https://github.com/applicativesystem/plant-resistance-gene-logistic-regression

logistic regressor for the plant disease resistance genes using sequence features and expression.
https://github.com/applicativesystem/plant-resistance-gene-logistic-regression

bioinformatics genome-analysis genome-annotation logistic-regression plant-disease-detection plant-disease-resistance plant-monitoring plant-resistance-genes

Last synced: 7 months ago
JSON representation

logistic regressor for the plant disease resistance genes using sequence features and expression.

• Host: GitHub
• URL: https://github.com/applicativesystem/plant-resistance-gene-logistic-regression
• Owner: applicativesystem
• License: mit
• Created: 2024-08-21T18:19:16.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-08-21T19:58:12.000Z (10 months ago)
• Last Synced: 2024-11-10T20:18:16.763Z (8 months ago)
• Topics: bioinformatics, genome-analysis, genome-annotation, logistic-regression, plant-disease-detection, plant-disease-resistance, plant-monitoring, plant-resistance-genes
• Language: Python
• Homepage:
• Size: 1.95 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# plant-resistance-gene-logistic-regressor

- an application of the logistic regressor for the plant disease resistance genes.

- Given a fasta file and the corresponding expression file and a motif types which you think are associated with the plant disease resistance, if prepares the classification datasets and then fits a logistic regressor for the model building.

- You can visualize the model using the meshgrid and the np.array and it saves the model to the file.

- plant resistance gene logistic regressor: applying a logistic regressor specific for the training on the plant resistance genes.

- This applies the logistic regession based on the sequence characteristics of the plant disease resistance genes and the corresponding expression profile.

- A normalized log transformed expression methods can be used.@fasta_file: file containing the plant disease resistance genes, @expression_file: file containing the expression profile for those genes.

- It also takes a prediction motif profile which defines the presence and the absence of the resistance genes and makes a probability index.

- The function returns a accuracy score and writed the model to an output file. You can put a meshgrid to  enable the visualization of the model using the np.array.

- You can change the save to a pickle file for the model

```

resistancegeneLogisticRegressor(fasta_file, \

                                       expression_file, \

                                             prediction_motif, \

                                             prediction_size, \

                                                      output_file)

```

Gaurav Sablok \

University of Potsdam \

Potsdam,Germany