期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Enhancing chemosensitivity in pancreatic cancer:Novel strategies to overcome therapeutic resistance
1
作者 Wenhao Luo Menggang Zhang +22 位作者 Hao Chen Jun Wang Zhe Cao Gang Yang Jiangdong Qiu Yueze Liu Yifan Fu Jinxin Tao Guihu Weng Tao Liu Yueyang Wang Liyuan Ye Chen Ding Xiaoyue Lu Yi Dong Zeyu Zhang Shijuan Jiang changwei du Bidong Fu Hua Huang Jianchun Xiao Lei You Taiping Zhang 《Oncology and Translational Medicine》 2025年第5期213-220,共8页
Pancreatic ductal adenocarcinoma(PDAC)is one of the most aggressive and fatal malignancies,with a 5-year survival rate of<15%.Despite significant advancements in targeted therapies and immunotherapy,these approache... Pancreatic ductal adenocarcinoma(PDAC)is one of the most aggressive and fatal malignancies,with a 5-year survival rate of<15%.Despite significant advancements in targeted therapies and immunotherapy,these approaches benefit only a limited subset of patients,leaving chemotherapy as the primary treatment modality for most patients.Chemotherapy is an essential adjunct to surgical resection,the only potentially curative option,playing a crucial role in reducing the tumor burden,delaying disease progression,and alleviating symptoms.However,its long-term efficacy is frequently undermined by the development of chemoresistance,wherein tumor cells adopt diverse strategies to evade or repair chemotherapy-induced damage.Addressing this critical barrier is imperative for improving the clinical outcomes of PDAC.This review comprehensively examines the multifaceted mechanisms of chemoresistance in PDAC and highlights innovative strategies designed to enhance chemosensitivity,thereby offering new hope for overcoming these challenges and improving patient survival. 展开更多
关键词 Pancreatic ductal adenocarcinoma CHEMORESISTANCE Chemosensitivity enhancement Tumor microenvironment Therapeutic strategies
暂未订购
基于图卷积神经网络的杀菌剂活性预测研究
2
作者 杜长委 凌晨阳 +1 位作者 贾利峰 陈园园 《建模与仿真》 2025年第7期260-269,共10页
本研究提出了一种基于图神经网络(GCN)的杀菌剂活性预测模型。该模型通过直接解析分子SMILES字符串构建分子图结构,并利用GCN进行端到端的图表示学习。这种方法避免了传统方法中依赖手工特征工程的局限性,能够更全面且自动化地捕捉分子... 本研究提出了一种基于图神经网络(GCN)的杀菌剂活性预测模型。该模型通过直接解析分子SMILES字符串构建分子图结构,并利用GCN进行端到端的图表示学习。这种方法避免了传统方法中依赖手工特征工程的局限性,能够更全面且自动化地捕捉分子的结构信息。为评估模型性能,我们在相同杀菌剂活性数据集上,将GCN模型与基于分子描述符的支持向量机(SVM)、随机森林(RF)及深度神经网络(DNN)模型进行了系统对比。实验结果表明,GCN模型显著提高了真阳性率(TPR),有效提高了筛选效率;同时,其在整体预测性能上全面超越了SVM、RF和DNN模型。本研究证实了图神经网络在直接从分子结构预测生物活性方面的强大能力,为高效发现新型杀菌剂候选分子提供了一种更具潜力的计算工具。 展开更多
关键词 杀菌剂 图卷积神经网络 支持向量机 随机森林 深度神经网络
在线阅读 下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部