SDLDpred is a web-based tool to predict drugs of lifestyle-related diseases using symptoms as features.
It uses an unsupervised machine learning model trained using Bisecting K-Means algorithm to perform the prediction. The model was trained with novel drug-symptom associations computed from the disease-symptom and drug-disease association data of 143 lifestyle-related diseases, 1271 drugs and 305 symptoms.
Cite as:
Bhattacharjee, S., Saha, B., & Saha, S. (2024). Symptom-based drug prediction of lifestyle-related chronic diseases using unsupervised machine learning techniques. Computers in Biology and Medicine, 174, 108413.
https://doi.org/10.1016/j.compbiomed.2024.108413.
SDLDpred is available at: http://bicresources.jcbose.ac.in/ssaha4/sdldpred.
To know more about the datasets and the methodology, please refer to the About page. Please refer to the Help page for understanding the inputs and outputs to the web application.
Python libraries used :
- numpy (Version
1.24.1) - scikit-learn (Version
1.2.1) - joblib (Version
1.2.0) - scipy (Version
1.10.1) - ssmpy (Version
0.2.5)
R libraries used :
- GOSemSim (Version
2.26.0) - clusterProfiler (Version
4.8.1) - fmcsR (Version
1.42.0) - ggplot2 (Version
3.4.2) - ggpubr (Version
0.6.0) - patchwork (Version
1.1.2) - pheatmap (Version
1.0.12)
The web application is deployed in an Apache HTTP server.
- Sudipto Bhattacharjee ([email protected])
Ph.D. Scholar,
Department of Computer Science and Engineering,
University of Calcutta, Kolkata, India. - Dr. Banani Saha ([email protected])
Associate Professor,
Department of Computer Science and Engineering,
University of Calcutta, Kolkata, India. - Dr. Sudipto Saha ([email protected])
Associate Professor,
Department of Biological Sciences,
Bose Institute, Kolkata, India.
Please contact Dr. Sudipto Saha regarding any further queries.
This tool is strictly for research use only. It should be used for medical purposes only by consulting with doctors.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent