Representing annotation compositionality and provenance for the Semantic Web

Mapping vaccine names in clinical trials to vaccine ontology using cascaded fine-tuned domain-specific language models

BACKGROUND

Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects.

CLINICALTRIALS

gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance.

RESULTS

In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, the Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy.

CONCLUSION

This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.

Mapping Vaccine Names in Clinical Trials to Vaccine Ontology using Cascaded Fine-Tuned Domain-Specific Language Models

Background

Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects. ClinicalTrials.gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance.

Results

In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy.

Conclusion

This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.

Extending the evaluation of Genia Event task toward knowledge base construction and comparison to Gene Regulation Ontology task

BACKGROUND

The third edition of the BioNLP Shared Task was held with the grand theme "knowledge base construction (KB)". The Genia Event (GE) task was re-designed and implemented in light of this theme. For its final report, the participating systems were evaluated from a perspective of annotation. To further explore the grand theme, we extended the evaluation from a perspective of KB construction. Also, the Gene Regulation Ontology (GRO) task was newly introduced in the third edition. The final evaluation of the participating systems resulted in relatively low performance. The reason was attributed to the large size and complex semantic representation of the ontology. To investigate potential benefits of resource exchange between the presumably similar tasks, we measured the overlap between the datasets of the two tasks, and tested whether the dataset for one task can be used to enhance performance on the other.

RESULTS

We report an extended evaluation on all the participating systems in the GE task, incoporating a KB perspective. For the evaluation, the final submission of each participant was converted to RDF statements, and evaluated using 8 queries that were formulated in SPARQL. The results suggest that the evaluation may be concluded differently between the two different perspectives, annotation vs. KB. We also provide a comparison of the GE and GRO tasks by converting their datasets into each other's format. More than 90% of the GE data could be converted into the GRO task format, while only half of the GRO data could be mapped to the GE task format. The imbalance in conversion indicates that the GRO is a comprehensive extension of the GE task ontology. We further used the converted GRO data as additional training data for the GE task, which helped improve GE task participant system performance. However, the converted GE data did not help GRO task participants, due to overfitting and the ontology gap.

Structuring research methods and data with the research object model: genomics workflows as a case study

BACKGROUND

One of the main challenges for biomedical research lies in the computer-assisted integrative study of large and increasingly complex combinations of data in order to understand molecular mechanisms. The preservation of the materials and methods of such computational experiments with clear annotations is essential for understanding an experiment, and this is increasingly recognized in the bioinformatics community. Our assumption is that offering means of digital, structured aggregation and annotation of the objects of an experiment will provide necessary meta-data for a scientist to understand and recreate the results of an experiment. To support this we explored a model for the semantic description of a workflow-centric Research Object (RO), where an RO is defined as a resource that aggregates other resources, e.g., datasets, software, spreadsheets, text, etc. We applied this model to a case study where we analysed human metabolite variation by workflows.

RESULTS

We present the application of the workflow-centric RO model for our bioinformatics case study. Three workflows were produced following recently defined Best Practices for workflow design. By modelling the experiment as an RO, we were able to automatically query the experiment and answer questions such as "which particular data was input to a particular workflow to test a particular hypothesis?", and "which particular conclusions were drawn from a particular workflow?".

CONCLUSIONS

Applying a workflow-centric RO model to aggregate and annotate the resources used in a bioinformatics experiment, allowed us to retrieve the conclusions of the experiment in the context of the driving hypothesis, the executed workflows and their input data. The RO model is an extendable reference model that can be used by other systems as well.

AVAILABILITY

The Research Object is available at http://www.myexperiment.org/packs/428 The Wf4Ever Research Object Model is available at http://wf4ever.github.io/ro.