GraphLoc: a graph neural network model for predicting protein subcellular localization from immunohistochemistry images.

MOTIVATION: Recognition of protein subcellular distribution patterns and identification of location biomarker proteins in cancer tissues are important for understanding protein functions and related diseases. Immunohistochemical (IHC) images enable visualizing the distribution of proteins at the tissue level, providing an important resource for the protein localization studies. In the past decades, several image-based protein subcellular location prediction methods have been developed, but the prediction accuracies still have much space to improve due to the complexity of protein patterns resulting from multi-label proteins and the variation of location patterns across cell types or states. RESULTS: Here, we propose a multi-label multi-instance model based on deep graph convolutional neural networks, GraphLoc, to recognize protein subcellular location patterns. GraphLoc builds a graph of multiple IHC images for one protein, learns protein-level representations by graph convolutions and predicts multi-label information by a dynamic threshold method. Our results show that GraphLoc is a promising model for image-based protein subcellular location prediction with model interpretability. Furthermore, we apply GraphLoc to the identification of candidate location biomarkers and potential members for protein networks. A large portion of the predicted results have supporting evidence from the existing literatures and the new candidates also provide guidance for further experimental screening. AVAILABILITY AND IMPLEMENTATION: The dataset and code are available at: www.csbio.sjtu.edu.cn/bioinf/GraphLoc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Incorporating label correlations into deep neural networks to classify protein subcellular location patterns in immunohistochemistry images.

Analysis of protein subcellular localization is a critical part of proteomics. In recent years, as both the number and quality of microscopic images are increasing rapidly, many automated methods, especially convolutional neural networks (CNN), have been developed to predict protein subcellular location(s) based on bioimages, but their performance always suffers from some inherent properties of the problem. First, many microscopic images have non-informative or noisy sections, like unstained stroma and unspecific background, which affect the extraction of protein expression information. Second, the patterns of protein subcellular localization are very complex, as a lot of proteins locate in more than one compartment. In this study, we propose a new label-correlation enhanced deep neural network, laceDNN, to classify the subcellular locations of multi-label proteins from immunohistochemistry images. The model uses small representative patches as input to alleviate the image noise issue, and its backbone is a hybrid architecture of CNN and recurrent neural network, where the former network extracts representative image features and the latter learns the organelle dependency relationships. Our experimental results indicate that the proposed model can improve the performance of multi-label protein subcellular classification.

Overexpression of EP300-interacting inhibitor of differentiation 3 predicts poor prognosis in patients with glioblastoma multiforme.

EP300-interacting inhibitor of differentiation 3 (EID3) is a member of the IED family and has been associated with tumorigenesis and tumor development in different cancer types. However, the role of EID3 in glioblastoma multiforme (GBM) prognosis is not clear. Whole transcriptome sequencing data of 249 and 149 GBM patients were collected from the Chinese Glioma Genome Atlas (CGGA) and The Cancer Genome Atlas (TCGA) database respectively. The correlation between EID3 expression and overall survival (OS)/clinical pathologic features of GBM patients was investigated. Based on the Wilcoxon rank-sum test, EID3 expression in GBM tissues was significantly lower than in normal brain tissues (P < 0.001), and significantly higher than in LGG (low-grade glioma) (P < 0.001).There was a significant correlation between high EID3 expression with poor OS in CGGA (P = 0.049) and TCGA data (P = 0.024). Gene set enrichment analysis (GSEA) data analysis revealed a significant difference (FDR < 0.25, NOM p-value < 0.05) in the enrichment of MSigDB Collection (h.all.v6.2.symbols.gmt). A total of eight enriched pathways were identified in the high EID3 expression group, including Myc Targets V1, Kras signaling DN, and DNA repair pathways. Multivariate Cox regression analysis indicated that high expression of EID3 correlated with poor OS (P = 0.032, HR = 1.41, CI: 1.03-1.90). We conclude that EID3 could serve as an independent factor for predicting the prognosis of patients with GBM. Moreover, it is associated with GBM development through the regulation of the Myc Targets, Kras signaling DN, and DNA repair pathways.

Lysosomal activity maintains glycolysis and cyclin E1 expression by mediating Ad4BP/SF-1 stability for proper steroidogenic cell growth.

The development and differentiation of steroidogenic organs are controlled by Ad4BP/SF-1 (adrenal 4 binding protein/steroidogenic factor 1). Besides, lysosomal activity is required for steroidogenesis and also enables adrenocortical cell to survive during stress. However, the role of lysosomal activity on steroidogenic cell growth is as yet unknown. Here, we showed that lysosomal activity maintained Ad4BP/SF-1 protein stability for proper steroidogenic cell growth. Treatment of cells with lysosomal inhibitors reduced steroidogenic cell growth in vitro. Suppression of autophagy did not affect cell growth indicating that autophagy was dispensable for steroidogenic cell growth. When lysosomal activity was inhibited, the protein stability of Ad4BP/SF-1 was reduced leading to reduced S phase entry. Interestingly, treatment of cells with lysosomal inhibitors reduced glycolytic gene expression and supplying the cells with pyruvate alleviated the growth defect. ChIP-sequence/ChIP studies indicated that Ad4BP/SF-1 binds to the upstream region of Ccne1 (cyclin E1) gene during G1/S phase. In addition, treatment of zebrafish embryo with lysosomal inhibitor reduced the levels of the interrenal (adrenal) gland markers. Thus lysosomal activity maintains steroidogenic cell growth via stabilizing Ad4BP/SF-1 protein.