https://github.com/hariprasath-v/dphi-data-sprint-52---covid-19-sars-b-cell-epitope-prediction

Predicting epitope regions using a machine learning model
https://github.com/hariprasath-v/dphi-data-sprint-52---covid-19-sars-b-cell-epitope-prediction

catboost optuna pandas python shap

Last synced: 5 days ago
JSON representation

Predicting epitope regions using a machine learning model

• Host: GitHub
• URL: https://github.com/hariprasath-v/dphi-data-sprint-52---covid-19-sars-b-cell-epitope-prediction
• Owner: hariprasath-v
• Created: 2021-11-02T04:18:05.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2022-01-15T14:46:33.000Z (about 3 years ago)
• Last Synced: 2024-11-13T15:54:31.618Z (2 months ago)
• Topics: catboost, optuna, pandas, python, shap
• Language: Jupyter Notebook
• Homepage:
• Size: 240 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Dphi-Data-Sprint-52---COVID-19-SARS-B-cell-Epitope-Prediction

# About

### Predicting epitope regions is beneficial for the design and development of vaccines aimed to induce antigen-specific antibody production.

### Competition hosted on  Dphi 

### Competition Leaderboard Rank - 2 

### Evaluation Metric is F1 Score.

### File information

 * Data_Sprint_52_COVID_19_SARS_B_cell_Epitope_Prediction.ipynb

    ### Packages Used,

        * Sklearn

        * catboost

        * Pandas

        * Numpy

        * Matplotlib

        * Optuna

        * shap

  

     ### Created Catboost classifier model and tune the hyperparameters with the optuna framework.

     ### Model interpretation with shap

     ### Model accuracy score is 70.0699

     

     

### Feature Importance     

![Alt text](https://github.com/hariprasath-v/Dphi-Data-Sprint-52---COVID-19-SARS-B-cell-Epitope-Prediction/blob/main/Feature%20%20Importance.png)

### Hyperparameter Importance

![Alt text](https://github.com/hariprasath-v/Dphi-Data-Sprint-52---COVID-19-SARS-B-cell-Epitope-Prediction/blob/main/Hyperparameter%20Importance.png)