AIM: To analyze the metastasis-related proteins in hepatocellular carcinoma (HCC) and discover the biomarker candidates for diagnosis and therapeutic intervention of HCC metastasis with bioinformatics tools. METHODS: ...AIM: To analyze the metastasis-related proteins in hepatocellular carcinoma (HCC) and discover the biomarker candidates for diagnosis and therapeutic intervention of HCC metastasis with bioinformatics tools. METHODS: Metastasis-related proteins were determined by stable isotope labeling and MS analysis and analyzed with bioinformatics resources, including Phobius, Kyoto encyclopedia of genes and genomes (KEGG), online mendelian inheritance in man (OMIM) and human protein reference database (HPRD). RESULTS: All the metastasis-related proteins were linked to 83 pathways in KEGG, including MAPK and p53 signal pathways. Protein-protein interaction network showed that all the metastasis-related proteins were categorized into 19 function groups, including cell cycle, apoptosis and signal transduction. OMIM analysis linked these proteins to 186 OMIM entries. CONCLUSION: Metastasis-related proteins provide HCC cells with biological advantages in cell proliferation,migration and angiogenesis, and facilitate metastasis of HCC cells. The bird's eye view can reveal a global characteristic of metastasis-related proteins and many differentially expressed proteins can be identified as candidates for diagnosis and treatment of HCC.展开更多
The identification of blood-secretory proteins and the detection of protein biomarkers in the blood have an important clinical application value.Existing methods for predicting blood-secretory proteins are mainly base...The identification of blood-secretory proteins and the detection of protein biomarkers in the blood have an important clinical application value.Existing methods for predicting blood-secretory proteins are mainly based on traditional machine learning algorithms,and heavily rely on annotated protein features.Unlike traditional machine learning algorithms,deep learning algorithms can automatically learn better feature representations from raw data,and are expected to be more promising to predict blood-secretory proteins.We present a novel deep learning model(DeepHBSP)combined with transfer learning by integrating a binary classification network and a ranking network to identify blood-secretory proteins from the amino acid sequence information alone.The loss function of DeepHBSP in the training step is designed to apply descriptive loss and compactness loss to the binary classification network and the ranking network,respectively.The feature extraction subnetwork of DeepHBSP is composed of a multi-lane capsule network.Additionally,transfer learning is used to train a highly accurate generalized model with small samples of blood-secretory proteins.The main contributions of this study are as follows:1)a novel deep learning architecture by integrating a binary classification network and a ranking network is proposed,superior to existing traditional machine learning algorithms and other state-of-the-art deep learning architectures for biological sequence analysis;2)the proposed model for blood-secretory protein prediction uses only amino acid sequences,overcoming the heavy dependence of existing methods on annotated protein features;3)the blood-secretory proteins predicted by our model are statistically significant compared with existing blood-based biomarkers of cancer.展开更多
基金National Basic Research Priorities Program No. 2001CB510202National Science and Technology Key Project No. 2002BAC11A11 and 2004BA711A19+2 种基金National Natural Science Foundation of China No. 20328508National High Technology Research Developing Program No. 02BAC11A11Shanghai Science and Technology Development Program No. 03DZ14024
文摘AIM: To analyze the metastasis-related proteins in hepatocellular carcinoma (HCC) and discover the biomarker candidates for diagnosis and therapeutic intervention of HCC metastasis with bioinformatics tools. METHODS: Metastasis-related proteins were determined by stable isotope labeling and MS analysis and analyzed with bioinformatics resources, including Phobius, Kyoto encyclopedia of genes and genomes (KEGG), online mendelian inheritance in man (OMIM) and human protein reference database (HPRD). RESULTS: All the metastasis-related proteins were linked to 83 pathways in KEGG, including MAPK and p53 signal pathways. Protein-protein interaction network showed that all the metastasis-related proteins were categorized into 19 function groups, including cell cycle, apoptosis and signal transduction. OMIM analysis linked these proteins to 186 OMIM entries. CONCLUSION: Metastasis-related proteins provide HCC cells with biological advantages in cell proliferation,migration and angiogenesis, and facilitate metastasis of HCC cells. The bird's eye view can reveal a global characteristic of metastasis-related proteins and many differentially expressed proteins can be identified as candidates for diagnosis and treatment of HCC.
基金The work was supported by the National Natural Science Foundation of China under Grant Nos.61872418,61972174,and 62002212the Natural Science Foundation of Jilin Province of China under Grant Nos.20180101050JC and 20180101331JC+1 种基金the Science and Technology Planning Project of Guangdong Province of China under Grant No.2020A0505100018the Guangdong Key-Project for Applied Fundamental Research under Grant No.2018KZDXM076.
文摘The identification of blood-secretory proteins and the detection of protein biomarkers in the blood have an important clinical application value.Existing methods for predicting blood-secretory proteins are mainly based on traditional machine learning algorithms,and heavily rely on annotated protein features.Unlike traditional machine learning algorithms,deep learning algorithms can automatically learn better feature representations from raw data,and are expected to be more promising to predict blood-secretory proteins.We present a novel deep learning model(DeepHBSP)combined with transfer learning by integrating a binary classification network and a ranking network to identify blood-secretory proteins from the amino acid sequence information alone.The loss function of DeepHBSP in the training step is designed to apply descriptive loss and compactness loss to the binary classification network and the ranking network,respectively.The feature extraction subnetwork of DeepHBSP is composed of a multi-lane capsule network.Additionally,transfer learning is used to train a highly accurate generalized model with small samples of blood-secretory proteins.The main contributions of this study are as follows:1)a novel deep learning architecture by integrating a binary classification network and a ranking network is proposed,superior to existing traditional machine learning algorithms and other state-of-the-art deep learning architectures for biological sequence analysis;2)the proposed model for blood-secretory protein prediction uses only amino acid sequences,overcoming the heavy dependence of existing methods on annotated protein features;3)the blood-secretory proteins predicted by our model are statistically significant compared with existing blood-based biomarkers of cancer.