<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>We developed a procedure for estimating competitive fitness by using <italic>Caenorhabditis elegans</italic> as a model organism and a Convolutional Neural Network (CNN) as a tool. Competitive fitness is usually the most informative fitness measure, and competitive fitness assays often rely on green fluorescent protein (GFP) marker strains. CNNs are a class of deep learning neural networks, which are well suited for image analysis and object classification. Our model analyses involved image classification of nematodes as wild-type vs. GFP-expressing, and counted both categories. The performance was analyzed with (i) precision and recall parameters, and (ii) comparison of the wild-type frequency calculated from the model against that obtained by visual scoring of the same images. The average precision and recall varied from 0.79 to 0.87 and from 0.84 to 0.92, respectively, depending on worm density in the images. Compared with manual counting, the model decreased counting time at least 20-fold while preventing human errors. Given the rapid development in the field of CNN, the model, which is fully available on GitHub, can be further optimized and adapted for other image-based uses.</p>
</abstract>

We developed a procedure for estimating competitive fitness by using Caenorhabditis elegans as a model organism and a Convolutional Neural Network (CNN) as a tool. Competitive fitness is usually the most informative fitness measure, and competitive fitness assays often rely on green fluorescent protein (GFP) marker strains. CNNs are a class of deep learning neural networks, which are well suited for image analysis and object classification. Our model analyses involved image classification of nematodes as wild-type vs. GFP-expressing, and counted both categories. The performance was analyzed with (i) precision and recall parameters, and (ii) comparison of the wild-type frequency calculated from the model against that obtained by visual scoring of the same images. The average precision and recall varied from 0.79 to 0.87 and from 0.84 to 0.92, respectively, depending on worm density in the images. Compared with manual counting, the model decreased counting time at least 20-fold while preventing human errors. Given the rapid development in the field of CNN, the model, which is fully available on GitHub, can be further optimized and adapted for other image-based uses.

Competitive fitness analysis using Convolutional Neural Network

Journal of Nematology

This work is licensed under the Creative Commons Attribution 4.0 International License.

running-head

Competitive fitness analysis by using CNN models:

We developed a procedure for estimating competitive fitness by using Caenorhabditis elegans as a model organism and a Convolutional Neural Network (CNN) as a...

	Area
Metric	Small	Medium	Large	All
Average precision @ IoU = 0.50	No animals	0.784	0.810	0.787
Average recall @ IoU = 0.50	No animals	0.851	0.856	0.842

	Area
Metric	Small	Medium	Large	All
Average precision @ IoU = 0.50	No animals	0.870	0.883	0.872
Average recall @ IoU = 0.50	No animals	0.930	0.918	0.917

Competitive fitness analysis using Convolutional Neural Network

Published Online: Nov 06, 2020

Page range: 1 - 15

DOI: https://doi.org/10.21307/jofnem-2020-108

Keywords
Competitive fitness, Convolutional neural network, Fitness method

© 2020 Joanna K. Palka et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1:

Figure S1:

Figure 2:

Figure 3:

Figure S2:

Performance metrics of the CNN model computed on the evaluation set for high animal densities (above 70).

Performance metrics of the CNN model computed on the evaluation set for low and moderate animal densities (below 70).

Competitive fitness analysis using Convolutional Neural Network

Published Online: Nov 06, 2020

Page range: 1 - 15

DOI: https://doi.org/10.21307/jofnem-2020-108

KeywordsCompetitive fitness, Convolutional neural network, Fitness method

© 2020 Joanna K. Palka et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1:

Figure S1:

Figure 2:

Figure 3:

Figure S2:

Performance metrics of the CNN model computed on the evaluation set for high animal densities (above 70).

Performance metrics of the CNN model computed on the evaluation set for low and moderate animal densities (below 70).

Keywords
Competitive fitness, Convolutional neural network, Fitness method