检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ramesh, Krithik Siddiqui, Sameed M. Gu, Albert mitzenmacher, Michael D. Sabeti, Pardis C. Broad Institute of MIT and Harvard CambridgeMA02142 United States Massachusetts Institute of Technology CambridgeMA02139 United States Computational and Systems Biology Program Massachusetts Institute of Technology CambridgeMA02139 United States Machine Learning Department Carnegie Mellon University PittsburgPA15213 United States School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Organismic and Evolutionary Biology Harvard University CambridgeMA02138 United States Department of Immunology and Infectious Diseases Harvard T.H. Chan School of Public Health Harvard University BostonMA02115 United States Howard Hughes Medical Institute Chevy ChaseMD20815 United States

Deep learning architectures such as convolutional neural networks and Transformers have revolutionized biological sequence modeling, with recent advances driven by scaling up foundation and task-specific models. The computational resources and large datasets required, however, limit their applicability in biological contexts. We introduce Lyra, a subquadratic architecture for sequence modeling, grounded in the biological framework of epistasis for understanding sequence-to-function relationships. Mathematically, we demonstrate that state space models efficiently capture global epistatic interactions and combine them with projected gated convolutions for modeling local relationships. We demonstrate that Lyra is performant across over 100 wide-ranging biological tasks, achieving state-of-the-art (SOTA) performance in many key areas, including protein fitness landscape prediction, biophysical property prediction (e.g. disordered protein region functions) peptide engineering applications (e.g. antibody binding, cell-penetrating peptide prediction), RNA structure analysis, RNA function prediction, and CRISPR guide design. It achieves this with orders-of-magnitude improvements in inference speed and reduction in parameters (up to 120,000-fold in our tests) compared to recent biology foundation models. Using Lyra, we were able to train and run every task in this study on two or fewer GPUs in under two hours, democratizing access to biological sequence modeling at SOTA performance, with potential applications to many fields. © 2025, CC BY-NC-ND.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples

arXiv

引用

arXiv 2023年

作者： Song, Andrew H. Williams, Mane Williamson, Drew F.K. Jaume, Guillaume Zhang, Andrew Chen, Bowen Serafin, Robert Liu, Jonathan T.C. Baras, Alex Parwani, Anil V. Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital Harvard Medical School BostonMA United States Department of Pathology Massachusetts General Hospital Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Mechanical Engineering Bioengineering Laboratory Medicine & Pathology University of Washington SeattleWA United States Department of Pathology Johns Hopkins Hospital BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins Hospital BaltimoreMD United States Department of Pathology The Ohio State University ColumbusOH United States

Human tissue consists of complex structures that display a diversity of morphologies, forming a tissue microenvironment that is, by nature, three-dimensional (3D). However, the current standard-of-care involves slicing 3D tissue specimens into two-dimensional (2D) sections and selecting a few for microscopic evaluation1,2, with concomitant risks of sampling bias and misdiagnosis3–6. To this end, there have been intense efforts to capture 3D tissue morphology and transition to 3D pathology, with the development of multiple high-resolution 3D imaging modalities7–18. However, these tools have had little translation to clinical practice as manual evaluation of such large data by pathologists is impractical and there is a lack of computational platforms that can efficiently process the 3D images and provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy12–14 or microcomputed tomography15,16 and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting that there is value in capturing larger extents of spatially heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, M

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Multiple Doses of Exogenous FSTL1 Delivered with an Epicardial Reservoir Improve Cardiac Function, Healing and Angiogenesis after a Myocardial Infarction

SSRN

引用

SSRN 2023年

作者： Varela, Claudia E. Monahan, David S. Islam, Shahrin Whyte, William Bonnemain, Jean Ngoy, Souen Fisch, Sudeshna Duffy, Garry P. Roche, Ellen T. Institute for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA United States Harvard-MIT Program in Health Sciences and Technology CambridgeMA United States University of Galway Galway Ireland Department of Mechanical Engineering Massachusetts Institute of Technology CambridgeMA United States Department of Adult Intensive Care Medicine Lausanne University Hospital University of Lausanne Lausanne Switzerland Department of Medicine Brigham & Women's Hospital Harvard Medical School BostonMA United States Advanced Materials and BioEngineering Research Centre AMBER University of Galway Galway Ireland

Epicardial delivery of human follistatin-like 1 protein (FSTL1) induces significant cardiac benefit following a myocardial infarction (MI). However, the optimal dosing regimen for maximal therapeutic benefit has not yet been elucidated. To investigate the impact of multiple FSTL1 doses, without the confounding effects of multiple surgical procedures for multidose delivery, alternative delivery strategies are needed. Here, we use an epicardial reservoir that allows non-invasive delivery of additional doses after implantation to investigate the impact of single, double, and triple FSTL1 dose regimens in a rat model of MI. Multidose delivery of FSTL1 improves ejection fraction (3 doses), fractional shortening (1, 2 and 3 doses), and chamber stiffness (2 doses) 28 days after MI. Histologically, multiple FSTL1 doses increase ventricular wall thickness (2 and 3 doses) and reduce infarct size (1, 2, and 3 doses). We also demonstrate a dose-dependent increase in blood vessel number and density in the infarct zone, with three FSTL1 doses leading to the highest improvements. This study shows that multidose delivery of FSTL1 improves cardiac function, healing, and angiogenesis following MI. The epicardial delivery platform used here may be essential in optimizing dosing regimens of various bioagent combinations for a range of clinical indications. © 2023, The Authors. All rights reserved.

关键词： Controlled drug delivery

来源：评论

学校读者我要写书评

暂无评论

AI-driven 3D Spatial Transcriptomics

arXiv

引用

arXiv 2025年

作者： Almagro-Pérez, Cristina Song, Andrew H. Weishaupt, Luca Kim, Ahrong Jaume, Guillaume Williamson, Drew F.K. Hemker, Konstantin Lu, Ming Y. Singh, Kritika Chen, Bowen Le, Long Phi Baras, Alexander S. Jiang, Sizun Bashashati, Ali Liu, Jonathan T.C. Mahmood, Faisal Department of Pathology Mass General Brigham Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Pathology Pusan National University Busan Korea Republic of Department of Pathology and Laboratory Medicine Emory University School of Medicine AtlantaGA United States Department of Computer Science & Technology University of Cambridge Cambridge United Kingdom Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Rutgers Robert Wood Johnson Medical School New BrunswickNJ United States Department of Pathology Johns Hopkins Hospital BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins Hospital BaltimoreMD United States Broad Institute of Harvard and MIT CambridgeMA United States Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School BostonMA United States Department of Pathology Dana Farber Cancer Institute BostonMA United States Department of Pathology and Laboratory Medicine University of British Columbia VancouverBC Canada School of Biomedical Engineering University of British Columbia VancouverBC Canada Department of Mechanical Engineering Bioengineering Laboratory Medicine & Pathology University of Washington SeattleWA United States Harvard Data Science Initiative Harvard University CambridgeMA United States

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications1. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue2–4. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability5–8. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology–transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://***/. © 2025, CC BY-NC-ND.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Pale Red Dot: A Large, Robust Architecture for Human Settlements on Mars

Pale Red Dot: A Large, Robust Architecture for Human Settlem...

引用

Accelerating Space Commerce, Exploration, and New Discovery Conference, ASCEND 2023

作者： Lordos, George Hoying, Madelyn McKinney, Lanie Webb, Alisa Lin, Yuying Martin, Estelle Beilstein, John Miller, Duncan Villegas, David Sepulveda, Francisco AlSadah, Yousif Iyer, Divya O’Neill, Cormac Patel, Palak Garcia, Ignacio Arzuaga Azzouz, H. Chan, Wing Lam Eyre, Ezra Gleason, Dane Romero, Elizabeth Arias, Liliana Orozco, Omar Gentgen, Chloe Latyshev, Kir Hoffman, Jeffrey de Weck, Olivier Ikinci, Meltem Lordos, Alexandros Aeronautics and Astronautics Massachusetts Institute of Technology 33-409 CambridgeMA02139 United States Massachusetts Institute of Technology Harvard-MIT Health Sciences and Technology Program and MIT Aeronautics and Astronautics 33-409 CambridgeMA02139 United States Massachusetts Institute of Technology CambridgeMA02139 United States Aeronautics and Astronautics Massachusetts Institute of Technology 77 Mass Ave. 33-409 CambridgeMA02139 United States System Design and Management Massachusetts Institute of Technology 77 Mass Ave. E40-300 CambridgeMA02139 United States Mechanical Engineering Massachusetts Institute of Technology 77 Mass Ave. 33-409 CambridgeMA02139 United States Civil and Environmental Engineering Massachusetts Institute of Technology 77 Mass Ave. CambridgeMA02139 United States Electrical Engineering Massachusetts Institute of Technology 77 Mass Ave. CambridgeMA02139 United States Nuclear Science and Engineering Massachusetts Institute of Technology 77 Mass Ave. CambridgeMA02139 United States Computer Science and Engineering Massachusetts Institute of Technology 77 Mass Ave. CambridgeMA02139 United States Massachusetts Institute of Technology 77 Mass Ave. 37-219 CambridgeMA02139 United States Massachusetts Institute of Technology 77 Mass Ave. 33-410 CambridgeMA02139 United States Behavioral Economics University of Cyprus Nicosia Cyprus Department of Psychology University of Cyprus Nicosia Cyprus

ISBN: (数字)9781624107054

ISBN: (纸本)9781624107054

We propose a ten-yearMars mission to establish Earth-independence and support efficient, safe, and sustainable science and exploration goals. The campaign begins with a series of precursor missions, starting with the Artemis program, followed by robotic missions to performsite surveys and selection, de-risk technologies, and to start stockpiling in-situ water and propellant. Robotic Cargo Starships would depart first in 2035 to deliver and deploy approximately 5,800 tons of habitats, nuclear microreactors, farmmodules, manufacturing and ISRU systems. In 2040, two Crew Starships carrying 36 persons would land onMars to establish two close-proximity villages. The lifecycle cost is estimated at $81 billion, with a peak annual cost of $6.6 billion. To meet RASC-AL competition requirements, intended to motivate the exploration of highly self-reliant architecture concepts, resupply from Earth was constrained to only 5 metric tons every two years and minimum surface endurance was set at 7 years. The risks to human life and to critical systems increase exponentially over a minimally-resupplied, 7-10 year mission toMars. Our approach focused on identifying capabilities to mitigate known and unknown risks. Using a high-fidelity crew time model, we found that large architectures, with their economies of scale and productivity gains from specialization, are essential to robustly support the necessary capabilities. The model also shows that small 7-year missions of 12 persons or less cannot provide value in terms of free surface traverse time for science and exploration. Given the necessity of a large, complex architecture, we then sought out efficiencies and synergies (value engineering) in order to make the mission feasible and affordable. In the process, we identified more benefits that are enabled only by large missions, including the creation of a true community on Mars with sufficient social complexity for humans to thrive, and the geopolitically compelling option to inclu

关键词： Value engineering

来源：评论

学校读者我要写书评

暂无评论

Left Atrial Appendage Occlusion: Current Stroke Prevention Strategies and a Shift Toward Data-Driven, Patient-Specific Approaches

引用

Journal of the Society for Cardiovascular Angiography and Interventions 2022年第5期1卷 100405-100405页

作者： Mendez, Keegan Kennedy, Darragh G. Wang, Dee Dee Roche, Ellen T. Harvard/MIT Health Sciences and Technology Program Massachusetts Institute of Technology Cambridge MA United States Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA United States Department of Biomedical Engineering Columbia University New York NY United States Henry Ford Health Detroit MI United States Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA United States

The left atrial appendage (LAA) is a complex structure with unknown physiologic function protruding from the main body of the left atrium. In patients with atrial fibrillation, the left atrium does not contract effectively. Insufficient atrial and LAA contractility predisposes the LAA morphology to hemostasis and thrombus formation, leading to an increased risk of cardioembolic events. Oral anticoagulation therapies are the mainstay of stroke prevention options for patients;however, not all patients are candidates for long-term oral anticoagulation. Percutaneous occlusion devices are an attractive alternative to long-term anticoagulation therapy, although they are not without limitations, such as peri-implant leakage and device-related thrombosis. Although efforts have been made to reduce these risks, significant interpatient heterogeneity inevitably yields some degree of device-anatomy mismatch that is difficult to resolve using current devices and can ultimately lead to insufficient occlusion and poor patient outcomes. In this state-of-the-art review, we evaluated the anatomy of the LAA as well as the current pathophysiologic understanding and stroke prevention strategies used in the management of the risk of stroke associated with atrial fibrillation. We highlighted recent advances in computed tomography imaging, preprocedural planning, computational modeling, and novel additive manufacturing techniques, which represent the tools needed for a paradigm shift toward patient-centric LAA occlusion. Together, we envisage that these techniques will facilitate a pipeline from the imaging of patient anatomy to patient-specific computational and bench-top models that enable customized, data-driven approaches for LAA occlusion that are engineered specifically to meet each patient's unique needs. © 2022 The Authors

关键词： computed tomography imaging left atrial appendage left atrial appendage occlusion stroke

来源：评论

学校读者我要写书评

暂无评论

Oncogenic RIT1 mutations in lung adenocarcinoma (vol 33, pg 4418, 2014)

引用

ONCOGENE 2022年第19期41卷 2788-2788页

作者： Berger, A. H. Imielinski, M. Duke, F. Wala, J. Kaplan, N. Shi, G. -X Andres, D. A. Meyerson, M. Cancer Program The Broad Institute of Harvard and M.I.T. 7 Cambridge Center Cambridge MA USA Department of Medical Oncology Dana Farber Cancer Institute Boston MA USA Department of Pathology Massachusetts General Hospital Boston MA USA Department of Pathology Harvard Medical School Boston MA USA Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology Cambridge MA USA Department of Molecular and Cellular Biochemistry University of Kentucky College of Medicine Lexington KY USA

来源：评论

学校读者我要写书评

暂无评论

A theoretical model of acousto-optic modulated diffuse correlation spectroscopy

A theoretical model of acousto-optic modulated diffuse corre...

引用

Clinical and Translational Biophotonics, Translational 2020

作者： Robinson, mitchell B. Sakadžić, Sava Carp, Stefan A. Boas, David A. Franceschini, Maria Angela Optics at Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Harvard Medical School 149 13th St. CharlestownMA United States Harvard-MIT Program in Health Sciences and Technology Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA United States Neurophotonics Center Department of Biomedical Engineering Boston University 610 Commonwealth Avenue BostonMA United States

In-vivo, optical measurements of cerebral blood flow are confounded by superficial blood flow. Here, we present acousto-optic modulated diffuse correlation spectroscopy (AOM-DCS) for blood flow monitoring, showing goo... 详细信息

ISBN: (纸本)9781943580743

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

Laser pulse shaping to increase brain blood flow sensitivity of time-domain diffuse correlation spectroscopy

Laser pulse shaping to increase brain blood flow sensitivity...

引用

Clinical and Translational Biophotonics, Translational 2020

作者： Carp, Stefan A. Peruch, Adriano Tamborini, Davide Mazumder, Dibbyan Wu, Melissa M. Chan, Suk-Tak Robinson, mitchell Qu, Jason Z. Delpont, Guillaume Schoenau, Thomas Bourdon, Alain Franceschini, Maria A. Optics Division Athinoula A. Martinos Center for Biomedical Imaging Department of Radiology Massachusetts General Hospital Harvard Medical School CharlestownMA02129 United States Harvard-MIT Program in Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA02139 United States Department of Anesthesia Critical Care and Pain Medicine Massachusetts General Hospital Harvard Medical School BostonMA02115 United States PicoQuant GmbH Berlin Germany PicoQuant USA West SpringfieldMA United States

Time-domain diffuse correlation spectroscopy (TD-DCS) aims to increase cerebral blood flow (CBF) sensitivity by discriminating photon time of flight. We report on the optimization of the laser pulse shape to maximize ... 详细信息

ISBN: (纸本)9781943580743

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

Enhancing Discovery of Genetic Variants for Posttraumatic Stress Disorder Through Integration of Quantitative Phenotypes and Trauma Exposure Information (vol 91, pg 626, 2022)

引用

BIOLOGICAL PSYCHIATRY 2022年第7期91卷 690-690页

作者： Maihofer, Adam X. Vinkers, Christiaan H. Department of Psychiatry University of California San Diego La Jolla California Department of Family Medicine and Public Health University of California San Diego La Jolla California Center of Excellence for Stress and Mental Health Veterans Affairs Healthcare System San Diego California. Electronic address: amaihofer@health.ucsd.edu. Department of Epidemiology Harvard T.H. Chan School of Public Health Boston Massachusetts Department of Psychiatry Massachusetts General Hospital Boston Massachusetts. Social Genetic and Developmental Psychiatry Centre Institute of Psychiatry Psychology and Neuroscience King's College London London United Kingdom National Institute of Health Research Maudsley Biomedical Research Centre King's College London London United Kingdom. Department of Psychiatry Harvard Medical School Boston Massachusetts Stanley Center for Psychiatric Research Broad Institute of MIT and Harvard Cambridge Massachusetts Center of Excellence in Depression and Anxiety Disorders Belmont Massachusetts. Department of Epidemiology Harvard T.H. Chan School of Public Health Boston Massachusetts Stanley Center for Psychiatric Research Broad Institute of MIT and Harvard Cambridge Massachusetts. Department of Psychiatry University of California San Diego La Jolla California Center of Excellence for Stress and Mental Health Veterans Affairs Healthcare System San Diego California Research Service Veterans Affairs Healthcare System San Diego California. Duke Molecular Physiology Institute Duke University School of Medicine Durham North Carolina. Department of Psychiatry Veterans Affairs Connecticut Healthcare System West Haven Connecticut Department of Psychiatry Yale University School of Medicine New Haven Connecticut. Department of Epidemiology Harvard T.H. Chan School of Public Health Boston Massachusetts Department of Epidemiology Columbia University Mailman School of Public Health New York. Division of Mental Health Atlanta Veterans Affairs Medical Center

BACKGROUND: Posttraumatic stress disorder (PTSD) is heritable and a potential consequence of exposure to traumatic stress. Evidence suggests that a quantitative approach to PTSD phenotype measurement and incorporation of lifetime trauma exposure (LTE) information could enhance the discovery power of PTSD genome-wide association studies (GWASs). METHODS: A GWAS on PTSD symptoms was performed in 51 cohorts followed by a fixed-effects meta-analysis (N = 182,199 European ancestry participants). A GWAS of LTE burden was performed in the UK Biobank cohort (N = 132,988). Genetic correlations were evaluated with linkage disequilibrium score regression. Multivariate analysis was performed using Multi-Trait Analysis of GWAS. Functional mapping and annotation of leading loci was performed with FUMA. Replication was evaluated using the Million Veteran program GWAS of PTSD total symptoms. RESULTS: GWASs of PTSD symptoms and LTE burden identified 5 and 6 independent genome-wide significant loci, respectively. There was a 72% genetic correlation between PTSD and LTE. PTSD and LTE showed largely similar patterns of genetic correlation with other traits, albeit with some distinctions. Adjusting PTSD for LTE reduced PTSD heritability by 31%. Multivariate analysis of PTSD and LTE increased the effective sample size of the PTSD GWAS by 20% and identified 4 additional loci. Four of these 9 PTSD loci were independently replicated in the Million Veteran program. CONCLUSIONS: Through using a quantitative trait measure of PTSD, we identified novel risk loci not previously identified using prior case-control analyses. PTSD and LTE have a high genetic overlap that can be leveraged to increase discovery power through multivariate methods.

关键词： GWAS Genetics Heritability PTSD PheWAS Trauma

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：