A fully automated deep learning pipeline for high-throughput colony segmentation and classification
Adenine auxotrophy is a commonly used non-selective genetic marker in yeast research. It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely time-consuming,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Company of Biologists
2020-06-01
|
| Series: | Biology Open |
| Subjects: | |
| Online Access: | http://bio.biologists.org/content/9/6/bio052936 |
| id |
doaj-4e994aace50441edb397c58bb3c414ed |
|---|---|
| record_format |
Article |
| spelling |
doaj-4e994aace50441edb397c58bb3c414ed2021-06-02T14:27:52ZengThe Company of BiologistsBiology Open2046-63902020-06-019610.1242/bio.052936052936A fully automated deep learning pipeline for high-throughput colony segmentation and classificationSarah H. Carl0Lea Duempelmann1Yukiko Shimada2Marc Bühler3 Friedrich Miescher Institute for Biomedical Research, Maulbeerstrasse 66, 4058 Basel, Switzerland Friedrich Miescher Institute for Biomedical Research, Maulbeerstrasse 66, 4058 Basel, Switzerland Friedrich Miescher Institute for Biomedical Research, Maulbeerstrasse 66, 4058 Basel, Switzerland Friedrich Miescher Institute for Biomedical Research, Maulbeerstrasse 66, 4058 Basel, Switzerland Adenine auxotrophy is a commonly used non-selective genetic marker in yeast research. It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely time-consuming, difficult to reproduce and possibly inaccurate. Using cutting-edge neural networks, we have developed a fully automated pipeline for colony segmentation and classification, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher. Our approach uses readily available training data and can be smoothly integrated into existing protocols, vastly speeding up screening assays and increasing the statistical power of experiments that employ adenine auxotrophy.http://bio.biologists.org/content/9/6/bio052936deep learningneural networksadenine auxotrophyyeastgrowth assay |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Sarah H. Carl Lea Duempelmann Yukiko Shimada Marc Bühler |
| spellingShingle |
Sarah H. Carl Lea Duempelmann Yukiko Shimada Marc Bühler A fully automated deep learning pipeline for high-throughput colony segmentation and classification Biology Open deep learning neural networks adenine auxotrophy yeast growth assay |
| author_facet |
Sarah H. Carl Lea Duempelmann Yukiko Shimada Marc Bühler |
| author_sort |
Sarah H. Carl |
| title |
A fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| title_short |
A fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| title_full |
A fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| title_fullStr |
A fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| title_full_unstemmed |
A fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| title_sort |
fully automated deep learning pipeline for high-throughput colony segmentation and classification |
| publisher |
The Company of Biologists |
| series |
Biology Open |
| issn |
2046-6390 |
| publishDate |
2020-06-01 |
| description |
Adenine auxotrophy is a commonly used non-selective genetic marker in yeast research. It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely time-consuming, difficult to reproduce and possibly inaccurate. Using cutting-edge neural networks, we have developed a fully automated pipeline for colony segmentation and classification, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher. Our approach uses readily available training data and can be smoothly integrated into existing protocols, vastly speeding up screening assays and increasing the statistical power of experiments that employ adenine auxotrophy. |
| topic |
deep learning neural networks adenine auxotrophy yeast growth assay |
| url |
http://bio.biologists.org/content/9/6/bio052936 |
| work_keys_str_mv |
AT sarahhcarl afullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT leaduempelmann afullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT yukikoshimada afullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT marcbuhler afullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT sarahhcarl fullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT leaduempelmann fullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT yukikoshimada fullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification AT marcbuhler fullyautomateddeeplearningpipelineforhighthroughputcolonysegmentationandclassification |
| _version_ |
1721403604474003456 |