MeSH Annotations Research Articles

Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network.

Segmentation of the coronary artery is an important task for the quantitative analysis of coronary computed tomography angiography (CCTA) images and is being stimulated by the field of deep learning. However, the complex structures with tiny and narrow branches of the coronary artery bring it a great challenge. Coupled with the medical image limitations of low resolution and poor contrast, fragmentations of segmented vessels frequently occur in the prediction. Therefore, a geometry-based cascaded segmentation method is proposed for the coronary artery, which has the following innovations: 1) Integrating geometric deformation networks, we design a cascaded network for segmenting the coronary artery and vectorizing results. The generated meshes of the coronary artery are continuous and accurate for twisted and sophisticated coronary artery structures, without fragmentations. 2) Different from mesh annotations generated by the traditional marching cube method from voxel-based labels, a finer vectorized mesh of the coronary artery is reconstructed with the regularized morphology. The novel mesh annotation benefits the geometry-based segmentation network, avoiding bifurcation adhesion and point cloud dispersion in intricate branches. 3) A dataset named CCA-200 is collected, consisting of 200 CCTA images with coronary artery disease. The ground truths of 200 cases are coronary internal diameter annotations by professional radiologists. Extensive experiments verify our method on our collected dataset CCA-200 and public ASOCA dataset, with a Dice of 0.778 on CCA-200 and 0.895 on ASOCA, showing superior results. Especially, our geometry-based model generates an accurate, intact and smooth coronary artery, devoid of any fragmentations of segmented vessels.

Analyzing the Information Content of Text-Based Files in Supplementary Materials of Biomedical Literature.

We present an analysis of supplementary materials of PubMed Central (PMC) articles and show their importance in indexing and searching biomedical literature, in particular for the emerging genomic medicine field. On a subset of articles from PubMed Central, we use text mining methods to extract MeSH terms from abstracts, full texts, and text-based supplementary materials. We find that the recall of MeSH annotations increases by about 5.9 percentage points (+20% on relative percentage) when considering supplementary materials compared to using only abstracts. We further compare the supplementary material annotations with full-text annotations and we find out that the recall of MeSH terms increases by 1.5 percentage point (+3% on relative percentage). Additionally, we analyze genetic variant mentions in abstracts and full-texts and compare them with mentions found in supplementary text-based files. We find that the majority (about 99%) of variants are found in text-based supplementary files. In conclusion, we suggest that supplementary data should receive more attention from the information retrieval community, in particular in life and health sciences.

PubMed-Scale Chemical Concept Embeddings Reconstruct Physical Protein Interaction Networks.

PubMed is the largest resource of curated biomedical knowledge to date, entailing more than 25 million documents. Large quantities of novel literature prevent a single expert from keeping track of all potentially relevant papers, resulting in knowledge gaps. In this article, we present CHEMMESHNET, a newly developed PubMed-based network comprising more than 10,000,000 associations, constructed from expert-curated MeSH annotations of chemicals based on all currently available PubMed articles. By learning latent representations of concepts in the obtained network, we demonstrate in a proof of concept study that purely literature-based representations are sufficient for the reconstruction of a large part of the currently known network of physical, empirically determined protein–protein interactions. We demonstrate that simple linear embeddings of node pairs, when coupled with a neural network–based classifier, reliably reconstruct the existing collection of empirically confirmed protein–protein interactions. Furthermore, we demonstrate how pairs of learned representations can be used to prioritize potentially interesting novel interactions based on the common chemical context. Highly ranked interactions are qualitatively inspected in terms of potential complex formation at the structural level and represent potentially interesting new knowledge. We demonstrate that two protein–protein interactions, prioritized by structure-based approaches, also emerge as probable with regard to the trained machine-learning model.

A cross-platform approach to characterize and screen potential neurovascular unit toxicants

Development of the neurovascular unit (NVU) is a complex, multistage process that requires orchestrated cell signaling mechanisms across several cell types and ultimately results in formation of the blood-brain barrier. Typical high-throughput screening (HTS) assays investigate single biochemical or single cell responses following chemical insult. As the NVU comprises multiple cell types interacting at various stages of development, a methodology combining high-throughput results across pertinent cell-based assays is needed to investigate potential chemical-induced disruption to the development of this complex cell system. To this end, we implemented a novel method for screening putative NVU disruptors across diverse assay platforms to predict chemical perturbation of the developing NVU. HTS assay results measuring chemical-induced perturbations to cellular key events across angiogenic and neurogenic outcomes in vitro were combined to create a cell-based prioritization of NVU hazard. Chemicals were grouped according to similar modes of action to train a logistic regression literature model on a training set of 38 chemicals. This model utilizes the chemical-specific pairwise mutual information score for PubMed MeSH annotations to represent a quantitative measure of previously published results. Taken together, this study presents a methodology to investigate NVU developmental hazard using cell-based HTS assays and literature evidence to prioritize screening of putative NVU disruptors towards a knowledge-driven characterization of neurovascular developmental toxicity. The results from these screening efforts demonstrate that chemicals representing a range of putative vascular disrupting compound (pVDC) scores can also produce effects on neurogenic outcomes and characterizes possible modes of action for disrupting the developing NVU.

Feature engineering for MEDLINE citation categorization with MeSH

BackgroundResearch in biomedical text categorization has mostly used the bag-of-words representation. Other more sophisticated representations of text based on syntactic, semantic and argumentative properties have been less studied. In this paper, we evaluate the impact of different text representations of biomedical texts as features for reproducing the MeSH annotations of some of the most frequent MeSH headings. In addition to unigrams and bigrams, these features include noun phrases, citation meta-data, citation structure, and semantic annotation of the citations.ResultsTraditional features like unigrams and bigrams exhibit strong performance compared to other feature sets. Little or no improvement is obtained when using meta-data or citation structure. Noun phrases are too sparse and thus have lower performance compared to more traditional features. Conceptual annotation of the texts by MetaMap shows similar performance compared to unigrams, but adding concepts from the UMLS taxonomy does not improve the performance of using only mapped concepts. The combination of all the features performs largely better than any individual feature set considered. In addition, this combination improves the performance of a state-of-the-art MeSH indexer. Concerning the machine learning algorithms, we find that those that are more resilient to class imbalance largely obtain better performance.ConclusionsWe conclude that even though traditional features such as unigrams and bigrams have strong performance compared to other features, it is possible to combine them to effectively improve the performance of the bag-of-words representation. We have also found that the combination of the learning algorithm and feature sets has an influence in the overall performance of the system. Moreover, using learning algorithms resilient to class imbalance largely improves performance. However, when using a large set of features, consideration needs to be taken with algorithms due to the risk of over-fitting. Specific combinations of learning algorithms and features for individual MeSH headings could further increase the performance of an indexing system.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0539-7) contains supplementary material, which is available to authorized users.

Drug Side Effect Profiles as Molecular Descriptors for Predictive Modeling of Target Bioactivity.

We have explored the potential of using side effect profiles of drugs to predict their bioactivities at the receptor level. Serotonin 5-HT6 binding and dopamine antagonism were investigated in separate studies. A set of 5-HT6 binders and non-binders was retrieved from the PDSP Ki database, whereas dopamine antagonists were retrieved from the MeSH Pharmaceutical Action file. The side effect data was extracted from ChemoText, a data repository containing MeSH annotations pulled from MEDLINE records. These side effects profiles were treated as molecular descriptors enabling a QSAR-like approach to build models that could reliably discriminate different classes of molecules, e.g., binders versus non-binders, and dopamine antagonists versus non-antagonists. Selected models with the best external prediction performances were applied to a library of ca. 1000 chemicals with known side effects profiles in order to predict their potential 5-HT6 binding and/or dopamine antagonism. In each case the virtual screening process was able to identify putatively active compounds that through subsequent literature-based validation were found to be likely or known 5-HT6 binders or dopamine antagonists. These results demonstrate that side effect profiles can be utilized to predict a drug's unknown molecular activity, thus representing a valuable opportunity in repositioning the drug for a new indications.

Automated Patent Categorization and Guided Patent Search using IPC as Inspired by MeSH and PubMed

Document search on PubMed, the pre-eminent database for biomedical literature, relies on the annotation of its documents with relevant terms from the Medical Subject Headings ontology (MeSH) for improving recall through query expansion. Patent documents are another important information source, though they are considerably less accessible. One option to expand patent search beyond pure keywords is the inclusion of classification information: Since every patent is assigned at least one class code, it should be possible for these assignments to be automatically used in a similar way as the MeSH annotations in PubMed. In order to develop a system for this task, it is necessary to have a good understanding of the properties of both classification systems. This report describes our comparative analysis of MeSH and the main patent classification system, the International Patent Classification (IPC). We investigate the hierarchical structures as well as the properties of the terms/classes respectively, and we compare the assignment of IPC codes to patents with the annotation of PubMed documents with MeSH terms.Our analysis shows a strong structural similarity of the hierarchies, but significant differences of terms and annotations. The low number of IPC class assignments and the lack of occurrences of class labels in patent texts imply that current patent search is severely limited. To overcome these limits, we evaluate a method for the automated assignment of additional classes to patent documents, and we propose a system for guided patent search based on the use of class co-occurrence information and external resources.

Toward a systems level view of the ECM and related proteins: A framework for the systematic definition and analysis of biological systems

Advances in high throughput 'omic technologies are starting to provide unprecedented insights into how components of biological systems are organized and interact. Key to exploiting these datasets is the definition of the components that comprise the system of interest. Although a variety of knowledge bases exist that capture such information, a major challenge is determining how these resources may be best utilized. Here we present a systematic curation strategy to define a systems-level view of the human extracellular matrix (ECM)--a three-dimensional meshwork of proteins and polysaccharides that impart structure and mechanical stability to tissues. Employing our curation strategy we define a set of 357 proteins that represent core components of the ECM, together with an additional 524 genes that mediate related functional roles, and construct a map of their physical interactions. Topological properties help identify modules of functionally related proteins, including those involved in cell adhesion, bone formation and blood clotting. Because of its major role in cell adhesion, proliferation and morphogenesis, defects in the ECM have been implicated in cancer, atherosclerosis, asthma, fibrosis, and arthritis. We use MeSH annotations to identify modules enriched for specific disease terms that aid to strengthen existing as well as predict novel gene-disease associations. Mapping expression and conservation data onto the network reveal modules evolved in parallel to convey tissue-specific functionality on otherwise broadly expressed units. In addition to demonstrating an effective workflow for defining biological systems, this study crystallizes our current knowledge surrounding the organization of the ECM.

Effective Navigation of Query Results Based on Concept Hierarchies

Search queries on biomedical databases, such as PubMed, often return a large number of results, only a small subset of which is relevant to the user. Ranking and categorization, which can also be combined, have been proposed to alleviate this information overload problem. Results categorization for biomedical databases is the focus of this work. A natural way to organize biomedical citations is according to their MeSH annotations. MeSH is a comprehensive concept hierarchy used by PubMed. In this paper, we present the BioNav system, a novel search interface that enables the user to navigate large number of query results by organizing them using the MeSH concept hierarchy. First, the query results are organized into a navigation tree. At each node expansion step, BioNav reveals only a small subset of the concept nodes, selected such that the expected user navigation cost is minimized. In contrast, previous works expand the hierarchy in a predefined static manner, without navigation cost modeling. We show that the problem of selecting the best concepts to reveal at each node expansion is NP-complete and propose an efficient heuristic as well as a feasible optimal algorithm for relatively small trees. We show experimentally that BioNav outperforms state-of-the-art categorization systems by up to an order of magnitude, with respect to the user navigation cost. BioNav for the MEDLINE database is available at http://db.cse.buffalo.edu/bionav.

Automated Acquisition of Disease–Drug Knowledge from Biomedical and Clinical Documents: An Initial Study

ObjectiveExplore the automated acquisition of knowledge in biomedical and clinical documents using text mining and statistical techniques to identify disease-drug associations. DesignBiomedical literature and clinical narratives from the patient record were mined to gather knowledge about disease-drug associations. Two NLP systems, BioMedLEE and MedLEE, were applied to Medline articles and discharge summaries, respectively. Disease and drug entities were identified using the NLP systems in addition to MeSH annotations for the Medline articles. Focusing on eight diseases, co-occurrence statistics were applied to compute and evaluate the strength of association between each disease and relevant drugs. ResultsRanked lists of disease-drug pairs were generated and cutoffs calculated for identifying stronger associations among these pairs for further analysis. Differences and similarities between the text sources (i.e., biomedical literature and patient record) and annotations (i.e., MeSH and NLP-extracted UMLS concepts) with regards to disease-drug knowledge were observed. ConclusionThis paper presents a method for acquiring disease-specific knowledge and a feasibility study of the method. The method is based on applying a combination of NLP and statistical techniques to both biomedical and clinical documents. The approach enabled extraction of knowledge about the drugs clinicians are using for patients with specific diseases based on the patient record, while it is also acquired knowledge of drugs frequently involved in controlled trials for those same diseases. In comparing the disease-drug associations, we found the results to be appropriate: the two text sources contained consistent as well as complementary knowledge, and manual review of the top five disease-drug associations by a medical expert supported their correctness across the diseases.

GENE ONTOLOGY SIMILARITY MEASURES BASED ON LINEAR ORDER STATISTICS

The standard method for comparing gene products (proteins or RNA) is to compare their DNA or amino acid sequences. Additional information about some gene products may come from multiple sources, including the set of Gene Ontology (GO) annotations and the set of journal abstracts related to each gene product. Gene product similarity measures can be based on evaluating sets of descriptor terms found in the GO taxonomy, and/or the index term sets of the related documents (MeSH annotations). While our techniques can be applied to term sets from any taxonomy, we restrict our examples in this article to GO annotations. We investigate the use of linear order statistics (LOS) to build similarity relations on pairs of terms that are used in the GO as linguistic descriptors of genes and gene products. One of our objectives is to investigate the construction and utility of visual assessments of relational data (in this case, dissimilarity matrices) for discovering tendencies of groups of gene products to "cluster together". We use gene product data derived from a group of 194 gene products representing three protein families extracted from ENSEMBL. Our examples suggest that LOS similarity measures are more effective than traditional sequence-based similarity measures at capturing relationships between pairs of gene products in ENSEMBL families when annotation information is available. We show examples of how these similarity measures can assist in knowledge discovery and gene product family validation.

Selection of Medline contents, the development of its thesaurus, and the indexing process

The operation of MEDLINE requires three ongoing activities by persons having subject matter knowledge. These are literature selection, thesaurus maintenance and indexing. MEDLINE is intended to give access to the most generally useful biomedical literature rather than to provide indiscriminate comprehensive coverage. Literature is selected with the guidance of a group of health-science educators, editors and librarians who review periodicals under consideration for inclusion and re-evaluate those that are already regularly indexed. The MeSH thesaurus provides the descriptors that are used for subject indexing. Its hierarchical structure facilitates both general and specific searching. The appearance of new concepts and terminology in the literature requires a dynamic MeSH, but MeSH changes may complicate the process of searching backward in time. Maintaining MeSH requires finding a balance between the need for adaptability and the need for stability. Quality indexing requires accuracy and consistency in the assignment of subject headings. To this end, indexers receive didactic training plus practice under supervision. Precedents for indexers are detailed in an extensive Indexer's Manual and in MeSH annotations. Work of all indexers is reviewed on at least a sampling basis, and special sessions are held each year to familiarize indexers with MeSH changes.