Deep neural network for the determination of transformed foci in Bhas 42 cell transformation assay

Bhas 42 cell transformation assay (CTA) has been used to estimate the carcinogenic potential of chemicals by exposing Bhas 42 cells to carcinogenic stimuli to form colonies, referred to as transformed foci, on the confluent monolayer. Transformed foci are classified and quantified by trained experts using morphological criteria. Although the assay has been certified by international validation studies and issued as a guidance document by OECD, this classification process is laborious, time consuming, and subjective. We propose using deep neural network to classify foci more rapidly and objectively. To obtain datasets, Bhas 42 CTA was conducted with a potent tumor promotor, 12-O-tetradecanoylphorbol-13-acetate, and focus images were classified by experts (1405 images in total). The labeled focus images were augmented with random image processing and used to train a convolutional neural network (CNN). The trained CNN exhibited an area under the curve score of 0.95 on a test dataset significantly outperforming conventional classifiers by beginners of focus judgment. The generalization performance of unknown chemicals was assessed by applying CNN to other tumor promotors exhibiting an area under the curve score of 0.87. The CNN-based approach could support the assay for carcinogenicity as a fundamental tool in focus scoring.

miR-1293 acts as a tumor promotor in lung adenocarcinoma via targeting phosphoglucomutase 5

Background Lung adenocarcinoma (LUAD) is the most common histologic subtype of lung cancer. Studies have found that miR-1293 is related to the survival of LUAD patients. Unfortunately, its role in LUAD remains not fully clarified. Methods miR-1293 expression and its association with LUAD patients’ clinical characteristics were analyzed in TCGA database. Also, miR-1293 expression was detected in LUAD cell lines. Cell viability, migration, invasion and expression of MMP2 and MMP9 were measured in LUAD cells following transfection with miR-1293 mimic or antagomir. Phosphoglucomutase (PGM) 5 was identified to be negatively related to miR-1293 in LUAD patients in TCGA database, and their association was predicated by Targetscan software. Hence, we further verified the relationship between miR-1293 and PGM5. Additionally, the effect and mechanism of miR-1293 were validated in a xenograft mouse model. Results We found miR-1293 expression was elevated, but PGM5 was decreased, in LUAD patients and cell lines. Higher miR-1293 expression was positively related to LUAD patients’ pathologic stage and poor overall survival. miR-1293 mimic significantly promoted, whereas miR-1293 antagomir suppressed the viability, migration, invasion, and expression of MMP2 and MMP9 in LUAD cells. PGM5 was a target of miR-1293. Overexpression of PGM5 abrogated the effects of miR-1293 on the malignant phenotypes of LUAD cells. Administration of miR-1293 antagomir reduced tumor volume and staining of Ki-67 and MMP9, but elevated PGM5 expression in vivo. Conclusions miR-1293 promoted the proliferation, migration and invasion of LUAD cells via targeting PGM5, which indicated that miR-1293 might serve as a potential therapeutic target for LUAD patients.

Deep Neural Network for the Determination of Transformed foci in Bhas 42 Cell Transformation Assay

Bhas 42 cell transformation assay (CTA) has been used to estimate the carcinogenic potential of chemicals by exposing Bhas 42 cells to carcinogenic stimuli to form colonies, referred to as transformed foci, on the confluent monolayer. Transformed foci are classified and quantified by trained experts using morphological criteria. Although the assay has been certified by international validation studies and issued as a guidance document by OECD, this classification procedure is laborious, time consuming, and subjective. We propose using deep neural network to classify foci more rapidly and objectively. To obtain datasets, Bhas 42 CTA was conducted with a potent tumor promotor, 12-O-tetradecanoylphorbol-13-acetate, and focus images were classified by experts (1405 images in total). The labeled focus images were augmented with random image processing and used to train a convolutional neural network (CNN). The trained CNN exhibited an area under the curve score of 0.95 on a test dataset significantly outperforming human-based classifiers by beginners of focus judgment. The generalization performance of unknown chemicals was assessed by applying CNN to other tumor promotors exhibiting an area under the curve score of 0.87. The CNN-based approach could support the assay for carcinogenicity as a fundamental tool in focus scoring.

ALPK2 acts as tumor promotor in development of bladder cancer through targeting DEPDC1A

Bladder cancer is one of the most common malignant tumors in the urinary system. The development and improvement of treatment efficiency require the deepening of the understanding of its molecular mechanism. This study investigated the role of ALPK2, which is rarely studied in malignant tumors, in the development of bladder cancer. Our results showed the upregulation of ALPK2 in bladder cancer, and data mining of TCGA database showed the association between ALPK2 and pathological parameters of patients with bladder cancer. In vitro and in vivo experiments demonstrated that knockdown of ALPK2 could inhibit bladder cancer development through regulating cell proliferation, cell apoptosis, and cell migration. Additionally, DEPDC1A is identified as a potential downstream of ALPK2 with direct interaction, whose overexpression/downregulation can inhibit/promote the malignant behavioral of bladder cancer cells. Moreover, the overexpression of DEPDC1A can rescue the inhibitory effects of ALPK2 knockdown on bladder cancer. In conclusion, ALPK2 exerts a cancer-promoting role in the development of bladder cancer by regulating DEPDC1A, which may become a promising target to improve the treatment strategy of bladder cancer.

MYC-mediated upregulation of PNO1 promotes glioma tumorigenesis by activating THBS1/FAK/Akt signaling

PNO1 has been reported to be involved in tumorigenesis, however, its role in glioma remains unexplored. In the present study, PNO1 expression in glioma from on-line databases, cDNA, and tissue microarrays was upregulated and associated with poor prognosis. PNO1 knockdown inhibits tumor cell growth and invasion both in vitro and in vivo; whereas PNO1 overexpression promoted cell proliferation and invasion in vitro. Notably, PNO1 interacted with THBS1 and the promotion of glioma by PNO1 overexpression could be attenuated or even reversed by simultaneously silencing THBS1. Functionally, PNO1 was involved in activation of FAK/Akt pathway. Moreover, overexpressing MYC increased PNO1 promoter activity. MYC knockdown decreased PNO1 and THBS1 expression, while inhibited cell proliferation and invasion. In conclusion, MYC-mediated upregulation of PNO1 contributes to glioma progression by activating THBS1/FAK/Akt signaling. PNO1 was reported to be a tumor promotor in the development and progression of glioma and may act as a candidate of therapeutic target in glioma treatment.

DEPDC1B is a tumor promotor in development of bladder cancer through targeting SHC1

Bladder cancer is one of the most commonly diagnosed malignant tumors in the urinary system and causes a massive cancer-related death. DEPDC1B is a DEP domain-containing protein that has been found to be associated with a variety of human cancers. This study aimed to explore the role and mechanism of DEPDC1B in the development of bladder cancer. The analysis of clinical specimens revealed the upregulated expression of DEPDC1B in bladder cancer, which was positively related to tumor grade. In vitro and in vivo studies showed that DEPDC1B knockdown could inhibit the growth of bladder cancer cells or xenografts in mice. The suppression of bladder cancer by DEPDC1B was executed through inhibiting cell proliferation, cell migration, and promoting cell apoptosis. Moreover, a mechanistic study found that SHC1 may be an important route through which DEPDC1B regulates the development of bladder cancer. Knockdown of SHC1 in DEPDC1B-overexpressed cancer cells could abolish the promotion effects induced by DEPDC1B. In conclusion, DEPDC1B was identified as a key regulator in the development of bladder cancer, which may be used as a potential therapeutic target in the treatment of bladder cancer.