Artificial intelligence in food and nutrition evidence: The challenges and opportunities.

Science-informed decisions are best guided by the objective synthesis of the totality of evidence around a particular question and assessing its trustworthiness through systematic processes. However, there are major barriers and challenges that limit science-informed food and nutrition policy, practice, and guidance. First, insufficient evidence, primarily due to acquisition cost of generating high-quality data, and the complexity of the diet-disease relationship.

Restoring the Multiple Sclerosis Associated Imbalance of Gut Indole Metabolites Promotes Remyelination and Suppresses Neuroinflammation.

In multiple sclerosis (MS) the circulating metabolome is dysregulated, with indole lactate (ILA) being one of the most significantly reduced metabolites. We demonstrate that oral supplementation of ILA impacts key MS disease processes in two preclinical models. ILA reduces neuroinflammation by dampening immune cell activation/ infiltration; and promotes remyelination and oligodendrocyte differentiation through the aryl hydrocarbon receptor (AhR).

Incomplete human reference genomes can drive false sex biases and expose patient-identifying information in metagenomic data.

As next-generation sequencing technologies produce deeper genome coverages at lower costs, there is a critical need for reliable computational host DNA removal in metagenomic data. We find that insufficient host filtration using prior human genome references can introduce false sex biases and inadvertently permit flow-through of host-specific DNA during bioinformatic analyses, which could be exploited for individual identification. To address these issues, we introduce and benchmark three host filtration methods of varying throughput, with concomitant applications across low biomass samples such as skin and high microbial biomass datasets including fecal samples.

Biomedical knowledge graph-optimized prompt generation for large language models.

Motivation: Large language models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains such as biomedicine. Solutions such as pretraining and domain-specific fine-tuning add substantial computational overhead, requiring further domain-expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.

Cosmic kidney disease: an integrated pan-omic, physiological and morphological study into spaceflight-induced renal dysfunction.

Missions into Deep Space are planned this decade. Yet the health consequences of exposure to microgravity and galactic cosmic radiation (GCR) over years-long missions on indispensable visceral organs such as the kidney are largely unexplored. We performed biomolecular (epigenomic, transcriptomic, proteomic, epiproteomic, metabolomic, metagenomic), clinical chemistry (electrolytes, endocrinology, biochemistry) and morphometry (histology, 3D imaging, miRNA-ISH, tissue weights) analyses using samples and datasets available from 11 spaceflight-exposed mouse and 5 human, 1 simulated microgravity rat and 4 simulated GCR-exposed mouse missions.

Inflammatory and neurodegenerative serum protein biomarkers increase sensitivity to detect clinical and radiographic disease activity in multiple sclerosis.

The multifaceted nature of multiple sclerosis requires quantitative biomarkers that can provide insights related to diverse physiological pathways. To this end, proteomic analysis of deeply-phenotyped serum samples, biological pathway modeling, and network analysis were performed to elucidate inflammatory and neurodegenerative processes, identifying sensitive biomarkers of multiple sclerosis disease activity. Here, we evaluated the concentrations of > 1400 serum proteins in 630 samples from three multiple sclerosis cohorts for association with clinical and radiographic new disease activity.

Leveraging electronic health records and knowledge networks for Alzheimer's disease prediction and sex-specific biological insights.

Identification of Alzheimer's disease (AD) onset risk can facilitate interventions before irreversible disease progression. We demonstrate that electronic health records from the University of California, San Francisco, followed by knowledge networks (for example, SPOKE) allow for (1) prediction of AD onset and (2) prioritization of biological hypotheses, and (3) contextualization of sex dimorphism. We trained random forest models and predicted AD onset on a cohort of 749 individuals with AD and 250,545 controls with a mean area under the receiver operating characteristic of 0.

Inflammatory and neurodegenerative serum protein biomarkers increase sensitivity to detect disease activity in multiple sclerosis.

Background/objectives: Serum proteomic analysis of deeply-phenotyped samples, biological pathway modeling and network analysis were performed to elucidate the inflammatory and neurodegenerative processes of multiple sclerosis (MS) and identify sensitive biomarkers of MS disease activity (DA).

Methods: Over 1100 serum proteins were evaluated in >600 samples from three MS cohorts to identify biomarkers of clinical and radiographic (gadolinium-enhancing lesions) new MS DA. Protein levels were analyzed and associated with presence of gadolinium-enhancing lesions, clinical relapse status (CRS), and annualized relapse rate (ARR) to create a custom assay panel.

Early detection of Parkinson's disease through enriching the electronic health record using a biomedical knowledge graph.

Introduction: Early diagnosis of Parkinson's disease (PD) is important to identify treatments to slow neurodegeneration. People who develop PD often have symptoms before the disease manifests and may be coded as diagnoses in the electronic health record (EHR).

Methods: To predict PD diagnosis, we embedded EHR data of patients onto a biomedical knowledge graph called Scalable Precision medicine Open Knowledge Engine (SPOKE) and created patient embedding vectors.

A Predictive Autoantibody Signature in Multiple Sclerosis.

Although B cells are implicated in multiple sclerosis (MS) pathophysiology, a predictive or diagnostic autoantibody remains elusive. Here, the Department of Defense Serum Repository (DoDSR), a cohort of over 10 million individuals, was used to generate whole-proteome autoantibody profiles of hundreds of patients with MS (PwMS) years before and subsequently after MS onset. This analysis defines a unique cluster of PwMS that share an autoantibody signature against a common motif that has similarity with many human pathogens.

Integration of epigenetic and genetic profiles identifies multiple sclerosis disease-critical cell types and genes.

Genome-wide association studies (GWAS) successfully identified multiple sclerosis (MS) susceptibility variants. Despite this notable progress, understanding the biological context of these associations remains challenging, due in part to the complexity of linking GWAS results to causative genes and cell types. Here, we aimed to address this gap by integrating GWAS data with single-cell and bulk chromatin accessibility data and histone modification profiles from immune and nervous systems.

The scalable precision medicine open knowledge engine (SPOKE): a massive knowledge graph of biomedical information.

Motivation: Knowledge graphs (KGs) are being adopted in industry, commerce and academia. Biomedical KG presents a challenge due to the complexity, size and heterogeneity of the underlying information.

Results: In this work, we present the Scalable Precision Medicine Open Knowledge Engine (SPOKE), a biomedical KG connecting millions of concepts via semantically meaningful relationships.

Time-aware Embeddings of Clinical Data using a Knowledge Graph.

Meaningful representations of clinical data using embedding vectors is a pivotal step to invoke any machine learning (ML) algorithm for data inference. In this article, we propose a time-aware embedding approach of electronic health records onto a biomedical knowledge graph for creating machine readable patient representations. This approach not only captures the temporal dynamics of patient clinical trajectories, but also enriches it with additional biological information from the knowledge graph.

A biomedical open knowledge network harnesses the power of AI to understand deep human biology.

Knowledge representation and reasoning (KR&R) has been successfully implemented in many fields to enable computers to solve complex problems with AI methods. However, its application to biomedicine has been lagging in part due to the daunting complexity of molecular and cellular pathways that govern human physiology and pathology. In this article we describe concrete uses of SPOKE, an open knowledge network that connects curated information from 37 specialized and human-curated databases into a single property graph, with 3 million nodes and 15 million edges to date.

The role of the gut microbiota in multiple sclerosis.

During the past decade, research has revealed that the vast community of micro-organisms that inhabit the gut - known as the gut microbiota - is intricately linked to human health and disease, partly as a result of its influence on systemic immune responses. Accumulating evidence demonstrates that these effects on immune function are important in neuroinflammatory diseases, such as multiple sclerosis (MS), and that modulation of the microbiome could be therapeutically beneficial in these conditions. In this Review, we examine the influence that the gut microbiota have on immune function via modulation of serotonin production in the gut and through complex interactions with components of the immune system, such as T cells and B cells.

FutureMS cohort profile: a Scottish multicentre inception cohort study of relapsing-remitting multiple sclerosis.

Purpose: Multiple sclerosis (MS) is an immune-mediated, neuroinflammatory disease of the central nervous system and in industrialised countries is the most common cause of progressive neurological disability in working age persons. While treatable, there is substantial interindividual heterogeneity in disease activity and response to treatment. Currently, the ability to predict at diagnosis who will have a benign, intermediate or aggressive disease course is very limited.

Progress toward a universal biomedical data translator.

Clinical, biomedical, and translational science has reached an inflection point in the breadth and diversity of available data and the potential impact of such data to improve human health and well-being. However, the data are often siloed, disorganized, and not broadly accessible due to discipline-specific differences in terminology and representation. To address these challenges, the Biomedical Data Translator Consortium has developed and tested a pilot knowledge graph-based "Translator" system capable of integrating existing biomedical data sets and "translating" those data into insights intended to augment human reasoning and accelerate translational science.

Polygenic risk score association with multiple sclerosis susceptibility and phenotype in Europeans.

Polygenic inheritance plays a pivotal role in driving multiple sclerosis susceptibility, an inflammatory demyelinating disease of the CNS. We developed polygenic risk scores (PRS) of multiple sclerosis and assessed associations with both disease status and severity in cohorts of European descent. The largest genome-wide association dataset for multiple sclerosis to date (n = 41 505) was leveraged to generate PRS scores, serving as an informative susceptibility marker, tested in two independent datasets, UK Biobank [area under the curve (AUC) = 0.