Knowledge Graphs and Their Applications in Drug Discovery

Generative AI-based knowledge graphs for the illustration and development of mHealth self-management content

Background

Digital therapeutics (DTx) in the form of mobile health (mHealth) self-management programs have demonstrated effectiveness in reducing disease activity across various diseases, including fibromyalgia and arthritis. However, the content of online self-management programs varies widely, making them difficult to compare.

Aim

This study aims to employ generative artificial intelligence (AI)-based knowledge graphs and network analysis to categorize and structure mHealth content at the example of a fibromyalgia self-management program.

Methods

A multimodal mHealth online self-management program targeting fibromyalgia and post-viral fibromyalgia-like syndromes was developed. In addition to general content, the program was customized to address specific features and digital personas identified through hierarchical agglomerative clustering applied to a cohort of 202 patients with chronic musculoskeletal pain syndromes undergoing multimodal assessment. Text files consisting of 22,150 words divided into 24 modules were used as the input data. Two generative AI web applications, ChatGPT-4 (OpenAI) and Infranodus (Nodus Labs), were used to create knowledge graphs and perform text network analysis, including 3D visualization. A sentiment analysis of 129 patient feedback entries was performed.

Results

The ChatGPT-generated knowledge graph model provided a simple visual overview with five primary edges: "Mental health challenges", "Stress and its impact", "Immune system function", "Long COVID and fibromyalgia" and "Pain management and therapeutic approaches". The 3D visualization provided a more complex knowledge graph, with the term "pain" appearing as the central edge, closely connecting with "sleep", "body", and "stress". Topical cluster analysis identified categories such as "chronic pain management", "sleep hygiene", "immune system function", "cognitive therapy", "healthy eating", "emotional development", "fibromyalgia causes", and "deep relaxation". Gap analysis highlighted missing links, such as between "negative behavior" and "systemic inflammation". Retro-engineering of the self-management program showed significant conceptual similarities between the knowledge graph and the original text analysis. Sentiment analysis of free text patient comments revealed that most relevant topics were addressed by the online program, with the exception of social contacts.

Conclusion

Generative AI tools for text network analysis can effectively structure and illustrate DTx content. Knowledge graphs are valuable for increasing the transparency of self-management programs, developing new conceptual frameworks, and incorporating feedback loops.

Community knowledge graph abstraction for enhanced link prediction: A study on PubMed knowledge graph

OBJECTIVE

As new knowledge is produced at a rapid pace in the biomedical field, existing biomedical Knowledge Graphs (KGs) cannot be manually updated in a timely manner. Previous work in Natural Language Processing (NLP) has leveraged link prediction to infer the missing knowledge in general-purpose KGs. Inspired by this, we propose to apply link prediction to existing biomedical KGs to infer missing knowledge. Although Knowledge Graph Embedding (KGE) methods are effective in link prediction tasks, they are less capable of capturing relations between communities of entities with specific attributes (Fanourakis et al., 2023).

METHODS

To address this challenge, we proposed an entity distance-based method for abstracting a Community Knowledge Graph (CKG) from a simplified version of the pre-existing PubMed Knowledge Graph (PKG) (Xu et al., 2020). For link prediction on the abstracted CKG, we proposed an extension approach for the existing KGE models by linking the information in the PKG to the abstracted CKG. The applicability of this extension was proved by employing six well-known KGE models: TransE, TransH, DistMult, ComplEx, SimplE, and RotatE. Evaluation metrics including Mean Rank (MR), Mean Reciprocal Rank (MRR), and Hits@k were used to assess the link prediction performance. In addition, we presented a backtracking process that traces the results of CKG link prediction back to the PKG scale for further comparison.

RESULTS

Six different CKGs were abstracted from the PKG by using embeddings of the six KGE methods. The results of link prediction in these abstracted CKGs indicate that our proposed extension can improve the existing KGE methods, achieving a top-10 accuracy of 0.69 compared to 0.5 for TransE, 0.7 compared to 0.54 for TransH, 0.67 compared to 0.6 for DistMult, 0.73 compared to 0.57 for ComplEx, 0.73 compared to 0.63 for SimplE, and 0.85 compared to 0.76 for RotatE on their CKGs, respectively. These improved performances also highlight the wide applicability of the extension approach.

CONCLUSION

This study proposed novel insights into abstracting CKGs from the PKG. The extension approach indicated enhanced performance of the existing KGE methods and has applicability. As an interesting future extension, we plan to conduct link prediction for entities that are newly introduced to the PKG.

Knowledge Graph for Breast Cancer Prevention and Treatment: Literature-Based Data Analysis Study

Background

The incidence of breast cancer has remained high and continues to rise since the 21st century. Consequently, there has been a significant increase in research efforts focused on breast cancer prevention and treatment. Despite the extensive body of literature available on this subject, systematic integration is lacking. To address this issue, knowledge graphs have emerged as a valuable tool. By harnessing their powerful knowledge integration capabilities, knowledge graphs offer a comprehensive and structured approach to understanding breast cancer prevention and treatment.

Objective

We aim to integrate literature data on breast cancer treatment and prevention, build a knowledge graph, and provide support for clinical decision-making.

Methods

We used Medical Subject Headings terms to search for clinical trial literature on breast cancer prevention and treatment published on PubMed between 2018 and 2022. We downloaded triplet data from the Semantic MEDLINE Database (SemMedDB) and matched them with the retrieved literature to obtain triplet data for the target articles. We visualized the triplet information using NetworkX for knowledge discovery.

Results

Within the scope of literature research in the past 5 years, malignant neoplasms appeared most frequently (587/1387, 42.3%). Pharmacotherapy (267/1387, 19.3%) was the primary treatment method, with trastuzumab (209/1805, 11.6%) being the most commonly used therapeutic drug. Through the analysis of the knowledge graph, we have discovered a complex network of relationships between treatment methods, therapeutic drugs, and preventive measures for different types of breast cancer.

Conclusions

This study constructed a knowledge graph for breast cancer prevention and treatment, which enabled the integration and knowledge discovery of relevant literature in the past 5 years. Researchers can gain insights into treatment methods, drugs, preventive knowledge regarding adverse reactions to treatment, and the associations between different knowledge domains from the graph.