Search

Literature-based discovery (LBD) aims to discover valuable latent relationships between disparate sets of literatures. This paper presents the first inclusive scientometric overview of LBD research. We utilize a comprehensive scientometric approach incorporating CiteSpace to systematically analyze the literature on LBD from the last four decades (1986-2020). After manual cleaning, we have retrieved a total of 409 documents from six bibliographic databases and two preprint servers. The 35 years' history of LBD could be partitioned into three phases according to the published papers per year: incubation (1986-2003), developing (2004-2008), and mature phase (2009-2020). The annual production of publications follows Price's law. The co-authorship network exhibits many subnetworks, indicating that LBD research is composed of many small and medium-sized groups with little collaboration among them. Science mapping reveals that mainstream research in LBD has shifted from baseline co-occurrence approaches to semantic-based methods at the beginning of the new millennium. In the last decade, we can observe the leaning of LBD towards modern network science ideas. In an applied sense, the LBD is increasingly used in predicting adverse drug reactions and drug repurposing. Besides theoretical considerations, the researchers have put a lot of effort into the development of Web-based LBD applications. Nowadays, LBD is becoming increasingly interdisciplinary and involves methods from information science, scientometrics, and machine learning. Unfortunately, LBD is mainly limited to the biomedical domain. The cascading citation expansion announces deep learning and explainable artificial intelligence as emerging topics in LBD. The results indicate that LBD is still growing and evolving., 43 pages, 12 figures

The field of bisociative literature-based discovery aims at mining scientific literature to reveal yet uncovered connections between different fields of specialization. This paper outlines several outlier-based literature mining approaches to bridging term detection and the lessons learned from selected biomedical literature-based discovery applications. The paper addresses also new prospects in bisociative literature-based discovery, proposing an advanced embeddings-based technology for cross-domain literature mining.

Literature-Based Discovery (LBD) aims to help researchers to identify relations between concepts which are worthy of further investigation by text-mining the biomedical literature. The vast majority of the LBD research follows the ABC model: a relation (A,C) is a candidate for discovery if there is some intermediate concept B which is related to both A and C. The ABC model has been successful in applications where the search space is strongly constrained, but there is limited evidence about its usefulness when applied in a broader context.Through a case study of 8 recent discoveries related to neurodegenerative diseases (NDs), we show the limitations of the ABC model in an open-ended context. The study emphasizes the impact of the choice of source data and extraction method on the resulting knowledge base: different “views” of the biomedical literature offer different levels of accuracy and coverage. We propose a novel contrastive approach which leverages these differences between “views” in order to target relations between concepts of interest. We explore various parameters and demonstrate the relevance of our approach through quantitative evaluation on the 8 target discoveries.The source data used in this article are publicly available. The different parts of the software used to process the data are published under open-source license and provided with detailed instructions. The main code for this paper is available at https://github.com/erwanm/lbd-contrast (required dependencies are detailed in the documentation). A prototype of the system is also provided as an online exploration tool at brainmend.adaptcentre.ie.

The vast nature of scientific publications brings out the importance of Literature-Based Discovery (LBD) research that is highly beneficial to accelerate knowledge acquisition and the research development process. LBD is a knowledge discovery workflow that automatically detects significant, implicit knowledge associations hidden in fragmented knowledge areas by analysing existing scientific literature. Therefore, the LBD output not only assists in formulating scientifically sensible, novel research hypotheses but also encourages the development of cross-disciplinary research. In this systematic review, we provide an in-depth analysis of the computational techniques used in the LBD process using a novel, up-to-date, and detailed classification. Moreover, we also summarise the key milestones of the discipline through a timeline of topics. To provide a general overview of the discipline, the review outlines LBD validation checks, major LBD tools, application areas, domains, and generalisability of LBD methodologies. We also outline the insights gathered through our statistical analysis that capture the trends in LBD literature. To conclude, we discuss the prevailing research deficiencies in the discipline by highlighting the challenges and opportunities of future LBD research.

This paper applied a literature-based discovery methodology utilizing citation networks and text mining in order to extract and represent shared terminologies found in disjoint academic literature on food security and the Internet of Things. The topic of food security includes research on improvements in nutrition, sustainable agriculture, and a plurality of other social challenges, while the Internet of Things refers to a collection of technologies from which solutions can be drawn. Academic articles on both topics were classified into subclusters, and their text contents were compared against each other to find shared terms. These terms formed a network from which clusters of related keywords could be identified, potentially easing the exploration of common themes. Thirteen transversal themes, including blockchain, healthcare, and air quality, were found. This method can be applied by policymakers and other stakeholders to understand how a given technology could contribute to solving a pressing social issue.

Purpose Literature-Based Discovery (LBD) is a text mining technique used to generate novel hypotheses from vast amounts of literature sources, by identifying links between concepts from disparate sources. One of the main areas where it has been predominantly applied is the healthcare domain, whereby promising results, in the form of novel hypotheses, have been reported. The purpose of this work was to conduct a systematic literature review of recent publications on LBD in the healthcare domain in order to assess the trends in the approaches used and to identify issues and challenges for such systems. Methods The review was conducted following the principles of the Kitchenham method. The selected studies have been scrutinized and the derived findings have been reported following the PRISMA guidelines. Results The review results reveal useful information regarding the application areas, the data sources considered, the approaches used, the performance in terms of accuracy and reliability and future research challenges. The results of this review will be beneficial to LBD researchers and other stakeholders in the healthcare domain, by providing them with useful insights on the approaches to adopt, data sources to consider, evaluation model to use and challenges to reflect on. Conclusion The synthesis of the results of this work has shed light on recent issues and challenges that drive new LBD models and provides avenues for their application in other diverse areas in the healthcare domain. To the best of our knowledge, no such recent review has been conducted.

Literature-based discovery (LBD) systems aim at helping researchers and scientists automatically generate and test potentially worthwhile research hypotheses. This is achieved by scouring vast collections of scientific publications for novel cross-applications of existing technological solutions from disparate fields. The inherent cross-disciplinary nature of LBD systems makes it an extremely valuable tool for accelerating humanitarian technology innovation through the facilitation of interdisciplinary problem solving. However, more evidence is currently needed to describe the extent to which LBD-style information search really helps researchers in their day-to-day scientific investigations. Of concern is the current lack of in-depth investigations into usability aspects and challenges in LBD system designs. This paper presents results from our preliminary user study of multidisciplinary researchers in interacting with LION-LBD, one of the most sophisticated LBD software available today. The study provides initial qualitative insights into four key usability issues faced by users in performing LBD-style hypothesis generation activities. Our findings suggest that addressing these challenges holds the key to increasing LBD systems future adoptions by researchers and scientists in practical settings.

Literature-based discovery (LBD) uncovers undiscovered public knowledge by linking terms A to C via a B intermediate. Existing LBD systems are limited to process certain A, B, and C terms, and many are not maintained. We present SKiM (Serial KinderMiner), a generalized LBD system for processing any combination of A, Bs, and Cs. We evaluate SKiM via the rediscovery of discoveries by Don Swanson, who pioneered LBD. Using only literature from the 19th century up to a year before Swanson’s discoveries, SKiM uncovers all five discoveries. We apply SKiM to repurposing drugs for 26 conditions of high prevalence. Manual analysis confirmed 65 discoveries useful for four diseases from Swanson’s discoveries from one to 31 years prior to their first validation by clinical trials. SKiM predicts many new potential drug candidates representing prime targets for wet lab validation. SKiM can be applied to any biomedical inquiry sufficiently mentioned in the literature.

In knowledge discovery, experts frequently need to combine knowledge from different domains to get new insights and derive new conclusions. Intelligent systems should support the experts in the search for relationships between concepts from different domains, where huge amounts of possible combinations require the systems to be efficient but also sufficiently general, open and interactive to enable the experts to creatively guide the discovery process. The paper proposes a cross-domain literature mining methodology that achieves this functionality by combining the functionality of two complementary text mining tools: clustering and topic ontology creation tool OntoGen and cross-domain bridging terms exploration tool CrossBee. Focusing on outlier documents identified by OntoGen contributes to the efficiency, while CrossBee allows for flexible and user-friendly bridging concepts exploration and identification. The proposed approach, which is domain independent and can support cross-domain knowledge discovery in any field of science, is illustrated on a biomedical case study dealing with Alzheimer’s disease, one of the most threatening age-related diseases, deteriorating lives of numerous individuals and challenging the ageing society as a whole. By applying the proposed methodology to Alzheimer’s disease and gut microbiota PubMed articles, we have identified Nitric oxide synthase (NOS) as a potentially valuable link between these two domains. The results support the hypothesis of neuroinflammatory nature of Alzheimer’s disease, and is indicative for the quest for identifying strategies to control nitric oxide-associated pathways in the periphery and in the brain. By addressing common mediators of inflammation using literature-based discovery, we have succeeded to uncover previously unidentified molecular links between Alzheimer’s disease and gut microbiota with a multi-target therapeutic potential.

Objectives This paper provides an introduction and overview of literature based discovery (LBD) in the biomedical domain. It introduces the reader to modern and historical LBD models, key system components, evaluation methodologies, and current trends. After completion, the reader will be familiar with the challenges and methodologies of LBD. The reader will be capable of distinguishing between recent LBD systems and publications, and be capable of designing an LBD system for a specific application. Target audience From biomedical researchers curious about LBD, to someone looking to design an LBD system, to an LBD expert trying to catch up on trends in the field. The reader need not be familiar with LBD, but knowledge of biomedical text processing tools is helpful. Scope This paper describes a unifying framework for LBD systems. Within this framework, different models and methods are presented to both distinguish and show overlap between systems. Topics include term and document representation, system components, and an overview of models including co-occurrence models, semantic models, and distributional models. Other topics include uninformative term filtering, term ranking, results display, system evaluation, an overview of the application areas of drug development, drug repurposing, and adverse drug event prediction, and challenges and future directions. A timeline showing contributions to LBD, and a table summarizing the works of several authors is provided. Topics are presented from a high level perspective. References are given if more detailed analysis is required.

Successful implementation remains a challenge as technology-enhanced learning (TEL) continues to progress. Therefore, it is necessary to develop a TEL maturity model as an assessment method and improvement roadmap. Recalling the analogy standing on the shoulders of giants, it emphasizes that we should build a model on previously established knowledge in literatures. Nonetheless, this resolution is followed by several challenges. They include the scope of discussion, purposive review, subjectivity, interpretable result, and trustworthiness. Thus, we set out the research objective on determining TEL maturity constructs using a literature-based knowledge discovery. This study uses content analysis as a technique to process the literatures, covering 548 research papers from 12 repositories. As an approach to building constructs and resolve the challenges as mentioned earlier, this study discusses how to set a research direction and uses Leximancer to improve the trustworthiness for both the analysis process and results. We then interpret the results to build a TEL maturity model constructs.

Literature-based discovery (LBD) has undergone an evolution from being an emerging area to a mature research field. Hence it is necessary to summarize the literature and scrutinize general bibliographic characteristics and publication trends. This paper presents very basic scientometric review of LBD in the period 1986–2020. We identified a total of 237 publications on LBD in the Web of Science database. The Journal of Biomedical Informatics published the greatest amount of papers on LBD. The United States plays a leading role in LBD research. Thomas C. Rindflesch is the most productive co-author in the field of LBD. Drawing on these first insights, we aim to better understand the historical progress of LBD in the last 35 years and to be able to improve the publishing practices to contribute to the field in the future.

The rapid increase in the academic literature has resulted in overspecialization of knowledge. To overcome this overspecialization, literature-based discovery (LBD) has been proposed to help discover promising and under-investigated hypotheses that connect two bodies of knowledge. The method has been around for more than 30 years, but its application has mostly been confined to the medical sciences. In this study, we perform a comprehensive survey of the literature on the application of LBD in nonmedical disciplines, summarize the approaches used, and discuss ways to promote the use of LBD in nonmedical disciplines.

This paper presents HBIN-LBD, a novel literature-based discovery (LBD) method that exploits the lexico-citation structures within the heterogeneous bibliographic information network (HBIN) graphs. Unlike other existing LBD methods, HBIN-LBD harnesses the metapath features found in HBIN graphs for discovering the latent associations between scientific papers published in otherwise disconnected research areas. Further, this paper investigates the effects of incorporating semantic and topic modeling components into the proposed models. Using time-sliced historical bibliographic data, we demonstrate the performance of our method by reconstructing two LBD hypotheses: the Fish Oil and Raynaud’s Syndrome hypothesis and the Migraine and Magnesium hypothesis. The proposed method is capable of predicting the future co-citation links between research papers of these previously disconnected research areas with up to 88.86% accuracy and 0.89 F-measure.

Literature-based discovery process identifies the important but implicit relations among information embedded in published literature. Existing techniques from Information Retrieval (IR) and Natural Language Processing (NLP) attempt to identify the hidden or unpublished connections between information concepts within published literature, however, these techniques overlooked the concept of predicting the future and emerging relations among scientific knowledge components such as author selected keywords encapsulated within the literature. Keyword Co-occurrence Network (KCN), built upon author selected keywords, is considered as a knowledge graph that focuses both on these knowledge components and knowledge structure of a scientific domain by examining the relationships between knowledge entities. Using data from two multidisciplinary research domains other than the bio-medical domain, and capitalizing on bibliometrics, the dynamicity of temporal KCNs, and a recurrent neural network, this study develops some novel features supportive for the prediction of the future literature-based discoveries - the emerging connections (co-appearances in the same article) among keywords. Temporal importance extracted from both bipartite and unipartite networks, communities defined by genealogical relations, and the relative importance of temporal citation counts were used in the feature construction process. Both node and edge-level features were input into a recurrent neural network to forecast the feature values and predict the future relations between different scientific concepts/topics represented by the author selected keywords. High performance rates, compared both against contemporary heterogeneous network-based method and preferential attachment process, suggest that these features complement both the prediction of future literature-based discoveries and emerging trend analysis.

Background Drug discovery is the process through which potential new medicines are identified. High-throughput screening and computer-aided drug discovery/design are the two main drug discovery methods for now, which have successfully discovered a series of drugs. However, development of new drugs is still an extremely time-consuming and expensive process. Biomedical literature contains important clues for the identification of potential treatments. It could support experts in biomedicine on their way towards new discoveries. Methods Here, we propose a biomedical knowledge graph-based drug discovery method called SemaTyP, which discovers candidate drugs for diseases by mining published biomedical literature. We first construct a biomedical knowledge graph with the relations extracted from biomedical abstracts, then a logistic regression model is trained by learning the semantic types of paths of known drug therapies’ existing in the biomedical knowledge graph, finally the learned model is used to discover drug therapies for new diseases. Results The experimental results show that our method could not only effectively discover new drug therapies for new diseases, but also could provide the potential mechanism of action of the candidate drugs. Conclusions In this paper we propose a novel knowledge graph based literature mining method for drug discovery. It could be a supplementary method for current drug discovery methods. Electronic supplementary material The online version of this article (10.1186/s12859-018-2167-5) contains supplementary material, which is available to authorized users.

The enormous amount of biomedicine's natural-language texts creates a daunting challenge to discover novel and interesting patterns embedded in the text corpora that help biomedical professionals find new drugs and treatments. These patterns constitute entities such as genes, compounds, treatments, and side effects and their associations that spread across publications in different biomedical specialties. This paper proposes SemPathFinder to discover previously unknown relations in biomedical text. SemPathFinder overcomes the problems of Swanson's ABC model by using semantic path analysis to tell a story about plausible connections between biological terms. Storytelling-based semantic path analysis can be viewed as relation navigation for bio-entities that are semantically close to each other, and reveals insight into how a series of entity pairs is organized, and how it can be harnessed to explain seemingly unrelated connections. We apply SemPathFinder for two well-known use cases of Swanson's ABC model, and the experimental results show that SemPathFinder detects all intermediate terms except for one and also infers several interesting new hypotheses.

During the last 30 years, Alzheimer's disease (AD) research, aiming to understand the pathophysiology and to improve the diagnosis, management, and, ultimately, treatment of the disease, has grown rapidly. Recently, some studies have used simple bibliometric approaches to investigate research trends and advances in the field. In our study, we map the AD research field by applying entitymetrics, an extended concept of bibliometrics, to capture viewpoints of indexers, authors, or citers. Using the full-text documents with reference section retrieved from PubMed Central, we constructed four types of networks: MeSH-MeSH (MM), MeSH-Citation-MeSH (MCM), Keyphrase-Keyphrase (KK), and Keyphrase-Citation-Keyphrase (KCK) networks. The working hypothesis was that MeSH, keyphrase, and citation relationships reflect the views of indexers, authors, and/or citers, respectively. In comparative network and centrality analysis, we found that those views are different: indexers emphasize amyloid-related entities, including methodological terms, while authors focus on specific biomedical terms, including clinical syndromes. The more dense and complex networks of citing relationships reported in our study, to a certain extent reflect the impact of basic science discoveries in AD. However, none of these could have had clinical relevance for patients without close collaboration between investigators in translational and clinical-related AD research (reflected in indexers and authors' networks). Our approach has relevance for researches in the field, since they can identify relations between different developments which are not otherwise evident. These developments combined with advanced visualization techniques, might aid the discovery of novel interactions between genes and pathways or used as a resource to advance clinical drug development.

Given a beginning and ending document, automated storytelling attempts to fill in intermediary documents to form a coherent story. This is a common problem for analysts; they often have two snippets of information and want to find the other pieces that relate them. The goal of storytelling is to help the analysts limit the number of documents that must be sifted through and show connections between events, people, organizations, and places. But existing algorithms fail to allow for the insertion of analyst knowledge into the story generation process. Often times, analysts have an understanding of the situation or prior knowledge that could be used to focus the story in a better way. A storytelling algorithm is proposed as a multi-criteria optimization problem that allows for signal injection by the analyst while maintaining good story flow and content.

Display Omitted We evaluate PSI-based identification of relationships between drugs and ADRs.PSI can incorporate relations and concepts and infer reasoning pathways.PSI is more predictive than a co-occurrence based model.Reasoning pathways suggest supporting evidence from literature for review. Pharmacovigilance involves continually monitoring drug safety after drugs are put to market. To aid this process; algorithms for the identification of strongly correlated drug/adverse drug reaction (ADR) pairs from data sources such as adverse event reporting systems or Electronic Health Records have been developed. These methods are generally statistical in nature, and do not draw upon the large volumes of knowledge embedded in the biomedical literature. In this paper, we investigate the ability of scalable Literature Based Discovery (LBD) methods to identify side effects of pharmaceutical agents. The advantage of LBD methods is that they can provide evidence from the literature to support the plausibility of a drug/ADR association, thereby assisting human review to validate the signal, which is an essential component of pharmacovigilance. To do so, we draw upon vast repositories of knowledge that has been extracted from the biomedical literature by two Natural Language Processing tools, MetaMap and SemRep. We evaluate two LBD methods that scale comfortably to the volume of knowledge available in these repositories. Specifically, we evaluate Reflective Random Indexing (RRI), a model based on concept-level co-occurrence, and Predication-based Semantic Indexing (PSI), a model that encodes the nature of the relationship between concepts to support reasoning analogically about drug-effect relationships. An evaluation set was constructed from the Side Effect Resource 2 (SIDER2), which contains known drug/ADR relations, and models were evaluated for their ability to "rediscover" these relations. In this paper, we demonstrate that both RRI and PSI can recover known drug-adverse event associations. However, PSI performed better overall, and has the additional advantage of being able to recover the literature underlying the reasoning pathways it used to make its predictions.

Literature Based Discovery (LBD) refers to the problem of inferring new and interesting knowledge by logically connecting independent fragments of information units through explicit or implicit means. This area of research, which incorporates techniques from Natural Language Processing (NLP), Information Retrieval and Artificial Intelligence, has significant potential to reduce discovery time in biomedical research fields. Formally introduced in 1986, LBD has grown to be a significant and a core task for text mining practitioners in the biomedical domain. Together with its inter-disciplinary nature, this has led researchers across domains to contribute in advancing this field of study. This survey attempts to consolidate and present the evolution of techniques in this area. We cover a variety of techniques and provide a detailed description of the problem setting, the intuition, the advantages and limitations of various influential papers. We also list the current bottlenecks in this field and provide a general direction of research activities for the future. In an effort to be comprehensive and for ease of reference for off-the-shelf users, we also list many publicly available tools for LBD. We hope this survey will act as a guide to both academic and industry (bio)-informaticians, introduce the various methodologies currently employed and also the challenges yet to be tackled.

Several researchers have studied serendipitous knowledge discovery in information-seeking behavior. Electronic data in the form of semantic predications have a potential role in literature-based discovery, which can be guided by serendipitous knowledge discovery research findings. We sought to model information-seeking behavior within the context of serendipitous knowledge discovery by leveraging existing research. These efforts were done with an eye for a potential literature-based discovery application that utilizes semantic predications. We performed a literature search, reviewed the results, and applied the findings in developing a model for serendipitous knowledge discovery as an information-seeking behavior. The literature review indicated four important themes in serendipitous knowledge discovery: iteration, change or clarification, a seeker's prior knowledge, and the role of information organization and presentation. The Interaction Flow in Serendipitous Knowledge Discovery (IF-SKD) model includes these themes, and accommodates iterative, evolving search interests. Output can be presented in a manner to enhance short-term memory conceptualization and connections with prior knowledge. Although the IF-SKD model is currently a theoretical structure, its utility is demonstrated through replicating a literature-based discovery event, using a documented search method within the model's steps. The IF-SKD model can potentially serve as the foundation for future literature-based discovery applications.

Clear documentation of literature search and presentation methodologies can improve transparency in chemical hazard assessments. We sought to improve clarity for the scientific support for cancer mechanisms of action using a systematic approach to literature retrieval, selection, and presentation of studies. The general question was “What are the mechanisms by which a chemical may cause carcinogenicity in the target tissue?”. Di(2-ethylhexyl)phthalate was used as a case study chemical with a complex database of >3000 publications. Relevant mechanistic events were identified from published reviews. The PubMed search strategy included relevant synonyms and wildcards for DEHP and its metabolites, mechanistic events, and species of interest. Tiered exclusion/inclusion criteria for study pertinence were defined, and applied to the retrieved literature. Manual curation was conducted for mechanistic events with large literature databases. Literature trees documented identification and selection of the literature evidence. The selected studies were summarized in evidence tables accompanied by succinct narratives. Primary publications were deposited into the Health and Environmental Research Online ( http://hero.epa.gov/ ) database and identified by pertinence criteria and key terms to permit organized retrieval. This approach contributes to human health assessment by effectively managing a large volume of literature, improving transparency, and facilitating subsequent synthesis of information across studies.

Literature-based discovery systems aim at discovering valuable latent connections between previously disparate research areas. This is achieved by analyzing the contents of their respective literatures with the help of various intelligent computational techniques. In this paper, we review the progress of literature-based discovery research, focusing on understanding their technical features and evaluating their performance. The present literature-based discovery techniques can be divided into two general approaches: the traditional approach and the emerging approach. The traditional approach, which dominate the current research landscape, comprises mainly of techniques that rely on utilizing lexical statistics, knowledge-based and visualization methods in order to address literature-based discovery problems. On the other hand, we have also observed the births of new trends and unprecedented paradigm shifts among the recently emerging literature-based discovery approach. These trends are likely to shape the future trajectory of the next generation literature-based discovery systems.

Literature-Based Discovery (LBD) refers to a range of approaches that take a body of scientific literature as the input, apply a series of computational, manual, or a hybrid processes, and finally generate hypotheses that are potentially novel and meaningful for further investigations. This chapter introduces the origin of LBD, its major landmark studies, available tools, and resources. In particular, we explain the design and application of PKD4J to illustrate the principles and analytic decisions one typically needs to make. We highlight the recent developments in this area and outline remaining challenges.

The massive and unprecedented volume of scientific literature readily available in the domain of biomedicine has presented us with challenges and opportunities to accelerate hypothesis generation. Advanced text mining techniques are required to leverage this abundant textual representation in order to provide timely access to explicit facts and aid in elucidating association among implicit facts. The problem of inferring novel knowledge from these implicit facts by logically connecting independent fragments of literature is known as Literature Based Discovery(LBD). In LBD, to discover hidden links, it is important to determine the relevancy between concepts using appropriate information measures. In this paper, to discover interesting and inherent links latent in large corpora, nine distinct methods, comprising variants of statistical information measures and derived semantic knowledge from domain ontology, are designed and compared. For better understanding of results, we split methods into three groups. The first group includes traditional information measures such as Mutual information, Chi-Square and those used in association rule mining; the second group incorporates popular null-invariant correlation measures: All_Confidence, Kulczynski, and Cosine; the third group consists of null-invariant measures combined with our proposed notion of semantic relatedness. We have also proposed a new strategy of effective preprocessing, which is capable of removing terms that are spurious, semantically unrelated or have meager chances of constituting a new discovery. A series of experiments are performed and analyzed for those proposed methods. In addition, we also provide an organized list of final concepts deemed worthy of scientific investigation or experimentation. Overall, our research presents a comprehensive analysis and perspective of how different statistical information measures and semantic knowledge affect the knowledge discovery procedure.

Literature-related discovery (LRD) is the linking of two or more previously disjoint concepts in order to produce novel, interesting, plausible, and intelligible connections (i.e., potential discovery). LRD has been used to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. Severe acute respiratory syndrome (SARS) was the first pandemic of the 21st century. SARS was eventually controlled through increased hygienic measures (e.g., face mask protection, frequent hand washing, living quarter disinfection), travel restrictions, and quarantine. According to recent reviews of SARS, none of the drugs that were used during the pandemic worked. For the present paper, SARS was selected as the first application of LRD to an infectious disease. The main goal of this research was to identify non-drug non-surgical treatments that would 1) prevent the occurrence, or 2) reduce the progression rate, or 3) stop/reverse the progression of SARS. The MeSH taxonomy of Medline was used to restrict potential discoveries to selected semantic classes, and to identify potential discoveries efficiently. To enhance the volume of potential discovery, databases were used in addition to Medline. These included the Science Citation Index (SCI) and, in contrast to previous work, a full text database. Because of the richness of the full text, ‘surgical’ queries were developed that targeted the exact types of potential discovery of interest while eliminating clutter more efficiently., Research highlights ► Generated potential discovery for treatment and prevention of SARS. ► Developed functional query approach for targeting potential discovery. ► Used full text and functional query for expanding potential discovery database. ► Used citation linkages from initial discovery to enhance discovery generation. ► Used proximity searching for ‘surgical’ targeting of desired concepts.

Literature-based discovery (LBD) refers to a particular type of text mining that seeks to identify nontrivial assertions that are implicit, and not explicitly stated, and that are detected by juxtaposing (generally a large body of) documents. In this review, I will provide a brief overview of LBD, both past and present, and will propose some new directions for the next decade. The prevalent ABC model is not “wrong”; however, it is only one of several different types of models that can contribute to the development of the next generation of LBD tools. Perhaps the most urgent need is to develop a series of objective literature-based interestingness measures, which can customize the output of LBD systems for different types of scientific investigations. © 2012 Wiley Periodicals, Inc.

Open Innovation presses the case for timely and thorough intelligence concerning research and development activities conducted outside one’s organization. To take advantage of this wealth of R&D, one needs to establish a systematic “tech mining” process. We propose a 5-stage framework that extends literature review into research profiling and pattern recognition to answer posed technology management questions. Ultimately one can even discover new knowledge by screening research databases. Once one determines the value in mining external R&D, tough issues remain to be overcome. Technology management has developed a culture that relies more on intuition than on evidence. Changing that culture and implementing effective technical intelligence capabilities is worth the effort. P&G's reported gains in innovation call attention to the huge payoff potential.

While medical researchers formulate new hypotheses to test, they need to identify connections to their work from other parts of the medical literature. However, the current volume of information has become a great barrier for this task. Recently, many literature-based discovery (LBD) systems have been developed to help researchers identify new knowledge that bridges gaps across distinct sections of the medical literature. Each LBD system uses different methods for mining the connections from text and ranking the identified connections, but none of the currently available LBD evaluation approaches can be used to compare the effectiveness of these methods. In this paper, we present an evaluation methodology for LBD systems that allows comparisons across different systems. We demonstrate the abilities of our evaluation methodology by using it to compare the performance of different correlation-mining and ranking approaches used by existing LBD systems. This evaluation methodology should help other researchers compare approaches, make informed algorithm choices, and ultimately help to improve the performance of LBD systems overall.

Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. The five immediately preceding papers in this Special Issue describe the application of ODS LRD to Raynaud's Phenomenon (RP), cataracts, Parkinson's Disease (PD), Multiple Sclerosis (MS), and Water Purification (WP). We describe the lessons learned from each application, and how the techniques can be improved further. Generation of much potential discovery using ODS LRD is possible when the conceptual roadblocks to discovery are removed. Some of these roadblocks include use of numerical filters that are unrelated to generating discovery, and excessive reliance on literatures directly related to the problem literature of interest. The issue of how to handle large amounts of potential discovery has not been addressed in the literature, since most ODS LRD researchers have tried to find a relatively few potential discovery items. We present a development strategy that capitalizes on the large amounts of potential discovery we have identified.

Discovery in science is the generation of novel, interesting, plausible, and intelligible knowledge about the objects of study. Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). LRD has two main components that differ in their methodological approach to discovery: • Literature-based discovery (LBD) produces potential discovery through analysis of the technical literature alone. • Literature-assisted discovery (LAD) produces potential discovery through both analysis of the technical literature and use of selected authors of that literature. These authors generate potential discovery as proposers, workshop/panel participants, or in other active roles. LRD offers the promise of large amounts of potential discovery, for the following reasons: • the burgeoning technical literature contains a very large pool of technical concepts in myriad technical areas; • researchers spend full time trying to cover the literature in their own research fields and are relatively unfamiliar with research in other especially disparate fields of research; • the large number of technical concepts (and disparate technical concepts) means that many combinations of especially disparate technical concepts exist • by the laws of probability, some of these combinations will produce novel, interesting, plausible, and intelligible knowledge about the objects of study. This Special Issue presents the LRD methodology and voluminous discovery results from five problem areas: four medical (treatments for Parkinson's Disease (PD), Multiple Sclerosis (MS), Raynaud's Phenomenon (RP), and Cataracts) and one non-medical (Water Purification (WP)). In particular, the open discovery systems (ODS) aspect of LRD (start with problem, generate potential solution(s), or vice versa) is addressed, rather than the closed discovery systems (CDS) aspect (start with problem and potential solution(s), generate linking mechanism(s)). In the presentation of potential discovery, a ‘vetting’ process is used that insures both requirements for ODS LBD are met: concepts are linked that have not been linked previously, and novel, interesting, plausible, and intelligible knowledge is produced. The potential discoveries for the PD, MS, Cataracts, and WP problems are the first we have seen reported by this ODS LBD approach, and the numbers of potential discoveries for the ODS LBD benchmark RP problem are almost two orders of magnitude greater than those reported in the open literature by any other ODS LBD researcher who has addressed this benchmark RP problem. The WP problem is the first non-medical technical topic to have been addressed successfully by ODS LBD. In all cases, but especially the medical, we have barely scratched the surface of quantity and quality of potential discovery that could be generated with adequately resourced studies. Based on the many potential discoveries we have obtained, and the promise of far more potential discoveries with adequately resourced studies, we have generated a new paradigm relative to discovery: while the key challenge in traditional discovery is finding a needle-in-a-haystack, the key challenge in ODS LRD (used appropriately) is handling the overwhelming amount of potential discovery available. Additionally, it is our thesis, as the specific ODS LBD studies will demonstrate, that synergistic combinations of our mainly individual potential discoveries are themselves potential discoveries. We demonstrate throughout this Special Issue the synergistic effects of combining a very few potential discoveries or interesting core literature concepts, and believe that these synergistic benefits are operable at larger scales of combination. In the final lessons-learned paper of this Special Issue, we also show that providing evidence for the synergistic benefits of large numbers of potential discoveries or interesting core concepts is very difficult due to the large numbers of potential combinations involved. One variant of the LAD operational mode (identifying disparate discipline recipients for Broad Agency Announcement (BAA) notifications in order to stimulate proposals of new ideas from these disparate disciplines) is presented for WP. Other possible applications of LAD include: 1. Recipients of solicitation announcements (other solicitations similar to BAA, journal Special Issue calls for papers, etc), 2. Participants in Workshops, Advisory Panels, Review Panels, Roadmaps, and War Games, 3. Points of Contact for Field Science Advisors, Foreign Field Offices, Program Officer site visits, and potential transitions.

Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. Raynaud's Phenomenon (RP) is a condition in which small arteries, most commonly in fingers and toes, contract and cause the skin to turn pale or a patchy red to blue. We selected the subject of RP for analysis by LRD because of RP's global prevalence, and its apparent intractability to all treatments except for palliative remediation mainly through drugs or surgery. Our main goal was to identify non-drug non-surgical treatments that would 1) prevent the occurrence, or 2) reduce the progression rate, or 3) stop the progression, or 4) maybe even reverse the progression, of RP. Our secondary goal was to compare our ODS LRD approach to the RP problem with other investigators who have addressed the RP problem since Swanson's pioneering 1986 ODS LRD paper on potential RP treatments [D.R. Swanson, Fish oil, Raynauds syndrome, and undiscovered public knowledge, Perspectives in Biology and Medicine 30 (1) (1986) 7–18]. We used Medline from 1965–1985 to identify potential discovery for RP. We differ from all the other authors who have addressed this problem in two major respects: we make no numerically-based filtering assumptions, and we generate substantial potential discovery (∼ 130 potential discoveries). Further, we believe our reported results are the tip of the iceberg. Much more potential discovery is possible with an adequately resourced study using the lessons learned from this demonstration study and the other demonstration studies that follow in this Special Issue.

Literature-related discovery (LRD) is the linking of two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge (i.e., potential discovery). LRD has two main components that differ in their methodological approach to discovery: Literature-based discovery (LBD) produces potential discovery through analysis of the technical literature alone; Literature-assisted discovery (LAD) produces potential discovery through both analysis of the technical literature and use of selected authors of that literature. These authors generate potential discovery as proposers, workshop/panel participants, or in other active roles. The open discovery systems (ODS) component of LRD starts with a problem to be solved, and generates solutions to that problem through potential discovery. We have been using ODS LRD to identify potential treatments or preventative actions for challenging medical problems, among myriad other applications. The previous four papers in this Special Issue describe the application of ODS LRD (specifically, the ODS LBD variant) to Raynaud's Phenomenon (RP), cataracts, Parkinson's Disease (PD), and Multiple Sclerosis (MS). One goal of the present study was to determine whether LRD could be successfully applied (for the first time) to a challenging non-medical technical problem to generate potential discovery. The second goal was to explore the use of both LRD variants (LBD and LAD) to a non-medical technical problem. We selected the problem of water purification (WP) because of universal applicability and sponsor interest. We used LRD to identify purification concepts, technology components and systems that could lead to improved water purification techniques. We accessed many disparate disciplines to identify purification concepts from literatures not normally associated with water purification. We used two LBD approaches, Cluster Filtering and Latent Semantic Indexing (LSI), to search for potential discovery. We generated voluminous amounts of potential discovery, and believe we have only scratched the surface of what is possible. We also ran a short experiment using LAD to identify experts associated with potential discovery concepts, and use their expertise to generate potential discovery for water purification.

Given its immense growth, scientific literature can be explored to reveal new discoveries, based on yet uncovered relations between knowledge from different, relatively isolated fields of research specialization. This chapter proposes a bisociation-based text mining approach, which shows to be effective for cross-domain knowledge discovery. The proposed cross-domain literature mining functionality, including text acquisition, text preprocessing, and bisociative cross-domain literature mining facilities, is made publicly available within a new browser-based workflow execution engine TextFlows, which supports visual construction and execution of text mining and natural language processing (NLP) workflows. To support bisociative cross-domain literature mining, the TextFlows platform includes implementations of several elementary and ensemble heuristics that guide the expert in the process of exploring new cross-context bridging terms. We have extended the TextFlows platform with several components, which—together with document exploration and visualization features of the CrossBee human-computer interface—make it a powerful, user-friendly text analysis tool for exploratory cross-domain knowledge discovery. Another novelty of the developed technology is the enabled use of controlled vocabularies to improve bridging term extraction. The potential of the developed functionality was showcased in two medical benchmark domains.

Background: Identifying information that implicitly links two disparate sets of articles is a fundamental and intuitive data mining strategy that can help investigators address real scientific questions. The Arrowsmith two-node search finds title words and phrases (so-called B-terms) that are shared across two sets of articles within MEDLINE and displays them in a manner that facilitates human assessment. A serious stumbling-block has been the lack of a quantitative model for predicting which of the hundreds if not thousands of B-terms computed for a given search are most likely to be relevant to the investigator. Methodology/Principal Findings: Using a public two-node search interface, field testers devised a set of two-node searches under real life conditions and a certain number of B-terms were marked relevant. These were employed as ‘gold standards;’ each B-term was characterized according to eight complementary features that were strongly correlated with relevance. A logistic regression model was developed that permits one to estimate the probability of relevance for each B-term, to rank B-terms according to their likely relevance, and to estimate the overall number of relevant B-terms inherent in a given two-node search. Conclusions/Significance: The model greatly simplifies and streamlines the process of carrying out a two-node search, and may be applicable to a number of other literature-based discovery applications, including the so-called one-node search and related gene-centric strategies that incorporate implicit links to predict how genes may be related to each other and to human diseases. This should encourage much wider exploration of text mining for implicit information among the general scientific community. Availability: Two-node searches can be carried out freely at http://arrowsmith.psych.uic.edu Contact:neils@uic.edu, vtorvik@uic.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Literature-Based Discovery (LBD) is the science of relating existing knowledge in literature to discover new relationships. It is sometimes referred to as hidden knowledge. This paper provides the most recent classification of the existing LBD methods relating the problem to other domains such as information retrieval. The papers identifies that Vector Space Model, Probabilistic Model, and Inference Network Model are the mostly used for LBD problem. The researchers of this paper justified their belief that there are important differences between the problem domains with regards to novelty, time factor, reasoning, and relevance. Moreover, the paper introduces the on-going work of the authors on proposing a new evaluation methodology that addresses the weaknesses of the current methodologies investigating the desirable characteristics of the future LBD evaluation methodology.

A systematic two-component approach (front-end component, back-end component) to bridging unconnected disciplines and accelerating potentially radical discovery and innovation (based wholly or partially on text mining procedures) is presented. The front-end component has similar objectives to those in the classical literature-based discovery (LBD) approach, although it is different mechanistically and operationally. The front-end component will systematically identify technical disciplines (and their associated leading experts) that are directly or indirectly-related to solving technical problems of high interest. The back-end component is actually a family of back-end techniques, only one of which shares the strictly literature-based analysis of the classical LBD approach. The non-LBD back-end techniques (literature-assisted discovery) make use of the human experts associated with the disparate literatures (disciplines) uncovered in the front-end to generate radical discovery and innovation. Specifically, in the literature-assisted discovery operational mode, these disparate discipline experts could be used as: 1. Recipients of solicitation announcements (BAA, SBIR, MURI, journal Special Issue calls for papers, etc.), 2. Participants in Workshops, Advisory Panels, Review Panels, Roadmaps, and War Games, 3. Points of Contact for Field Science Advisors, Foreign Field Offices, Program Officer site visits, and potential transitions.

Summary We present BITOLA, an interactive literature-based biomedical discovery support system. The goal of this system is to discover new, potentially meaningful relations between a given starting concept of interest and other concepts, by mining the bibliographic database MEDLINE ® . To make the system more suitable for disease candidate gene discovery and to decrease the number of candidate relations, we integrate background knowledge about the chromosomal location of the starting disease as well as the chromosomal location of the candidate genes from resources such as LocusLink and Human Genome Organization (HUGO). BITOLA can also be used as an alternative way of searching the MEDLINE database. The system is available at http://www.mf.uni-lj.si/bitola/.

The ever-growing literature in biomedicine makes it virtually impossible for individuals to grasp all the information relevant to their interests. Since even experts' knowledge is limited, important associations among key biomedical concepts may remain unnoticed in the flood of information. Discovering those hidden associations is called hypothesis discovery or literature-based discovery. This paper propose an approach to this problem taking advantage of a closed, triangular chain of relations extracted from the existing literature. We consider such chains of relations as implicit rules to generate explanatory hypotheses. The hypotheses generated from the implicit rules are then compared with newer knowledge for assessing their validity and, if validated, they are served as positive examples for learning a regression model to rank hypotheses. As a proof of concept, the proposed framework is empirically evaluated on real-world knowledge extracted from the biomedical literature. The results demonstrate that the framework is able to produce legitimate hypotheses and that the proposed ranking approach is more effective than the previous work.

Automated Literature Based Discovery (LBD) generates new knowledge by combining what is already known in literature. Facilitating large-scale hypothesis testing and generation from huge collections of literature, LBD could significantly support research in biomedical sciences. However, the uptake of LBD by the scientific community has been limited. One of the key reasons for this is the limited nature of existing LBD methodology. Based on fairly shallow methods, current LBD captures only some of the information available in literature. We discuss how advanced Text Mining based on Information retrieval, Natural Language Processing and data mining could open the doors to much deeper, wider coverage and dynamic LBD better capable of evolving with science, in particular when combined with sophisticated, state-of-the-art knowledge discovery techniques.

Previous research has shown that researchers can generate medical hypotheses by using computers to analyze several, seemingly unrelated, medical literatures. In this work we suggest broader application for the ideas of literature-based discovery. Specifically, we suggest that literature-based discovery can be fruitful in areas other than medicine; that in addition to finding "cures" for "problems," literature-based discovery offers the possibility of finding new problems for existing technologies; that the analysis of a single literature may be sufficient for literature-based discovery; and that literature-based discovery can support individuals seeking to draw together ideas from various areas of inquiry, even if such connections have been previously made by others.We describe literature-based discovery experiments conducted on the World Wide Web that support these ideas.

Literature-based discovery tools have been often used to overcome the problem of fragmentation of science and to assist researchers in their process of cross-domain knowledge discovery. In this paper we propose a methodology for cross-domain literature-based discovery that focuses on outlier documents to reduce the search space of potential cross-domain links and to improve search efficiency. In a previous study, literature mining tools OntoGen for document clustering and CrossBee for cross-domain bridging term exploration were combined to search for hidden relations in scientific papers from two different domains of interest, where the utility of the approach was demonstrated in a study involving PubMed papers about Alzheimer’s disease and gut microbiome. This paper extends the approach by proposing a methodology, implemented as a repeatable workflow in a web-based text mining platform TextFlows, which enables easy access and execution of the methodology for the interested researcher.

The rate at which biomedical literature is being published is quickly outpacing our ability to effectively leverage this information for evidence-based medicine. While papers are readily searchable through databases such as Pub Med, clinicians are often left with the time-consuming task of finding, assessing, interpreting, and applying this information. Tools that structure evidence from published papers using a standardized data model and provide an intuitive query interface for exploring documented biomedical entities would be valuable in utilizing this information as part of the clinical decision making process. This talk presents efforts towards developing computational tools and a representation for modeling and relating evidence from multiple clinical trial reports for lung cancer. Challenges related to representing this information in a machine-interpretable manner, assessing study quality, and handling conflicting evidence are described. I discuss the development of two tools: 1) an annotator tool used to extract information from papers, mapping it to concepts in an ontology-based representation and 2) a visualization that summarizes information about a single paper based on information captured in the model. Using lung cancer as a driving example, I demonstrate how these tools help users apply information reported in literature towards individually tailored medicine.