Bioinformatics analysis of metastasis-related proteins in hepatocellular carcinoma

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.

DeepHBSP:A Deep Learning Framework for Predicting Human Blood-Secretory Proteins Using Transfer Learning

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.