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

AbstractBhas 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.

Download Full-text

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

10.21203/rs.3.rs-711267/v1 ◽

2021 ◽

Author(s):

Minami Masumoto ◽

Ittetsu Fukuda ◽

Suguru Furihata ◽

Takahiro Arai ◽

Tatsuto Kageyama ◽

...

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Cell Transformation ◽

Area Under The Curve ◽

Guidance Document ◽

Transformation Assay ◽

Tumor Promotor ◽

Carcinogenic Potential ◽

Morphological Criteria

Abstract 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.

Download Full-text

Method of determination of the text direction on the image with the use of convolutional neural network

Informatization and communication ◽

10.34219/2078-8320-2020-11-2-96-99 ◽

2020 ◽

pp. 96-99

Author(s):

P.L. Nikolaev

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Deep Neural Network ◽

Binary Classification ◽

Synthetic Data ◽

Real Data ◽

Method Of Determination ◽

Classification Of Images

This article deals with method of binary classification of images with small text on them Classification is based on the fact that the text can have 2 directions – it can be positioned horizontally and read from left to right or it can be turned 180 degrees so the image must be rotated to read the sign. This type of text can be found on the covers of a variety of books, so in case of recognizing the covers, it is necessary first to determine the direction of the text before we will directly recognize it. The article suggests the development of a deep neural network for determination of the text position in the context of book covers recognizing. The results of training and testing of a convolutional neural network on synthetic data as well as the examples of the network functioning on the real data are presented.

Download Full-text

DNN-m6A: A Cross-Species Method for Identifying RNA N6-Methyladenosine Sites Based on Deep Neural Network with Multi-Information Fusion

Genes ◽

10.3390/genes12030354 ◽

2021 ◽

Vol 12 (3) ◽

pp. 354

Author(s):

Lu Zhang ◽

Xinyi Qin ◽

Min Liu ◽

Ziwei Xu ◽

Guangzhong Liu

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Area Under The Curve ◽

Nucleotide Composition ◽

Computational Method ◽

Feature Subset ◽

Accurate Identification ◽

Genome Wide ◽

Dinucleotide Composition ◽

Optimal Feature Subset

As a prevalent existing post-transcriptional modification of RNA, N6-methyladenosine (m6A) plays a crucial role in various biological processes. To better radically reveal its regulatory mechanism and provide new insights for drug design, the accurate identification of m6A sites in genome-wide is vital. As the traditional experimental methods are time-consuming and cost-prohibitive, it is necessary to design a more efficient computational method to detect the m6A sites. In this study, we propose a novel cross-species computational method DNN-m6A based on the deep neural network (DNN) to identify m6A sites in multiple tissues of human, mouse and rat. Firstly, binary encoding (BE), tri-nucleotide composition (TNC), enhanced nucleic acid composition (ENAC), K-spaced nucleotide pair frequencies (KSNPFs), nucleotide chemical property (NCP), pseudo dinucleotide composition (PseDNC), position-specific nucleotide propensity (PSNP) and position-specific dinucleotide propensity (PSDP) are employed to extract RNA sequence features which are subsequently fused to construct the initial feature vector set. Secondly, we use elastic net to eliminate redundant features while building the optimal feature subset. Finally, the hyper-parameters of DNN are tuned with Bayesian hyper-parameter optimization based on the selected feature subset. The five-fold cross-validation test on training datasets show that the proposed DNN-m6A method outperformed the state-of-the-art method for predicting m6A sites, with an accuracy (ACC) of 73.58%–83.38% and an area under the curve (AUC) of 81.39%–91.04%. Furthermore, the independent datasets achieved an ACC of 72.95%–83.04% and an AUC of 80.79%–91.09%, which shows an excellent generalization ability of our proposed method.

Download Full-text

The testing of chemicals in the Syrian hamster embryo (SHE) cell transformation assay for assessment of carcinogenic potential

Toxicology in Vitro ◽

10.1016/j.tiv.2003.08.001 ◽

2004 ◽

Vol 18 (2) ◽

pp. 213-218 ◽

Cited By ~ 14

Author(s):

G. Engelhardt ◽

K.-R. Schwind ◽

B. Mußler

Keyword(s):

Syrian Hamster ◽

Cell Transformation ◽

Transformation Assay ◽

Carcinogenic Potential

Download Full-text

An Optimised Data Analysis for the Balb/c3T3 Cell Transformation Assay and its Application to Metal Compounds

International Journal of Immunopathology and Pharmacology ◽

10.1177/039463200702000403 ◽

2007 ◽

Vol 20 (4) ◽

pp. 673-684 ◽

Cited By ~ 6

Author(s):

J. Ponti ◽

B. Munaro ◽

M. Fischbach ◽

S. Hoffmann ◽

E. Sabbioni

Keyword(s):

Data Analysis ◽

Cell Transformation ◽

T Test ◽

Alternative Methods ◽

Metal Compounds ◽

Exact Test ◽

Fisher's Exact Test ◽

Transformation Assay ◽

Carcinogenic Potential ◽

Fisher’S Exact Test

The Balb/c3T3 cell transformation assay (CTA) is an available in vitro system to detect the carcinogenic potential of chemicals. Currently, the European Centre for the Validation of Alternative Methods (ECVAM) is validating this test, assessing its reliability and relevance. Its endpoint is the formation of type III foci, which is, when using clone A31-1-1, a very rare event that usually does not occur at all for negative controls. The carcinogenic potential of a compound tested is assessed by comparing the number of foci in treated and untreated cells. The objective of the present work is to optimise the data analysis for this endpoint by applying the most commonly used approach by a t-test and the Fisher's exact test as an alternative approach. For this purpose selected metal compounds classified as carcinogenic (NaAsO2, CdCl2 cisPt), as suspected carcinogenic (C6H5)4AsCl, CH3HgCl), or as compounds without evidence of carcinogenic properties in humans ((NH4)2PtCl6, NaVO3) as well as a non-carcinogenic (AgNO3) were analysed. Our evaluation revealed that the t-test approach, which assumes normality of data, is not appropriate. The results demonstrated that the statistical analysis by Fisher's exact test better reflects the data properties and greatly facilitates the interpretation of Balb/c3T3 CTA data regarding carcinogenic potential.

Download Full-text

BALB/c 3T3 cell transformation assay for the prediction of carcinogenic potential of chemicals and environmental mixtures

Toxicology in Vitro ◽

10.1016/j.tiv.2010.03.003 ◽

2010 ◽

Vol 24 (4) ◽

pp. 1292-1300 ◽

Cited By ~ 24

Author(s):

Maria Grazia Mascolo ◽

Stefania Perdichizzi ◽

Francesca Rotondo ◽

Elena Morandi ◽

Angela Guerrini ◽

...

Keyword(s):

Cell Transformation ◽

Transformation Assay ◽

Carcinogenic Potential ◽

Environmental Mixtures

Download Full-text

Two particle picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

10.1101/2020.02.28.969196 ◽

2020 ◽

Cited By ~ 1

Author(s):

Thorsten Wagner ◽

Luca Lusnig ◽

Sabrina Pospich ◽

Markus Stabrin ◽

Fabian Schönfeld ◽

...

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Molecular Complexes ◽

High Accuracy ◽

The Other ◽

Line Detection ◽

Data Sets ◽

Detection Approach ◽

Selection Of

AbstractStructure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here we present two approaches for selecting filamentous complexes: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, the other one, called SPHIRE-STRIPER, is based on a classical line detection approach. The advantage of the crYOLO based procedure is that it accurately performs on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. We evaluate the performance of both procedures on tobacco mosaic virus and filamentous F-actin data sets to demonstrate the robustness of each method.

Download Full-text

Improving porosity and gamma ray prediction for the Middle Jurassic Hugin sandstones in southern Norwegian North Sea with the application of deep neural networks

Interpretation ◽

10.1190/int-2021-0107.1 ◽

2021 ◽

pp. 1-46

Author(s):

Satinder Chopra ◽

Ritesh Sharma ◽

Kurt J. Marfurt ◽

Rongfeng Zhang ◽

Renjun Wen

Keyword(s):

Neural Network ◽

North Sea ◽

Seismic Data ◽

Deep Neural Network ◽

Gamma Ray ◽

Accurate Determination ◽

Empirical Relation ◽

Reservoir Property ◽

Well Data

The complete characterization of a reservoir requires accurate determination of properties such as porosity, gamma ray and density, amongst others. A common workflow is to predict the spatial distribution of properties measured by well logs to those that can be computed from the seismic data. Generally, a high degree of scatter of data points is seen on crossplots between P-impedance and porosity, or P-impedance and gamma ray suggesting large uncertainty in the determined relationship. Although for many rocks there is a well established petrophysical model correlating P-impedance to porosity, there is not a comparable model correlating P-impedance to gamma ray. To address this issue, interpreters can use crossplots to graphically correlate two seismically derived variables to well measurements plotted in color. When there are more than two seismically derived variables, the interpreter can use multilinear regression or artificial neural network (ANN) analysis that uses a percentage of the upscaled well data for training to establish an empirical relation with the input seismic data and then uses the remaining well data to validate the relationship. Once validated at the wells, this relationship can then be used to predict the desired reservoir property volumetrically. We describe the application of deep neural network (DNN) analysis for the determination of porosity and gamma ray over the Volve Field in the southern Norwegian North Sea. After employing several quality-control steps in the deep neural network workflow and observing encouraging results, we validate the final prediction of both porosity and gamma ray properties using blind well correlation. The application of this workflow promises significant improvement to the reservoir property determination for fields that have good well control and exhibit lateral variations in the sought properties.

Download Full-text