Clustering cliques for graph-based summarization of the biomedical research literature

Zhang, Han; Fiszman, Marcelo; Shin, Dongwook; Wilkowski, Bartłomiej; Rindflesch, Thomas C.

doi:10.1186/1471-2105-14-182

Cited by 19 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach creates an n-ary similarity tree in which 7 new p53 kinases were discovered, which could revolutionize Cancer treatments. The approach for clustering of cliques developed by Zhang et al [ 49 , 50 ] may be used to capture subgraphs on multiple thematic dimensions. However, the approach is based on degree centrality and is therefore more likely to create subgraphs that only consist of highly connected concepts from the literature.…”

Section: Related Workmentioning

confidence: 99%

Context-driven automatic subgraph creation for literature-based discovery

Cameron

Kavuluru

Rindflesch

et al. 2015

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Background Literature-based discovery (LBD) is characterized by uncovering hidden associations in non-interacting scientific literature. Prior approaches to LBD include use of: 1) domain expertise and structured background knowledge to manually filter and explore the literature, 2) distributional statistics and graph-theoretic measures to rank interesting connections, and 3) heuristics to help eliminate spurious connections. However, manual approaches to LBD are not scalable and purely distributional approaches may not be sufficient to obtain insights into the meaning of poorly understood associations. While several graph-based approaches have the potential to elucidate associations, their effectiveness has not been fully demonstrated. A considerable degree of a priori knowledge, heuristics, and manual filtering is still required. Objectives In this paper we implement and evaluate a context-driven, automatic subgraph creation method that captures multifaceted complex associations between biomedical concepts to facilitate LBD. Given a pair of concepts, our method automatically generates a ranked list of subgraphs, which provide informative and potentially unknown associations between such concepts. Methods To generate subgraphs, the set of all MEDLINE articles that contain either of the two specified concepts (A, C) are first collected. Then binary relationships or assertions, which are automatically extracted from the MEDLINE articles, called semantic predications, are used to create a labeled directed predications graph. In this predications graph, a path is represented as a sequence of semantic predications. The hierarchical agglomerative clustering (HAC) algorithm is then applied to cluster paths that are bounded by the two concepts (A, C). HAC relies on implicit semantics captured through Medical Subject Heading (MeSH) descriptors, and explicit semantics from the MeSH hierarchy, for clustering. Paths that exceed a threshold of semantic relatedness are clustered into subgraphs based on their shared context. Finally, the automatically generated clusters are provided as a ranked list of subgraphs. Results The subgraphs generated using this approach facilitated the rediscovery of 8 out of 9 existing scientific discoveries. In particular, they directly (or indirectly) led to the recovery of several intermediates (or B-concepts) between A- and C-terms, while also providing insights into the meaning of the associations. Such meaning is derived from predicates between the concepts, as well as the provenance of the semantic predications in MEDLINE. Additionally, by generating subgraphs on different thematic dimensions (such as Cellular Activity, Pharmaceutical Treatment and Tissue Function), the approach may enable a broader understanding of the nature of complex associations between concepts. Finally, in a statistical evaluation to determine the interestingness of the subgraphs, it was observed that an arbitrary association is mentioned in only approximately 4 articles in MEDLINE on average. Conclusion Thes...

show abstract

Section: Related Workmentioning

confidence: 99%

Context-driven automatic subgraph creation for literature-based discovery

Cameron

Kavuluru

Rindflesch

et al. 2015

Journal of Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…Multi-document summarization aims at extracting principle information from a given collection of documents about one topic. Commonly used methods are centroid-based [1], graph-based [2] and knowledge-based [3]. Other algorithms such as non-negative matrix factorization (NMF) and latent semantic analysis (LSA) are also adopted to convert the selected sentence into the summarization.…”

Section: Related Work a Multi-document Summarizationmentioning

confidence: 99%

Generating Multimedia Storyline for Effective Disaster Information Awareness

Yuan

Zhou

2019

IEEE Access

View full text Add to dashboard Cite

Storyline generation has emerged to be an effective method to describe the evolution of disaster. However, due to the temporal-spatial, heterogeneous, and information overload, most of the existing storylines are only based on textual data and deliver limited information. In this paper, we introduce a novel framework for generating multimedia storylines to provide more concise and vivid information and deeper understanding of real-time events. We first adopt generative adversarial networks to implement an unsupervised bilingual document summarizing model. Then, we transform image and text incorporation problem into a multi-label learning problem and use convolutional neural networks to train a classification model. And finally, the bilingual documents and images are jointly summarized and embedded into a two-layer storyline generating framework. The experiments on real Hurricane data sets demonstrate the effectiveness of the proposed methods in each level and the overall framework.INDEX TERMS Storyline, disaster management, generative adversarial networks, convolutional neural networks.

show abstract

“…[16, 17] Finally, popular graph-based approaches, such as TextRank, use graph algorithms to compute the similarity between a topic and sentences as well as among sentences themselves. [18–22]…”

Section: Background and Significancementioning

confidence: 99%

Classification of clinically useful sentences in clinical evidence resources

Morid

Fiszman

Raja

et al. 2016

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

Most patient care questions raised by clinicians can be answered by online clinical knowledge resources. However, important barriers still challenge the use of these resources at the point of care. Objective To design and assess a method for extracting clinically useful sentences from synthesized online clinical resources that represent the most clinically useful information for directly answering clinicians’ information needs. Materials and methods We developed a Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents. These features included UMLS concepts and their semantic groups, semantic predications extracted by SemRep, patient population identified by a pattern-based natural language processing (NLP) algorithm, and cue words extracted by a feature selection technique. Algorithm performance was measured in terms of precision, recall, and F-measure. Results The feature-rich approach yielded an F-measure of 74% versus 37% for a feature co-occurrence method (p<0.001). Excluding predication, population, semantic concept or text-based features reduced the F-measure to 62%, 66%, 58% and 69% respectively (p<0.01). The classifier applied to Medline sentences reached an F-measure of 73%, which is equivalent to the performance of the classifier on UpToDate sentences (p=0.62). Conclusions The feature-rich approach significantly outperformed general baseline methods. This approach significantly outperformed classifiers based on a single type of feature. Different types of semantic features provided a unique contribution to overall classification performance. The classifier’s model and features used for UpToDate generalized well to Medline abstracts.

show abstract

Clustering cliques for graph-based summarization of the biomedical research literature

Cited by 19 publications

References 39 publications

Context-driven automatic subgraph creation for literature-based discovery

Context-driven automatic subgraph creation for literature-based discovery

Generating Multimedia Storyline for Effective Disaster Information Awareness

Classification of clinically useful sentences in clinical evidence resources

Contact Info

Product

Resources

About