DeepCIA: a novel deep-learning model for cancer type identification using class activation map via transcription factor expression.

Deep learning methods are powerful analytical tools for large-scale data analysis. Here, we introduce DeepCIA as a novel diagnostic deep-learning model for cancer type identification using a class activation map via transcription factor expression. Although many deep learning researches attempts have recently been made in relation to cancer diagnosis, there are difficulties in using cancer data due to a large-scale problem. Therefore, From The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) public databases, we selected transcription factor expression profiles of eight cancer types. TCGA included 3496 samples and divided the train and validation sets in an 8:2 ratio. ICGC included 552 samples and was used as a test set for external validation. To compare the performance of 1D-CNN models, we also used SVM and KNN from machine learning. In external validation, 1D-CNN showed a high average accuracy of 98% and was superior to support vector machine (SVM) and k-nearest neighbor (KNN) with a difference in the accuracy of 10-12%. Also, 1D-CNN performed very well in several performance metrics (98.2% Recall, 98.1% Precision, 98.2% F score, 99.8% Specificity, 99.8% AUC, and 99.0% Balanced Accuracy). In each data set evaluation, 1-network, 5-network, and 2-network with high accuracy were selected and visualized through the Class Activation Map. We identified the Cys2Hys2 zinc finger group with the highest distribution across all cancer types. Collectively, DeepCIA can be used as a decision support system for cancer and a classifier for diagnosing unknown primary cancer, while emphasizing its usefulness in cancer diagnosis.

Prognostic role of high cathepsin D expression in breast cancer: a systematic review and meta-analysis.

BACKGROUND: High cathepsin D has been associated with poor prognosis in breast cancer; however, the results of many studies are controversial. Here, we assessed the association between high cathepsin D levels and worse breast cancer prognosis by conducting a meta-analysis. METHODS: A comprehensive search strategy was used to search relevant literature in PUBMED and EMBASE by September 2018. The meta-analysis was performed in Review Manager 5.3 using hazard ratios (HRs) with 95% confidence intervals (CIs). RESULTS: A total of 15,355 breast cancer patients from 26 eligible studies were included in this meta-analysis. Significant associations between elevated high cathepsin D and poor overall survival (OS) (HR = 1.61, 95% CI: 1.35-1.92, p < 0.0001) and disease-free survival (DFS) (HR = 1.52, 95% CI: 1.31-2.18, p < 0.001) were observed. In the subgroup analysis for DFS, high cathepsin D was significantly associated with poor prognosis in node-positive patients (HR = 1.38, 95% CI: 1.25-1.71, p < 0.00001), node-negative patients (HR = 1.78, 95% CI: 1.39-2.27, p < 0.0001), early stage patients (HR = 1.73, 95% CI: 1.34-2.23, p < 0.0001), and treated with chemotherapy patients (HR = 1.60, 95% CI: 1.21-2.12, p < 0.001). Interestingly, patients treated with tamoxifen had a low risk of relapse when their cathepsin D levels were high (HR = 0.71, 95% CI: 0.52-0.98, p = 0.04) and a high risk of relapse when their cathepsin D levels were low (HR = 1.50, 95% CI: 1.22-1.85, p = 0.0001). CONCLUSIONS: Our meta-analysis suggests that high expression levels of cathepsin D are associated with a poor prognosis in breast cancer. Based on our subgroup analysis, we believe that cathepsin D can act as a marker for poor breast cancer prognosis and also as a therapeutic target for breast cancer.

Risk of metastatic pheochromocytoma and paraganglioma in SDHx mutation carriers: a systematic review and updated meta-analysis.

BACKGROUND: Pheochromocytoma and paraganglioma (PPGL) are tumours that arise from chromaffin cells. Some genetic mutations influence PPGL, among which, those in genes encoding subunits of succinate dehydrogenase (SDHA, SDHB, SDHC and SDHD) and assembly factor (SDHAF2) are the most relevant. However, the risk of metastasis posed by these mutations is not reported except for SDHB and SDHD mutations. This study aimed to update the metastatic risks, considering prevalence and incidence of each SDHx mutation, which were dealt formerly all together. METHODS: We searched EMBASE and MEDLINE and selected 27 articles. The patients included in the studies were divided into three groups depending on the presence of PPGL. We checked the heterogeneity between studies and performed a meta-analysis using Hartung-Knapp-Sidik-Jonkman method based on a random effect model. RESULTS: The highest PPGL prevalence was for SDHB mutation, ranging from 23% to 31%, and for SDHC mutation (23%), followed by that for SDHA mutation (16%). The lowest prevalence was for SDHD mutation, ranging from 6% to 8%. SDHAF2 mutation showed no metastatic events. The PPGL incidence showed a tendency similar to that of its prevalence with the highest risk of metastasis posed by SDHB mutation (12%-41%) and the lowest risk by SDHD mutation (~4%). CONCLUSION: There was no integrated evidence of how SDHx mutations are related to metastatic PPGL. However, these findings suggest that SDHA, SDHB and SDHC mutations are highly associated and should be tested as indicators of metastasis in patients with PPGL.

Anti-inflammatory effects of pelargonidin on TGFBIp-induced responses.

Transforming growth factor ß induced protein (TGFBIp) is an extracellular matrix protein expressed in several cell types in response to TGF-ß. TGFBIp is released by human umbilical vein endothelial cells (HUVECs) and functions as a mediator of experimental sepsis. Pelargonidin (PEL) is a well-known red pigment found in plants, and has been reported as having important biological activities that are potentially beneficial for human health. This study was undertaken to investigate whether PEL can modulate TGFBIp-mediated inflammatory responses in HUVECs and in mice. The anti-inflammatory activities of PEL were determined by measuring permeability, leukocyte adhesion and migration, and activation of proinflammatory proteins in TGFBIp-activated HUVECs and mice. In addition, the beneficial effects of PEL on survival rate in a mouse sepsis model were tested. We found that PEL inhibited TGFBIp-induced barrier disruption, expression of cell adhesion molecules and adhesion/transendothelial migration of neutrophils to human endothelial cells. PEL also suppressed TGFBIp-induced hyperpermeability and leukocyte migration in vivo. These results suggest that PEL possesses anti-inflammatory properties that result in inhibition of hyperpermeability, expression of cell adhesion molecules, and adhesion and migration of leukocytes, thereby endorsing its usefulness as a therapy for vascular inflammatory diseases.

Suppressive effects of three diketopiperazines from marine-derived bacteria on polyphosphate-mediated septic responses.

Diketopiperazine is a natural products found from bacteria, fungi, marine sponges, gorgonian and red algae. They are cyclic dipeptides possessing relatively simple and rigid structures with chiral nature and various side chains. The compounds in this structure class have been known to possess diverse bioactivities including antibiotic activity, anti-cancer activity, neuroprotective activity, and anti-inflammatory activity. Previous studies have reported proinflammatory responses of endothelial cells to the release of polyphosphate (PolyP). In this study, we examined the anti-inflammatory responses and mechanisms of diketopiperazine and its effects on PolyP-induced septic activities in human umbilical vein endothelial cells (HUVECs) and mice. The survival rates, septic biomarker levels, behavior of human neutrophils, and vascular permeability were determined in PolyP-activated HUVECs and mice. Diketopiperazine suppressed the PolyP-mediated vascular barrier permeability, upregulation of inflammatory biomarkers, adhesion/migration of leukocytes, and activation and/or production of nuclear factor-κB, tumor necrosis factor-α, and interleukin-6. Furthermore, diketopiperazine demonstrated protective effects on PolyP-mediated lethal death and the levels of the related septic biomarkers. Therefore, these results indicated the therapeutic potential of diketopiperazine on various systemic inflammatory diseases, such as sepsis or septic shock.

Suppressive effects of methylthiouracil on polyphosphate-mediated vascular inflammatory responses.

Drug repositioning is used to discover drug candidates to treat human diseases, through the application of drugs or compounds that are approved for the treatment of other diseases. This method can significantly reduce the time required and cost of discovering new drug candidates for human diseases. Previous studies have reported pro-inflammatory responses of endothelial cells to the release of polyphosphate (PolyP). In this study, we examined the anti-inflammatory responses and mechanisms of methylthiouracil (MTU), which is an antithyroid drug, and its effects on PolyP-induced septic activities in human umbilical vein endothelial cells (HUVECs) and mice. The survival rates, septic biomarker levels, behaviour of human neutrophils and vascular permeability were determined in PolyP-activated HUVECs and mice. MTU suppressed the PolyP-mediated vascular barrier permeability, up-regulation of inflammatory biomarkers, adhesion/migration of leucocytes, and activation and/or production of nuclear factor-κB, tumour necrosis factor-α and interleukin-6. Furthermore, MTU demonstrated protective effects on PolyP-mediated lethal death and the levels of the related septic biomarkers. Therefore, these results indicated the therapeutic potential of MTU on various systemic inflammatory diseases, such as sepsis or septic shock.