Biomedical discovery through the integrative biomedical knowledge hub (iBKH)

Su, Chang; Hou, Yu; Zhou, Manqi; Rajendran, Suraj; Maasch, Jacqueline R. M. A.; Abedi, Zehra; Zhang, Haotan; Bai, Zilong; Cuturrufo, Anthony; Guo, Winston; Chaudhry, Fayzan; Ghahramani, Gregory; Tang, Jian; Cheng, Feixiong; Li, Yue; Zhang, Rui; DeKosky, Steven T.; Bian, Jiang; Wang, Fei

doi:10.1016/j.isci.2023.106460

Cited by 8 publications

(5 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integrative Biomedical Knowledge Hub (iBKH) 30 was developed through a meticulous process of harmonizing and integrating information from a diverse range of biomedical resources. This comprehensive knowledge hub incorporates data from 18 highly regarded and carefully curated sources.…”

Section: Compared Methodsmentioning

confidence: 99%

“…1. whether they were already present in existing BKGs (speci cally, iBKH 30 for drugs and ADInt 36 for DSs); 2. whether they were documented in clinical trials; and 3. whether they were supported by existing literature.…”

Section: And Please Give Your Rationale (Ds)mentioning

confidence: 99%

“…AD drug/DS repurposing based on BKG. Building upon our previous research 30,36 , we employed knowledge graph embedding (KGE) algorithms to compute machine-readable embedding vectors for entities and relations within the BKGs (iBKH and ADInt) while preserving the graph structure.…”

Section: And Please Give Your Rationale (Ds)mentioning

confidence: 99%

“…To assess the comprehensiveness of ChatGPT's knowledge base, we further examined its capability in establishing associations between the proposed drug and DS candidates with AD. In our previous study, we investigated potential pharmaceuticals and DS for the treatment or prevention of AD using link prediction techniques 30,36 . Building upon these previous ndings, our objective was to evaluate ChatGPT's knowledge base by examining the associations it provides between these hypothetical drug/DS candidates and AD, as well as the corresponding references it offers to support these hypotheses.…”

Section: Performance Evaluation Of Chatgpt and Bkg In Knowledge Reaso...mentioning

confidence: 99%

See 3 more Smart Citations

From Answers to Insights: Unveiling the Strengths and Limitations of ChatGPT and Biomedical Knowledge Graphs

Hou

Yeung

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Large Language Models (LLMs) have shown exceptional performance in various natural language processing tasks, benefiting from their language generation capabilities and ability to acquire knowledge from unstructured text. However, in the biomedical domain, LLMs face limitations that lead to inaccurate and inconsistent answers. Knowledge Graphs (KGs) have emerged as valuable resources for organizing structured information. Biomedical Knowledge Graphs (BKGs) have gained significant attention for managing diverse and large-scale biomedical knowledge. The objective of this study is to assess and compare the capabilities of ChatGPT and existing BKGs in question-answering, biomedical knowledge discovery, and reasoning tasks within the biomedical domain. Methods: We conducted a series of experiments to assess the performance of ChatGPT and the BKGs in various aspects of querying existing biomedical knowledge, knowledge discovery, and knowledge reasoning. Firstly, we tasked ChatGPT with answering questions sourced from the "Alternative Medicine" sub-category of Yahoo! Answers and recorded the responses. Additionally, we queried BKG to retrieve the relevant knowledge records corresponding to the questions and assessed them manually. In another experiment, we formulated a prediction scenario to assess ChatGPT's ability to suggest potential drug/dietary supplement repurposing candidates. Simultaneously, we utilized BKG to perform link prediction for the same task. The outcomes of ChatGPT and BKG were compared and analyzed. Furthermore, we evaluated ChatGPT and BKG's capabilities in establishing associations between pairs of proposed entities. This evaluation aimed to assess their reasoning abilities and the extent to which they can infer connections within the knowledge domain. Results: The results indicate that ChatGPT with GPT-4.0 outperforms both GPT-3.5 and BKGs in providing existing information. However, BKGs demonstrate higher reliability in terms of information accuracy. ChatGPT exhibits limitations in performing novel discoveries and reasoning, particularly in establishing structured links between entities compared to BKGs. Conclusions: To address the limitations observed, future research should focus on integrating LLMs and BKGs to leverage the strengths of both approaches. Such integration would optimize task performance and mitigate potential risks, leading to advancements in knowledge within the biomedical field and contributing to the overall well-being of individuals.

show abstract

Section: Compared Methodsmentioning

confidence: 99%

Section: And Please Give Your Rationale (Ds)mentioning

confidence: 99%

Section: And Please Give Your Rationale (Ds)mentioning

confidence: 99%

Section: Performance Evaluation Of Chatgpt and Bkg In Knowledge Reaso...mentioning

confidence: 99%

See 2 more Smart Citations

From Answers to Insights: Unveiling the Strengths and Limitations of ChatGPT and Biomedical Knowledge Graphs

Hou

Yeung

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Necessary connective data can also be extracted from large-scale knowledge graphs such as the Integrative Biomedical Knowledge Hub and the Clinical Knowledge Graph. 103 , 104 Biomedical knowledge graphs can be a valuable resource for connecting disparate datasets in C 4 solutions as well. These graphs are large-scale, structured networks of biomedical information that can be used to represent and link various concepts, entities, and relationships in the domain of health and medicine.…”

Section: Challengesmentioning

confidence: 99%