RESUMEN
Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here we introduce PINNACLE, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multiorgan single-cell atlas, PINNACLE learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. PINNACLE's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. PINNACLE outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases and pinpoints cell type contexts with higher predictive capability than context-free models. PINNACLE's ability to adjust its outputs on the basis of the context in which it operates paves the way for large-scale context-specific predictions in biology.
Asunto(s)
Aprendizaje Profundo , Análisis de la Célula Individual , Humanos , Análisis de la Célula Individual/métodos , Algoritmos , Mapas de Interacción de Proteínas , Proteínas/metabolismo , Proteínas/química , Biología Computacional/métodosRESUMEN
SUMMARY: Heterogeneous knowledge graphs (KGs) have enabled the modeling of complex systems, from genetic interaction graphs and protein-protein interaction networks to networks representing drugs, diseases, proteins, and side effects. Analytical methods for KGs rely on quantifying similarities between entities, such as nodes, in the graph. However, such methods must consider the diversity of node and edge types contained within the KG via, for example, defined sequences of entity types known as meta-paths. We present metapaths, the first R software package to implement meta-paths and perform meta-path-based similarity search in heterogeneous KGs. The metapaths package offers various built-in similarity metrics for node pair comparison by querying KGs represented as either edge or adjacency lists, as well as auxiliary aggregation methods to measure set-level relationships. Indeed, evaluation of these methods on an open-source biomedical KG recovered meaningful drug and disease-associated relationships, including those in Alzheimer's disease. The metapaths framework facilitates the scalable and flexible modeling of network similarities in KGs with applications across KG learning. AVAILABILITY AND IMPLEMENTATION: The metapaths R package is available via GitHub at https://github.com/ayushnoori/metapaths and is released under MPL 2.0 (Zenodo DOI: 10.5281/zenodo.7047209). Package documentation and usage examples are available at https://www.ayushnoori.com/metapaths.
Asunto(s)
Enfermedad de Alzheimer , Reconocimiento de Normas Patrones Automatizadas , Humanos , Programas Informáticos , Mapas de Interacción de ProteínasRESUMEN
PURPOSE: Anemia reduces the blood's ability to carry and deliver oxygen. Following cardiac surgery, anemia is very common and affects up to 90% of patients. Nevertheless, there is a paucity of data examining the prognostic value of postoperative anemia. In this narrative review, we present findings from the relevant literature on postoperative anemia in cardiac surgery patients, focusing on the incidence, risk factors, and prognostic value of postoperative anemia. We also explore the potential utility of postoperative anemia as a therapeutic target to improve clinical outcomes. SOURCE: We conducted a targeted search of MEDLINE, Embase, and the Cochrane Database of Systematic Reviews up to September 2022, using a combination of search terms including postoperative (post-operative), perioperative (peri-operative), anemia (anaemia), and cardiac surgery. PRINCIPAL FINDINGS: The reported incidence of postoperative anemia varied from 29% to 94% across the studies, likely because of variations in patient inclusion criteria and classification of postoperative anemia. Nonetheless, the weight of the evidence suggests that postoperative anemia is common and is an independent risk factor for adverse postoperative outcomes such as acute kidney injury, stroke, mortality, and functional outcomes. CONCLUSIONS: In cardiac surgery patients, postoperative anemia is a common and prognostically important risk factor for postoperative morbidity and mortality. Nevertheless, there is a lack of data on whether active management of postoperative anemia is feasible or effective in improving patient outcomes.
RéSUMé: OBJECTIF: L'anémie réduit la capacité du sang à transporter et à fournir de l'oxygène. Suite à une chirurgie cardiaque, l'anémie est très fréquente et touche jusqu'à 90 % des patient·es. Néanmoins, il existe peu de données examinant la valeur pronostique de l'anémie postopératoire. Dans ce compte rendu narratif, nous présentons les résultats de la littérature pertinente sur l'anémie postopératoire chez les patient·es ayant bénéficié d'une chirurgie cardiaque, en mettant l'accent sur l'incidence, les facteurs de risque et la valeur pronostique de l'anémie postopératoire chez les personnes ayant bénéficié d'une chirurgie cardiaque. Nous explorons également l'utilité potentielle de l'anémie postopératoire en tant que cible thérapeutique pour améliorer les devenirs cliniques. SOURCES: Nous avons réalisé une recherche ciblée dans MEDLINE, Embase et la base de données des revues systématiques Cochrane jusqu'en septembre 2022, en utilisant une combinaison de termes de recherche, notamment postopératoire (postoperative/post-operative), périopératoire (perioperative/peri-operative), anémie (anemia/anaemia) et chirurgie cardiaque (cardiac surgery). CONSTATATIONS PRINCIPALES: L'incidence rapportée de l'anémie postopératoire variait de 29 % à 94 % d'une étude à l'autre, probablement en raison des variations dans les critères d'inclusion des patient·es et la classification de l'anémie postopératoire. Néanmoins, le poids de la preuve suggère que l'anémie postopératoire est courante et constitue un facteur de risque indépendant pour les devenirs postopératoires indésirables tels que l'insuffisance rénale aiguë, les accidents vasculaires cérébraux, la mortalité et les devenirs fonctionnels. CONCLUSION: Chez la patientèle en chirurgie cardiaque, l'anémie postopératoire est un facteur de risque commun et pronostiquement important de morbidité et de mortalité postopératoires. Néanmoins, il y a un manque de données sur la faisabilité ou l'efficacité de la prise en charge active de l'anémie postopératoire pour améliorer les devenirs des patient·es.
Asunto(s)
Anemia , Procedimientos Quirúrgicos Cardíacos , Humanos , Revisiones Sistemáticas como Asunto , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Anemia/epidemiología , Anemia/terapia , Anemia/etiología , Incidencia , Complicaciones Posoperatorias/etiologíaRESUMEN
OBJECTIVES: Traditional antimicrobial susceptibility testing (AST) is growth dependent and time-consuming. With rising rates of drug-resistant infections, a novel diagnostic method is critically needed that can rapidly reveal a pathogen's antimicrobial susceptibility to guide appropriate treatment. Recently, RNA sequencing has been identified as a powerful diagnostic tool to explore transcriptional gene expression and improve AST. METHODS: RNA sequencing was used to investigate the potential of RNA markers for rapid molecular AST using Klebsiella pneumoniae and ciprofloxacin as a model. Downstream bioinformatic analysis was applied for optimal marker selection. Further validation on 11 more isolates of K. pneumoniae was performed using quantitative real-time PCR. RESULTS: From RNA sequencing, we identified RNA signatures that were induced or suppressed following exposure to ciprofloxacin. Significant shifts at the transcript level were observed as early as 10 min after antibiotic exposure. Lastly, we confirmed marker expression profiles with concordant MIC results from traditional culture-based AST and validated across 11 K. pneumoniae isolates. recA, coaA and metN transcripts harbour the most sensitive susceptibility information and were selected as our top markers. CONCLUSIONS: Our results suggest that RNA signature is a promising approach to AST development, resulting in faster clinical diagnosis and treatment of infectious disease. This approach is potentially applicable in other models including other pathogens exposed to different classes of antibiotics.
Asunto(s)
Infecciones por Klebsiella , Klebsiella pneumoniae , Antibacterianos/farmacología , Ciprofloxacina/farmacología , Fluoroquinolonas/farmacología , Humanos , Infecciones por Klebsiella/tratamiento farmacológico , Klebsiella pneumoniae/genética , Pruebas de Sensibilidad Microbiana , ARNRESUMEN
In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data-from patient records to imaging-graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters and with minimal to no retraining. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pretraining, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way toward clinically meaningful predictions.
RESUMEN
Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across diverse biological contexts, such as tissues and cell types, remains a significant challenge for existing algorithms. We introduce Pinnacle, a flexible geometric deep learning approach that is trained on contextualized protein interaction networks to generate context-aware protein representations. Leveraging a human multi-organ single-cell transcriptomic atlas, Pinnacle provides 394,760 protein representations split across 156 cell type contexts from 24 tissues and organs. Pinnacle's contextualized representations of proteins reflect cellular and tissue organization and Pinnacle's tissue representations enable zero-shot retrieval of the tissue hierarchy. Pretrained Pinnacle's protein representations can be adapted for downstream tasks: to enhance 3D structure-based protein representations for important protein interactions in immuno-oncology (PD-1/PD-L1 and B7-1/CTLA-4) and to study the effects of drugs across cell type contexts. Pinnacle outperforms state-of-the-art, yet context-free, models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases, and can pinpoint cell type contexts that predict therapeutic targets better than context-free models (29 out of 156 cell types in rheumatoid arthritis; 13 out of 152 cell types in inflammatory bowel diseases). Pinnacle is a graph-based contextual AI model that dynamically adjusts its outputs based on biological contexts in which it operates.
RESUMEN
Therapeutics Data Commons (tdcommons.ai) is an open science initiative with unified datasets, AI models, and benchmarks to support research across therapeutic modalities and drug discovery and development stages. The Commons 2.0 (TDC-2) is a comprehensive overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new multimodal tasks and model frameworks, and comprehensive benchmarks. TDC-2 introduces over 1,000 multimodal datasets spanning approximately 85 million cells, pre-calculated embeddings from 5 state-of-the-art single-cell models, and a biomedical knowledge graph. TDC-2 drastically expands the coverage of ML tasks across therapeutic pipelines and 10+ new modalities, spanning but not limited to single-cell gene expression data, clinical trial data, peptide sequence data, peptidomimetics protein-peptide interaction data regarding newly discovered ligands derived from AS-MS spectroscopy, novel 3D structural data for proteins, and cell-type-specific protein-protein interaction networks at single-cell resolution. TDC-2 introduces multimodal data access under an API-first design using the model-view-controller paradigm. TDC-2 introduces 7 novel ML tasks with fine-grained biological contexts: contextualized drug-target identification, single-cell chemical/genetic perturbation response prediction, protein-peptide binding affinity prediction task, and clinical trial outcome prediction task, which introduce antigen-processing-pathway-specific, cell-type-specific, peptide-specific, and patient-specific biological contexts. TDC-2 also releases benchmarks evaluating 15+ state-of-the-art models across 5+ new learning tasks evaluating models on diverse biological contexts and sampling approaches. Among these, TDC-2 provides the first benchmark for context-specific learning. TDC-2, to our knowledge, is also the first to introduce a protein-peptide binding interaction benchmark.
RESUMEN
Summary: Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology, focusing on molecular/cellular networks but also on other biological network types such as biomedical knowledge graphs, patient similarity networks, brain networks, and social/contact networks relevant to disease spread. In more detail, we highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on future directions of network biology. Additionally, we discuss scientific communities, educational initiatives, and the importance of fostering diversity within the field. This article establishes a roadmap for an immediate and long-term vision for network biology. Availability and implementation: Not applicable.
RESUMEN
Rare Mendelian disorders pose a major diagnostic challenge and collectively affect 300-400 million patients worldwide. Many automated tools aim to uncover causal genes in patients with suspected genetic disorders, but evaluation of these tools is limited due to the lack of comprehensive benchmark datasets that include previously unpublished conditions. Here, we present a computational pipeline that simulates realistic clinical datasets to address this deficit. Our framework jointly simulates complex phenotypes and challenging candidate genes and produces patients with novel genetic conditions. We demonstrate the similarity of our simulated patients to real patients from the Undiagnosed Diseases Network and evaluate common gene prioritization methods on the simulated cohort. These prioritization methods recover known gene-disease associations but perform poorly on diagnosing patients with novel genetic disorders. Our publicly-available dataset and codebase can be utilized by medical genetics researchers to evaluate, compare, and improve tools that aid in the diagnostic process.
Asunto(s)
Pacientes , Enfermedades Raras , Humanos , Simulación por Computador , Fenotipo , Enfermedades Raras/diagnóstico , Enfermedades Raras/genéticaRESUMEN
Networks-or graphs-are universal descriptors of systems of interacting elements. In biomedicine and healthcare, they can represent, for example, molecular interactions, signalling pathways, disease co-morbidities or healthcare systems. In this Perspective, we posit that representation learning can realize principles of network medicine, discuss successes and current limitations of the use of representation learning on graphs in biomedicine and healthcare, and outline algorithmic strategies that leverage the topology of graphs to embed them into compact vectorial spaces. We argue that graph representation learning will keep pushing forward machine learning for biomedicine and healthcare applications, including the identification of genetic variants underlying complex traits, the disentanglement of single-cell behaviours and their effects on health, the assistance of patients in diagnosis and treatment, and the development of safe and effective medicines.
Asunto(s)
Atención a la Salud , Aprendizaje Automático , HumanosRESUMEN
Charcot-Marie-Tooth type 1A (CMT1A) is typically characterised as a childhood-onset, symmetrical, length-dependent polyneuropathy with a gradual progressive clinical course. Acute to subacute neurological deterioration in CMT1A is rare, and has been reported secondary to overlap pathologies including inflammatory neuropathy. We identified two patients with CMT1A who presented with acute to subacute, atraumatic, entrapment neuropathies as an initial symptom. A superimposed inflammatory neuropathy was excluded. Both patients had a diffuse demyelinating polyneuropathy, with markedly low motor nerve conduction velocities (<20 m/s). In both patients, we demonstrated symptomatic and asymptomatic partial conduction blocks at multiple entrapment sites. Nerve ultrasound findings in our patients demonstrated marked diffuse nerve enlargement, more pronounced at non-entrapment sites compared to entrapment sites. We discuss ways to distinguish this condition from its other differentials. We propose pathophysiological mechanisms underlying this condition. We propose that CMT1A with acute to subacute, atraumatic, entrapment neuropathies to be a distinct phenotypic variant of CMT1A.
RESUMEN
BACKGROUNDGut decontamination (GD) can decrease the incidence and severity of acute graft-versus-host disease (aGVHD) in murine models of allogeneic hematopoietic cell transplantation (HCT). In this pilot study, we examined the impact of GD on gut microbiome composition and the incidence of aGVHD in HCT patients.METHODSWe randomized 20 patients undergoing allogeneic HCT to receive (GD) or not receive (no-GD) oral vancomycin-polymyxin B from day -5 through neutrophil engraftment. We evaluated shotgun metagenomic sequencing of serial stool samples to compare the composition and diversity of the gut microbiome between study arms. We assessed clinical outcomes in the 2 arms and performed strain-specific analyses of pathogens that caused bloodstream infections (BSI).RESULTSThe 2 arms did not differ in the predefined primary outcome of Shannon diversity of the gut microbiome at 2 weeks post-HCT (genus, P = 0.8; species, P = 0.44) or aGVHD incidence (P = 0.58). Immune reconstitution of T cell and B cell subsets was similar between groups. Five patients in the no-GD arm had 8 BSI episodes versus 1 episode in the GD arm (P = 0.09). The BSI-causing pathogens were traceable to the gut in 7 of 8 BSI episodes in the no-GD arm, including Staphylococcus species.CONCLUSIONWhile GD did not differentially affect Shannon diversity or clinical outcomes, our findings suggest that GD may protect against gut-derived BSI in HCT patients by decreasing the prevalence or abundance of gut pathogens.TRIAL REGISTRATIONClinicalTrials.gov NCT02641236.FUNDINGNIH, Damon Runyon Cancer Research Foundation, V Foundation, Sloan Foundation, Emerson Collective, and Stanford Maternal & Child Health Research Institute.
Asunto(s)
Enfermedad Injerto contra Huésped , Trasplante de Células Madre Hematopoyéticas , Microbiota , Animales , Niño , Descontaminación , Enfermedad Injerto contra Huésped/etiología , Enfermedad Injerto contra Huésped/prevención & control , Trasplante de Células Madre Hematopoyéticas/efectos adversos , Humanos , Ratones , Proyectos PilotoRESUMEN
Mobile genetic elements (MGEs) contribute to bacterial adaptation and evolution; however, high-throughput, unbiased MGE detection remains challenging. We describe MGEfinder, a bioinformatic toolbox that identifies integrative MGEs and their insertion sites by using short-read sequencing data. MGEfinder identifies the genomic site of each MGE insertion and infers the identity of the inserted sequence. We apply MGEfinder to 12,374 sequenced isolates of 9 prevalent bacterial pathogens, including Mycobacterium tuberculosis, Staphylococcus aureus, and Escherichia coli, and identify thousands of MGEs, including candidate insertion sequences, conjugative transposons, and prophage elements. The MGE repertoire and insertion rates vary across species, and integration sites often cluster near genes related to antibiotic resistance, virulence, and pathogenicity. MGE insertions likely contribute to antibiotic resistance in laboratory experiments and clinical isolates. Additionally, we identified thousands of mobility genes, a subset of which have unknown function opening avenues for exploration. Future application of MGEfinder to commensal bacteria will further illuminate bacterial adaptation and evolution.