检索结果-内蒙古大学图书馆

Quantum variational autoencoder utilizing regularized mixed-state latent representations

学校读者我要写书评

暂无评论

Physical Review A 2025年第4期111卷 042416-042416页

作者： Gaoyuan Wang Jonathan Warrell Prashant S. Emani Mark Gerstein Program in Computational Biology and Bioinformatics Yale University New Haven Connecticut 06520 USA Department of Molecular Biophysics and Biochemistry Yale University New Haven Connecticut 06520 USA NEC Laboratories America Princeton New Jersey 08540 USA Department of Computer Science Yale University New Haven Connecticut 06520 USA Department of Statistics & Data Science Yale University New Haven Connecticut 06520 USA Department of Biomedical Informatics & Data Science Yale University New Haven Connecticut 06520 USA

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional representations that preserve essential information for downstream analysis. In classical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representation learning for subsequent tasks, and novel data generation. However, no quantum model has been proposed that exactly captures all of these features for direct application to quantum data on quantum computers. Some existing quantum models for data compression lack regularization of latent representations, thus preventing direct use for generation and control of generalization. Others are hybrid models with only some internal quantum components, impeding direct training on quantum data. To address this, we present a fully quantum framework, ζ-QVAE, which encompasses all the capabilities of classical VAEs and can be directly applied to map both classical and quantum data to a lower-dimensional space, while effectively reconstructing much of the original state from it. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodates various divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at every stage, it can utilize the full data density matrix and allow for a training objective defined on probabilistic mixtures of input data. Doing so, in turn, makes efficient optimization possible and has potential implications for private and federated learning. In addition to exploring the theoretical properties of ζ-QVAE, we demonstrate its performance on representative genomics and synthetic data. Our results indicate that ζ-QVAE consistently learns representations that better utilize the capacity of the latent space and exhibits similar or better performance compared with

关键词： Quantum computers

The effect of stereochemical constraints on the radius of gyration of folded proteins

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Logan, Jack A. Sumner, Jacob Grigas, Alex T. Shattuck, Mark D. O'Hern, Corey S. Department of Mechanical Engineering Yale University New HavenCT06520 United States Graduate Program in Computational Biology & Biomedical Informatics Yale University New HavenCT06520 United States Integrated Graduate Program in Physical and Engineering Biology Yale University New HavenCT06520 United States Benjamin Levich Institute and Physics Department The City College of New York New YorkNY10031 United States Department of Applied Physics Yale University New HavenCT06520 United States Department of Physics Yale University New HavenCT06520 United States

Proteins are composed of linear chains of amino acids that fold into complex three-dimensional structures. A general feature of folded proteins is that they are compact with a radius of gyration Rg(N) ∼ Nν that obeys power-law scaling with the number of amino acids N in each protein and ν ∼ 1/3. In this study, we investigate the internal scaling of the radius of gyration Rg(n) versus the chemical separation n between amino acids for all subchains of length n. We show that for globular proteins Rg(n) ∼ nν1,2 with a larger exponent ν1 > 1/3 for small n and a smaller exponent ν2 g(N) ∝ Nν. To describe this scaling behavior for Rg(n), we carry out folding simulations for a series of coarse-grained models for proteins beginning with the freely-jointed and freely-rotating chain models composed of spherical monomers and varying degrees of stereochemical constraints. We show that a minimal model, which coarse-grains amino acids into a single spherical backbone atom and one variable-sized spherical side-chain atom, and enforces bend- and dihedral-angle constraints, can recapitulate Rg(n) for x-ray crystal structures of globular proteins. In addition, this model predicts the correct average packing fraction and size of the hydrophobic core, which are two key physical features that can be used to distinguish between computational 'decoys' and correctly folded proteins in protein design applications. © 2025, CC BY.

关键词： Spheres

Generalization is not a universal guarantee: Estimating similarity to training data with an ensemble out-of-distribution metric

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Schreyer, W. Max Anderson, Christopher Thompson, Reid F. Computational Biology Program Oregon Health & Science University PortlandOR United States Department of Biomedical Engineering Oregon Health & Science University PortlandOR United States Portland VA Research Foundation PortlandOR United States Department of Radiation Medicine Oregon Health & Science University PortlandOR United States Department of Medical Informatics and Clinical Epidemiology Oregon Health & Science University PortlandOR United States Division of Hospital and Specialty Medicine VA Portland Healthcare System PortlandOR United States

Failure of machine learning models to generalize to new data is a core problem limiting the reliability of AI systems, partly due to the lack of simple and robust methods for comparing new data to the original training dataset. We propose a standardized approach for assessing data similarity in a model-agnostic manner by constructing a supervised autoencoder for generalizability estimation (SAGE). We compare points in a low-dimensional embedded latent space, defining empirical probability measures for k-Nearest Neighbors (kNN) distance, reconstruction of inputs and task-based performance. As proof of concept for classification tasks, we use MNIST and CIFAR-10 to demonstrate how an ensemble output probability score can separate deformed images from a mixture of typical test examples, and how this SAGE score is robust to transformations of increasing severity. As further proof of concept, we extend this approach to a regression task using non-imaging data (UCI Abalone). In all cases, we show that out-of-the-box model performance increases after SAGE score filtering, even when applied to data from the model’s own training and test datasets. Our out-of-distribution scoring method can be introduced during several steps of model construction and assessment, leading to future improvements in responsible deep learning implementation. Copyright © 2025, The Authors. All rights reserved.

关键词：

Characterizing Emergency Department Care for Patients With Histories of Incarceration

学校读者我要写书评

暂无评论

JACEP Open 2025年第1期6卷 100022-100022页

作者： Huang, Thomas Socrates, Vimig Ovchinnikova, Polina Faustino, Isaac Kumar, Anusha Safranek, Conrad Chi, Ling Wang, Emily A. Puglisi, Lisa Wong, Ambrose H. Wang, Karen H. Taylor, R. Andrew Department of Emergency Medicine Yale School of Medicine New Haven CT United States Department for Biomedical Informatics and Data Science Yale University School of Medicine New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States SEICHE Center for Health and Justice Yale School of Medicine New Haven CT United States Equity Research and Innovation Center Yale School of Medicine Yale University New Haven CT United States

Objectives: Patients with a history of incarceration experience bias from health care team members, barriers to privacy, and a multitude of health care disparities. We aimed to assess care processes delivered in emergency departments (EDs) for people with histories of incarceration. Methods: We utilized a fine-tuned large language model to identify patient incarceration status from 480,374 notes from the ED setting. We compared socio-demographic characteristics, comorbidities, and care processes, including disposition, restraint use, and sedation, between individuals with and without a history of incarceration. We then conducted multivariable logistic regression to assess the independent correlation of incarceration history and management in the ED while adjusting for demographic characteristics, health behaviors, presentation, and past medical history. Results: We found 1734 unique patient encounters with a history of incarceration from a total of 177,987 encounters. Patients with history of incarceration were more likely to be male, Black, Hispanic, or other race/ethnicity, currently unemployed or disabled, and had smoking and substance use histories, compared with those without. This cohort demonstrated higher odds of elopement (OR: 3.59 [95% CI: 2.41–5.12]), leaving against medical advice (OR: 2.39 [95% CI: 1.46–3.67]), and being subjected to sedation (OR: 3.89 [95% CI: 3.19–4.70]) and restraint use (OR: 3.76 [95% CI: 3.06–4.57]). After adjusting for covariates, the association between incarceration and elopement remained significant (adjusted odds ratio: 1.65 [95% CI: 1.08–2.43]), while associations with other dispositions, restraint use, and sedation did not persist. Conclusion: This study identified differences in patient characteristics and care processes in the ED for patients with histories of incarceration and demonstrated the potential of using natural language processing in measuring care processes in populations that are largely hidden, but highly prev

关键词： artificial intelligence emergency medicine incarceration large language models quality of health care

Sex differences in proteomics of cardiovascular disease – Results from the Yale-CMD registry

学校读者我要写书评

暂无评论

IJC Heart and Vasculature 2025年 58卷 101667-101667页

作者： Liu, Yihan Wang, Zuoheng Collins, Sean P. Testani, Jeffery Safdar, Basmah Program in Computational Biology & Biomedical informatics Yale University New Haven CT United States Department of Biostatistics Yale University School of Public Health New Haven CT United States Department of Biomedical Informatics & Data Science Yale University School of Medicine New Haven CT United States Department of Emergency Medicine Vanderbilt University Medical Center Veterans Affairs Tennessee Valley Healthcare System Geriatric Research Education and Clinical Center (GRECC) Nashville TN United States Section of Cardiovascular Medicine Department of Internal Medicine Yale University School of Medicine New Haven CT United States Department of Emergency Medicine Yale University School of Medicine New Haven CT United States

Aims This study assessed sex-specific proteomic profiles by cardiovascular disease (CVD) phenotype (coronary artery disease [CAD] vs coronary microvascular dysfunction [CMD]) and describe their role in sex-specific pathways. Methods: In a secondary biobank analysis of the Yale-CMD registry, adults with ischemic symptoms who underwent cardiac positron emission test/computed tomography were categorized as a) controls (normal coronary flow reserve (CFR) > 2 without perfusion defect or coronary calcification), b) having CMD (CFR < 2 without defect or calcification), or c) having CAD (known CAD or new perfusion defect). Using proximity extension assays (Olink® Explore 3072), we examined 2944 proteins. Differential protein expression was assessed using linear regression models, adjusting for age, race, body mass index, diabetes, dyslipidemia, hypertension, or smoking. Results: Of 190 patients, 91 provided blood samples (mean age, 56 years;66 %, females;48 %, controls;24 %, CAD;27 %, CMD). Among controls, 15 proteins showed sex differences (5 proteins upregulated in females, 10 in males;false discovery rate [FDR < 0.05]). Upregulated in CAD patients were FSHB in females and INSL3 and EDDM3B in males (FDR < 0.05). Among CMD patients, SCGB3A1 and HGFAC were higher in females;INSL3, SPINT3, EDDM3B, and KLK3 were higher in males (FDR < 0.05). Per pathway analysis, females showed upregulation of immune pathways in CAD and lipid and glucose metabolism pathways in CMD. Males showed upregulated endothelial regulation of blood flow in CAD and increased angiogenesis in CMD. Conclusions: Sex differences exist in the proteomic profiles of CAD and CMD patients, highlighting a need for precision medicine. © 2025

关键词： Coronary artery disease Coronary microvascular dysfunction Olink Precision medicine Proteomics Sex differences

Tuning the Size and Stiffness of Inflatable Particles

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pashine, Nidhi Wang, Dong Baines, Robert Goyal, Medha Shattuck, Mark D. O’Hern, Corey S. Kramer-Bottiglio, Rebecca Department of Mechanical Engineering Yale University New HavenCT06520 United States Department of Physics BioInspired Institute Syracuse University SyracuseNY13244 United States Department of Physics Benjamin Levich Institute City College of New York New York CityNY10031 United States Department of Physics Yale University New HavenCT06520 United States Department of Applied Physics Yale University New HavenCT06520 United States Graduate Program in Computational Biology & Biomedical Informatics Yale University New HavenCT06520 United States

We describe size-varying cylindrical particles made from silicone elastomers that can serve as building blocks for robotic granular materials. The particle size variation, which is achieved by inflation, gives rise to changes in stiffness under compression. We design and fabricate inflatable particles that can become stiffer or softer during inflation, depending on key parameters of the particle geometry, such as the ratio of the fillet radius to the wall thickness, r/t. We also conduct numerical simulations of the inflatable particles and show that they only soften during inflation when localization of large strains occurs in the regime r/t → 0. This work introduces novel particle systems with tunable size and stiffness that can be implemented in numerous soft robotic applications. © 2025, CC BY.

关键词： Stiffness

Mapping Emergency Medicine Data to the Observational Medical Outcomes Partnership Common Data Model: A Gap Analysis of the American College of Emergency Physicians Clinical Emergency Data Registry

学校读者我要写书评

暂无评论

JACEP Open 2025年第1期6卷 100016-100016页

作者： Cohen, Inessa Diao, Zihan Goyal, Pawan Gupta, Aarti Hawk, Kathryn Malcom, Bill Malicki, Caitlin Sharma, Dhruv Sweeney, Brian Weiner, Scott G. Venkatesh, Arjun Taylor, R. Andrew Department of Emergency Medicine Yale School of Medicine New Haven CT United States Section for Biomedical Informatics and Data Science Yale University School of Medicine New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States American College of Emergency Physicians Washington DC United States Department of Emergency Medicine Brigham and Women's Hospital Boston MA United States Center for Outcomes Research and Evaluation (CORE) Section of Cardiovascular Medicine Yale School of Medicine New Haven CT United States

Objectives: This study aims to conduct a gap analysis to determine the feasibility of mapping electronic health record data from the Clinical Emergency Data Registry (CEDR) to the Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM). Methods: We employed a structured approach using a custom-built comparison matrix. This matrix facilitated the alignment of CEDR data fields with the corresponding elements in the OMOP-CDM schema. Each field was evaluated for compatibility, with categorization into 3 distinct types: direct matches, fields requiring transformation, and fields with no OMOP-CDM equivalent. The mapping process was informed by consultations with the Observational Health Data Sciences and informatics community forums and was guided by existing documentation and best practices in data harmonization. We performed descriptive analyses, quantifying the extent of direct matches and identifying the specific transformations needed for each CEDR-CDM field to ensure compliance with the OMOP-CDM model. Results: Our analysis indicates a high degree of compatibility between CEDR and OMOP, with over 90% (244/269) of CEDR fields being successfully mapped. Specifically, 173 fields had direct matches, whereas 71 required transformations. Challenges identified include addressing fields unique to CEDR with no OMOP-CDM equivalent and managing the transformations required for proper alignment. Conclusion: The OMOP-CDM presents a promising framework for standardizing emergency medicine data, thereby enhancing future query automation, analytics, and cross-institutional collaboration. Despite the potential challenges in capturing unique CEDR fields and addressing necessary transformations, most emergency department data can be standardized within the OMOP-CDM, fostering broader insights and applications in research and public health. © 2024 The Author(s)

关键词： databases electronic health records emergency service informatics opioid/adverse effects quality of health care registries

Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yepeng Su, Xiaorui Ullanat, Varun Liang, Ivy Clegg, Lindsay Olabode, Damilola Ho, Nicholas John, Bino Gibbs, Megan Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA United States Program in Biological and Biomedical Sciences Harvard Medical School BostonMA United States Harvard College CambridgeMA United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca GaithersburgMD United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Program in Computational Biology Carnegie Mellon University PittsburghPA United States Imaging and Data Analytics Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University AllstonMA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative CambridgeMA United States

Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations, reducing late-stage clinical failures, and accelerating the development of precision therapies. Current models rely on structural or target-based features to identify high-efficacy, low-toxicity drug combinations. However, these approaches fail to incorporate the multimodal data necessary for accurate, clinically-relevant predictions. Here, we introduce MADRIGAL, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug combination effects across 953 clinical outcomes and 21,842 compounds, including combinations of approved drugs and novel compounds in development. MADRIGAL uses a transformer bottleneck module to unify preclinical drug data modalities while handling missing data during training and inference—a major challenge in multimodal learning. It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions. MADRIGAL performs virtual screening of anticancer drug combinations and supports polypharmacy management for type II diabetes and metabolic dysfunction-associated steatohepatitis (MASH). It identifies transporter-mediated drug interactions. MADRIGAL predicts resmetirom, the first and only FDA-approved drug for MASH, among therapies with the most favorable safety profile. It supports personalized cancer therapy by integrating genomic profiles from cancer patients. Using primary acute myeloid leukemia samples and patient-derived xenograft models, it predicts the efficacy of personalized drug combinations. Integrating MADRIGAL with a large language model allows users to describe clinical outcomes in natural language, improving safety assessment by identifying potential adverse interactions and toxicity risks. MADRIGAL provides a multimodal approach for designing combination therapies with improved predictive accuracy and clinical relevance. Copy

关键词： Diseases

Uncertainty abounds, what now?

学校读者我要写书评

暂无评论

Science 2025年第6740期387卷 1261页

作者： Dov Greenbaum Mark Gerstein The reviewer is at the Zvi Meitar Institute for Legal Implications of Emerging Technologies The reviewer is at the Harry Radzyner Law School The reviewer is at the Dina Recanati School of Medicine Reichman University Herzliya Israel The reviewer is at the Department of Biomedical Informatics and Data Science The reviewer is at the Program in Computational Biology and Bioinformatics The reviewer is at the Department of Computer Science Yale University New Haven CT USA.