蛋白质-药物相互作用在许多生物过程和治疗中发挥着重要作用,预测蛋白质的结合位点有助于发现这种相互作用,指导设计新药来优化这些相互作用,改善蛋白质功能;蛋白质的三级结构决定了药物分子可用的结合位点,但 3D 结构的确定速度慢且成本高;但是,氨基酸序列则相对容易获取,尽管仅使用序列来快速准确地预测结合位点比较难,近...
VGG-nets, ResNets, and Inception Networks have gained a lot of momentum in the field of feature engineering. Despite their great performances, they still face a handful of limitations. These models are well-suited for several datasets, but due to the many hyperparameters and computations involved...
Count-adapted regularized deep embedded clustering (CarDEC) [117] is an advanced deep architecture that enables simultaneous batch effect correction, denoising, and clustering of scRNA-seq data. An innovation of CarDEC is that it treats the highly variable genes (HVGs) and lowly variably genes (...
DeepDPM: Deep Clustering With an Unknown Number of ClustersDeepDPMCVPR 2022Pytorch Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering-CVPR 2022- Efficient Deep Embedded Subspace ClusteringEDESCCVPR 2022Pytorch SLIC: Self-Supervised Learning With Iterative Clustering for Hum...
Efficient Deep Embedded Subspace Clustering Jinyu Cai1,3, Jicong Fan2,3∗, Wenzhong Guo1, Shiping Wang1, Yunhe Zhang1, Zhao Zhang4 1College of Computer and Data Science, Fuzhou University, China 2School of Data Science, The Chinese University of Hong Kong (Shenzhen), China 3Shenzhen ...
it can be applied to image recognition and speech recognition as well. The major innovation is the integration of soft thresholding as nonlinear transformation layers into ResNets. Moreover, the thresholds are automatically determined by a specially designed sub-network, so that no professional experti...
However, the node features obtained by our proposed edge construction method are clearly classified in space, resulting in the best clustering effect for similar nodes. This demonstrates that the multi-channel edge feature coding method has a better classification effect than the low-channel edge ...
, have also been employed for unsupervised learning in a wide range of applications. The main disadvantages of unsupervised learning are unable to provide accurate information concerning data sorting and computationally complex. One of the most popular unsupervised learning approaches is clustering [54]...
Deep Embedded Clustering with Data Augmentation (DEC-DA) [78] represents an enhanced iteration of DEC, encompassing a data enhancement strategy. Adaptive Self-Paced Deep Clustering with Data Augmentation (ASPC-DA) [79] interweaves autonomic learning with data enhancement and optimizes autonomic ...
Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large-scale datasets. In this work, we present