This study evaluated large language models (LLMs), particularly the GPT-4 with vision (GPT-4 V) and GPT-4 Turbo, for annotating biomedical figures, focusing on cellular senescence. We assessed the ability of LLMs to categorize and annotate complex biomedical images to enhance their accuracy and efficiency. Our experiments employed prompt engineering with figures from review articles, achieving more than 70% accuracy for label extraction and approximately 80% accuracy for node-type classification. Challenges were noted in the correct annotation of the relationship between directionality and inhibitory processes, which were exacerbated as the number of nodes increased. Using figure legends was a more precise identification of sources and targets than using captions, but sometimes lacked pathway details. This study underscores the potential of LLMs in decoding biological mechanisms from text and outlines avenues for improving inhibitory relationship representations in biomedical informatics.

Data curators play an important role in assessing data quality and take actions that may ultimately lead to better, more valuable data products. This study explores the curation practices of data curators working within US-based data repositories. We performed a survey in January 2021 to benchmark the levels of curation performed by repositories and assess the perceived value and impact of curation on the data sharing process. Our analysis included 95 responses from 59 unique data repositories. Respondents primarily were professionals working within repositories and examined curation performed within a repository setting. A majority 72.6% of respondents reported that \"data-level\" curation was performed by their repository and around half reported their repository took steps to ensure interoperability and reproducibility of their repository\'s datasets. Curation actions most frequently reported include checking for duplicate files, reviewing documentation, reviewing metadata, minting persistent identifiers, and checking for corrupt/broken files. The most \"value-add\" curation action across generalist, institutional, and disciplinary repository respondents was related to reviewing and enhancing documentation. Respondents reported high perceived impact of curation by their repositories on specific data sharing outcomes including usability, findability, understandability, and accessibility of deposited datasets; respondents associated with disciplinary repositories tended to perceive higher impact on most outcomes. Most survey participants strongly agreed that data curation by the repository adds value to the data sharing process and that it outweighs the effort and cost. We found some differences between institutional and disciplinary repositories, both in the reported frequency of specific curation actions as well as the perceived impact of data curation. Interestingly, we also found variation in the perceptions of those working within the same repository regarding the level and frequency of curation actions performed, which exemplifies the complexity of a repository curation work. Our results suggest data curation may be better understood in terms of specific curation actions and outcomes than broadly defined curation levels and that more research is needed to understand the resource implications of performing these activities. We share these results to provide a more nuanced view of curation, and how curation impacts the broader data lifecycle and data sharing behaviors.

Alzheimer\'s disease (AD) is a universal neurodegenerative disease with the feature of progressive dementia. Currently, there are only seven Food and Drug Administration-approved drugs for the treatment of AD, which merely offer temporary relief from symptom deterioration without reversing the underlying disease process. The identification of inhibitors capable of interacting with proteins associated with AD plays a pivotal role in the development of effective therapeutic interventions. However, a vast number of such inhibitors are dispersed throughout numerous published articles, rendering it inconvenient for researchers to explore potential drug candidates for AD. In light of this, we have manually compiled inhibitors targeting proteins associated with AD and constructed a comprehensive database known as IPAD-DB (Inhibitors of Proteins associated with Alzheimer\'s Disease Database). The curated inhibitors within this database encompass a diverse range of compounds, including natural compounds, synthetic compounds, drugs, natural extracts and nano-inhibitors. To date, the database has compiled >4800 entries, each representing a correspondent relationship between an inhibitor and its target protein. IPAD-DB offers a user-friendly interface that facilitates browsing, searching and downloading of its records. We firmly believe that IPAD-DB represents a valuable resource for screening potential AD drug candidates and investigating the underlying mechanisms of this debilitating disease. Access to IPAD-DB is freely available at http://www.lamee.cn/ipad-db/ and is compatible with all major web browsers. Database URL: http://www.lamee.cn/ipad-db/.

While biomedical relation extraction (bioRE) datasets have been instrumental in the development of methods to support biocuration of single variants from texts, no datasets are currently available for the extraction of digenic or even oligogenic variant relations, despite the reports in literature that epistatic effects between combinations of variants in different loci (or genes) are important to understand disease etiologies. This work presents the creation of a unique dataset of oligogenic variant combinations, geared to train tools to help in the curation of scientific literature. To overcome the hurdles associated with the number of unlabelled instances and the cost of expertise, active learning (AL) was used to optimize the annotation, thus getting assistance in finding the most informative subset of samples to label. By pre-annotating 85 full-text articles containing the relevant relations from the Oligogenic Diseases Database (OLIDA) with PubTator, text fragments featuring potential digenic variant combinations, i.e. gene-variant-gene-variant, were extracted. The resulting fragments of texts were annotated with ALAMBIC, an AL-based annotation platform. The resulting dataset, called DUVEL, is used to fine-tune four state-of-the-art biomedical language models: BiomedBERT, BiomedBERT-large, BioLinkBERT and BioM-BERT. More than 500 000 text fragments were considered for annotation, finally resulting in a dataset with 8442 fragments, 794 of them being positive instances, covering 95% of the original annotated articles. When applied to gene-variant pair detection, BiomedBERT-large achieves the highest F1 score (0.84) after fine-tuning, demonstrating significant improvement compared to the non-fine-tuned model, underlining the relevance of the DUVEL dataset. This study shows how AL may play an important role in the creation of bioRE dataset relevant for biomedical curation applications. DUVEL provides a unique biomedical corpus focusing on 4-ary relations between two genes and two variants. It is made freely available for research on GitHub and Hugging Face. Database URL: https://huggingface.co/datasets/cnachteg/duvel or https://doi.org/10.57967/hf/1571.

Multiple sclerosis (MS) is the most common inflammatory demyelinating disease of the central nervous system. \'Omics\' technologies (genomics, transcriptomics, proteomics) and associated drug information have begun reshaping our understanding of multiple sclerosis. However, these data are scattered across numerous references, making them challenging to fully utilize. We manually mined and compiled these data within the Multiple Sclerosis Gene Database (MSGD) database, intending to continue updating it in the future. We screened 5485 publications and constructed the current version of MSGD. MSGD comprises 6255 entries, including 3274 variant entries, 1175 RNA entries, 418 protein entries, 313 knockout entries, 612 drug entries and 463 high-throughput entries. Each entry contains detailed information, such as species, disease type, detailed gene descriptions (such as official gene symbols), and original references. MSGD is freely accessible and provides a user-friendly web interface. Users can easily search for genes of interest, view their expression patterns and detailed information, manage gene sets and submit new MS-gene associations through the platform. The primary principle behind MSGD\'s design is to provide an exploratory platform, aiming to minimize filtration and interpretation barriers while ensuring highly accessible presentation of data. This initiative is expected to significantly assist researchers in deciphering gene mechanisms and improving the prevention, diagnosis and treatment of MS. Database URL: http://bio-bigdata.hrbmu.edu.cn/MSGD.

Enzymes catalyze diverse biochemical reactions and are building blocks of cellular and metabolic pathways. Data and metadata of enzymes are distributed across databases and are archived in various formats. The enzyme databases provide utilities for efficient searches and downloading enzyme records in batch mode but do not support organism-specific extraction of subsets of data. Users are required to write scripts for parsing entries for customized data extraction prior to downstream analysis. Integrated Customized Extraction of Enzyme Data (iCEED) has been developed to provide organism-specific customized data extraction utilities for seven commonly used enzyme databases and brings these resources under an integrated portal. iCEED provides dropdown menus and search boxes using typehead utility for submission of queries as well as enzyme class-based browsing utility. A utility to facilitate mapping and visualization of functionally important features on the three-dimensional (3D) structures of enzymes is integrated. The customized data extraction utilities provided in iCEED are expected to be useful for biochemists, biotechnologists, computational biologists, and life science researchers to build curated datasets of their choice through an easy to navigate web-based interface. The integrated feature visualization system is useful for a fine-grained understanding of the enzyme structure-function relationship. Desired subsets of data, extracted and curated using iCEED can be subsequently used for downstream processing, analyses, and knowledge discovery. iCEED can also be used for training and teaching purposes.

In the past 40 years, therapeutic antibody discovery and development have advanced considerably, with machine learning (ML) offering a promising way to speed up the process by reducing costs and the number of experiments required. Recent progress in ML-guided antibody design and development (D&D) has been hindered by the diversity of data sets and evaluation methods, which makes it difficult to conduct comparisons and assess utility. Establishing standards and guidelines will be crucial for the wider adoption of ML and the advancement of the field. This perspective critically reviews current practices, highlights common pitfalls and proposes method development and evaluation guidelines for various ML-based techniques in therapeutic antibody D&D. Addressing challenges across the ML process, best practices are recommended for each stage to enhance reproducibility and progress.

Breast cancer is notorious for its high mortality and heterogeneity, resulting in different therapeutic responses. Classical biomarkers have been identified and successfully commercially applied to predict the outcome of breast cancer patients. Accumulating biomarkers, including non-coding RNAs, have been reported as prognostic markers for breast cancer with the development of sequencing techniques. However, there are currently no databases dedicated to the curation and characterization of prognostic markers for breast cancer. Therefore, we constructed a curated database for prognostic markers of breast cancer (PMBC). PMBC consists of 1070 markers covering mRNAs, lncRNAs, miRNAs and circRNAs. These markers are enriched in various cancer- and epithelial-related functions including mitogen-activated protein kinases signaling. We mapped the prognostic markers into the ceRNA network from starBase. The lncRNA NEAT1 competes with 11 RNAs, including lncRNAs and mRNAs. The majority of the ceRNAs in ABAT belong to pseudogenes. The topology analysis of the ceRNA network reveals that known prognostic RNAs have higher closeness than random. Among all the biomarkers, prognostic lncRNAs have a higher degree, while prognostic mRNAs have significantly higher closeness than random RNAs. These results indicate that the lncRNAs play important roles in maintaining the interactions between lncRNAs and their ceRNAs, which might be used as a characteristic to prioritize prognostic lncRNAs based on the ceRNA network. PMBC renders a user-friendly interface and provides detailed information about individual prognostic markers, which will facilitate the precision treatment of breast cancer. PMBC is available at the following URL: http://www.pmbreastcancer.com/.

BACKGROUND: Major advances in sequencing technologies and the sharing of data and metadata in science have resulted in a wealth of publicly available datasets. However, working with and especially curating public omics datasets remains challenging despite these efforts. While a growing number of initiatives aim to re-use previous results, these present limitations that often lead to the need for further in-house curation and processing.
RESULTS: Here, we present the Omics Dataset Curation Toolkit (OMD Curation Toolkit), a python3 package designed to accompany and guide the researcher during the curation process of metadata and fastq files of public omics datasets. This workflow provides a standardized framework with multiple capabilities (collection, control check, treatment and integration) to facilitate the arduous task of curating public sequencing data projects. While centered on the European Nucleotide Archive (ENA), the majority of the provided tools are generic and can be used to curate datasets from different sources.
CONCLUSIONS: Thus, it offers valuable tools for the in-house curation previously needed to re-use public omics data. Due to its workflow structure and capabilities, it can be easily used and benefit investigators in developing novel omics meta-analyses based on sequencing data.

OBJECTIVE: ModelDB (https://modeldb.science) is a discovery platform for computational neuroscience, containing over 1850 published model codes with standardized metadata. These codes were mainly supplied from unsolicited model author submissions, but this approach is inherently limited. For example, we estimate we have captured only around one-third of NEURON models, the most common type of models in ModelDB. To more completely characterize the state of computational neuroscience modeling work, we aim to identify works containing results derived from computational neuroscience approaches and their standardized associated metadata (eg, cell types, research topics).
METHODS: Known computational neuroscience work from ModelDB and identified neuroscience work queried from PubMed were included in our study. After pre-screening with SPECTER2 (a free document embedding method), GPT-3.5, and GPT-4 were used to identify likely computational neuroscience work and relevant metadata.
RESULTS: SPECTER2, GPT-4, and GPT-3.5 demonstrated varied but high abilities in identification of computational neuroscience work. GPT-4 achieved 96.9% accuracy and GPT-3.5 improved from 54.2% to 85.5% through instruction-tuning and Chain of Thought. GPT-4 also showed high potential in identifying relevant metadata annotations.
CONCLUSIONS: Accuracy in identification and extraction might further be improved by dealing with ambiguity of what are computational elements, including more information from papers (eg, Methods section), improving prompts, etc.
CONCLUSIONS: Natural language processing and large language model techniques can be added to ModelDB to facilitate further model discovery, and will contribute to a more standardized and comprehensive framework for establishing domain-specific resources.