针对现有图嵌入方法损失函数来源单一导致节点表示不能被充分优化的问题,提出了基于同步联合优化的注意力图自编码器(attentional graph auto-encoder based on synchronous joint optimization,AGE-SJO)。设计基于注意力机制的编码器...针对现有图嵌入方法损失函数来源单一导致节点表示不能被充分优化的问题,提出了基于同步联合优化的注意力图自编码器(attentional graph auto-encoder based on synchronous joint optimization,AGE-SJO)。设计基于注意力机制的编码器学习节点表示,并利用内积解码器重建图结构生成重建损失(L_(R));为从多方面优化表示,将编码器和多层感知机分别作为生成模型和判别模型进行对抗训练,获得生成损失(L_(G))和判别损失(L_(D));提出同步联合优化策略,依次在L_(R)的k步、L_(D)的k步和L_(G)的1步之间优化表示,并将其应用于链路预测和节点聚类。在引文数据集上的实验结果表明,所提出的AGE-SJO性能优越,与最强基线相比,AUC、AP、ACC、NMI和ARI指标可分别提升1.6%、2.1%、10.6%、4.9%和12.4%。展开更多
单细胞数据聚类在生物信息分析中具有重要作用,但受测序原理和测序平台的限制,单细胞数据集普遍存在高维稀疏性、高方差噪声和基因数据缺失的问题,导致单细胞数据在聚类分析和应用方面仍面临诸多挑战。现有的单细胞聚类方法主要针对细...单细胞数据聚类在生物信息分析中具有重要作用,但受测序原理和测序平台的限制,单细胞数据集普遍存在高维稀疏性、高方差噪声和基因数据缺失的问题,导致单细胞数据在聚类分析和应用方面仍面临诸多挑战。现有的单细胞聚类方法主要针对细胞和基因表达间的关系进行建模,忽略了对细胞间潜在特征关系的充分挖掘以及对噪声的去除,导致聚类结果不理想,从而阻碍了后期对数据的分析。针对上述问题,提出了一种联合零膨胀负二项(Zero Inflated Negative Binomial,ZINB)模型与图注意力自编码器的自优化单细胞聚类算法(Self-optimized Single Cell Clustering Using ZINB Model and Graph Attention Autoencoder,scZDGAC)。该算法首先使用ZINB模型并结合可扩展的DCA去噪算法,通过ZINB分布更好地拟合数据特征分布,提升自编码器的去噪性能,并减小噪声和数据丢失对KNN算法输出的影响;然后通过图注意力自编码器在不同权重的细胞之间传播信息,更好地捕获细胞间的潜在特征进行聚类;最后scZDGAC采用自优化的方法使原本两个独立的聚类模块和特征模块相互受益,不断迭代更新聚类中心,进一步提升聚类性能。为了对聚类结果进行评价,文中使用调整兰德指数(ARI)和标准化互信息(NMI)两个通用评价指标。在6个不同规模的单细胞数据集上与其他算法进行对比实验,结果表明,所提聚类算法在聚类性能上较其他方法有很大提高,很好地展现了该算法的鲁棒性。展开更多
Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited t...Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.展开更多
文摘针对现有图嵌入方法损失函数来源单一导致节点表示不能被充分优化的问题,提出了基于同步联合优化的注意力图自编码器(attentional graph auto-encoder based on synchronous joint optimization,AGE-SJO)。设计基于注意力机制的编码器学习节点表示,并利用内积解码器重建图结构生成重建损失(L_(R));为从多方面优化表示,将编码器和多层感知机分别作为生成模型和判别模型进行对抗训练,获得生成损失(L_(G))和判别损失(L_(D));提出同步联合优化策略,依次在L_(R)的k步、L_(D)的k步和L_(G)的1步之间优化表示,并将其应用于链路预测和节点聚类。在引文数据集上的实验结果表明,所提出的AGE-SJO性能优越,与最强基线相比,AUC、AP、ACC、NMI和ARI指标可分别提升1.6%、2.1%、10.6%、4.9%和12.4%。
文摘单细胞数据聚类在生物信息分析中具有重要作用,但受测序原理和测序平台的限制,单细胞数据集普遍存在高维稀疏性、高方差噪声和基因数据缺失的问题,导致单细胞数据在聚类分析和应用方面仍面临诸多挑战。现有的单细胞聚类方法主要针对细胞和基因表达间的关系进行建模,忽略了对细胞间潜在特征关系的充分挖掘以及对噪声的去除,导致聚类结果不理想,从而阻碍了后期对数据的分析。针对上述问题,提出了一种联合零膨胀负二项(Zero Inflated Negative Binomial,ZINB)模型与图注意力自编码器的自优化单细胞聚类算法(Self-optimized Single Cell Clustering Using ZINB Model and Graph Attention Autoencoder,scZDGAC)。该算法首先使用ZINB模型并结合可扩展的DCA去噪算法,通过ZINB分布更好地拟合数据特征分布,提升自编码器的去噪性能,并减小噪声和数据丢失对KNN算法输出的影响;然后通过图注意力自编码器在不同权重的细胞之间传播信息,更好地捕获细胞间的潜在特征进行聚类;最后scZDGAC采用自优化的方法使原本两个独立的聚类模块和特征模块相互受益,不断迭代更新聚类中心,进一步提升聚类性能。为了对聚类结果进行评价,文中使用调整兰德指数(ARI)和标准化互信息(NMI)两个通用评价指标。在6个不同规模的单细胞数据集上与其他算法进行对比实验,结果表明,所提聚类算法在聚类性能上较其他方法有很大提高,很好地展现了该算法的鲁棒性。
文摘Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases.Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model generalization.Addressing these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion.In response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion module.Additionally,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the model.With a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art models.Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.
