Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Texts

Noriega-Atala, Enrique; Hein, Paul D.; Thumsi, Shraddha Satish; Wong, Zechy; Wang, Xia; Hendryx, Sean M.; Morrison, Clayton T.

doi:10.1109/tcbb.2019.2904231

Cited by 9 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use a cross validation evaluation framework similar to the evaluation methodology used by (Noriega-Atala et al 2020). Each fold contains all of the event-context pairs that belong to three different articles.…”

Section: Resultsmentioning

confidence: 99%

“…We used a corpus of biochemical events annotated with biological context to test the neural architectures for context assignment. Our version of the corpus is an extension of the corpus published by (Noriega-Atala et al 2020).…”

Section: Full-text Context-event Relation Corpusmentioning

confidence: 99%

“…The result is a set of annotated events, where each event can have zero or more biological context associations, and there is at least one explicit mention for each biological context in the same article. The specifics of the automated event extraction procedure, annotation tool, annotations protocols and inter-annotator agreements are thoroughly detailed in (Noriega-Atala et al 2020). Table 2 contains summary statistics of the data set's documents.…”

Section: Full-text Context-event Relation Corpusmentioning

confidence: 99%

See 2 more Smart Citations

Neural Architectures for Biological Inter-Sentence Relation Extraction

Noriega-Atala¹,

Lovett²,

Morrison³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We introduce a family of deep-learning architectures for inter-sentence relation extraction, i.e., relations where the participants are not necessarily in the same sentence. We apply these architectures to an important use case in the biomedical domain: assigning biological context to biochemical events. In this work, biological context is defined as the type of biological system within which the biochemical event is observed. The neural architectures encode and aggregate multiple occurrences of the same candidate context mentions to determine whether it is the correct context for a particular event mention. We propose two broad types of architectures: the first type aggregates multiple instances that correspond to the same candidate context with respect to event mention before emitting a classification; the second type independently classifies each instance and uses the results to vote for the final class, akin to an ensemble approach. Our experiments show that the proposed neural classifiers are competitive and some achieve better performance than previous state of the art traditional machine learning methods without the need for feature engineering. Our analysis shows that the neural methods particularly improve precision compared to traditional machine learning classifiers and also demonstrates how the difficulty of inter-sentence relation extraction increases as the distance between the event and context mentions increase.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Full-text Context-event Relation Corpusmentioning

confidence: 99%

Section: Full-text Context-event Relation Corpusmentioning

confidence: 99%

See 1 more Smart Citation

Neural Architectures for Biological Inter-Sentence Relation Extraction

Noriega-Atala¹,

Lovett²,

Morrison³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Semantic and syntactic features were extracted about annotated contextual mentions such as species or cell line and about the sentences from which KG predications were extracted. These derived features were used in a supervised framework of associating predications to relevant contextual mentions in the same paper [ 89 ].…”

Section: Adjudicating Apparent Contradictions With Contextmentioning

confidence: 99%

Contexts and contradictions: a roadmap for computational drug repurposing with knowledge inference

Sosa

Altman

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

The cost of drug development continues to rise and may be prohibitive in cases of unmet clinical need, particularly for rare diseases. Artificial intelligence-based methods are promising in their potential to discover new treatment options. The task of drug repurposing hypothesis generation is well-posed as a link prediction problem in a knowledge graph (KG) of interacting of drugs, proteins, genes and disease phenotypes. KGs derived from biomedical literature are semantically rich and up-to-date representations of scientific knowledge. Inference methods on scientific KGs can be confounded by unspecified contexts and contradictions. Extracting context enables incorporation of relevant pharmacokinetic and pharmacodynamic detail, such as tissue specificity of interactions. Contradictions in biomedical KGs may arise when contexts are omitted or due to contradicting research claims. In this review, we describe challenges to creating literature-scale representations of pharmacological knowledge and survey current approaches toward incorporating context and resolving contradictions.

show abstract

“…The second paper invited from DMBIH 2018, "Extracting Inter-Sentence Relations for Associating Biological Context with Events in Biomedical Text," by Enrique Noriega-Atala, Paul D. Hein, Shraddha S. Thumsi, Zechy Wong, Xia Wang, Sean M. Hendryx, and Clayton T. Morrison [6] studies the problem of identifying biological contexts in biomedical texts and associating them with biochemical events described in texts. They cast the problem as an inter-sentential relation extraction problem where related entities can be separated by a significant distance.…”

mentioning

confidence: 99%