firstly, AbdomenAtlas provides important resources for AI development at scale, branded as large pre-trained models, which can alleviate the annotation workload of expert radiologists to transfer to broader clinical applications. Secondly, AbdomenAtlas establishes a large-scale benchmark for evaluating AI algorithms-the more data we use to test the algorithms, the better we can guarantee reliable performance in complex clinical scenarios. An ISBI & MICCAI challenge named BodyMaps: Towards 3D Atlas of Human Body was launched using a subset of our AbdomenAtlas, aiming to stimulate AI innovation and to benchmark segmentation accuracy, inference efficiency, and domain generalizability. We hope our AbdomenAtlas can set the stage for larger-scale clinical trials and offer exceptional opportunities to practitioners in the medical imaging community. Codes, models, and datasets are available at https://www.zongweiz.com/dataset.

UNASSIGNED: Analyzing the anatomy of the aorta and left ventricular outflow tract (LVOT) is crucial for risk assessment and planning of transcatheter aortic valve implantation (TAVI). A comprehensive analysis of the aortic root and LVOT requires the extraction of the patient-individual anatomy via segmentation. Deep learning has shown good performance on various segmentation tasks. If this is formulated as a supervised problem, large amounts of annotated data are required for training. Therefore, minimizing the annotation complexity is desirable.
UNASSIGNED: We propose two-dimensional (2D) cross-sectional annotation and point cloud-based surface reconstruction to train a fully automatic 3D segmentation network for the aortic root and the LVOT. Our sparse annotation scheme enables easy and fast training data generation for tubular structures such as the aortic root. From the segmentation results, we derive clinically relevant parameters for TAVI planning.
UNASSIGNED: The proposed 2D cross-sectional annotation results in high inter-observer agreement [Dice similarity coefficient (DSC): 0.94]. The segmentation model achieves a DSC of 0.90 and an average surface distance of 0.96 mm. Our approach achieves an aortic annulus maximum diameter difference between prediction and annotation of 0.45 mm (inter-observer variance: 0.25 mm).
UNASSIGNED: The presented approach facilitates reproducible annotations. The annotations allow for training accurate segmentation models of the aortic root and LVOT. The segmentation results facilitate reproducible and quantifiable measurements for TAVI planning.

Crop growth monitoring is essential for both crop and supply chain management. Conventional manual sampling is not feasible for assessing the spatial variability of crop growth within an entire field or across all fields. Meanwhile, UAV-based remote sensing enables the efficient and nondestructive investigation of crop growth. A variety of crop-specific training image datasets are needed to detect crops from UAV imagery using a deep learning model. Specifically, the training dataset of cabbage is limited. This data article includes annotated cabbage images in the fields to recognize cabbages using machine learning models. This dataset contains 458 images with 17,621 annotated cabbages. Image sizes are approximately 500 to 1000 pixel squares. Since these cabbage images were collected from different cultivars during the whole growing season over the years, deep learning models trained with this dataset will be able to recognize a wide variety of cabbage shapes. In the future, this dataset can be used not only in UAVs but also in land-based robot applications for crop sensing or associated plant-specific management.

Comprehensive and accurate genome annotation is crucial for inferring the predicted functions of an organism. Numerous tools exist to annotate genes, gene clusters, mobile genetic elements, and other diverse features. However, these tools and pipelines can be difficult to install and run, be specialized for a particular element or feature, or lack annotations for larger elements that provide important genomic context. Integrating results across analyses is also important for understanding gene function. To address these challenges, we present the Beav annotation pipeline. Beav is a command-line tool that automates the annotation of bacterial genome sequences, mobile genetic elements, molecular systems and gene clusters, key regulatory features, and other elements. Beav uses existing tools in addition to custom models, scripts, and databases to annotate diverse elements, systems, and sequence features. Custom databases for plant-associated microbes are incorporated to improve annotation of key virulence and symbiosis genes in agriculturally important pathogens and mutualists. Beav includes an optional Agrobacterium-specific pipeline that identifies and classifies oncogenic plasmids and annotates plasmid-specific features. Following the completion of all analyses, annotations are consolidated to produce a single comprehensive output. Finally, Beav generates publication-quality genome and plasmid maps. Beav is on Bioconda and is available for download at https://github.com/weisberglab/beav.
OBJECTIVE: Annotation of genome features, such as the presence of genes and their predicted function, or larger loci encoding secretion systems or biosynthetic gene clusters, is necessary for understanding the functions encoded by an organism. Genomes can also host diverse mobile genetic elements, such as integrative and conjugative elements and/or phages, that are often not annotated by existing pipelines. These elements can horizontally mobilize genes encoding for virulence, antimicrobial resistance, or other adaptive functions and alter the phenotype of an organism. We developed a software pipeline, called Beav, that combines new and existing tools for the comprehensive annotation of these and other major features. Existing pipelines often misannotate loci important for virulence or mutualism in plant-associated bacteria. Beav includes custom databases and optional workflows for the improved annotation of plant-associated bacteria. Beav is designed to be easy to install and run, making comprehensive genome annotation broadly available to the research community.

OBJECTIVE: Ants are ecologically dominant insects in most terrestrial ecosystems, with more than 14,000 extant species in about 340 genera recorded to date. However, genomic resources are still scarce for most species, especially for species endemic in East or Southeast Asia, limiting the study of phylogeny, speciation and adaptation of this evolutionarily successful animal lineage. Here, we assemble and annotate the genomes of Odontoponera transversa and Camponotus friedae, two ant species with a natural distribution in China, to facilitate future study of ant evolution.
METHODS: We obtained a total of 16 Gb and 51 Gb PacBio HiFi data for O. transversa and C. friedae, respectively, which were assembled into the draft genomes of 339 Mb for O. transversa and 233 Mb for C. friedae. Genome assessments by multiple metrics showed good completeness and high accuracy of the two assemblies. Gene annotations assisted by RNA-seq data yielded a comparable number of protein-coding genes in the two genomes (10,892 for O. transversa and 11,296 for C. friedae), while repeat annotations revealed a remarkable difference of repeat content between these two ant species (149.4 Mb for O. transversa versus 49.7 Mb for C. friedae). Besides, complete mitochondrial genomes for the two species were assembled and annotated.

Exhaled breath volatilomics is a powerful non-invasive tool for biomarker discovery in medical applications, but compound annotation is essential for pathophysiological insights and technology transfer. This study was aimed at investigating the interest of a hybrid approach combining real-time proton transfer reaction-time-of-flight mass spectrometry (PTR-TOF-MS) with comprehensive thermal desorption-two-dimensional gas chromatography coupled to time-of-flight mass spectrometry (TD-GCxGC-TOF-MS) to enhance the analysis and characterization of VOCs in clinical research, using COVID-19 as a use case. VOC biomarker candidates were selected from clinical research using PTR-TOF-MS fingerprinting in patients with COVID-19 and matched to the Human Breathomic Database. Corresponding analytical standards were analysed using both a liquid calibration unit coupled to PTR-TOF-MS and TD-GCxGC-TOF-MS, together with confirmation on new clinical samples with TD-GCxGC-TOF-MS. From 26 potential VOC biomarkers, 23 were successfully detected with PTR-TOF-MS. All VOCs were successfully detected using TD-GCxGC-TOF-MS, providing effective separation of highly chemically related compounds, including isomers, and enabling high-confidence annotation based on two-dimensional chromatographic separation and mass spectra. Four VOCs were identified with a level 1 annotation in the clinical samples. For future applications, the combination of real-time PTR-TOF-MS and comprehensive TD-GCxGC-TOF-MS, at least on a subset of samples from a whole study, would enhance the performance of VOC annotation, offering potential advancements in biomarker discovery for clinical research.

BACKGROUND: Named entity recognition (NER) is a fundamental task in natural language processing. However, it is typically preceded by named entity annotation, which poses several challenges, especially in the clinical domain. For instance, determining entity boundaries is one of the most common sources of disagreements between annotators due to questions such as whether modifiers or peripheral words should be annotated. If unresolved, these can induce inconsistency in the produced corpora, yet, on the other hand, strict guidelines or adjudication sessions can further prolong an already slow and convoluted process.
OBJECTIVE: The aim of this study is to address these challenges by evaluating 2 novel annotation methodologies, lenient span and point annotation, aiming to mitigate the difficulty of precisely determining entity boundaries.
METHODS: We evaluate their effects through an annotation case study on a Japanese medical case report data set. We compare annotation time, annotator agreement, and the quality of the produced labeling and assess the impact on the performance of an NER system trained on the annotated corpus.
RESULTS: We saw significant improvements in the labeling process efficiency, with up to a 25% reduction in overall annotation time and even a 10% improvement in annotator agreement compared to the traditional boundary-strict approach. However, even the best-achieved NER model presented some drop in performance compared to the traditional annotation methodology.
CONCLUSIONS: Our findings demonstrate a balance between annotation speed and model performance. Although disregarding boundary information affects model performance to some extent, this is counterbalanced by significant reductions in the annotator\'s workload and notable improvements in the speed of the annotation process. These benefits may prove valuable in various applications, offering an attractive compromise for developers and researchers.

Nanopore direct RNA sequencing (DRS) enables the capture and full-length sequencing of native RNAs, without recoding or amplification bias. Resulting data sets may be interrogated to define the identity and location of chemically modified ribonucleotides, as well as the length of poly(A) tails, on individual RNA molecules. The success of these analyses is highly dependent on the provision of high-resolution transcriptome annotations in combination with workflows that minimize misalignments and other analysis artifacts. Existing software solutions for generating high-resolution transcriptome annotations are poorly suited to small gene-dense genomes of viruses due to the challenge of identifying distinct transcript isoforms where alternative splicing and overlapping RNAs are prevalent. To resolve this, we identified key characteristics of DRS data sets that inform resulting read alignments and developed the nanopore guided annotation of transcriptome architectures (NAGATA) software package (https://github.com/DepledgeLab/NAGATA). We demonstrate, using a combination of synthetic and original DRS data sets derived from adenoviruses, herpesviruses, coronaviruses, and human cells, that NAGATA outperforms existing transcriptome annotation software and yields a consistently high level of precision and recall when reconstructing both gene sparse and gene-dense transcriptomes. Finally, we apply NAGATA to generate the first high-resolution transcriptome annotation of the neglected pathogen human adenovirus type F41 (HAdV-41) for which we identify 77 distinct transcripts encoding at least 23 different proteins.
OBJECTIVE: The transcriptome of an organism denotes the full repertoire of encoded RNAs that may be expressed. This is critical to understanding the biology of an organism and for accurate transcriptomic and epitranscriptomic-based analyses. Annotating transcriptomes remains a complex task, particularly in small gene-dense organisms such as viruses which maximize their coding capacity through overlapping RNAs. To resolve this, we have developed a new software nanopore guided annotation of transcriptome architectures (NAGATA) which utilizes nanopore direct RNA sequencing (DRS) datasets to rapidly produce high-resolution transcriptome annotations for diverse viruses and other organisms.

This dataset involves a collection of soybean market news through web scraping from a Brazilian website. The news articles gathered span from January 2015 to June 2023 and have undergone a labeling process to categorize them as relevant or non-relevant. The news labeling process was conducted under the guidance of an agricultural economics expert, who collaborated with a group of nine individuals. Ten parameters were considered to assist participants in the labeling process. The dataset comprises approximately 11,000 news articles and serves as a valuable resource for researchers interested in exploring trends in the soybean market. Importantly, this dataset can be utilized for tasks such as classification and natural language processing. It provides insights into labeled soybean market news and supports open science initiatives, facilitating further analysis within the research community.

This study describes the development of a resource module that is part of a learning platform named \"NIGMS Sandbox for Cloud-based Learning\" (https://github.com/NIGMS/NIGMS-Sandbox). The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox at the beginning of this Supplement. This module delivers learning materials on de novo transcriptome assembly using Nextflow in an interactive format that uses appropriate cloud resources for data access and analysis. Cloud computing is a powerful new means by which biomedical researchers can access resources and capacity that were previously either unattainable or prohibitively expensive. To take advantage of these resources, however, the biomedical research community needs new skills and knowledge. We present here a cloud-based training module, developed in conjunction with Google Cloud, Deloitte Consulting, and the NIH STRIDES Program, that uses the biological problem of de novo transcriptome assembly to demonstrate and teach the concepts of computational workflows (using Nextflow) and cost- and resource-efficient use of Cloud services (using Google Cloud Platform). Our work highlights the reduced necessity of on-site computing resources and the accessibility of cloud-based infrastructure for bioinformatics applications.