In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the researc...In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the research of multi-label classification algorithms. Considering the fact that the high dimensionality of the multi-label datasets may cause the curse of dimensionality and wil hamper the classification process, a dimensionality reduction algorithm, named multi-label kernel discriminant analysis (MLKDA), is proposed to reduce the dimensionality of multi-label datasets. MLKDA, with the kernel trick, processes the multi-label integrally and realizes the nonlinear dimensionality reduction with the idea similar with linear discriminant analysis (LDA). In the classification process of multi-label data, the extreme learning machine (ELM) is an efficient algorithm in the premise of good accuracy. MLKDA, combined with ELM, shows a good performance in multi-label learning experiments with several datasets. The experiments on both static data and data stream show that MLKDA outperforms multi-label dimensionality reduction via dependence maximization (MDDM) and multi-label linear discriminant analysis (MLDA) in cases of balanced datasets and stronger correlation between tags, and ELM is also a good choice for multi-label classification.展开更多
Colonization is believed a rate-limiting step of metastasis cascade.However,its underlying mechanism is not well understood.Uveal melanoma(UM),which is featured with single organ liver metastasis,may provide a simplif...Colonization is believed a rate-limiting step of metastasis cascade.However,its underlying mechanism is not well understood.Uveal melanoma(UM),which is featured with single organ liver metastasis,may provide a simplified model for realizing the complicated colonization process.Because DDR1 was identified to be overexpressed in UM cell lines and specimens,and abundant pathological deposition of extracellular matrix collagen,a type of DDR1 ligand,was noted in the microenvironment of liver in metastatic patients with UM,we postulated the hypothesis that DDR1 and its ligand might ignite the interaction between UM cells and their surrounding niche of liver thereby conferring strengthened survival,proliferation,sternness and eventually promoting metastatic colonization in liver.We tested this hypothesis and found that DDR1 promoted these malignant cellular phenotypes and facilitated metastatic colonization of UM in liver.Mechanistically,UM cells secreted TGF-β1 which induced quiescent hepatic stellate cells(qHSCs)into activated HSCs(aHSCs)which secreted collagen type I.Such a remodeling of extracellular matrix,in turn,activated DDR1,strengthening survival through upregulating STAT3-dependent Mcl-1 expression,enhancing sternness via upregulating STAT3-dependent S0X2,and promoting clonogenicity in cancer cells.Targeting DDR1 by using 7rh,a specific inhibitor,repressed proliferation and survival in vitro and in vivo outgrowth.More importantly,targeting cancer cells by pharmacological inactivation of DDR1 or targeting microenvironmental TGF-β1-collagen I loop exhibited a prominent anti-metastasis effect in mice.In conclusion,targeting DDR1 signaling and TGF-β1 signaling may be a novel approach to diminish hepatic metastasis in UM.展开更多
基金supported by the National Natural Science Foundation of China(5110505261173163)the Liaoning Provincial Natural Science Foundation of China(201102037)
文摘In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the research of multi-label classification algorithms. Considering the fact that the high dimensionality of the multi-label datasets may cause the curse of dimensionality and wil hamper the classification process, a dimensionality reduction algorithm, named multi-label kernel discriminant analysis (MLKDA), is proposed to reduce the dimensionality of multi-label datasets. MLKDA, with the kernel trick, processes the multi-label integrally and realizes the nonlinear dimensionality reduction with the idea similar with linear discriminant analysis (LDA). In the classification process of multi-label data, the extreme learning machine (ELM) is an efficient algorithm in the premise of good accuracy. MLKDA, combined with ELM, shows a good performance in multi-label learning experiments with several datasets. The experiments on both static data and data stream show that MLKDA outperforms multi-label dimensionality reduction via dependence maximization (MDDM) and multi-label linear discriminant analysis (MLDA) in cases of balanced datasets and stronger correlation between tags, and ELM is also a good choice for multi-label classification.
基金supported by National Key Research and Development Program of China(2020YFA0509400 to J.Pan)Natural Science Foundation of China(Key Program Project 81930101 to J.Pan,Youth Project 82003797 to W.D.)the Research Foundation of Guangzhou Municipal Science and Technology Bureau(Key Program project 201904020003 to J.Pan).
文摘Colonization is believed a rate-limiting step of metastasis cascade.However,its underlying mechanism is not well understood.Uveal melanoma(UM),which is featured with single organ liver metastasis,may provide a simplified model for realizing the complicated colonization process.Because DDR1 was identified to be overexpressed in UM cell lines and specimens,and abundant pathological deposition of extracellular matrix collagen,a type of DDR1 ligand,was noted in the microenvironment of liver in metastatic patients with UM,we postulated the hypothesis that DDR1 and its ligand might ignite the interaction between UM cells and their surrounding niche of liver thereby conferring strengthened survival,proliferation,sternness and eventually promoting metastatic colonization in liver.We tested this hypothesis and found that DDR1 promoted these malignant cellular phenotypes and facilitated metastatic colonization of UM in liver.Mechanistically,UM cells secreted TGF-β1 which induced quiescent hepatic stellate cells(qHSCs)into activated HSCs(aHSCs)which secreted collagen type I.Such a remodeling of extracellular matrix,in turn,activated DDR1,strengthening survival through upregulating STAT3-dependent Mcl-1 expression,enhancing sternness via upregulating STAT3-dependent S0X2,and promoting clonogenicity in cancer cells.Targeting DDR1 by using 7rh,a specific inhibitor,repressed proliferation and survival in vitro and in vivo outgrowth.More importantly,targeting cancer cells by pharmacological inactivation of DDR1 or targeting microenvironmental TGF-β1-collagen I loop exhibited a prominent anti-metastasis effect in mice.In conclusion,targeting DDR1 signaling and TGF-β1 signaling may be a novel approach to diminish hepatic metastasis in UM.