Biomedical Knowledge Research Articles

Bridging chemical structure and conceptual knowledge enables accurate prediction of compound-protein interaction

BackgroundAccurate prediction of compound-protein interaction (CPI) plays a crucial role in drug discovery. Existing data-driven methods aim to learn from the chemical structures of compounds and proteins yet ignore the conceptual knowledge that is the interrelationships among the fundamental elements in the biomedical knowledge graph (KG). Knowledge graphs provide a comprehensive view of entities and relationships beyond individual compounds and proteins. They encompass a wealth of information like pathways, diseases, and biological processes, offering a richer context for CPI prediction. This contextual information can be used to identify indirect interactions, infer potential relationships, and improve prediction accuracy. In real-world applications, the prevalence of knowledge-missing compounds and proteins is a critical barrier for injecting knowledge into data-driven models.ResultsHere, we propose BEACON, a data and knowledge dual-driven framework that bridges chemical structure and conceptual knowledge for CPI prediction. The proposed BEACON learns the consistent representations by maximizing the mutual information between chemical structure and conceptual knowledge and predicts the missing representations by minimizing their conditional entropy. BEACON achieves state-of-the-art performance on multiple datasets compared to competing methods, notably with 5.1% and 6.6% performance gain on the BIOSNAP and DrugBank datasets, respectively. Moreover, BEACON is the only approach capable of effectively predicting knowledge representations for knowledge-lacking compounds and proteins.ConclusionsOverall, our work provides a general approach for directly injecting conceptual knowledge to enhance the performance of CPI prediction.

Creating a safe space: medical students’ perspectives on using actor simulations for learning communication skills

BackgroundCommunication skills are an essential part of clinical competence that need to be acquired during health professions education. Simulations are extensively used for learning communication skills and have long been integral to medical degree programmes. In this research we use qualitative methodology to explore fourth-year medical students’ experiences in simulations aimed at improving versatile doctor-patient communication, focusing on their learning with trained actors.MethodsThe data comprises reflective writings from 208 fourth-year medical students, gathered after a communication skills course. These students provided informed consent for their writings to be included in the research. We performed an inductive qualitative content analysis on the textual data, with findings presented as themes, supported by categories, codes, and excerpts from raw data to enhance the trustworthiness of the analysis.ResultsWe identified eight key themes capturing students’ learning experiences through simulations: practising in a safe learning environment, valuing feedback, gaining new perspectives, finding simulations valuable and enjoyable, boosting confidence and self-knowledge, and viewing simulations as authentic and engaging learning opportunities. Some students offered critical perspectives on simulations. Throughout the course, students learned diverse aspects of patient care, emotional and behavioural communication dynamics, and lessons from medical errors. Some students offered critical perspectives on simulations, and a few indicated they did not learn anything new.ConclusionsA safe learning environment is vital for encouraging learners to explore, make errors, and absorb feedback to improve their communication with patients. Students predominantly valued the communication skills training with actors and the constructive feedback received and given in the debriefing discussions. However, some students expressed critical views toward simulations. Simulations are not static; they evolve and require continual improvements. Hence, we advocate for the ongoing exploration and enhancement of communication skills learning methods, including simulations, with careful consideration for students’ vulnerability and the importance of psychological safety. Additionally, it is critical to address students’ perceptions that certain clinical teachers prioritise biomedical knowledge over communication skills. Providing tailored training for teachers regarding the learning methods and the desired outcomes of communication courses is essential.

The role and value of counsellors in the treatment journeys of people with tuberculosis and their families: Qualitative insights from the South Fly District of Papua New Guinea.

Combined education and counselling can contribute to person-centred care for tuberculosis (TB), improving uptake, adherence, and outcomes of treatment for TB disease and TB infection. Though strongly recommended by the World Health Organization for all people diagnosed with TB, education and counselling is not widely implemented in TB programs around the world. In 2016, a pilot TB education and counselling program, delivered by trained professionals and peers, was initiated to support people on TB treatment in the South Fly District of Papua New Guinea. This article reports on select findings from a qualitative study that examined the socio-cultural dimensions of TB, including treatment support such as education and counselling, in the South Fly District. An assessment on data collected during 128 semi-structured in-depth interviews of the role of counsellors on TB treatment journeys revealed strong participant support for the counsellors and the services they delivered, with particular emphasis on the emotional support provided to address fears and concerns related to TB diagnosis and treatment, and to support treatment adherence; valuable attributes of counsellors; their role as intermediaries between patients and health workers; their provision of biomedical knowledge of TB transmission and disease; and their assistance in addressing stigma and discrimination from family and community. Participants also noted how tackling the socio-structural issues that drive TB transmission in people's homes and communities were beyond the remit of counsellors' work. TB education and counselling should be an essential part of all TB services to provide support and encouragement for people to continue treatment to completion.

Creating a biomedical knowledge base by addressing GPT inaccurate responses and benchmarking context.

We created GNQA, a generative pre-trained transformer (GPT) knowledge base driven by a performant retrieval augmented generation (RAG) with a focus on aging, dementia, Alzheimer's and diabetes. We uploaded a corpus of three thousand peer reviewed publications on these topics into the RAG. To address concerns about inaccurate responses and GPT 'hallucinations', we implemented a context provenance tracking mechanism that enables researchers to validate responses against the original material and to get references to the original papers. To assess the effectiveness of contextual information we collected evaluations and feedback from both domain expert users and 'citizen scientists' on the relevance of GPT responses. A key innovation of our study is automated evaluation by way of a RAG assessment system (RAGAS). RAGAS combines human expert assessment with AI-driven evaluation to measure the effectiveness of RAG systems. When evaluating the responses to their questions, human respondents give a "thumbs-up" 76% of the time. Meanwhile, RAGAS scores 90% on answer relevance on questions posed by experts. And when GPT-generates questions, RAGAS scores 74% on answer relevance. With RAGAS we created a benchmark that can be used to continuously assess the performance of our knowledge base. Full GNQA functionality is embedded in the free GeneNetwork.org web service, an open-source system containing over 25 years of experimental data on model organisms and human. The code developed for this study is published under a free and open-source software license at https://git.genenetwork.org/gn-ai/tree/README.md .

'The MRI-scan says it is completely normal': Reassurance attempts in clinical encounters among patients with chronic musculoskeletal pain.

In clinical guidelines for patients with chronic musculoskeletal pain, reassurance is a key element. The purpose of reassuring patients is to change their views on their illness and, thereby, their actions. However, when symptoms persist without pathological findings, reassurance can be difficult to achieve. Drawing on observations of nineteen naturally occurring hospital consultations with chronic musculoskeletal pain patients, followed by individual interviews with both patients and clinicians, we study how they interact in relation to reassurance. Our main aim is to explore the ways in which clinicians explicitly attempt to provide reassurance, and how patients receive these attempts, before reflecting on facilitating and hindering factors for successful reassurance in relation to the sociocultural context in which their interaction takes place. Through a thematic analysis, four dominating elements of explicit reassurance were identified: (1) education through visualisation, (2) validation through technological findings, (3) validation through physical examination and (4) normalising pain. To gain a deeper understanding of the reassurance process, we then narratively explored dialogical extracts containing these elements. The analysis shows a potential lack of congruence between what patients experience, and the biomedical knowledge clinicians rely on. Despite employing a combination of affective and cognitive modes of reassurance, clinicians tend to build their final conclusions not on patients experiences but on biomedical knowledge, which is knowledge that holds epistemic primacy for themselves. In that sense, their efforts to reassure the patients might also be a way in which they seek to reassure themselves.

Reimagining IR’s biomedical foundations: East Asian medicine and the need for cosmological plurality

Critical scholarship has long pointed to the problematic ways in which mainstream International Relations (IR) takes Westphalian state politics to be universally applicable, yet existing analyses fall short of providing an alternative grounding for IR. Departing from the close relationship between medicine and politics, this article advances two arguments. First, Westphalian IR is based on a particular Western conception of biomedicine. Second, biomedicine is treated as the hallmark of modern science, which exacerbates the discipline’s gatekeeping against ‘alternative’ scholarship that does not look like this particular description of science. By mobilising the notion of ‘cosmology’, we suggest that East Asian medicine (EAM), informed by Daoist yin-yang dialectics, can help to rethink the alleged universality of IR’s biomedical metatheoretical foundations. Specifically, we illustrate how the Westphalian state body and its territorial politics are made possible by biomedical knowledge, and how EAM’s relational cosmology and method of employing creative images helps to conceive shared communal bodies and re-evaluate territorial conflicts. Ultimately, this article argues for the necessity of a plurality of cosmological viewpoints in IR to overcome exclusionary oppositions in both the practice and study of global politics.

MeSHelper: Predicting the evolution of Medical Subject Headings based on knowledge graph dynamics

The Medical Subject Headings (MeSH) thesaurus is a controlled vocabulary widely used in biomedical knowledge systems. We propose a novel framework, termed MeSHelper, that employs a dynamic knowledge graph to predict whether the MeSH main headings (MHs) will evolve while also predicting their corresponding revision type. We parsed the whole PubMed database and all MeSH releases to construct a dynamic semantic tree (DST) and a dynamic knowledge network (DKN) to characterise the evolutionary patterns of MHs and create prediction models. Our results show that DST-related features play a major role in predicting whether the MHs will be revised. Our prediction performance achieved an F1 score of 92.07%. Both DST- and DKN-related features play a crucial role in predicting which types of MHs will evolve. The prediction performance achieved a Macro-F1 score of 72.15%, a Micro-F1 score of 84.09% and a Weighted-F1 score of 84.55%. The findings of this work aid both in constructing an automatic update model for domain thesauruses and in detecting evolutionary trends of the domain knowledge system.

Use of SNOMED CT in Large Language Models: Scoping Review.

Large language models (LLMs) have substantially advanced natural language processing (NLP) capabilities but often struggle with knowledge-driven tasks in specialized domains such as biomedicine. Integrating biomedical knowledge sources such as SNOMED CT into LLMs may enhance their performance on biomedical tasks. However, the methodologies and effectiveness of incorporating SNOMED CT into LLMs have not been systematically reviewed. This scoping review aims to examine how SNOMED CT is integrated into LLMs, focusing on (1) the types and components of LLMs being integrated with SNOMED CT, (2) which contents of SNOMED CT are being integrated, and (3) whether this integration improves LLM performance on NLP tasks. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we searched ACM Digital Library, ACL Anthology, IEEE Xplore, PubMed, and Embase for relevant studies published from 2018 to 2023. Studies were included if they incorporated SNOMED CT into LLM pipelines for natural language understanding or generation tasks. Data on LLM types, SNOMED CT integration methods, end tasks, and performance metrics were extracted and synthesized. The review included 37 studies. Bidirectional Encoder Representations from Transformers and its biomedical variants were the most commonly used LLMs. Three main approaches for integrating SNOMED CT were identified: (1) incorporating SNOMED CT into LLM inputs (28/37, 76%), primarily using concept descriptions to expand training corpora; (2) integrating SNOMED CT into additional fusion modules (5/37, 14%); and (3) using SNOMED CT as an external knowledge retriever during inference (5/37, 14%). The most frequent end task was medical concept normalization (15/37, 41%), followed by entity extraction or typing and classification. While most studies (17/19, 89%) reported performance improvements after SNOMED CT integration, only a small fraction (19/37, 51%) provided direct comparisons. The reported gains varied widely across different metrics and tasks, ranging from 0.87% to 131.66%. However, some studies showed either no improvement or a decline in certain performance metrics. This review demonstrates diverse approaches for integrating SNOMED CT into LLMs, with a focus on using concept descriptions to enhance biomedical language understanding and generation. While the results suggest potential benefits of SNOMED CT integration, the lack of standardized evaluation methods and comprehensive performance reporting hinders definitive conclusions about its effectiveness. Future research should prioritize consistent reporting of performance comparisons and explore more sophisticated methods for incorporating SNOMED CT's relational structure into LLMs. In addition, the biomedical NLP community should develop standardized evaluation frameworks to better assess the impact of ontology integration on LLM performance.

Social perceptions of childhood diarrhea in Lubumbashi, Democratic Republic of the Congo: A qualitative study

Introduction: Infantile diarrhea remains a public health problem in the Democratic Republic of the Congo, where infant mortality linked to this disease remains high despite the proven efficacy of oral rehydration therapy. This study aims to understand the social perceptions of childhood diarrhea among mothers in Lubumbashi, by examining how they diagnose and treat the disease through both popular and biomedical representations.Material and methods: The study was conducted in Lubumbashi, the capital of Haut-Katanga in the DRC, utilizing a qualitative methodology that involved semi-structured interviews with 32 randomly chosen mothers. Selection criteria encompassed the number of children, educational level, religion, and age range (18 to 60). Information was gathered through documents and interviews conducted in Swahili, subsequently translated into French, and analyzed utilizing Jean-Blaise Grize’s ‘natural logic’ to grasp social representations.Results: The study revealed that the majority of mothers associated diarrhea with physical signs such as dehydration, watery stools, depressed fontanel, and sunken eyes. Several mothers attributed the diarrhea to cultural causes, such as the consumption of certain foods by pregnant women (e.g. “kabambale”) or the practice of breastfeeding by pregnant mothers. Local diseases such as “lukunga” and “kilonda ntumbo” are considered to be specific forms of diarrhea in popular culture. Treatments include traditional remedies such as ash applications and sitz baths.Conclusion: Perceptions of childhood diarrhea in Lubumbashi reflect a tension between cultural beliefs and biomedical knowledge, where rehydration is often neglected. The study recommends raising community awareness of the effectiveness of ORT while respecting local beliefs.

BAMRE: Joint extraction model of Chinese medical entities and relations based on Biaffine transformation with relation attention

Electronic Health Records (EHRs) contain various valuable medical entities and their relationships. Although the extraction of biomedical relationships has achieved good results in the mining of electronic health records and the construction of biomedical knowledge bases, there are still some problems. There may be implied complex associations between entities and relationships in overlapping triplets, and ignoring these interactions may lead to a decrease in the accuracy of entity extraction. To address this issue, a joint extraction model for medical entity relations based on a relation attention mechanism is proposed. The relation extraction module identifies candidate relationships within a sentence. The attention mechanism based on these relationships assigns weights to contextual words in the sentence that are associated with different relationships. Additionally, it extracts the subject and object entities. Under a specific relationship, entity vector representations are utilized to construct a global entity matching matrix based on Biaffine transformations. This matrix is designed to enhance the semantic dependencies and relational representations between entities, enabling triplet extraction. This allows the two subtasks of named entity recognition and relation extraction to be interrelated, fully utilizing contextual information within the sentence, and effectively addresses the issue of overlapping triplets.Experimental observations from the CMeIE Chinese medical relation extraction dataset and the Baidu2019 Chinese dataset confirm that our approach yields the superior F1 score across all cutting-edge baselines. Moreover, it offers substantial performance improvements in intricate situations involving diverse overlapping patterns, multitudes of triplets, and cross-sentence triplets.

HeteroKGRep: Heterogeneous Knowledge Graph based Drug Repositioning

The process of developing new drugs is both time-consuming and costly, often taking over a decade and billions of dollars to obtain regulatory approval. Additionally, the complexity of patent protection for novel compounds presents challenges for pharmaceutical innovation. Drug repositioning offers an alternative strategy to uncover new therapeutic uses for existing medicines. Previous repositioning models have been limited by their reliance on homogeneous data sources, failing to leverage the rich information available in heterogeneous biomedical knowledge graphs. We propose HeteroKGRep, a novel drug repositioning model that utilizes heterogeneous graphs to address these limitations. HeteroKGRep is a multi-step framework that first generates a similarity graph from hierarchical concept relations. It then applies SMOTE over-sampling to address class imbalance before generating node sequences using a heterogeneous graph neural network. Drug and disease embeddings are extracted from the network and used for prediction. We evaluated HeteroKGRep on a graph containing biomedical concepts and relations from ontologies, pathways and literature. It achieved state-of-the-art performance with 99% accuracy, 95% AUC ROC and 94% average precision on predicting repurposing opportunities. Compared to existing homogeneous approaches, HeteroKGRep leverages diverse knowledge sources to enrich representation learning. Based on heterogeneous graphs, HeteroKGRep can discover new drug-disease associations, leveraging de novo drug development. This work establishes a promising new paradigm for knowledge-guided drug repositioning using multimodal biomedical data.

PLRTE: Progressive learning for biomedical relation triplet extraction using large language models

Document-level relation triplet extraction is crucial in biomedical text mining, aiding in drug discovery and the construction of biomedical knowledge graphs. Current language models face challenges in generalizing to unseen datasets and relation types in biomedical relation triplet extraction, which limits their effectiveness in these crucial tasks. To address this challenge, our study optimizes models from two critical dimensions: data-task relevance and granularity of relations, aiming to enhance their generalization capabilities significantly. We introduce a novel progressive learning strategy to obtain the PLRTE model. This strategy not only enhances the model’s capability to comprehend diverse relation types in the biomedical domain but also implements a structured four-level progressive learning process through semantic relation augmentation, compositional instruction and dual-axis level learning. Our experiments on the DDI and BC5CDR document-level biomedical relation triplet datasets demonstrate a significant performance improvement of 5% to 20% over the current state-of-the-art baselines. Furthermore, our model exhibits exceptional generalization capabilities on the unseen Chemprot and GDA datasets, further validating the effectiveness of optimizing data-task association and relation granularity for enhancing model generalizability.

TarKG: a comprehensive biomedical knowledge graph for target discovery.

Target discovery is a crucial step in drug development, as it directly affects the success rate of clinical trials. Knowledge graphs (KGs) offer unique advantages in processing complex biological data and inferring new relationships. Existing biomedical KGs primarily focus on tasks such as drug repositioning and drug-target interactions, leaving a gap in the construction of KGs tailored for target discovery. We established a comprehensive biomedical KG focusing on target discovery, termed TarKG, by integrating seven existing biomedical KGs, nine public databases, and traditional Chinese medicine knowledge databases. TarKG consists of 1143313 entities and 32806467 relations across 15 entity categories and 171 relation types, all centered around 3 core entity types: Disease, Gene, and Compound. TarKG provides specialized knowledges for the core entities including chemical structures, protein sequences, or text descriptions. By using different KG embedding algorithms, we assessed the knowledge completion capabilities of TarKG, particularly for disease-target link prediction. In case studies, we further examined TarKG's ability to predict potential protein targets for Alzheimer's disease (AD) and to identify diseases potentially associated with the metallo-deubiquitinase CSN5, using literature analysis for validation. Furthermore, we provided a user-friendly web server (https://tarkg.ddtmlab.org) that enables users to perform knowledge retrieval and relation inference using TarKG. TarKG is accessible at https://tarkg.ddtmlab.org.

A framework for integrating biomedical knowledge in Wikidata with open biological and biomedical ontologies and MeSH keywords

This study presents a comprehensive framework to enhance Wikidata as an open and collaborative knowledge graph by integrating Open Biological and Biomedical Ontologies (OBO) and Medical Subject Headings (MeSH) keywords from PubMed publications. The primary data sources include OBO ontologies and MeSH keywords, which were collected and classified using SPARQL queries for RDF knowledge graphs. The semantic alignment between OBO ontologies and Wikidata was evaluated, revealing significant gaps and distorted representations that necessitate both automated and manual interventions for improvement. We employed pointwise mutual information to extract biomedical relations among the 5000 most common MeSH keywords in PubMed, achieving an accuracy of 89.40 % for superclass-based classification and 75.32 % for relation type-based classification. Additionally, Integrated Gradients were utilized to refine the classification by removing irrelevant MeSH qualifiers, enhancing overall efficiency. The framework also explored the use of MeSH keywords to identify PubMed reviews supporting unsupported Wikidata relations, finding that 45.8 % of these relations were not present in PubMed, indicating potential inconsistencies in Wikidata. The contributions of this study include improved methodologies for enriching Wikidata with biomedical information, validated semantic alignments, and efficient classification processes. This work enhances the interoperability and multilingual capabilities of biomedical ontologies and demonstrates the critical role of MeSH keywords in verifying semantic relations, thereby contributing to the robustness and accuracy of collaborative biomedical knowledge graphs.

Empowering Graph Neural Network-Based Computational Drug Repositioning with Large Language Model-Inferred Knowledge Representation.

Computational drug repositioning, through predicting drug-disease associations (DDA), offers significant potential for discovering new drug indications. Current methods incorporate graph neural networks (GNN) on drug-disease heterogeneous networks to predict DDAs, achieving notable performances compared to traditional machine learning and matrix factorization approaches. However, these methods depend heavily on network topology, hampered by incomplete and noisy network data, and overlook the wealth of biomedical knowledge available. Correspondingly, large language models (LLMs) excel in graph search and relational reasoning, which can possibly enhance the integration of comprehensive biomedical knowledge into drug and disease profiles. In this study, we first investigate the contribution of LLM-inferred knowledge representation in drug repositioning and DDA prediction. A zero-shot prompting template was designed for LLM to extract high-quality knowledge descriptions for drug and disease entities, followed by embedding generation from language models to transform the discrete text to continual numerical representation. Then, we proposed LLM-DDA with three different model architectures (LLM-DDANode Feat, LLM-DDADual GNN, LLM-DDAGNN-AE) to investigate the best fusion mode for LLM-based embeddings. Extensive experiments on four DDA benchmarks show that, LLM-DDAGNN-AE achieved the optimal performance compared to 11 baselines with the overall relative improvement in AUPR of 23.22%, F1-Score of 17.20%, and precision of 25.35%. Meanwhile, selected case studies of involving Prednisone and Allergic Rhinitis highlighted the model's capability to identify reliable DDAs and knowledge descriptions, supported by existing literature. This study showcases the utility of LLMs in drug repositioning with its generality and applicability in other biomedical relation prediction tasks.

FuseLinker: Leveraging LLM’s pre-trained text embeddings and domain knowledge to enhance GNN-based link prediction on biomedical knowledge graphs

ObjectiveTo develop the FuseLinker, a novel link prediction framework for biomedical knowledge graphs (BKGs), which fully exploits the graph’s structural, textual and domain knowledge information. We evaluated the utility of FuseLinker in the graph-based drug repurposing task through detailed case studies. MethodsFuseLinker leverages fused pre-trained text embedding and domain knowledge embedding to enhance the graph neural network (GNN)-based link prediction model tailored for BKGs. This framework includes three parts: a) obtain text embeddings for BKGs using embedding-visible large language models (LLMs), b) learn the representations of medical ontology as domain knowledge information by employing the Poincaré graph embedding method, and c) fuse these embeddings and further learn the graph structure representations of BKGs by applying a GNN-based link prediction model. We evaluated FuseLinker against traditional knowledge graph embedding models and a conventional GNN-based link prediction model across four public BKG datasets. Additionally, we examined the impact of using different embedding-visible LLMs on FuseLinker’s performance. Finally, we investigated FuseLinker’s ability to generate medical hypotheses through two drug repurposing case studies for Sorafenib and Parkinson’s disease. ResultsBy comparing FuseLinker with baseline models on four BKGs, our method demonstrates superior performance. The Mean Reciprocal Rank (MRR) and Area Under receiver operating characteristic Curve (AUROC) for KEGG50k, Hetionet, SuppKG and ADInt are 0.969 and 0.987, 0.548 and 0.903, 0.739 and 0.928, and 0.831 and 0.890, respectively. ConclusionOur study demonstrates that FuseLinker is an effective novel link prediction framework that integrates multiple graph information and shows significant potential for practical applications in biomedical and clinical tasks. Source code and data are available at https://github.com/YKXia0/FuseLinker.

Challenges and opportunities of translating animal research into human trials in Ethiopia

Background and objectivesAlthough the goal of translational research is to bring biomedical knowledge from the laboratory to clinical trial and therapeutic products for improving health, this goal has not been well achieved as often as desired because of many barriers documented in different countries. Therefore, the aim of this study was to investigate the challenges and opportunities of translating animal research into human trials in Ethiopia.MethodsA descriptive qualitative study, using in-depth interviews, was conducted in which preclinical and clinical trial researchers who have been involved in animal research or clinical trials as principal investigator were involved. Data were analyzed using inductive thematic process.ResultsSix themes were emerged for challenges: lack of financial and human capacity, inadequate infrastructure, operational obstacles and poor research governance, lack of collaboration, lack of reproducibility of results and prolonged ethical and regulatory approval processes. Furthermore, three themes were synthesized for opportunities: growing infrastructure and resources, improved human capacity and better administrative processes and initiatives for collaboration.Conclusion and recommendationsThe study found that the identified characteristics/features are of high importance either to hurdle or enable the practice of translating animal research into human trials. The study suggests that there should be adequate infrastructure and finance, human capacity building, good research governance, improved ethical and regulatory approval process, multidisciplinary collaboration, and incentives and recognition for researchers to overcome the identified challenges and allow translating of animal research into human trials to proceed more efficiently.

BioPathNet: Enhancing Link Prediction in Biomedical Knowledge Graphs through Path Representation Learning.

Understanding complex interactions in biomedical networks is crucial for advancements in biomedicine, but traditional link prediction (LP) methods are limited in capturing this complexity. Representation-based learning techniques improve prediction accuracy by mapping nodes to low-dimensional embeddings, yet they often struggle with interpretability and scalability. We present BioPathNet, a novel graph neural network framework based on the Neural Bellman-Ford Network (NBFNet), addressing these limitations through path-based reasoning for LP in biomedical knowledge graphs. Unlike node-embedding frameworks, BioPathNet learns representations between node pairs by considering all relations along paths, enhancing prediction accuracy and interpretability. This allows visualization of influential paths and facilitates biological validation. BioPathNet leverages a background regulatory graph (BRG) for enhanced message passing and uses stringent negative sampling to improve precision. In evaluations across various LP tasks, such as gene function annotation, drug-disease indication, synthetic lethality, and lncRNA-mRNA interaction prediction, BioPathNet consistently outperformed shallow node embedding methods, relational graph neural networks and task-specific state-of-the-art methods, demonstrating robust performance and versatility. Our study predicts novel drug indications for diseases like acute lymphoblastic leukemia (ALL) and Alzheimer's, validated by medical experts and clinical trials. We also identified new synthetic lethality gene pairs and regulatory interactions involving lncRNAs and target genes, confirmed through literature reviews. BioPathNet's interpretability will enable researchers to trace prediction paths and gain molecular insights, making it a valuable tool for drug discovery, personalized medicine and biology in general.

Exploring the implicit meanings of 'cultural diversity': a critical conceptual analysis of commonly used approaches in medical education.

Existing approaches to cultural diversity in medical education may be implicitly based on different conceptualisations of culture. Research has demonstrated that such interpretations matter to practices and people concerned. We therefore sought to identify the different conceptualisations espoused by these approaches and investigated their implications for education. We critically reviewed 52 articles from eight top medical education journals and subjected these to a conceptual analysis. Via open coding, we looked for references to approaches, their objectives, implicit notions of culture, and to implementation practices. We iteratively developed themes from the collected findings. We identified several approaches to cultural diversity teaching that used four different ways to conceptualise cultural diversity: culture as 'fixed patient characteristic', as 'multiple fixed characteristics', as 'dynamic outcome impacting social interactions', and as 'power dynamics'. We discussed the assumptions underlying these different notions, and reflected upon limitations and implications for educational practice. The notion of 'cultural diversity' challenges learners' communication skills, touches upon inherent inequalities and impacts how the field constructs knowledge. This study adds insights into how inherent inequalities in biomedical knowledge construction are rooted in methodological, ontological, and epistemological principles. Although these insights carry laborious implications for educational implementation, educators can learn from first initiatives, such as: standardly include information on patients' multiple identities and lived experiences in case descriptions, stimulate more reflection on teachers' and students' own values and hierarchical position, acknowledge Western epistemological hegemony, explicitly include literature from diverse sources, and monitor diversity-integrated topics in the curriculum.

Construction and analysis of protein-protein interaction network for esophageal squamous cell carcinoma

Esophageal squamous cell carcinoma (ESCC) is a prevalent malignant tumor of the digestive tract. Clinical findings reveal that the five-year survival rate for mid-to late-stage ESCC patients is merely around 20 %, whereas those diagnosed at an early stage can achieve up to a 95 % survival rate. Consequently, early detection is paramount to improving ESCC patient survival. Protein markers are essential for diagnosing diseases, and the identification of new candidate proteins associated with ESCC through the protein-protein interaction (PPI) network is aimed for in this paper. The PPI network related to ESCC was constructed using protein data, comprising 2094 nodes and 19,660 edges. To assess the nodes' importance in the network, three metrics—degree centrality, betweenness centrality, and closeness centrality—were employed, leading to the identification of 81 key proteins. Subsequently, the biological significance of these proteins in the network was explored, combining biomedical knowledge from three perspectives: network, node, and cluster. The results demonstrated that 52 out of 81 key proteins were confirmed to be linked to ESCC. Among the remaining 29 unreported proteins, 18 displayed significant biological significance, indicating their potential as protein markers related to ESCC.