Improving precision in concept normalization.
Ontology highlight
ABSTRACT:
SUBMITTER: Boguslav M
PROVIDER: S-EPMC5730334 | biostudies-literature | 2018
REPOSITORIES: biostudies-literature
Publications
Improving precision in concept normalization.
Boguslav Mayla M Cohen K Bretonnel KB Baumgartner William A WA Hunter Lawrence E LE
Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing 20180101
Most natural language processing applications exhibit a trade-off between precision and recall. In some use cases for natural language processing, there are reasons to prefer to tilt that trade-off toward high precision. Relying on the Zipfian distribution of false positive results, we describe a strategy for increasing precision, using a variety of both pre-processing and post-processing methods. They draw on both knowledge-based and frequentist approaches to modeling language. Based on an exis ...[more]
Similar Datasets
Project description:We consider the task of Medical Concept Normalization (MCN) which aims to map informal medical phrases such as "loosing weight" to formal medical concepts, such as "Weight loss". Deep learning models have shown high performance across various MCN datasets containing small number of target concepts along with adequate number of training examples per concept. However, scaling these models to millions of medical concepts entails the creation of much larger datasets which is cost and effort intensive. Recent works have shown that training MCN models using automatically labeled examples extracted from medical knowledge bases partially alleviates this problem. We extend this idea by computationally creating a distant dataset from patient discussion forums. We extract informal medical phrases and medical concepts from these forums using a synthetically trained classifier and an off-the-shelf medical entity linker respectively. We use pretrained sentence encoding models to find the k-nearest phrases corresponding to each medical concept. These mappings are used in combination with the examples obtained from medical knowledge bases to train an MCN model. Our approach outperforms the previous state-of-the-art by 15.9% and 17.1% classification accuracy across two datasets while avoiding manual labeling.
| S-EPMC7415240 | biostudies-literature
Project description:Specialized de novo assemblers for diverse datatypes have been developed and are in widespread use for the analyses of single-cell genomics, metagenomics and RNA-seq data. However, assembly of large sequencing datasets produced by modern technologies is challenging and computationally intensive. In-silico read normalization has been suggested as a computational strategy to reduce redundancy in read datasets, which leads to significant speedups and memory savings of assembly pipelines. Previously, we presented a set multi-cover optimization based approach, ORNA, where reads are reduced without losing important k-mer connectivity information, as used in assembly graphs. Here we propose extensions to ORNA, named ORNA-Q and ORNA-K, which consider a weighted set multi-cover optimization formulation for the in-silico read normalization problem. These novel formulations make use of the base quality scores obtained from sequencers (ORNA-Q) or k-mer abundances of reads (ORNA-K) to improve normalization further. We devise efficient heuristic algorithms for solving both formulations. In applications to human RNA-seq data, ORNA-Q and ORNA-K are shown to assemble more or equally many full length transcripts compared to other normalization methods at similar or higher read reduction values. The algorithm is implemented under the latest version of ORNA (v2.0, https://github.com/SchulzLab/ORNA ).
| S-EPMC6435659 | biostudies-literature
Project description:MotivationPrevious studies have shown that automated text-mining tools are becoming increasingly important for successfully unlocking variant information in scientific literature at large scale. Despite multiple attempts in the past, existing tools are still of limited recognition scope and precision.ResultWe propose tmVar 3.0: an improved variant recognition and normalization system. Compared to its predecessors, tmVar 3.0 recognizes a wider spectrum of variant-related entities (e.g. allele and copy number variants), and groups together different variant mentions belonging to the same genomic sequence position in an article for improved accuracy. Moreover, tmVar 3.0 provides advanced variant normalization options such as allele-specific identifiers from the ClinGen Allele Registry. tmVar 3.0 exhibits state-of-the-art performance with over 90% in F-measure for variant recognition and normalization, when evaluated on three independent benchmarking datasets. tmVar 3.0 as well as annotations for the entire PubMed and PMC datasets are freely available for download.Availability and implementationhttps://github.com/ncbi/tmVar3.
| S-EPMC9477515 | biostudies-literature
Project description:Nutritional and lifestyle changes remain at the core of healthy aging and disease prevention. Accumulating evidence underscores the impact of genetic, metabolic, and host gut microbial factors on individual responses to nutrients, paving the way for the stratification of nutritional guidelines. However, technological advances that incorporate biological, nutritional, lifestyle, and health data at an unprecedented scale and depth conceptualize a future where preventative dietary interventions will exceed stratification and will be highly individualized. We herein discuss how genetic information combined with longitudinal metabolomic, immune, behavioral, and gut microbial parameters, and bioclinical variables could define a digital replica of oneself, a "virtual digital twin," which could serve to guide nutrition in a personalized manner. Such a model may revolutionize the management of obesity and its comorbidities, and provide a pillar for healthy aging.
| S-EPMC7666894 | biostudies-literature
Project description:With currently available RNA-Seq pipelines, expression estimates for most genes are very noisy. We here introduce MapAl, a tool for RNA-Seq expression profiling that builds on the established programs Bowtie and Cufflinks. In the post-processing of RNA-Seq reads, it incorporates gene models already at the stage of read alignment, increasing the number of reliably measured known transcripts consistently by 50%. Adding genes identified de novo then allows a reliable assessment of double the total number of transcripts compared to other available pipelines. This substantial improvement is of general relevance: Measurement precision determines the power of any analysis to reliably identify significant signals, such as in screens for differential expression, independent of whether the experimental design incorporates replicates or not.
| S-EPMC3316937 | biostudies-literature
Project description:Producing independent and accurate chronologies for marine sediments is a prerequisite to understand the sequence of millennial-scale events and reveal potential temporal offsets between marine and continental records, or between different marine records, possibly from different regions. The last 40 ky is a generally well-constrained period since radiocarbon (14C) can be used as an absolute dating tool. However, in the northern North Atlantic, calendar ages cannot be directly derived from 14C ages, due to temporal and spatial variations of surface reservoir ages. Alternatively, chronologies can be derived by aligning Greenland ice-core time series with marine surface records. Yet this approach suffers from the lack of clearly defined climatic events between 14.7 and 23.3 cal ky BP (hereafter ka), a crucial period encompassing Heinrich Stadial 1 and the onset of the last deglaciation. In this study, (i) we assess the benefits of 230Th normalization to refine the sedimentation history between surface temperature alignment tie points and (ii) revisit the chronologies of three North Atlantic marine records. Our study supports the contention that the marked increase in the Greenland Ca2+ record at 17.48 ka ± 0.21 ky (1?) occurred within dating uncertainty of sea surface temperature cooling in the North Atlantic at the onset of Heinrich Stadial 1. This sharp feature might be useful for future chronostratigraphic alignments to remedy the lack of chronological constraint between 14.7 and 23.3 ka for North Atlantic marine records that are subject to large changes in 14C surface reservoir age.
| S-EPMC6774303 | biostudies-literature
Project description:Atlases provide a framework for spatially mapping information from diverse sources into a common reference space. Specifically, brain atlases allow annotation of gene expression, cell morphology, connectivity, and activity. In larval zebrafish, advances in genetics, imaging, and computational methods now allow the collection of such information brain-wide. However, due to technical considerations, disparate datasets may use different references and may not be aligned to the same coordinate space. Two recent larval zebrafish atlases exemplify this problem: Z-Brain, containing gene expression, neural activity, and neuroanatomical segmentations, was acquired using immunohistochemical stains, while the Zebrafish Brain Browser (ZBB) was constructed from live scans of fluorescent reporters in transgenic larvae. Although different references were used, the atlases included several common transgenic patterns that provide potential "bridges" for transforming each into the other's coordinate space. We tested multiple bridging channels and registration algorithms and found that the symmetric diffeomorphic normalization algorithm improved live brain registration precision while better preserving cell morphology than B-spline-based registrations. Symmetric diffeomorphic normalization also corrected for tissue distortion introduced during fixation. Multi-reference channel optimization provided a transformation that enabled Z-Brain and ZBB to be co-aligned with precision of approximately a single cell diameter and minimal perturbation of cell and tissue morphology. Finally, we developed software to visualize brain regions in 3 dimensions, including a virtual reality neuroanatomy explorer. This study demonstrates the feasibility of integrating whole brain datasets, despite disparate reference templates and acquisition protocols, when sufficient information is present for bridging. Increased accuracy and interoperability of zebrafish digital brain atlases will facilitate neurobiological studies.
| S-EPMC5597853 | biostudies-literature
Project description:Information encoded in natural language in biomedical literature publications is only useful if efficient and reliable ways of accessing and analyzing that information are available. Natural language processing and text mining tools are therefore essential for extracting valuable information, however, the development of powerful, highly effective tools to automatically detect central biomedical concepts such as diseases is conditional on the availability of annotated corpora. This paper presents the disease name and concept annotations of the NCBI disease corpus, a collection of 793 PubMed abstracts fully annotated at the mention and concept level to serve as a research resource for the biomedical natural language processing community. Each PubMed abstract was manually annotated by two annotators with disease mentions and their corresponding concepts in Medical Subject Headings (MeSH®) or Online Mendelian Inheritance in Man (OMIM®). Manual curation was performed using PubTator, which allowed the use of pre-annotations as a pre-step to manual annotations. Fourteen annotators were randomly paired and differing annotations were discussed for reaching a consensus in two annotation phases. In this setting, a high inter-annotator agreement was observed. Finally, all results were checked against annotations of the rest of the corpus to assure corpus-wide consistency. The public release of the NCBI disease corpus contains 6892 disease mentions, which are mapped to 790 unique disease concepts. Of these, 88% link to a MeSH identifier, while the rest contain an OMIM identifier. We were able to link 91% of the mentions to a single disease concept, while the rest are described as a combination of concepts. In order to help researchers use the corpus to design and test disease identification methods, we have prepared the corpus as training, testing and development sets. To demonstrate its utility, we conducted a benchmarking experiment where we compared three different knowledge-based disease normalization methods with a best performance in F-measure of 63.7%. These results show that the NCBI disease corpus has the potential to significantly improve the state-of-the-art in disease name recognition and normalization research, by providing a high-quality gold standard thus enabling the development of machine-learning based approaches for such tasks. The NCBI disease corpus, guidelines and other associated resources are available at: http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/DISEASE/.
| S-EPMC3951655 | biostudies-literature
Project description:MotivationClinical trials are the essential stage of every drug development program for the treatment to become available to patients. Despite the importance of well-structured clinical trial databases and their tremendous value for drug discovery and development such instances are very rare. Presently large-scale information on clinical trials is stored in clinical trial registers which are relatively structured, but the mappings to external databases of drugs and diseases are increasingly lacking. The precise production of such links would enable us to interrogate richer harmonized datasets for invaluable insights.ResultsWe present a neural approach for medical concept normalization of diseases and drugs. Our two-stage approach is based on Bidirectional Encoder Representations from Transformers (BERT). In the training stage, we optimize the relative similarity of mentions and concept names from a terminology via triplet loss. In the inference stage, we obtain the closest concept name representation in a common embedding space to a given mention representation. We performed a set of experiments on a dataset of abstracts and a real-world dataset of trial records with interventions and conditions mapped to drug and disease terminologies. The latter includes mentions associated with one or more concepts (in-KB) or zero (out-of-KB, nil prediction). Experiments show that our approach significantly outperforms baseline and state-of-the-art architectures. Moreover, we demonstrate that our approach is effective in knowledge transfer from the scientific literature to clinical trial data.Availability and implementationWe make code and data freely available at https://github.com/insilicomedicine/DILBERT.
| S-EPMC8570806 | biostudies-literature
Project description:The incidence of diet-induced metabolic disease has soared over the last half-century, despite national efforts to improve health through universal dietary recommendations. Studies comparing dietary patterns of populations with health outcomes have historically provided the basis for healthy diet recommendations. However, evidence that population-level diet responses are reliable indicators of responses across individuals is lacking. This study investigated how genetic differences influence health responses to several popular diets in mice, which are similar to humans in genetic composition and the propensity to develop metabolic disease, but enable precise genetic and environmental control. We designed four human-comparable mouse diets that are representative of those eaten by historical human populations. Across four genetically distinct inbred mouse strains, we compared the American diet's impact on metabolic health to three alternative diets (Mediterranean, Japanese, and Maasai/ketogenic). Furthermore, we investigated metabolomic and epigenetic alterations associated with diet response. Health effects of the diets were highly dependent on genetic background, demonstrating that individualized diet strategies improve health outcomes in mice. If similar genetic-dependent diet responses exist in humans, then a personalized, or "precision dietetics," approach to dietary recommendations may yield better health outcomes than the traditional one-size-fits-all approach.
| S-EPMC5753872 | biostudies-other