High Content Screening (HCS) combines high throughput techniques with the ability to generate cellular images of biological systems. The objective of this work is to evaluate the performance of predictive models using CNN to identify the number of cells present in digital contrast microscopy images obtained by HCS. One way to evaluate the algorithm was through the Mean Squared Error metric. The MSE was 4,335.99 in the A549 cell line, 25,295.23 in the Huh7 and 36,897.03 in the 3T3. After obtaining these values, different parameters of the models were changed to verify how they behave. By reducing the number of images, the MSE increased considerably, with the A549 cell line changing to 49,973.52, Huh7 to 79,473.88 and 3T3 to 52,977.05. Correlation analyzes were performed for the different models. In lineage A549, the best model showed a positive correlation with R = 0.953. In Huh7, the best correlation of the model was R = 0.821, it was also a positive correlation. In 3T3, the models showed no correlation, with the best model having R = 0.100. The models performed well in quantifying the number of cells, and the number and quality of the images interfered with this predictive ability.
High Content Screening (HCS) combines high throughput techniques with the ability to generate cellular images of biological systems. The objective of this work is to evaluate the performance of predictive models using CNN to identify the number of cells present in digital contrast microscopy images obtained by HCS. One way to evaluate the algorithm was through the Mean Squared Error metric. The MSE was 4,335.99 in the A549 cell line, 25,295.23 in the Huh7 and 36,897.03 in the 3T3. After obtaining these values, different parameters of the models were changed to verify how they behave. By reducing the number of images, the MSE increased considerably, with the A549 cell line changing to 49,973.52, Huh7 to 79,473.88 and 3T3 to 52,977.05. Correlation analyzes were performed for the different models. In lineage A549, the best model showed a positive correlation with R = 0.953. In Huh7, the best correlation of the model was R = 0.821, it was also a positive correlation. In 3T3, the models showed no correlation, with the best model having R = 0.100. The models performed well in quantifying the number of cells, and the number and quality of the images interfered with this predictive ability.
Background With the enactment of the Brazilian Law Arouca 11,794/2008 and Decree 6.899/2009, there has been an urgent need for changes in the processes related to animal experimentation in Brazil; in particular, there is a need for improvements in enhancements of the lab animal management. To improve the management capacity of the Lab animal facility of the Carlos Chagas Institute’s Laboratory Animals Science (LAS), BioterC software was developed and implemented in 2014 for tracking mouse laboratory colonies. Five years after the implementation of this software, we sought to analyze the information in the database originated from BioterC using the Exploratory Analysis Data methodology (EDA). This article aims to identify animal breeding patterns using a data mining tool (Data Science) with Python programming language. Results The results show that from September 2014 to June 2019, under the license IACUC number LW- 6/17, 15.106 animals were produced. The C57BL/6, BALB/c and Swiss strains were the most frequently produced strains. The distribution of births due to crosses between these strains showed a median of 6 to 10 animals, depending on the genetic homozygosis and heterozygosis of the animal. The median number of days of mating was 35 days. In the sexing period, the records reported a median of 19 days. A total of 393 requests for animals from internal and external laboratories were registered. It was noted that approximately half of the animals produced to meet the demand for orders were discarded. Of the 15,106 animals, 38% were requested for animal experimentation, 58% were discarded and 4% did not have an outcome recorded in the data. Conclusions This volume of data provides an initial view of the information retrieval capabilities contained in BioterC, allowing for unique breeding knowledge by installing laboratory animals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.