A5024324107- Radiomics and Machine Learning in Medical Imaging
- Topic Modeling
- Enzyme Structure and Function
- Radiology practices and education
- Generative Adversarial Networks and Image Synthesis
- RNA modifications and cancer
- Viral Infectious Diseases and Gene Expression in Insects
- Cancer, Hypoxia, and Metabolism
- Receptor Mechanisms and Signaling
- Malaria Research and Control
- HIV/AIDS drug development and treatment
- Heat shock proteins research
- Blockchain Technology Applications and Security
- Signaling Pathways in Disease
- Artificial Intelligence in Healthcare and Education
- CRISPR and Genetic Engineering
- AI in cancer detection
- Biomedical Text Mining and Ontologies
- RNA Research and Splicing
- Transportation Planning and Optimization
- Digital Media Forensic Detection
- Advanced Malware Detection Techniques
- Machine Learning in Healthcare
- Traffic Prediction and Management Techniques
- Cybercrime and Law Enforcement Studies
University of Washington
2025
Tsinghua University
2019-2024
Center for Life Sciences
2020-2024
Microsoft (United States)
2024
Abstract Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands image tiles 1–3 . Prior models have often resorted to subsampling small portion for each slide, thus missing the important slide-level context 4 Here we present Prov-GigaPath, whole-slide foundation model pretrained on 1.3 billion 256 × in 171,189 whole slides from Providence, large US health network comprising 28 cancer centres. The originated more than 30,000...
Abstract GLUT4 is the primary glucose transporter in adipose and skeletal muscle tissues. Its cellular trafficking regulated by insulin signaling. Failed or reduced plasma membrane localization of associated with diabetes. Here, we report cryo-EM structures human bound to a small molecule inhibitor cytochalasin B (CCB) at resolutions 3.3 Å both detergent micelles lipid nanodiscs. CCB-bound exhibits an inward-open conformation. Despite nearly identical conformation transmembrane domain GLUT1,...
Abstract Human glucose transporters (GLUTs) are responsible for cellular uptake of hexoses. Elevated expression GLUTs, particularly GLUT1 and GLUT3, is required to fuel the hyperproliferation cancer cells, making GLUT inhibitors potential anticancer therapeutics. Meanwhile, inhibitor-conjugated insulin being explored mitigate hypoglycemia side effect therapy in type 1 diabetes. Reasoning that exofacial GLUT1/3 may be favored therapeutic applications, we report here engineering a GLUT3...
Promoters with desirable properties are crucial in biotechnological applications. Generative AI (GenAI) has demonstrated potential creating novel synthetic promoters significantly enhanced functionality. However, these methods' reliance on various programming frameworks and specific task-oriented contexts limits their flexibilities. Overcoming limitations is essential for researchers to fully leverage the power of GenAI design tasks.
Large foundation models show promise in biomedicine but face challenges clinical use due to performance gaps, accessibility, cost, and lack of scalable evaluation. Here we that open-source small multimodal can bridge these gaps radiology by generating free-text findings from chest X-ray images. Our data-centric approach leverages 697K curated image-text pairs train a specialized, domain-adapted encoder. We integrate this encoder with pre-trained language via lightweight adapter aligns image...
Plasmodium falciparum , the deadliest causal agent of malaria, caused more than half 229 million malaria cases worldwide in 2019. The emergence and spreading frontline drug-resistant strains are challenging to overcome battle against raise urgent demands for novel antimalarial agents. P . formate–nitrite transporter (PfFNT) is a potential drug target due its housekeeping role lactate efflux during intraerythrocytic stage. Targeting PfFNT, MMV007839 was identified as lead compound that kills...
The Traffic flow forecasting (TFF) problem is essential to modern intelligent transport systems (ITS). Massive data from contemporary have put forward the challenge of effectively capturing both latent spatial patterns and temporal dynamics traffic data, when an ITS doing forecasting. To cope with this challenge, we introduce a novel spatial-temporal graph self-attentive model (STGSA) for short-term Our learns graph-level embedding using self-attention layers Gumbel-Softmax technique,...
The scaling laws and extraordinary performance of large foundation models motivate the development utilization such in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these can used real-world applications. Frontier as GPT-4V have competency gaps multimodal capabilities for Moreover, pragmatic issues access, cost, latency, compliance make it hard clinicians use privately-hosted...
With smart devices being an essential part of our everyday lives, unsupervised access to the mobile sensors' data can result in a multitude side-channel attacks. In this paper, we study potential leaks from Apple Pencil (2nd generation) supported by iPad Pro, latest stylus pen which attaches body magnetically for charging. We observe that Pencil's affects magnetic readings sensed iPad's magnetometer when user is using Pencil. Therefore, ask: Can infer what writing on screen with Pencil,...