Dataset Information

Improving chemical entity recognition through h-index based semantic similarity.

ABSTRACT: BACKGROUND:Our approach to the BioCreative IV challenge of recognition and classification of drug names (CHEMDNER task) aimed at achieving high levels of precision by applying semantic similarity validation techniques to Chemical Entities of Biological Interest (ChEBI) mappings. Our assumption is that the chemical entities mentioned in the same fragment of text should share some semantic relation. This validation method was further improved by adapting the semantic similarity measure to take into account the h-index of each ancestor. We applied this method in two measures, simUI and simGIC, and validated the results obtained for the competition, comparing each adapted measure to its original version. RESULTS:For the competition, we trained a Random Forest classifier that uses various scores provided by our system, including semantic similarity, which improved the F-measure obtained with the Conditional Random Fields classifiers by 4.6%. Using a notion of concept relevance based on the h-index measure, we were able to enhance our validation process so that for a fixed recall, we increased precision by excluding from the results a higher amount of false positives. We plotted precision and recall values for a range of validation thresholds using different similarity measures, obtaining higher precision values for the same recall with the measures based on the h-index. CONCLUSIONS:The semantic similarity measure we introduced was more efficient at validating text mining results from machine learning classifiers than other measures. We improved the results we obtained for the CHEMDNER task by maintaining high precision values while improving the recall and F-measure.

SUBMITTER: Lamurias A

PROVIDER: S-EPMC4331689 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving chemical entity recognition through h-index based semantic similarity.

Lamurias Andre A Ferreira João D JD Couto Francisco M FM

Journal of cheminformatics 20150119 Suppl 1 Text mining for chemistry and the CHEMDNER trac

<h4>Background</h4>Our approach to the BioCreative IV challenge of recognition and classification of drug names (CHEMDNER task) aimed at achieving high levels of precision by applying semantic similarity validation techniques to Chemical Entities of Biological Interest (ChEBI) mappings. Our assumption is that the chemical entities mentioned in the same fragment of text should share some semantic relation. This validation method was further improved by adapting the semantic similarity measure to ...[more]

PMID: 25810770

Similar Datasets

Project description:BACKGROUND:Over the past several centuries, chemistry has permeated virtually every facet of human lifestyle, enriching fields as diverse as medicine, agriculture, manufacturing, warfare, and electronics, among numerous others. Unfortunately, application-specific, incompatible chemical information formats and representation strategies have emerged as a result of such diverse adoption of chemistry. Although a number of efforts have been dedicated to unifying the computational representation of chemical information, disparities between the various chemical databases still persist and stand in the way of cross-domain, interdisciplinary investigations. Through a common syntax and formal semantics, Semantic Web technology offers the ability to accurately represent, integrate, reason about and query across diverse chemical information. RESULTS:Here we specify and implement the Chemical Entity Semantic Specification (CHESS) for the representation of polyatomic chemical entities, their substructures, bonds, atoms, and reactions using Semantic Web technologies. CHESS provides means to capture aspects of their corresponding chemical descriptors, connectivity, functional composition, and geometric structure while specifying mechanisms for data provenance. We demonstrate that using our readily extensible specification, it is possible to efficiently integrate multiple disparate chemical data sources, while retaining appropriate correspondence of chemical descriptors, with very little additional effort. We demonstrate the impact of some of our representational decisions on the performance of chemically-aware knowledgebase searching and rudimentary reaction candidate selection. Finally, we provide access to the tools necessary to carry out chemical entity encoding in CHESS, along with a sample knowledgebase. CONCLUSIONS:By harnessing the power of Semantic Web technologies with CHESS, it is possible to provide a means of facile cross-domain chemical knowledge integration with full preservation of data correspondence and provenance. Our representation builds on existing cheminformatics technologies and, by the virtue of RDF specification, remains flexible and amenable to application- and domain-specific annotations without compromising chemical data integration. We conclude that the adoption of a consistent and semantically-enabled chemical specification is imperative for surviving the coming chemical data deluge and supporting systems science research.

Project description:ImportanceThe study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets.ObjectivesThis study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance.Materials and methodsWe evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT.ResultsUsing baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed.DiscussionThe study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings.ConclusionWhile direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.

Dataset Information

Improving chemical entity recognition through h-index based semantic similarity.

Publications

Improving chemical entity recognition through h-index based semantic similarity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets