Results 81 to 90 of about 31,762 (259)

Spatio-Temporal Capsule Networks for Weakly Supervised Surveillance Video Anomaly Detection

Applied Sciences
Real surveillance systems require weakly supervised video anomaly detection due to the fact that long untrimmed videos do not always have accurate temporal labels. Models will be required to label a video as normal or abnormal and also to identify sparse
Mohammed Iqbal Dohan Almurumudhe, Olivér Hornyák   +1 more
doaj   +1 more source

In vitro and in silico modelling of ROS1‐positive non‐small cell lung cancer reveals fusion‐dependent tyrosine kinase inhibitor responses

Molecular Oncology, EarlyView.
Drug resistance limits treatment success in a subset of lung cancers driven by ROS1 gene alterations. Using patient‐derived cells and computer simulations, we studied three key mutations and how they affect five targeted drugs. The mutations reduced drug effectiveness in different ways by altering protein structure and behavior.
Farhan Ul Haq, Marc Terrones, Felicia Rodrigues Fortes, Anne Schepers, Alessia Denis, Christophe Deben, Ken Op de Beeck, Guy Van Camp, Geert Vandeweyer   +8 more
wiley   +1 more source

Addressing Imbalance in Weakly Supervised Multi-Label Learning

IEEE Access, 2019
Multi-label learning has been widely used in many fields to solve the problem of assigning multiple related categories to an instance. Nevertheless, the label for each training example is assumed complete in most of the current multi-label learning ...
Fang-Fang Luo, Wen-zhong Guo, Guo-Long Chen   +2 more
doaj   +1 more source

Raman‐based label‐free microscopic analysis of the pancreas in living zebrafish larvae

FEBS Open Bio, EarlyView.
Forward stimulated Raman scattering (F‐SRS) and epi coherent anti‐Stokes Raman scattering (E‐CARS) allow label‐free discrimination of distinct subcellular structures in the pancreas of living zebrafish larvae. Given the straightforward applicability, we anticipate broad implementation of Raman microscopy in other organs and across various biomedical ...
Noura Faraj, Eline M. F. de Lange, Klaas A. Sjollema, Ben N. G. Giepmans   +3 more
wiley   +1 more source

A light‐triggered Time‐Resolved X‐ray Solution Scattering (TR‐XSS) workflow with application to protein conformational dynamics

FEBS Open Bio, EarlyView.
Time‐resolved X‐ray solution scattering captures how proteins change shape in real time under near‐native conditions. This article presents a practical workflow for light‐triggered TR‐XSS experiments, from data collection to structural refinement. Using a calcium‐transporting membrane protein as an example, the approach can be broadly applied to study ...
Fatemeh Sabzian‐Molaei, Fredrik Orädd, Konstantinos Magkakis, Magnus Andersson   +3 more
wiley   +1 more source

Single‐molecule DNA flow‐stretch assays for high‐throughput DNA–protein interaction studies

FEBS Open Bio, EarlyView.
We describe an optimised single‐molecule DNA flow‐stretch assay that visualises DNA–protein interactions in real time. Linear DNA fragments are tethered to a surface and stretched by buffer flow for fluorescence imaging. Using λ and φX174 DNA, this protocol enhances reproducibility and accessibility, providing a versatile approach for studying diverse ...
Ayush Kumar Ganguli, Mohammad Nour Alsamsam, Ugnė Bagdonaitė, Van Truc Vu, Chun‐Jen Huang, Polina Kuzhir, Mindaugas Zaremba, Aurimas Kopūstas, Marijonas Tutkus   +8 more
wiley   +1 more source

Establishing an assay to evaluate d‐amino acid oxidase enzyme kinetics and inhibition using WST‐8 redox dye

FEBS Open Bio, EarlyView.
This study investigated a novel WST‐8‐based assay for evaluating d‐Amino acid oxidase (DAO) inhibitors. We confirmed its effectiveness using known inhibitors and found that uremic toxins possess relatively weak inhibitory activity compared to existing drugs.
Kahoko Miyake, Yuki Enoki, Yuka Nakazawa, Kazuaki Taguchi, Kazuaki Matsumoto   +4 more
wiley   +1 more source

Weakly Supervised Deep Learning for Arabic Tweet Sentiment Analysis on Education Reforms: Leveraging Pre-Trained Models and LLMs With Snorkel

IEEE Access
This study introduces a novel approach to sentiment classification of Arabic tweets regarding educational reforms in Saudi Arabia. The complexity of the Arabic language, with its numerous dialects, poses challenges for natural language processing tasks ...
Alanoud Alotaibi, Farrukh Nadeem, Mohamed Hamdy   +2 more
doaj   +1 more source

Rapid screening of staphylokinase protein variants using an unpurified cell‐free expression system

FEBS Open Bio, EarlyView.
An unpurified cell‐free protein synthesis (CFPS) platform enables rapid functional screening of staphylokinase variants. Direct plasminogen‐activation assays performed in microplate format provide real‐time activity readouts, allowing rapid identification and ranking of variants with improved or reduced fibrinolytic activity without protein ...
Maria Tomková, Veronika Hovanová, Jiri Damborsky, Erik Sedlák   +3 more
wiley   +1 more source

Region-CAM: Toward Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks

IEEE Access
Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target.
Qingdong Cai, Charith Abhayaratne
doaj   +1 more source