Results 91 to 100 of about 24,031,398 (300)

Castration‐resistant prostate cancer cells are addicted to the high activity of cyclin‐dependent kinase 2

Molecular Oncology, EarlyView.
We show that emergence of castration‐resistant prostate (CRPC) is associated with significant upregulation of cyclins that positively regulate cyclin‐dependent kinase 2 (CDK2) and concomitant downregulation of CDK4 cyclins. This renders CRPC cells dependent on the high activity of CDK2, and CDK2 inhibitors synergistically sensitize CRPC cells to both ...
Joyeeta Chatterjee, Alessia Marin, Shivani Yalala, Harri M. Itkonen   +3 more
wiley   +1 more source

Comparison of Different Image Data Augmentation Approaches

Journal of Imaging, 2021
Convolutional neural networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small ...
Loris Nanni, Michelangelo Paci, Sheryl Brahnam, Alessandra Lumini   +3 more
doaj   +1 more source

NAPRT loss promotes lung tumor initiation and growth through AKT signaling independently of NAD+ biosynthesis

Molecular Oncology, EarlyView.
Loss of NAPRT promotes lung tumor initiation and growth through a noncanonical mechanism, independent of its role in NAD+ biosynthesis. Mechanistically, NAPRT depletion activates the mTORC2‐driven AKT/β‐catenin signaling axis to enhance clonogenic and invasive phenotypes. Furthermore, lung‐specific Naprt deletion significantly increases tumor burden in
Myung Joon Oh, Ji Yun Jang, Yoon Jeon, Gi‐Cheon Kim, Hwanho Lee, Jooyoung Lee, Ju‐Hwa Kim, Hakhyun Kim, Minjee Kim, Ho‐Keun Kwon, Ho Lee, Hyun Seok Kim   +11 more
wiley   +1 more source

Virtual data augmentation method for reaction prediction

Scientific Reports, 2022
To improve the performance of data-driven reaction prediction models, we propose an intelligent strategy for predicting reaction products using available data and increasing the sample size using fake data augmentation.
Xinyi Wu, Yun Zhang, Jiahui Yu, Chengyun Zhang, Haoran Qiao, Yejian Wu, Xinqiao Wang, Zhipeng Wu, Hongliang Duan   +8 more
doaj   +1 more source

Remote Sensing Data Augmentation Through Adversarial Training

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
The lack of remote sensing images and poor quality limit the performance improvement of follow-up research such as remote sensing interpretation. In this article, a generative adversarial network (GAN) is proposed for data augmentation of remote sensing ...
Ning Lv, Hongxiang Ma, Chen Chen, Qingqi Pei, Yang Zhou, Fenglin Xiao, Ji Li   +6 more
doaj   +1 more source

AugLy: Data Augmentations for Robustness

CoRR, 2022
We introduce AugLy, a data augmentation library with a focus on adversarial robustness. AugLy provides a wide array of augmentations for multiple modalities (audio, image, text, & video). These augmentations were inspired by those that real users perform on social media platforms, some of which were not already supported by existing data ...
Zoe Papakipos, Joanna Bitton
openaire   +2 more sources

Extracellular matrix remodeling and immune reprogramming drive residual tumor progression of liver cancer after incomplete microwave ablation

Molecular Oncology, EarlyView.
Incomplete microwave ablation (iMWA) of liver cancer triggers a biphasic progression in residual tumors. At Day 3, the microenvironment is characterized by acute inflammatory responses and extracellular matrix (ECM) remodeling. By Day 14, a profound shift occurs toward oncogenic signal transduction and immunosuppression, marked by macrophage ...
Yu Liu, Yubei He, Nikolaus Berndt, Michael Mülleder, Kathrin Textoris‐Taube, Jing Guo, Matthias Stechele, Justus Ramtke, Shraga Nahum Goldberg, Lynn Jeanette Savic   +9 more
wiley   +1 more source

Engineering IL‐4 resistant proinflammatory human myeloid cells for cancer immunotherapy

Molecular Oncology, EarlyView.
We developed a scalable workflow to generate proinflammatory human myeloid cells. CRISPR/Cas9‐edited CD34+ hematopoietic stem and progenitor cells were expanded and differentiated with M‐CSF. Deletion of STAT6 or STAT6/NFKB1 enhanced macrophage proinflammatory gene expression and cytokine secretion in the presence of IL‐4 while maintaining antibody ...
Theresa Barberi, Alan D. Friedman
wiley   +1 more source

A survey on Image Data Augmentation for Deep Learning

Journal of Big Data, 2019
Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very
Connor Shorten, Taghi M. Khoshgoftaar
doaj   +1 more source

UiO‐66 metal–organic frameworks in biomedicine: From structural tunability to bioimaging, photodiagnostics, and photodynamic cancer therapy

FEBS Open Bio, EarlyView.
UiO‐66(Zr) metal–organic frameworks are chemically stable, biocompatible, and highly tunable nanomaterials. Their modular structure enables controlled drug delivery, multimodal bioimaging, and light‐activated photodynamic therapy, supporting integrated diagnostic and therapeutic (theranostic) applications in cancer and biomedical research.
Veronika Huntošová, Grigorii Rakhalskii, Miroslav Almáši   +2 more
wiley   +1 more source