A bird's-eye view of deep learning in bioimage analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Meijering E
PROVIDER: S-EPMC7494605 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
A bird's-eye view of deep learning in bioimage analysis.
Computational and structural biotechnology journal 20200807
Deep learning of artificial neural networks has become the de facto standard approach to solving data analysis problems in virtually all fields of science and engineering. Also in biology and medicine, deep learning technologies are fundamentally transforming how we acquire, process, analyze, and interpret data, with potentially far-reaching consequences for healthcare. In this mini-review, we take a bird's-eye view at the past, present, and future developments of deep learning, starting from sc ...[more]
Similar Datasets
Project description:BackgroundA wealth of information on clinical trials has been provided by publicly accessible online registries. Information technology and data exchange standards enable rapid extraction, summarization, and visualization of information and derived knowledge from these data sets. Clinical trials data was extracted in the XML format from the National Library of Medicine ClinicalTrials.gov site. This data includes categories such as 'Summary of Purpose', 'Trial Sponsor', 'Phase of the Trial', 'Recruiting Status', and 'Location'. We focused on 645 clinical trials related to cancer vaccines. Additional facts on cancer types, including incidence and survival rates, were retrieved from the National Cancer Institute Surveillance data.ResultsThis application enables rapid extraction of information about institutions, diseases, clinical approaches, clinical trials dates, predominant cancer types in the trials, clinical opportunities and pharmaceutical market coverage. Presentation of results is facilitated by visualization tools that summarize the landscape of ongoing and completed cancer vaccine trials. Our summaries show the number of clinical vaccine trials per cancer type, over time, by phase, by lead sponsors, as well as trial activity relative to cancer type and survival data. We also have identified cancers that are neglected in the cancer vaccine field: bladder, liver, pancreatic, stomach, esophageal, and all of the low-incidence cancers.ConclusionWe have developed a data mining approach that enables rapid extraction of complex data from the major clinical trial repository. Summarization and visualization of these data represents a cost-effective means of making informed decisions about future cancer vaccine clinical trials.
| S-EPMC2639543 | biostudies-literature
Project description:Birds (Aves) are the most speciose of terrestrial vertebrates, displaying Class-specific characteristics yet incredible external phenotypic diversity. Critical to agriculture and as model organisms, birds have adapted to many habitats. The only extant examples of dinosaurs, birds emerged ~150 mya and >10% are currently threatened with extinction. This review is a comprehensive overview of avian genome ("chromosomic") organization research based mostly on chromosome painting and BAC-based studies. We discuss traditional and contemporary tools for reliably generating chromosome-level assemblies and analyzing multiple species at a higher resolution and wider phylogenetic distance than previously possible. These results permit more detailed investigations into inter- and intrachromosomal rearrangements, providing unique insights into evolution and speciation mechanisms. The 'signature' avian karyotype likely arose ~250 mya and remained largely unchanged in most groups including extinct dinosaurs. Exceptions include Psittaciformes, Falconiformes, Caprimulgiformes, Cuculiformes, Suliformes, occasional Passeriformes, Ciconiiformes, and Pelecaniformes. The reasons for this remarkable conservation may be the greater diploid chromosome number generating variation (the driver of natural selection) through a greater possible combination of gametes and/or an increase in recombination rate. A deeper understanding of avian genomic structure permits the exploration of fundamental biological questions pertaining to the role of evolutionary breakpoint regions and homologous synteny blocks.
| S-EPMC10886771 | biostudies-literature
Project description:The genomic variation of the Italian peninsula populations is currently under characterised: the only Italian whole-genome reference is represented by the Tuscans from the 1000 Genome Project. To address this issue, we sequenced a total of 947 Italian samples from three different geographical areas. First, we defined a new Italian Genome Reference Panel (IGRP1.0) for imputation, which improved imputation accuracy, especially for rare variants, and we tested it by GWAS analysis on red blood traits. Furthermore, we extended the catalogue of genetic variation investigating the level of population structure, the pattern of natural selection, the distribution of deleterious variants and occurrence of human knockouts (HKOs). Overall the results demonstrate a high level of genomic differentiation between cohorts, different signatures of natural selection and a distinctive distribution of deleterious variants and HKOs, confirming the necessity of distinct genome references for the Italian population.
| S-EPMC7080768 | biostudies-literature
Project description:During early embryogenesis, the hemogenic endothelium of the developing dorsal aorta is the main source of definitive hematopoietic stem cells (HSCs), which will generate all blood cell lineages of the adult organism. The hemogenic endothelial cells (HECs) of the dorsal aorta are known to arise from the splanchnic lateral plate mesoderm. However, the specific cell lineages and developmental paths that give rise to aortic HECs are still unclear. Over the past half a century, the scientific debate on the origin of aortic HECs and HSCs has largely focused on two potential and apparently alternative birthplaces, the extraembryonic yolk sac blood islands and the intraembryonic splanchnic mesoderm. However, as we argue, both yolk sac blood islands and aortic HECs may have a common hemangioblastic origin. Further insight into aortic HEC development is being gained from fate-mapping studies that address the identity of progenitor cell lineages, rather than their physical location within the developing embryo. In this perspective article, we discuss the current knowledge on the origin of aortic HECs with a particular focus on the evidence provided by studies in the avian embryo, a model that pioneered the field of developmental hematopoiesis.
| S-EPMC7717972 | biostudies-literature
Project description:It is well-established that anterior pituitary contains multiple endocrine cell populations, and each of them can secrete one/two hormone(s) to regulate vital physiological processes of vertebrates. However, the gene expression profiles of each pituitary cell population remains poorly characterized in most vertebrate groups. Here we analyzed the transcriptome of each cell population in adult chicken anterior pituitaries using single-cell RNA sequencing technology. The results showed that: (1) four out of five known endocrine cell clusters have been identified and designated as the lactotrophs, thyrotrophs, corticotrophs, and gonadotrophs, respectively. Somatotrophs were not analyzed in the current study. Each cell cluster can express at least one known endocrine hormone, and novel marker genes (e.g., CD24 and HSPB1 in lactotrophs, NPBWR2 and NDRG1 in corticotrophs; DIO2 and SOUL in thyrotrophs, C5H11ORF96 and HPGDS in gonadotrophs) are identified. Interestingly, gonadotrophs were shown to abundantly express five peptide hormones: FSH, LH, GRP, CART and RLN3; (2) four non-endocrine/secretory cell types, including endothelial cells (expressing IGFBP7 and CFD) and folliculo-stellate cells (FS-cells, expressing S100A6 and S100A10), were identified in chicken anterior pituitaries. Among them, FS-cells can express many growth factors, peptides (e.g., WNT5A, HBEGF, Activins, VEGFC, NPY, and BMP4), and progenitor/stem cell-associated genes (e.g., Notch signaling components, CDH1), implying that the FS-cell cluster may act as a paracrine/autocrine signaling center and enrich pituitary progenitor/stem cells; (3) sexually dimorphic expression of many genes were identified in most cell clusters, including gonadotrophs and lactotrophs. Taken together, our data provides a bird's-eye view on the diverse aspects of anterior pituitaries, including cell composition, heterogeneity, cell-to-cell communication, and gene expression profiles, which facilitates our comprehensive understanding of vertebrate pituitary biology.
| S-EPMC8276247 | biostudies-literature
Project description:: Hematological malignancies comprise over a hundred different types of cancers and account for around 6.5% of all cancers. Despite the significant improvements in diagnosis and treatment, many of those cancers remain incurable. In recent years, cancer cell-based therapy has become a promising approach to treat those incurable hematological malignancies with striking results in different clinical trials. The most investigated, and the one that has advanced the most, is the cell-based therapy with T lymphocytes modified with chimeric antigen receptors. Those promising initial results prepared the ground to explore other cell-based therapies to treat patients with blood cancer. In this review, we want to provide an overview of the different types of cell-based therapies in blood cancer, describing them according to the cell source.
| S-EPMC7281611 | biostudies-literature
Project description:Commercial capture fisheries produce huge quantities of offal, as well as undersized and unwanted catch in the form of discards. Declines in global catches and legislation to ban discarding will significantly reduce discards, but this subsidy supports a large scavenger community. Understanding the potential impact of declining discards for scavengers should feature in an eco-system based approach to fisheries management, but requires greater knowledge of scavenger/fishery interactions. Here we use bird-borne cameras, in tandem with GPS loggers, to provide a unique view of seabird/fishery interactions. 20,643 digital images (one min(-1)) from ten bird-borne cameras deployed on central place northern gannets Morus bassanus revealed that all birds photographed fishing vessels. These were large (>15 m) boats, with no small-scale vessels. Virtually all vessels were trawlers, and gannets were almost always accompanied by other scavenging birds. All individuals exhibited an Area-Restricted Search (ARS) during foraging, but only 42% of ARS were associated with fishing vessels, indicating much 'natural' foraging. The proportion of ARS behaviours associated with fishing boats were higher for males (81%) than females (30%), although the reasons for this are currently unclear. Our study illustrates that fisheries form a very important component of the prey-landscape for foraging gannets and that a discard ban, such as that proposed under reforms of the EU Common Fisheries Policy, may have a significant impact on gannet behaviour, particularly males. However, a continued reliance on 'natural' foraging suggests the ability to switch away from scavenging, but only if there is sufficient food to meet their needs in the absence of a discard subsidy.
| S-EPMC3590202 | biostudies-literature
Project description:Understanding physical mechanisms underlying seabird foraging is fundamental to predict responses to coastal change. For instance, turbulence in the water arising from natural or anthropogenic structures can affect foraging opportunities in tidal seas. Yet, identifying ecologically important localized turbulence features (e.g. upwellings approximately 10-100 m) is limited by observational scale, and this knowledge gap is magnified in volatile predators. Here, using a drone-based approach, we present the tracking of surface-foraging terns (143 trajectories belonging to three tern species) and dynamic turbulent surface flow features in synchrony. We thereby provide the earliest evidence that localized turbulence features can present physical foraging cues. Incorporating evolving vorticity and upwelling features within a hidden Markov model, we show that terns were more likely to actively forage as the strength of the underlying vorticity feature increased, while conspicuous upwellings ahead of the flight path presented a strong physical cue to stay in transit behaviour. This clearly encapsulates the importance of prevalent turbulence features as localized foraging cues. Our quantitative approach therefore offers the opportunity to unlock knowledge gaps in seabird sensory and foraging ecology on hitherto unobtainable scales. Finally, it lays the foundation to predict responses to coastal change to inform sustainable ocean development.
| S-EPMC8079999 | biostudies-literature
Project description:BACKGROUND: The objective of this evaluation was to determine whether reports of dead corvid sightings and submissions of dead corvids for West Nile virus testing were representative of true corvid mortality in British Columbia in 2004, a year with no West Nile virus activity, in order to ensure the system was accurately describing corvid mortality rather than reflecting regional differences in surveillance methods. RESULTS: Local Health Areas reported 0-159 (median = 3) dead corvid sightings and 0-209 (median = 5) submissions for West Nile virus testing. The expected numbers of dead corvid sightings and submissions for testing from each Local Health Area were 0-232 (median = 3) and 0-258 (median = 4), respectively. Twelve Local Health Areas reported significantly fewer sightings than expected; 21 reported significantly more. Eleven Local Health Areas submitted significantly fewer corvids than expected; 26 submitted significantly more. CONCLUSION: Some Local Health Areas were over-represented and others under-represented in terms of corvid West Nile virus surveillance indicators. Recommendations were made to improve the representativeness of corvid surveillance data. Geographic analysis can be used to evaluate the representativeness of surveillance systems and result in improvements to surveillance.
| S-EPMC1796857 | biostudies-other
Project description:ObjectiveIn preference-sensitive conditions such as back pain, there can be high levels of variability in the trajectory of patient care. We sought to develop a methodology that extracts a realistic and comprehensive understanding of the patient journey using medical and pharmaceutical insurance claims data.Materials and methodsWe processed a sample of 10 000 patient episodes (comprised of 113 215 back pain-related claims) into strings of characters, where each letter corresponds to a distinct encounter with the healthcare system. We customized the Levenshtein edit distance algorithm to evaluate the level of similarity between each pair of episodes based on both their content (types of events) and ordering (sequence of events). We then used clustering to extract the main variations of the patient journey.ResultsThe algorithm resulted in 12 comprehensive and clinically distinct patterns (clusters) of patient journeys that represent the main ways patients are diagnosed and treated for back pain. We further characterized demographic and utilization metrics for each cluster and observed clear differentiation between the clusters in terms of both clinical content and patient characteristics.DiscussionDespite being a complex and often noisy data source, administrative claims provide a unique longitudinal overview of patient care across multiple service providers and locations. This methodology leverages claims to capture a data-driven understanding of how patients traverse the healthcare system.ConclusionsWhen tailored to various conditions and patient settings, this methodology can provide accurate overviews of patient journeys and facilitate a shift toward high-quality practice patterns.
| S-EPMC7647282 | biostudies-literature