Foundation Models (FMs) are gaining increasing attention in the biomedical artificial intelligence (AI) ecosystem due to their ability to represent and contextualize multimodal biomedical data. These capabilities make FMs a valuable tool for a variety of tasks, including biomedical reasoning, hypothesis generation, and interpreting complex imaging data. In this review paper, we address the unique challenges associated with establishing an ethical and trustworthy biomedical AI ecosystem, with a particular focus on the development of FMs and their downstream applications. We explore strategies that can be implemented throughout the biomedical AI pipeline to effectively tackle these challenges, ensuring that these FMs are translated responsibly into clinical and translational settings. Additionally, we emphasize the importance of key stewardship and co-design principles that not only ensure robust regulation but also guarantee that the interests of all stakeholders—especially those involved in or affected by these clinical and translational applications—are adequately represented. We aim to empower the biomedical AI community to harness these models responsibly and effectively. As we navigate this exciting frontier, our collective commitment to ethical stewardship, co-design, and responsible translation will be instrumental in ensuring that the evolution of FMs truly enhances patient care and medical decision-making, ultimately leading to a more equitable and trustworthy biomedical AI ecosystem.

The scale of biomedical knowledge, spanning scientific literature and curated knowledge bases, poses a significant challenge for investigators in processing, evaluating, and interpreting findings effectively. Large Language Models (LLMs) have emerged as powerful tools for navigating this complex knowledge landscape but may produce hallucinatory responses. Retrieval-Augmented Generation (RAG) is essential for identifying relevant information to enhance accuracy and reliability. This protocol introduces RUGGED (Retrieval Under Graph-Guided Explainable disease Distinction), a comprehensive workflow designed to support knowledge integration, to mitigate bias, and to explore and validate new research directions. Biomedical information from publications and knowledge bases are synthesized and analyzed through text-mining association analysis and explainable graph prediction models to uncover potential drug-disease relationships. These findings, along with the source text corpus and knowledge bases, are incorporated into a framework that employs RAG-enhanced LLMs to enables users to explore hypotheses and investigate underlying mechanisms. A clinical use case demonstrates RUGGED's capability in evaluating and recommending therapeutics for Arrhythmogenic Cardiomyopathy (ACM) and Dilated Cardiomyopathy (DCM), analyzing prescribed drugs for molecular interactions and potential new applications. The platform reduces LLM hallucinations, highlights actionable insights, and streamlines the investigation of novel therapeutics.

A growing body of biomedical literature suggests a bidirectional regulatory relationship between cardiac calcium (Ca²⁺)-regulating proteins and reactive oxygen species (ROS) that is integral to the pathogenesis of various cardiac disorders via oxidative stress (OS) signaling. To address the challenge of finding hidden connections within the growing volume of biomedical research, we developed a data science pipeline for efficient data extraction, transformation, and loading. Employing the CaseOLAP (Context-Aware Semantic Analytic Processing) algorithm, our pipeline quantifies interactions between 128 human cardiomyocyte Ca²⁺-regulating proteins and eight cardiovascular disease (CVD) categories. Our machine-learning analysis of CaseOLAP scores reveals that the molecular interfaces of Ca²⁺-regulating proteins uniquely associate with cardiac arrhythmias and diseases of the cardiac conduction system, distinguishing them from other CVDs. Additionally, a knowledge graph analysis identified 59 of the 128 Ca²⁺-regulating proteins as involved in OS-related cardiac diseases, with cardiomyopathy emerging as the predominant category. By leveraging a link prediction algorithm, our research illuminates the interactions between Ca²⁺-regulating proteins, OS, and CVDs. The insights gained from our study provide a deeper understanding of the molecular interplay between cardiac ROS and Ca²⁺-regulating proteins in the context of CVDs. Such an understanding is essential for the innovation and development of targeted therapeutic strategies.

BACKGROUND: Macrophages are key players in the pathogenesis of atherosclerosis. They trigger immune responses through their cell-surface receptors. However, how macrophages regulate those receptors in response to proinflammatory stimuli is not completely understood. Endocytic membrane trafficking involving receptor internalization, followed by endosomal transport and recycling of the internalized receptors, plays essential roles in balancing cell-surface receptors to meet cellular needs. Here, we explored the role of the endocytic regulator EHD (c-terminal Eps15 [Epidermal growth factor receptor substrate 15] homology domain) 1 in immune responses in macrophages and determined its contribution to atherosclerosis progression. METHODS: EHD1 expression profiles in mouse and human plaques were determined by single-cell RNA sequencing and immunofluorescence staining. Bone marrow transplantation by transplanting bone marrow cells from Ehd1 ^−/− or littermate wild-type mice to irradiated Ldlr ^−/− mice was performed to determine the effect of EHD1 deletion on atherosclerosis progression. In vitro mechanistic studies, including inflammation signaling and endocytosis assays, were performed in bone marrow–derived macrophages. RESULTS: EHD1 expression in macrophages is enhanced as atherosclerosis progresses in both mice and humans. Histological analysis of aortic root sections from bone marrow transplantation mice showed that EHD1 deletion reduces lesion size. Single-cell RNA sequencing of aortic CD (cluster of differentiation) 45 ⁺ cells demonstrated that EHD1 deletion attenuates proinflammatory responses and cell–cell interactions. Mechanistic studies revealed that EHD1 accelerates the endocytic recycling of TNFR2 (tumor necrosis factor receptor 2) and activates NF-κB (nuclear factor kappa B), leading to increased expression of inflammatory cytokines. Moreover, EHD1 interacts with retromer and stabilizes sortilin, a retrograde cargo of retromer and a risk factor for atherosclerosis. CONCLUSIONS: EHD1 promotes inflammation by enhancing TNFR2−NF-κB signaling and stabilizing sortilin, leading to accelerated atherosclerosis. Our study reveals novel roles for EHD1-mediated membrane trafficking in macrophage function and paves the way to innovative therapeutic strategies that aim to address dysregulated membrane trafficking in atherosclerosis.

The scale of biomedical knowledge, spanning scientific literature and curated knowledge bases, poses a significant challenge for investigators in processing, evaluating, and interpreting findings effectively. Large Language Models (LLMs) have emerged as powerful tools for navigating this complex knowledge landscape but may produce hallucinatory responses. Retrieval-Augmented Generation (RAG) is essential for identifying relevant information to enhance accuracy and reliability. This protocol introduces RUGGED (Retrieval Under Graph-Guided Explainable disease Distinction), a comprehensive workflow designed to support knowledge integration, to mitigate bias, and to explore and validate new research directions. Biomedical information from publications and knowledge bases are synthesized and analyzed through text-mining association analysis and explainable graph prediction models to uncover potential drug-disease relationships. These findings, along with the source text corpus and knowledge bases, are incorporated into a framework that employs RAG-enhanced LLMs to enables users to explore hypotheses and investigate underlying mechanisms. A clinical use case demonstrates RUGGED's capability in evaluating and recommending therapeutics for Arrhythmogenic Cardiomyopathy (ACM) and Dilated Cardiomyopathy (DCM), analyzing prescribed drugs for molecular interactions and potential new applications. The platform reduces LLM hallucinations, highlights actionable insights, and streamlines the investigation of novel therapeutics.