Camilo Espinosa
A5033491491- Single-cell and spatial transcriptomics
- Birth, Development, and Health
- Pregnancy and preeclampsia studies
- Neonatal Respiratory Health Research
- Machine Learning in Healthcare
- Gestational Diabetes Research and Management
- Immune cells in cancer
- Radiomics and Machine Learning in Medical Imaging
- Distributed and Parallel Computing Systems
- Advanced Neural Network Applications
- Neonatal and fetal brain pathology
- Preterm Birth and Chorioamnionitis
- Child Nutrition and Water Access
- Dementia and Cognitive Impairment Research
- Bioinformatics and Genomic Networks
- Metabolomics and Mass Spectrometry Studies
- T-cell and B-cell Immunology
- Infant Development and Preterm Care
- Enhanced Recovery After Surgery
- AI in cancer detection
- Cell Image Analysis Techniques
- Infant Nutrition and Health
- Parkinson's Disease Mechanisms and Treatments
- Immunotherapy and Immune Responses
- Neuroinflammation and Neurodegeneration Mechanisms
Stanford University
2020-2025
Stanford Medicine
2020-2025
District University of Bogotá
2020
Dana-Farber Cancer Institute
2018
Whitehead Institute for Biomedical Research
2017
Massachusetts Institute of Technology
2017
Omics studies produce a large number of measurements, enabling the development, validation and interpretation systems-level biological models. Large cohorts are required to power these complex models; yet, cohort size remains limited due clinical budgetary constraints. We introduce omics multimodal analysis enhanced with transfer learning (COMET), machine framework that incorporates large, observational electronic health record databases improve small datasets from studies. By pretraining on...
Ipilimumab, a monoclonal antibody that recognizes cytotoxic T lymphocyte antigen (CTLA)-4, was the first approved "checkpoint"-blocking anticancer therapy. In mouse tumor models, response to antibodies against CTLA-4 depends entirely on expression of Fcγ receptor (FcγR), which may facilitate antibody-dependent cellular phagocytosis, but contribution simple blockade remains unknown. To understand role in complete absence Fc-dependent functions, we developed H11, high-affinity alpaca heavy...
Significance CD47 is a broadly expressed membrane-associated innate immune regulator that acts as ligand of signal regulatory protein alpha (SIRPα) on antigen-presenting cells to inhibit phagocytosis. In xenograft models, inhibitors the CD47–SIRPα interaction selectively target tumor-expressed and improve antibody responses tumors by enhancing antibody-dependent cellular syngeneic settings, however, broad expression hematopoietic lineage creates formidable antigen sink increases toxicity. We...
Programmed death ligand 1 (PD-L1) is expressed on a number of immune and cancer cells, where it can downregulate antitumor responses. Its expression has been linked to metabolic changes in these cells. Here we develop radiolabeled camelid single-domain antibody (anti-PD-L1 VHH) track PD-L1 by immuno-positron emission tomography (PET). PET-CT imaging shows robust specific signal brown adipose tissue (BAT). We confirm adipocytes demonstrate that intensity does not change response cold exposure...
<h3>Importance</h3> Worldwide, preterm birth (PTB) is the single largest cause of deaths in perinatal and neonatal period associated with increased morbidity young children. The PTB multifactorial, development generalizable biological models may enable early detection guide therapeutic studies. <h3>Objective</h3> To investigate ability transcriptomics proteomics profiling plasma metabolomics analysis urine to identify measurements PTB. <h3>Design, Setting, Participants</h3> This...
Although prematurity is the single largest cause of death in children under 5 years age, current definition prematurity, based on gestational lacks precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment adverse neonatal outcomes newborns deep learning model that uses electronic health records (EHRs) to predict wide range over period starting shortly before conception and ending months after birth. By linking EHRs Lucile Packard Children’s Hospital...
Preeclampsia is a complex disease of pregnancy whose physiopathology remains unclear. We developed machine-learning models for early prediction preeclampsia (first 16 weeks pregnancy) and over gestation by analyzing six omics datasets from longitudinal cohort pregnant women. For pregnancy, model using nine urine metabolites had the highest accuracy was validated on an independent (area under receiver-operating characteristic curve [AUC] = 0.88, 95% confidence interval [CI] [0.76, 0.99]...
Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling multivariate modeling to investigate biological signatures these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples 231...
Abstract Advanced measurement and data storage technologies have enabled high-dimensional profiling of complex biological systems. For this, modern multiomics studies regularly produce datasets with hundreds thousands measurements per sample, enabling a new era precision medicine. Correlation analysis is an important first step to gain deeper insights into the coordination underlying processes such However, construction large correlation networks in remains major computational challenge...
Abstract Preterm birth (PTB) is the leading cause of infant mortality globally. Research has focused on developing predictive models for PTB without prioritizing cost-effective interventions. Physical activity and sleep present unique opportunities interventions in low- middle-income populations (LMICs). However, objective measurement physical remains challenging self-reported metrics suffer from low-resolution accuracy. In this study, we use data collected using a wearable device comprising...
Abstract High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity cellular systems. We introduce VoPo ( https://github.com/stanleyn/VoPo ), a machine learning algorithm predictive modeling and comprehensive visualization captured in large datasets. In three mass cytometry datasets, with largest measuring hundreds millions cells over samples, defines phenotypically functionally homogeneous cell populations. further...
Abstract Assay for Transposase Accessible Chromatin by sequencing (ATAC-seq) accurately depicts the chromatin regulatory state and altered mechanisms guiding gene expression in disease. However, bulk entangles information from different cell types obscures cellular heterogeneity. To address this, we developed Cellformer, a deep learning method that deconvolutes ATAC-seq into type-specific across whole genome. Cellformer enables cost-effective open profiling large cohorts. Applied to 191...
Multiple lines of evidence support peripheral organs in the initiation or progression Lewy body disease (LBD), a spectrum neurodegenerative diagnoses that include Parkinson's Disease (PD) without with dementia (PDD) and bodies (DLB). However, potential contribution immune response to LBD remains unclear. This study aims characterize responses unique participants at single-cell resolution highlight biomarkers increase mechanistic understanding pathogenesis humans.
While medication intake is common among pregnant women, safety remains underexplored, leading to unclear guidance for patients and healthcare professionals. PregMedNet addresses this gap by providing a multifaceted maternal framework based on systematic analysis of 1.19 million mother-baby dyads from U.S. claims databases. A novel confounding adjustment pipeline was applied systematically control confounders multiple medication-disease pairs, robustly identifying both known effects. Notably,...
One in ten neonates are admitted to neonatal intensive care units, highlighting the need for precise interventions. However, application of artificial intelligence (AI) guiding remains underexplored. Total parenteral nutrition (TPN) is a life-saving treatment preterm neonates; however, implementation therapy its current form subjective, error-prone and resource-consuming. Here, we developed TPN2.0—a data-driven approach that optimizes standardizes TPN using information collected routinely...
Abstract INTRODUCTION Post‐mortem analysis provides definitive diagnoses of neurodegenerative diseases; however, only a few can be diagnosed during life. METHODS This study employed statistical tools and machine learning to predict 17 neuropathologic lesions from cohort 6518 individuals using 381 clinical features (Table S1 ). The multisite data allowed validation the model's robustness by splitting train/test sets sites. A similar was performed for predicting Alzheimer's disease (AD) change...
Abstract Translational biology posits a strong bi-directional link between clinical phenotypes and patient’s biological profile. By leveraging this link, we can efficiently deconvolute pre-existing information into profiles. However, traditional computational tools are limited in their ability to resolve because of the relatively small sizes paired clinical–biological datasets for training high dimensionality/sparsity tabular data. Here, use state-of-the-art foundation models (FMs)...
Abstract Background Preclinical evidence suggests that young plasma has beneficial effects on multiple organ systems in aged mice. Whether exerts an aging human population remains highly controversial. Despite lacking data, donor infusions have been promoted for age-related conditions. Given the preclinical by attenuating inflammation, this study examined whether administering a protein fraction to elderly would exert anti-inflammatory and immune modulating humans, using surgery as tissue...