Gully A. P. C. Burns

Text mining for the biocuration workflow

Molecular biology has become heavily dependent on biological knowledge encoded in expert curated biological databases. As the volume of biological literature increases, biocurators need help in keeping up with the literature; (semi-) automated aids for biocuration would seem to be an ideal application for natural language processing and text mining. However, to date, there have been few documented successes for improving biocuration throughput using text mining. Our initial investigations took place for the workshop on ‘Text Mining for the BioCuration Workflow’ at the third International Biocuration Conference (Berlin, 2009). We interviewed biocurators to obtain workflows from eight biological databases. This initial study revealed high-level commonalities, including (i) selection of documents for curation; (ii) indexing of documents with biologically relevant entities (e.g. genes); and (iii) detailed curation of specific relations (e.g. interactions); however, the detailed workflows also showed many variabilities. Following the workshop, we conducted a survey of biocurators. The survey identified biocurator priorities, including the handling of full text indexed with biological entities and support for the identification and prioritization of documents for curation. It also indicated that two-thirds of the biocuration teams had experimented with text mining and almost half were using text mining at that time. Analysis of our interviews and survey provide a set of requirements for the integration of text mining into the biocuration workflow. These can guide the identification of common needs across curated databases and encourage joint experimentation involving biocurators, text mining developers and the larger biomedical research community.

Projections from the subfornical region of the lateral hypothalamic area

The L‐shaped anterior zone of the lateral hypothalamic areas subfornical region (LHAsfa) is delineated by a pontine nucleus incertus input. Functional evidence suggests that the subfornical region and nucleus incertus modulate foraging and defensive behaviors, although subfornical region connections are poorly understood. A high‐resolution Phaseolus vulgaris‐leucoagglutinin (PHAL) structural analysis is presented here of the LHAsfa neuron populations overall axonal projection pattern. The strongest LHAsfa targets are in the interbrain and cerebral hemisphere. The former include inputs to anterior hypothalamic nucleus, dorsomedial part of the ventromedial nucleus, and ventral region of the dorsal premammillary nucleus (defensive behavior control system components), and to lateral habenula and dorsal region of the dorsal premammillary nucleus (foraging behavior control system components). The latter include massive inputs to lateral and medial septal nuclei (septo‐hippocampal system components), and inputs to bed nuclei of the stria terminalis posterior division related to the defensive behavior system, intercalated amygdalar nucleus (projecting to central amygdalar nucleus), and posterior part of the basomedial amygdalar nucleus. LHAsfa vertical and horizontal limb basic projection patterns are similar, although each preferentially innervates certain terminal fields. Lateral hypothalamic area regions immediately medial, lateral, and caudal to the LHAsfa each generate quite distinct projection patterns. Combined with previous evidence that major sources of LHAsfa neural inputs include the parabrachial nucleus (nociceptive information), defensive and foraging behavior system components, and the septo‐hippocampal system, the present results suggest that the LHAsfa helps match adaptive behavioral responses (either defensive or foraging) to current internal motivational status and external environmental conditions. J. Comp. Neurol. 493:412–438, 2005.

Database of NIH grants using machine-learned categories and graphical clustering

framework that is based on scientific research rather than NIH administrative and categorical designations. We found that topic-based categories are not strictly associated with the missions of individual Institutes but instead cut across the NIH, albeit in varying proportions consistent with each Institute’s distinct mission (Supplementary Table 1). The graphical map layout (Fig. 1) shows a global research structure that is logically coherent but only loosely related to Institute organization (Supplementary Table 1). We describe four example use cases (Supplementary Data). First, we show a query using an algorithm-derived category relevant to angiogenesis (Supplementary Fig. 1). Unlike standard keywordbased searches, this type of query allows retrieval of grants that are truly focused on a particular research area. In addition, the resulting graphical clusters reveal clear patterns in the relationships between the retrieved grants and the multiple Institutes funding this research. Second, we examine an NIH peer review study section. The database categories and clusters clarify the complex relationship between the NIH Institutes and the centralized NIH peer review system, which is distinct and independent from the Institutes. Third, we show an analysis of the NIH RCDC category ‘sleep research’ in conjunction with the database topics, the latter Database of NIH grants using machine-learned categories and graphical clustering

Towards structured sharing of raw and derived neuroimaging data across existing resources

Data sharing efforts increasingly contribute to the acceleration of scientific discovery. Neuroimaging data is accumulating in distributed domain-specific databases and there is currently no integrated access mechanism nor an accepted format for the critically important meta-data that is necessary for making use of the combined, available neuroimaging data. In this manuscript, we present work from the Derived Data Working Group, an open-access group sponsored by the Biomedical Informatics Research Network (BIRN) and the International Neuroimaging Coordinating Facility (INCF) focused on practical tools for distributed access to neuroimaging data. The working group develops models and tools facilitating the structured interchange of neuroimaging meta-data and is making progress towards a unified set of tools for such data and meta-data exchange. We report on the key components required for integrated access to raw and derived neuroimaging data as well as associated meta-data and provenance across neuroimaging resources. The components include (1) a structured terminology that provides semantic context to data, (2) a formal data model for neuroimaging with robust tracking of data provenance, (3) a web service-based application programming interface (API) that provides a consistent mechanism to access and query the data model, and (4) a provenance library that can be used for the extraction of provenance data by image analysts and imaging software developers. We believe that the framework and set of tools outlined in this manuscript have great potential for solving many of the issues the neuroimaging community faces when sharing raw and derived neuroimaging data across the various existing database systems for the purpose of accelerating scientific discovery.

Layout-aware text extraction from full-text PDF of scientific articles

BackgroundThe Portable Document Format (PDF) is the most commonly used file format for online scientific publications. The absence of effective means to extract text from these PDF files in a layout-aware manner presents a significant challenge for developers of biomedical text mining or biocuration informatics systems that use published literature as an information source. In this paper we introduce the ‘Layout-Aware PDF Text Extraction’ (LA-PDFText) system to facilitate accurate extraction of text from PDF files of research articles for use in text mining applications.ResultsOur paper describes the construction and performance of an open source system that extracts text blocks from PDF-formatted full-text research articles and classifies them into logical units based on rules that characterize specific sections. The LA-PDFText system focuses only on the textual content of the research articles and is meant as a baseline for further experiments into more advanced extraction methods that handle multi-modal content, such as images and graphs. The system works in a three-stage process: (1) Detecting contiguous text blocks using spatial layout processing to locate and identify blocks of contiguous text, (2) Classifying text blocks into rhetorical categories using a rule-based method and (3) Stitching classified text blocks together in the correct order resulting in the extraction of text from section-wise grouped blocks. We show that our system can identify text blocks and classify them into rhetorical categories with Precision1 = 0.96% Recall = 0.89% and F1 = 0.91%. We also present an evaluation of the accuracy of the block detection algorithm used in step 2. Additionally, we have compared the accuracy of the text extracted by LA-PDFText to the text from the Open Access subset of PubMed Central. We then compared this accuracy with that of the text extracted by the PDF2Text system, 2commonly used to extract text from PDF. Finally, we discuss preliminary error analysis for our system and identify further areas of improvement.ConclusionsLA-PDFText is an open-source tool for accurately extracting text from full-text scientific articles. The release of the system is available at http://code.google.com/p/lapdftext/.

Intelligent Approaches to Mining the Primary Research Literature: Techniques, Systems, and Examples

In this chapter, we describe how creating knowledge bases from the primary biomedical literature is formally equivalent to the process of performing a literature review or a ‘research synthesis’. We describe a principled approach to partitioning the research literature according to the different types of experiments performed by researchers and how knowledge engineering approaches must be carefully employed to model knowledge from different types of experiment. The main body of the chapter is concerned with the use of text mining approaches to populate knowledge representations for different types of experiment. We provide a detailed example from neuroscience (based on anatomical tract-tracing experiments) and provide a detailed description of the methodology used to perform the text mining itself (based on the Conditional Random Fields model). Finally, we present data from text-mining experiments that illustrate the use of these methods in a real example. This chapter is designed to act as an introduction to the field of biomedical text-mining for computer scientists who are unfamiliar with the way that biomedical research uses the literature.

The NIH Visual Browser: An Interactive Visualization of Biomedical Research

This paper presents a technical description of the methods used to generate an interactive, two-dimensional visualization of 60,568 grants funded by the National Institutes of Health in 2007. The visualization is made intelligible by providing interactive features for assessing the data in a web-based visual browser, see http://www.nihmaps.org. The key features include deep zooming, selection, full-text querying, overlays, color-coding schemes, and multi-level labeling. Major insights, broader applicability, and future directions are discussed.

Tools and approaches for the construction of knowledge models from the neuroscientific literature

Within this paper, we describe a neuroinformatics project (called “NeuroScholar,” http://www.neuroscholar.org/) that enables researchers to examine, manage, manipulate, and use the information contained within the published neuroscientific literature. The project is built within a multi-level, multi-component framework constructed with the use of software engineering methods that themselves provide code-building functionality for neuroinformaticians. We describe the different software layers of the system. First, we present a hypothetical usage scenario illustrating how NeuroScholar permits users to address largescale questions in a way that would otherwise be impossible. We do this by applying NeuroScholar to a “real-world” neuroscience question: How is stress-related information processed in the brain? We then explain how the overall design of NeuroScholar enables the system to work and illustrate different components of the user interface. We then describe the knowledge management strategy we use to store interpretations. Finally, we describe the software engineering framework we have devised (called the “View-Primitive-Data Model framework,” [VPDMf]) to provide an open-source, accelerated software development environment for the project. We believe that NeuroScholar will be useful to experimental neuroscientists by helping them interact with the primary neuroscientific literature in a meaningful way, and to neuroinformaticians by providing them with useful, affordable software engineering tools.

Knowledge Mechanics and the Neuroscholar Project: A New Approach to Neuroscientific Theory

Publisher Summary Neuroscience literature has intrinsic complications because its subject matter is both broad and deep. It involves many different scientific subdisciplines ranging from animal behavior and psychology, through cellular anatomy and physiology, to studies of molecular biophysics and biochemistry. This chapter describes how knowledge mechanics will examine the philosophical basis of the concept of theory in neuroscience and how a knowledge mechanical approach may address key issues. It discusses the high-level software requirements and the fundamental design concepts of the neuroscholar system, neuroscholar, and the significance of knowledge mechanics in detail. The process of building a representation of user knowledge in neuroscholar is accomplished by placing a computational structure on the data that adequately captures the concepts of neuroscience theory. The retrieval of knowledge from the system may rely on the structured, interconnected nature of the ontology to give the user the capability to query data and information or knowledge in a combinatorial way. The strength of neuroanatomical connections is often used to prioritize how different connections influence the global organization of the system.

NeuroScholar's electronic laboratory notebook and its application to neuroendocrinology

Scientists continually relate information from the published literature to their current research. The challenge of this essential and time-consuming activity increases as the body of scientific literature continues to grow. In an attempt to lessen the challenge, we have developed an Electronic Laboratory Notebook (ELN) application. Our ELN functions as a component of another application we have developed, an open-source knowledge management system for the neuroscientific literature called NeuroScholar (http://www. neuroscholar.org/). Scanned notebook pages, images, and data files are entered into the ELN, where they can be annotated, organized, and linked to similarly annotated excerpts from the published literature within Neuroscholar. Associations between these knowledge constructs are created within a dynamic node-and-edge user interface. To produce an interactive, adaptable knowledge base. We demonstrate the ELNs utility by using it to organize data and literature related to our studies of the neuroendocrine hypothalamic paraventricular nucleus (PVH). We also discuss how the ELN could be applied to model other neuroendocrine systems; as an example we look at the role of PVH stressor-responsive neurons in the context of their involvement in the suppression of reproductive function. We present this application to the community as open-source software and invite contributions to its development.