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.

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.

Transcriptomics and Cell Transformation Assay: an Integrated Approach to Evaluate the Effects of Low Dose Ionizing Radiation

Background and aims: Ionizing radiation (IR) are a well-known carcinogenic agent, acting through genotoxic mechanisms. In the last years, great attention has been paid to the effects of IR at low doses and to the non-monotonic dose-response curve for IR exposures. To improve the knowledge of IR-mediated effects and possibly identify biomarkers for IR effects, we combined the Cell Transformation Assay (CTA) with transcriptomics, to correlate cytotoxicity and transformation endpoints with the modulation of gene profiles after IR exposure. Methods: BALB/c3T3 cells were exposed to ionizing radiation ranging from 0.25Gy and 6Gy. Irradiated cells were seeded for the CTA 20h later. At the same time, RNA was extracted for microarray experiments. The cell clonal survival was significantly increased in 0.25Gy IR exposed cells, while the 3Gy dose strongly inhibited cellular growth. Cell transformation was observed only at the highest dose (3Gy). Results: Cell’s transformation was observed at 1.5, 2 and 3Gy doses. The 0.25Gy dose, which was able to induce an increment of clonal efficiency, did not induce cell transformation. The gene expression profile, which was obtained by comparing cells treated with the highest tested dose of 3Gy with the cells exposed to the lowest, not transforming, dose of 0.25Gy, identified several genes related to mitotic cell cycle and cholesterol biosynthesis. Conclusion: Our study showed that the up-regulation of genes belonging to the Spindle Assembly Checkpoint and mitosis progression could support the transforming ability of the 3Gy BALB/c3T3 exposed cells, probably through the involvement of genomic instability. Gene transcripts involved into cholesterol biosynthesis appear to be critical, as well. All these transcripts may be regarded as potential biomarkers of IR effects.