Search

Pharmacovigilance plays a crucial role in ensuring the safety of pharmaceutical products. It involves the systematic monitoring of adverse events and the detection of potential safety concerns related to drugs. Manual literature screening for pharmacovigilance related articles is a labor-intensive and time-consuming task, requiring streamlined solutions to cope with the continuous growth of literature. The primary objective of this study is to assess the performance of Large Language Models (LLMs) in automating literature screening for pharmacovigilance, aiming to enhance the process by identifying relevant articles more effectively. This study represents a novel application of LLMs including OpenAI's GPT-3.5, GPT-4, and Anthropic's Claude2, in the field of pharmacovigilance, evaluating their ability to categorize medical publications as relevant or irrelevant for safety signal reviews. Our analysis encompassed N-shot learning, chain-of-thought reasoning, and evaluating metrics, with a focus on factors impacting accuracy. The findings highlight the promising potential of LLMs in literature screening, achieving a reproducibility of 93%, sensitivity of 97%, and specificity of 67% showcasing notable strengths in terms of reproducibility and sensitivity, although with moderate specificity. Notably, performance improved when models were provided examples consisting of abstracts, labels, and corresponding reasoning explanations. Moreover, our exploration identified several potential contributing factors influencing prediction outcomes. These factors encompassed the choice of key words and prompts, the balance of the examples, and variations in reasoning explanations. By configuring advanced LLMs for efficient screening of extensive literature databases, this study underscores the transformative potential of these models in drug safety monitoring. Furthermore, these insights gained from this study can inform the development of automated systems for pharmacovigilance, contributing to the ongoing efforts to ensure the safety and efficacy of pharmacovigilance products. [ABSTRACT FROM AUTHOR]

Over the last few years Literature-based Discovery (LBD) has regained popularity as a means to enhance the scientific research process. The resurgent interest has spurred the development of supervised and semi-supervised machine learning models aimed at making previously implicit connections between scientific concepts/entities within often extensive bodies of literature explicit—i.e., suggesting novel scientific hypotheses. In doing so, understanding the temporally evolving interactions between these entities can provide valuable information for predicting the future development of entity relationships. However, existing methods often underutilize the latent information embedded in the temporal aspects of the interaction data. Motivated by applications in the food domain—where we aim to connect nutritional information with health-related benefits—we address the hypothesis-generation problem using a temporal graph-based approach. Given that hypothesis generation involves predicting future (i.e., still to be discovered) entity connections, in our view the ability to capture the dynamic evolution of connections over time is pivotal for a robust model. To address this, we introduce THiGER, a novel batch contrastive temporal node-pair embedding method. THiGER excels in providing a more expressive node-pair encoding by effectively harnessing node-pair relationships. Furthermore, we present THiGER-A, an incremental training approach that incorporates an active curriculum learning strategy to mitigate label bias arising from unobserved connections. By progressively training on increasingly challenging and high-utility samples, our approach significantly enhances the performance of the embedding model. Empirical validation of our proposed method demonstrates its effectiveness on established temporal-graph benchmark datasets, as well as on real-world datasets within the food domain. [ABSTRACT FROM AUTHOR]

Pharmacovigilance plays a crucial role in ensuring the safety of pharmaceutical products. It involves the systematic monitoring of adverse events and the detection of potential safety concerns related to drugs. Manual literature screening for pharmacovigilance related articles is a labor-intensive and time-consuming task, requiring streamlined solutions to cope with the continuous growth of literature. The primary objective of this study is to assess the performance of Large Language Models (LLMs) in automating literature screening for pharmacovigilance, aiming to enhance the process by identifying relevant articles more effectively. This study represents a novel application of LLMs including OpenAI's GPT-3.5, GPT-4, and Anthropic's Claude2, in the field of pharmacovigilance, evaluating their ability to categorize medical publications as relevant or irrelevant for safety signal reviews. Our analysis encompassed N-shot learning, chain-of-thought reasoning, and evaluating metrics, with a focus on factors impacting accuracy. The findings highlight the promising potential of LLMs in literature screening, achieving a reproducibility of 93%, sensitivity of 97%, and specificity of 67% showcasing notable strengths in terms of reproducibility and sensitivity, although with moderate specificity. Notably, performance improved when models were provided examples consisting of abstracts, labels, and corresponding reasoning explanations. Moreover, our exploration identified several potential contributing factors influencing prediction outcomes. These factors encompassed the choice of key words and prompts, the balance of the examples, and variations in reasoning explanations. By configuring advanced LLMs for efficient screening of extensive literature databases, this study underscores the transformative potential of these models in drug safety monitoring. Furthermore, these insights gained from this study can inform the development of automated systems for pharmacovigilance, contributing to the ongoing efforts to ensure the safety and efficacy of pharmacovigilance products. [ABSTRACT FROM AUTHOR]

Abstract Background Traditional literature based discovery is based on connecting knowledge pairs extracted from separate publications via a common mid point to derive previously unseen knowledge pairs. To avoid the over generation often associated with this approach, we explore an alternative method based on word evolution. Word evolution examines the changing contexts of a word to identify changes in its meaning or associations. We investigate the possibility of using changing word contexts to detect drugs suitable for repurposing. Results Word embeddings, which represent a word’s context, are constructed from chronologically ordered publications in MEDLINE at bi-monthly intervals, yielding a time series of word embeddings for each word. Focusing on clinical drugs only, any drugs repurposed in the final time segment of the time series are annotated as positive examples. The decision regarding the drug’s repurposing is based either on the Unified Medical Language System (UMLS), or semantic triples extracted using SemRep from MEDLINE. Conclusions The annotated data allows deep learning classification, with a 5-fold cross validation, to be performed and multiple architectures to be explored. Performance of 65% using UMLS labels, and 81% using SemRep labels is attained, indicating the technique’s suitability for the detection of candidate drugs for repurposing. The investigation also shows that different architectures are linked to the quantities of training data available and therefore that different models should be trained for every annotation approach.

Background: Traditional literature based discovery is based on connecting knowledge pairs extracted from separate publications via a common mid point to derive previously unseen knowledge pairs. To avoid the over generation often associated with this approach, we explore an alternative method based on word evolution. Word evolution examines the changing contexts of a word to identify changes in its meaning or associations. We investigate the possibility of using changing word contexts to detect drugs suitable for repurposing. Results: Word embeddings, which represent a word's context, are constructed from chronologically ordered publications in MEDLINE at bi-monthly intervals, yielding a time series of word embeddings for each word. Focusing on clinical drugs only, any drugs repurposed in the final time segment of the time series are annotated as positive examples. The decision regarding the drug's repurposing is based either on the Unified Medical Language System (UMLS), or semantic triples extracted using SemRep from MEDLINE. Conclusions: The annotated data allows deep learning classification, with a 5-fold cross validation, to be performed and multiple architectures to be explored. Performance of 65% using UMLS labels, and 81% using SemRep labels is attained, indicating the technique's suitability for the detection of candidate drugs for repurposing. The investigation also shows that different architectures are linked to the quantities of training data available and therefore that different models should be trained for every annotation approach. [ABSTRACT FROM AUTHOR]

Abstract Background Automatic literature based discovery attempts to uncover new knowledge by connecting existing facts: information extracted from existing publications in the form of $$A \rightarrow B$$ A → B and $$B \rightarrow C$$ B → C relations can be simply connected to deduce $$A \rightarrow C$$ A → C . However, using this approach, the quantity of proposed connections is often too vast to be useful. It can be reduced by using subject $$\rightarrow$$ → (predicate) $$\rightarrow$$ → object triples as the $$A \rightarrow B$$ A → B relations, but too many proposed connections remain for manual verification. Results Based on the hypothesis that only a small number of subject–predicate–object triples extracted from a publication represent the paper’s novel contribution(s), we explore using BERT embeddings to identify these before literature based discovery is performed utilizing only these, important, triples. While the method exploits the availability of full texts of publications in the CORD-19 dataset—making use of the fact that a novel contribution is likely to be mentioned in both an abstract and the body of a paper—to build a training set, the resulting tool can be applied to papers with only abstracts available. Candidate hidden knowledge pairs generated from unfiltered triples and those built from important triples only are compared using a variety of timeslicing gold standards. Conclusions The quantity of proposed knowledge pairs is reduced by a factor of $$10^3$$ 10 3 , and we show that when the gold standard is designed to avoid rewarding background knowledge, the precision obtained increases up to a factor of 10. We argue that the gold standard needs to be carefully considered, and release as yet undiscovered candidate knowledge pairs based on important triples alongside this work.

We present an automated knowledge synthesis and discovery framework to analyze published literature to identify and represent underlying mechanistic associations that aggravate chronic conditions due to COVID-19. Our literature-based discovery approach integrates text mining, knowledge graphs and medical ontologies to discover hidden and previously unknown pathophysiologic relations, dispersed across multiple public literature databases, between COVID-19 and chronic disease mechanisms. We applied our approach to discover mechanistic associations between COVID-19 and chronic conditions--i.e. diabetes mellitus and chronic kidney disease--to understand the long-term impact of COVID-19 on patients with chronic diseases. We found several gene-disease associations that could help identify mechanisms driving poor outcomes for COVID-19 patients with underlying conditions. [ABSTRACT FROM AUTHOR]

Abstract Background Literature Based Discovery (LBD) produces more potential hypotheses than can be manually reviewed, making automatically ranking these hypotheses critical. In this paper, we introduce the indirect association measures of Linking Term Association (LTA), Minimum Weight Association (MWA), and Shared B to C Set Association (SBC), and compare them to Linking Set Association (LSA), concept embeddings vector cosine, Linking Term Count (LTC), and direct co-occurrence vector cosine. Our proposed indirect association measures extend traditional association measures to quantify indirect rather than direct associations while preserving valuable statistical properties. Results We perform a comparison between several different hypothesis ranking methods for LBD, and compare them against our proposed indirect association measures. We intrinsically evaluate each method’s performance using its ability to estimate semantic relatedness on standard evaluation datasets. We extrinsically evaluate each method’s ability to rank hypotheses in LBD using a time-slicing dataset based on co-occurrence information, and another time-slicing dataset based on SemRep extracted-relationships. Precision and recall curves are generated by ranking term pairs and applying a threshold at each rank. Conclusions Results differ depending on the evaluation methods and datasets, but it is unclear if this is a result of biases in the evaluation datasets or if one method is truly better than another. We conclude that LTC and SBC are the best suited methods for hypothesis ranking in LBD, but there is value in having a variety of methods to choose from.

Abstract Background The quantity of documents being published requires researchers to specialize to a narrower field, meaning that inferable connections between publications (particularly from different domains) can be missed. This has given rise to automatic literature based discovery (LBD). However, unless heavily filtered, LBD generates more potential new knowledge than can be manually verified and another form of selection is required before the results can be passed onto a user. Since a large proportion of the automatically generated hidden knowledge is valid but generally known, we investigate the hypothesis that non trivial, interesting, hidden knowledge can be treated as an anomaly and identified using anomaly detection approaches. Results Two experiments are conducted: (1) to avoid errors arising from incorrect extraction of relations, the hypothesis is validated using manually annotated relations appearing in a thesaurus, and (2) automatically extracted relations are used to investigate the hypothesis on publication abstracts. These allow an investigation of a potential upper bound and the detection of limitations yielded by automatic relation extraction. Conclusion We apply one-class SVM and isolation forest anomaly detection algorithms to a set of hidden connections to rank connections by identifying outlying (interesting) ones and show that the approach increases the F 1 measure by a factor of 10 while greatly reducing the quantity of hidden knowledge to manually verify. We also demonstrate the statistical significance of this result.

In this paper, we describe how we applied LBD techniques to discover lecithin cholesterol acyltransferase (LCAT) as a druggable target for cardiac arrest. We fully describe our process which includes the use of high-throughput metabolomic analysis to identify metabolites significantly related to cardiac arrest, and how we used LBD to gain insights into how these metabolites relate to cardiac arrest. These insights lead to our proposal (for the first time) of LCAT as a druggable target; the effects of which are supported by in vivo studies which were brought forth by this work. Metabolites are the end product of many biochemical pathways within the human body. Observed changes in metabolite levels are indicative of changes in these pathways, and provide valuable insights toward the cause, progression, and treatment of diseases. Following cardiac arrest, we observed changes in metabolite levels pre- and post-resuscitation. We used LBD to help discover diseases implicitly linked via these metabolites of interest. Results of LBD indicated a strong link between Fish Eye disease and cardiac arrest. Since fish eye disease is characterized by an LCAT deficiency, it began an investigation into the effects of LCAT and cardiac arrest survival. In the investigation, we found that decreased LCAT activity may increase cardiac arrest survival rates by increasing ω-3 polyunsaturated fatty acid availability in circulation. We verified the effects of ω-3 polyunsaturated fatty acids on increasing survival rate following cardiac arrest via in vivo with rat models.

BackgroundJournal editors have exercised their control over submitted papers having a high similarity index. Despite widespread suspicion of possible plagiarism on a high similarity index, our study focused on the real effect of the similarity index on the value of a scientific paper.MethodsThis research examined the percent values of the similarity index from 978 submitted (420 published) papers in the Korean Journal of Anesthesiology since 2012. Thus, this study aimed to identify the correlation between the similarity index and the value of a paper. The value of a paper was evaluated in two distinct phases (during a peer-review process vs. after publication), and the value of a published paper was evaluated in two aspects (academic citation vs. social media appearance).ResultsYearly mean values of the similarity index ranged from 16% to 19%. There were 254 papers cited at least once and 179 papers appearing at least once in social media. The similarity index affected the acceptance/rejection of a paper in various ways; although the influence was not linear and the cutoff measures were distinctive among the types of papers, both extremes were related to a high rate of rejection. After publication, the similarity index had no effect on academic citation or social media appearance according to the paper.ConclusionsThe finding suggested that the similarity index no longer had an influence on academic citation or social media appearance according to the paper after publication, while the similarity index affected the acceptance/rejection of a submitted paper. Proofreading and intervention for finalizing the draft by the editors might play a role in achieving uniform quality of the publication.

Literature-Based Discovery (LBD) aims to connect scientists across silos by assembling models of the literature to reveal previously hidden connections. Unfortunately, LBD systems have been unable to achieve user adoption on a large scale. This work develops opens source software in Python to convert a database of semantic predications of all of PubMed's 27.9 million indexed abstracts into a semantic inference network and biomedical concept graph in Neo4j. The developed software, called SemNet, queries a modified version of the publicly available SemMedDB and computes feature vectors on source-target pairs. Each unique United Medical Language System (UMLS) concept is represented as a node and each predication as an edge. Each node is assigned one of 132 node labels (e.g., Amino Acid, Peptide, or Protein (AAPP); Gene or Genome (GG); etc.) and each edge is labeled with one of 58 predications (e.g. treats, causes, inhibits, etc.). SemNet computes a single feature value for each metapath, or sequence of node types, between a source node and user-specified target node(s). Several different types of metapath-based features (count, degree weighted path count, and HeteSim metric) are computed and vectorized. SemNet employs an unsupervised learning algorithm for rank aggregation (ULARA) to rank identified source nodes that are most relevant to the user-specified target nodes(s). Statistical analysis of correlation among identified source nodes or resultant literature network features are used to identify patterns that can guide future research. Analysis of high residual nodes is used to compare and contrast SemNet rankings between different targets of interest. An example SemNet use case is presented to assess “the differential impact of smoking on cognition in males and females” using the following target nodes: nicotine, learning, memory, tetrahydrocannabinol (THC), cigarette smoke, X chromosome, and Y chromosome. Detailed rankings are discussed. Overall results suggest a hypothesis where smoking negatively impacts cognition to a greater extent in females, but smoking has stronger cardiovascular impacts in males. In summary, SemNet provides an adoptable method for efficient LBD of PubMed that extends beyond omics-only relationships to true multi-scalar connections that can provide actionable insight for predictive medicine, research prioritization, and clinical care.

Highlights from the article: No wonder that a search of Clinicaltrials.gov (carried out in April 2019) shows 152 trials of ketamine in depression, and 38 trials that involve various antidepressants in Alzheimer patients, but no registered trials that involve giving ketamine to Alzheimer patients. However, in most studies, the molecular effects of ketamine which are associated with antidepressant activity are not produced by memantine (Gideons et al., [10]), and indeed, memantine has failed to produce rapid antidepressant effects in human clinical trials of depression (Kishi et al., [16]). However, the antidepressant effects of (2 I R i ,6 I R i )-HNK were not accompanied by NMDA receptor-dependent side effects, suggesting that ketamine metabolites may provide a safer means for treating depressed patients - and by implication, a safer venue for testing procognitive effects in Alzheimer patients. Comparison of antidepressant and side effects in mice after intranasal administration of (R,S)-ketamine, (R)-ketamine, and (S)-ketamine.

Background: The quantity of documents being published requires researchers to specialize to a narrower field, meaning that inferable connections between publications (particularly from different domains) can be missed. This has given rise to automatic literature based discovery (LBD). However, unless heavily filtered, LBD generates more potential new knowledge than can be manually verified and another form of selection is required before the results can be passed onto a user. Since a large proportion of the automatically generated hidden knowledge is valid but generally known, we investigate the hypothesis that non trivial, interesting, hidden knowledge can be treated as an anomaly and identified using anomaly detection approaches. Results: Two experiments are conducted: (1) to avoid errors arising from incorrect extraction of relations, the hypothesis is validated using manually annotated relations appearing in a thesaurus, and (2) automatically extracted relations are used to investigate the hypothesis on publication abstracts. These allow an investigation of a potential upper bound and the detection of limitations yielded by automatic relation extraction. Conclusion: We apply one-class SVM and isolation forest anomaly detection algorithms to a set of hidden connections to rank connections by identifying outlying (interesting) ones and show that the approach increases the F1 measure by a factor of 10 while greatly reducing the quantity of hidden knowledge to manually verify. We also demonstrate the statistical significance of this result. [ABSTRACT FROM AUTHOR]

Background Citations of papers are positively influenced by the journal’s impact factor (IF). For non-open access (non-OA) journals, this influence may be due to the fact that high-IF journals are more often purchased by libraries, and are therefore more often available to researchers, than low-IF journals. This positive influence has not, however, been shown specifically for papers published in open access (OA) journals, which are universally accessible, and do not need library purchase. It is therefore important to ascertain if the IF influences citations in OA journals too. Methods 203 randomized controlled trials (102 OA and 101 non-OA) published in January 2011 were included in the study. Five-year citations for papers published in OA journals were compared to those for non-OA journals. Source papers were derived from PubMed. Citations were retrieved from Web of Science, Scopus, and Google Scholar databases. The Thompson-Reuter’s IF was used. Results OA journals were found to have significantly more citations overall compared to non-OA journals (median 15.5 vs 12, p=0.039). The IF did not correlate with citations for OA journals (Spearman’s rho =0.187, p=0.60). The increase in the citations with increasing IF was minimal for OA journals (beta coefficient = 3.346, 95% CI -0.464, 7.156, p=0.084). In contrast, the IF did show moderate correlation with citations for articles published in non-OA journals (Spearman’s rho=0.514, p Conclusion It is better to publish in an OA journal for more citations. It may not be worth paying high publishing fees for higher IF journals, because there is minimal gain in terms of increased number of citations. On the other hand, if one wishes to publish in a non-OA journal, it is better to choose one with a high IF.

Objective. To determine the level of stability or change in topic areas published by public health journals in Latin America and the Caribbean, using keywords and co-word analysis, in order to support evidence-based research planning. Methods. Keywords were extracted from papers indexed in Scopus® that were published by the Revista de Salud Pública (RSP; Colombia), the Salud Pública de México (SPM; Mexico), and the Revista Peruana de Medicina Experimental y Salud Pública (RPMESP; Peru) for three periods: 2005 - 2007, 2008 - 2010, and 2011 - 2013. Co-word analysis was used to examine keywords extracted. Textual information was analyzed using centrality measures (inbetweenness and closeness). The hypothesis of stability/change of thematic coverage was tested using the Spearman's rho correlation coefficient. VOSviewer was used to visualize the co-word maps. Results. A moderate level of change in thematic coverage was observed in 2005 -- 2010, as evidenced by the correlation coefficients for two of the 3-year periods, 2005 -- 2007 and 2008 -- 2010: 0.545 for RSP and 0.593 for SPM. However, in 2008 -- 2013, more keywords remained constant from one period to the next, given the size of the correlation coefficients for the last 3-year periods: 2008 -- 2010 and 2011 -- 2013: 0.727 for RSP and 0.605 for SPM. Conclusion. The research hypothesis was partially accepted given that just two consecutive 3-year periods showed a statistically-significant degree of stability in thematic coverage in public health studies. In that sense, this study provides compelling evidence of the effectiveness of using a combined approach for examining the dynamics of thematic coverage: centrality measures for identifying the main keywords and visual inspection for detecting the structure of textual information. [ABSTRACT FROM AUTHOR]

Objective: The aim of this work is to leverage relational information extracted from biomedical literature using a novel synthesis of unsupervised pretraining, representational composition, and supervised machine learning for drug safety monitoring.Methods: Using ≈80 million concept-relationship-concept triples extracted from the literature using the SemRep Natural Language Processing system, distributed vector representations (embeddings) were generated for concepts as functions of their relationships utilizing two unsupervised representational approaches. Embeddings for drugs and side effects of interest from two widely used reference standards were then composed to generate embeddings of drug/side-effect pairs, which were used as input for supervised machine learning. This methodology was developed and evaluated using cross-validation strategies and compared to contemporary approaches. To qualitatively assess generalization, models trained on the Observational Medical Outcomes Partnership (OMOP) drug/side-effect reference set were evaluated against a list of ≈1100 drugs from an online database.Results: The employed method improved performance over previous approaches. Cross-validation results advance the state of the art (AUC 0.96; F1 0.90 and AUC 0.95; F1 0.84 across the two sets), outperforming methods utilizing literature and/or spontaneous reporting system data. Examination of predictions for unseen drug/side-effect pairs indicates the ability of these methods to generalize, with over tenfold label support enrichment in the top 100 predictions versus the bottom 100 predictions.Discussion and Conclusion: Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples. [ABSTRACT FROM AUTHOR]

Given the occurrence frequency of any term within any set of articles within MEDLINE, we define “characteristic” terms as words and phrases that occur in that literature more frequently than expected by chance (at p < 0.001 or better). In this report, we studied how the cut-off criterion varied as a function of literature size and term frequency in MEDLINE as a whole, and have compared the distribution of characteristic terms within a number of journal-defined, affiliation-defined and random literatures. We also investigated how the characteristic terms were distributed among MEDLINE titles, abstracts, and last sentence of abstracts, including “regularized” terms that appear both in the title and abstract of the same paper for at least one paper in the literature. For a set of 10 disciplinary journals, the characteristic terms comprised 18% of the total terms on average. Characteristic terms are utilized in several of our web-based services (Anne O’Tate and Arrowsmith), and should be useful for a variety of other information-processing tasks designed to improve text mining in MEDLINE.

Background: The volume of research published in the biomedical domain has increasingly lead to researchers focussing on specific areas of interest and connections between findings being missed. Literature based discovery (LBD) attempts to address this problem by searching for previously unnoticed connections between published information (also known as "hidden knowledge"). A common approach is to identify hidden knowledge via shared linking terms. However, biomedical documents are highly ambiguous which can lead LBD systems to over generate hidden knowledge by hypothesising connections through different meanings of linking terms. Word Sense Disambiguation (WSD) aims to resolve ambiguities in text by identifying the meaning of ambiguous terms. This study explores the effect of WSD accuracy on LBD performance.Methods: An existing LBD system is employed and four approaches to WSD of biomedical documents integrated with it. The accuracy of each WSD approach is determined by comparing its output against a standard benchmark. Evaluation of the LBD output is carried out using timeslicing approach, where hidden knowledge is generated from articles published prior to a certain cutoff date and a gold standard extracted from publications after the cutoff date.Results: WSD accuracy varies depending on the approach used. The connection between the performance of the LBD and WSD systems are analysed to reveal a correlation between WSD accuracy and LBD performance.Conclusion: This study reveals that LBD performance is sensitive to WSD accuracy. It is therefore concluded that WSD has the potential to improve the output of LBD systems by reducing the amount of spurious hidden knowledge that is generated. It is also suggested that further improvements in WSD accuracy have the potential to improve LBD accuracy. [ABSTRACT FROM AUTHOR]

Background: Automatic literature based discovery attempts to uncover new knowledge by connecting existing facts: information extracted from existing publications in the form of [Formula: see text] and [Formula: see text] relations can be simply connected to deduce [Formula: see text]. However, using this approach, the quantity of proposed connections is often too vast to be useful. It can be reduced by using subject[Formula: see text](predicate)[Formula: see text]object triples as the [Formula: see text] relations, but too many proposed connections remain for manual verification., Results: Based on the hypothesis that only a small number of subject-predicate-object triples extracted from a publication represent the paper's novel contribution(s), we explore using BERT embeddings to identify these before literature based discovery is performed utilizing only these, important, triples. While the method exploits the availability of full texts of publications in the CORD-19 dataset-making use of the fact that a novel contribution is likely to be mentioned in both an abstract and the body of a paper-to build a training set, the resulting tool can be applied to papers with only abstracts available. Candidate hidden knowledge pairs generated from unfiltered triples and those built from important triples only are compared using a variety of timeslicing gold standards., Conclusions: The quantity of proposed knowledge pairs is reduced by a factor of [Formula: see text], and we show that when the gold standard is designed to avoid rewarding background knowledge, the precision obtained increases up to a factor of 10. We argue that the gold standard needs to be carefully considered, and release as yet undiscovered candidate knowledge pairs based on important triples alongside this work., (© 2023. The Author(s).)

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. [ABSTRACT FROM AUTHOR]

Objective: Literature-based discovery (LBD) aims to identify "hidden knowledge" in the medical literature by: (1) analyzing documents to identify pairs of explicitly related concepts (terms), then (2) hypothesizing novel relations between pairs of unrelated concepts that are implicitly related via a shared concept to which both are explicitly related. Many LBD approaches use simple techniques to identify semantically weak relations between concepts, for example, document co-occurrence. These generate huge numbers of hypotheses, difficult for humans to assess. More complex techniques rely on linguistic analysis, for example, shallow parsing, to identify semantically stronger relations. Such approaches generate fewer hypotheses, but may miss hidden knowledge. The authors investigate this trade-off in detail, comparing techniques for identifying related concepts to discover which are most suitable for LBD. Materials and methods: A generic LBD system that can utilize a range of relation types was developed. Experiments were carried out comparing a number of techniques for identifying relations. Two approaches were used for evaluation: replication of existing discoveries and the "time slicing" approach. Results: Previous LBD discoveries could be replicated using relations based either on document co-occurrence or linguistic analysis. Using relations based on linguistic analysis generated many fewer hypotheses, but a significantly greater proportion of them were candidates for hidden knowledge. Discussion and Conclusion: The use of linguistic analysis-based relations improves accuracy of LBD without overly damaging coverage. LBD systems often generate huge numbers of hypotheses, which are infeasible to manually review. Improving their accuracy has the potential to make these systems significantly more usable. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The present paper tries to show that the current state of the art in syntactics and semantics, in computer systems based on the theory of inventive problem solving known as TRIZ, may help in the task of literature based discovery. With a structured and logic cause linkage between concepts, LBD could be faster and with less expert involvement at the beginning of the LBD process. The author tries to demonstrate the concept with two different problems: the hearing and balance problem known as Meniere's disease, and to some of the current problems in the lithium air batteries for electric vehicles. By using open literature based discovery from An to Bn and from Bn to Cn, and with the logic relationships of real causes and effects approach, the author finds several relative new concepts such as vitamin A. Other concepts as niacin or fish oil, are also found, as potential to help in the Meniere's disease. Secondly, using such procedure the author is able to find patents from disparate domain of expertise, as patents about odor control or metal casting. [ABSTRACT FROM AUTHOR]

Highlights: [•] Knowledge-based functional enrichment for gene prioritization of high throughput data. [•] Automatic ontology generation from MEDLINE. [•] Novel and fully automatic literature-based discovery. [•] Literature ontologies perform better than expert-derived ones. [ABSTRACT FROM AUTHOR]

Copyright of Perspectivas em Ciência da Informaçao is the property of Nova Economia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The major outcomes and insights of scientific research and clinical study end up in the form of publication or clinical record in an unstructured text format. Due to advancements in biomedical research, the growth of published literature is getting tremendous large in recent years. The scientists and clinical researchers are facing a big challenge to stay current with the knowledge and to extract hidden information from this sheer quantity of millions of published biomedical literature. The potential one-stop automated solution to this problem is biomedical literature mining. One of the long-standing goals in biology is to discover the disease-causing genes and their specific roles in personalized precision medicine and drug repurposing. However, the empirical approaches and clinical affirmation are expensive and time-consuming. In silico approach using text mining to identify the disease causing genes can contribute towards biomarker discovery. This chapter presents a protocol on combining literature mining and machine learning for predicting biomedical discoveries with a special emphasis on gene-disease relation based discovery. The protocol is presented as a literature based discovery (LBD) pipeline for gene-disease based discovery. The protocol includes our web based tools: (1) DNER (Disease Named Entity Recognizer) for disease entity recognition, (2) BCCNER (Bidirectional, Contextual clues Named Entity Tagger) for gene/protein entity recognition, (3) DisGeReExT (Disease-Gene Relation Extractor) for statistically validated results and visualization, and (4) a newly introduced deep learning based method for association discovery. Our proposed deep learning based method can be generalized and applied to other important biomedical discoveries focusing on entities such as drug/chemical, or miRNA., (© 2022. The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature.)

In this paper, we describe how we applied LBD techniques to discover lecithin cholesterol acyltransferase (LCAT) as a druggable target for cardiac arrest. We fully describe our process which includes the use of high-throughput metabolomic analysis to identify metabolites significantly related to cardiac arrest, and how we used LBD to gain insights into how these metabolites relate to cardiac arrest. These insights lead to our proposal (for the first time) of LCAT as a druggable target; the effects of which are supported by in vivo studies which were brought forth by this work. Metabolites are the end product of many biochemical pathways within the human body. Observed changes in metabolite levels are indicative of changes in these pathways, and provide valuable insights toward the cause, progression, and treatment of diseases. Following cardiac arrest, we observed changes in metabolite levels pre- and post-resuscitation. We used LBD to help discover diseases implicitly linked via these metabolites of interest. Results of LBD indicated a strong link between Fish Eye disease and cardiac arrest. Since fish eye disease is characterized by an LCAT deficiency, it began an investigation into the effects of LCAT and cardiac arrest survival. In the investigation, we found that decreased LCAT activity may increase cardiac arrest survival rates by increasing ω -3 polyunsaturated fatty acid availability in circulation. We verified the effects of ω -3 polyunsaturated fatty acids on increasing survival rate following cardiac arrest via in vivo with rat models., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Henry, Wijesinghe, Myers and McInnes.)

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. [ABSTRACT FROM AUTHOR]

Clinical paper searching is a major task for clinical researchers to collect authoritative and up-to-date evidences to support their research works and clinical practices. Currently, this task needs huge amount of labor work. Researchers usually spend a lot of time searching on the online repository and iterating many times to get the final paper list. Systematic review is a special case, in which the paper searching process is a critical step. To address this challenge, this paper introduces a method to streamline the iterative paper searching process. It automatically selects the most probably matched papers, and then generates new search strategy. All the intermediate results are visualized based on the paper citation graph. It assembles technologies such as PageRank and Topic-based clustering to accelerate the paper searching tasks. The precision, recall, and execution time of the proposed method are then evaluated by comparing with published systematic reviews.

Literature-Based Discovery (LBD) aims to connect scientists across silos by assembling models of the literature to reveal previously hidden connections. Unfortunately, LBD systems have been unable to achieve user adoption on a large scale. This work develops opens source software in Python to convert a database of semantic predications of all of PubMed's 27.9 million indexed abstracts into a semantic inference network and biomedical concept graph in Neo4j. The developed software, called SemNet, queries a modified version of the publicly available SemMedDB and computes feature vectors on source-target pairs. Each unique United Medical Language System (UMLS) concept is represented as a node and each predication as an edge. Each node is assigned one of 132 node labels (e.g., Amino Acid, Peptide, or Protein (AAPP); Gene or Genome (GG); etc.) and each edge is labeled with one of 58 predications (e.g. treats, causes, inhibits, etc.). SemNet computes a single feature value for each metapath, or sequence of node types, between a source node and user-specified target node(s). Several different types of metapath-based features (count, degree weighted path count, and HeteSim metric) are computed and vectorized. SemNet employs an unsupervised learning algorithm for rank aggregation (ULARA) to rank identified source nodes that are most relevant to the user-specified target nodes(s). Statistical analysis of correlation among identified source nodes or resultant literature network features are used to identify patterns that can guide future research. Analysis of high residual nodes is used to compare and contrast SemNet rankings between different targets of interest. An example SemNet use case is presented to assess "the differential impact of smoking on cognition in males and females" using the following target nodes: nicotine, learning, memory, tetrahydrocannabinol (THC), cigarette smoke, X chromosome, and Y chromosome. Detailed rankings are discussed. Overall results suggest a hypothesis where smoking negatively impacts cognition to a greater extent in females, but smoking has stronger cardiovascular impacts in males. In summary, SemNet provides an adoptable method for efficient LBD of PubMed that extends beyond omics-only relationships to true multi-scalar connections that can provide actionable insight for predictive medicine, research prioritization, and clinical care.

A mineração de textos vem sendo, cada vez mais, empregada para automatizar o processo de extração de informações importantes, contidas em textos biomédicos, possibilitando que os pesquisadores fiquem a par do desenvolvimento da biomedicina. Considerando a importância deste campo de pesquisa, este artigo apresenta um mapeamento das publicações científicas sobre mineração de textos biomédicos e discute as principais tarefas desse campo de pesquisa, as quais os pesquisadores têm dedicado maior atenção. Para isso, foi utilizada a bibliometria, uma técnica que permite analisar o desenvolvimento de um campo da ciência, visando identificar suas características. O mapeamento apresentado promove o conhecimento sobre o histórico e o estado atual do campo de pesquisa e disponibiliza insumos, que permitem enriquecer a discussão sobre os possíveis rumos que as pesquisas, na área, têm tomado e as prováveis tendências científicas para os pesquisadores e interessados no tema.