Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text

Detecting protein-protein interactions (PPIs) is crucial for understanding genetic mechanisms, disease pathogenesis, and drug design. However, with the fast-paced growth of biomedical literature, there is a growing need for automated and accurate extraction of PPIs to facilitate scientific knowledge discovery. Pre-trained language models, such as generative pre-trained transformer (GPT) and bidirectional encoder representations from transformers (BERT), have shown promising results in natural language processing (NLP) tasks. We evaluated the PPI identification performance of various GPT and BERT models using a manually curated benchmark corpus of 164 PPIs in 77 sentences from learning language in logic (LLL). BERT-based models achieved the best overall performance, with PubMedBERT achieving the highest precision (85.17%) and F1-score (86.47%) and BioM-ALBERT achieving the highest recall (93.83%). Despite not being explicitly trained for biomedical texts, GPT-4 achieved comparable performance to the best BERT models with 83.34% precision, 76.57% recall, and 79.18% F1-score. These findings suggest that GPT models can effectively detect PPIs from text data and have the potential for use in biomedical literature mining tasks.

An Open Natural Language Processing Development Framework for EHR-based Clinical Research: A case demonstration using the National COVID Cohort Collaborative (N3C)

While we pay attention to the latest advances in clinical natural language processing (NLP), we can notice some resistance in the clinical and translational research community to adopt NLP models due to limited transparency, Interpretability and usability. Built upon our previous work, in this study, we proposed an open natural language processing development framework and evaluated it through the implementation of NLP algorithms for the National COVID Cohort Collaborative (N3C). Based on the interests in information extraction from COVID-19 related clinical notes, our work includes 1) an open data annotation process using COVID-19 signs and symptoms as the use case, 2) a community-driven ruleset composing platform, and 3) a synthetic text data generation workflow to generate texts for information extraction tasks without involving human subjects. The generated corpora derived out of the texts from multiple intuitions and gold standard annotation are tested on a single institution's rule set has the performances in F1 score of 0.876, 0.706 and 0.694, respectively. The study as a consortium effort of the N3C NLP subgroup demonstrates the feasibility of creating a federated NLP algorithm development and benchmarking platform to enhance multi-institution clinical NLP study.

OntoPlot: A Novel Visualisation for Non-hierarchical Associations in Large Ontologies

Ontologies are formal representations of concepts and complex relationships among them. They have been widely used to capture comprehensive domain knowledge in areas such as biology and medicine, where large and complex ontologies can contain hundreds of thousands of concepts. Especially due to the large size of ontologies, visualisation is useful for authoring, exploring and understanding their underlying data. Existing ontology visualisation tools generally focus on the hierarchical structure, giving much less emphasis to non-hierarchical associations. In this paper we present OntoPlot, a novel visualisation specifically designed to facilitate the exploration of all concept associations whilst still showing an ontology's large hierarchical structure. This hybrid visualisation combines icicle plots, visual compression techniques and interactivity, improving space-efficiency and reducing visual structural complexity. We conducted a user study with domain experts to evaluate the usability of OntoPlot, comparing it with the de facto ontology editor Prot{\'e}g{\'e}. The results confirm that OntoPlot attains our design goals for association-related tasks and is strongly favoured by domain experts.

HINO: a BFO-aligned ontology representing human molecular interactions and pathways

Many database resources, such as Reactome, collect manually annotated reactions, interactions, and pathways from peer-reviewed publications. The interactors (e.g., a protein), interactions, and pathways in these data resources are often represented as instances in using BioPAX, a standard pathway data exchange format. However, these interactions are better represented as classes (or universals) since they always occur given appropriate conditions. This study aims to represent various human interaction pathways and networks as classes via a formal ontology aligned with the Basic Formal Ontology (BFO). Towards this goal, the Human Interaction Network Ontology (HINO) was generated by extending the BFO-aligned Interaction Network Ontology (INO). All human pathways and associated processes and interactors listed in Reactome and represented in BioPAX were first converted to ontology classes by aligning them under INO. Related terms and associated relations and hierarchies from external ontologies (e.g., CHEBI and GO) were also retrieved and imported into HINO. HINO ontology terms were resolved in the linked ontology data server Ontobee. The RDF triples stored in the RDF triple store are queryable through a SPARQL program. Such an ontology system supports advanced pathway data integration and applications.