Download
- This Software was made with an intention to make QSAR building more efficient and reproducible.
- Published in ACS, Journal of Chemical Information and Modeling . Link : https://pubs.acs.org/doi/10.1021/acs.jcim.4c02372
- Simple to use and no compromise on essential features necessary to make reliable QSAR models.
- From Generating Reliable ML Based QSAR Models to Developing Your Own QSAR WebApp.
For any feedback or queries, contact
kabeermuzammil614@gmail.com
- Available on Windows and Linux
-If You are Facing Issues in Deployment to Streamlit, Try 'requirements.txt' in the Github repo or The Files Deposited Here.
Features
- Extraction of Data From ChEMBL Database or Users In-House Data
- Automatic Processing of Y-Label Depending TASK(Regression\Classification) according to users preferences
- Defining Applicability Domain (FP - Tanimoto Similarity & Descriptors - Boundary Box)
- Comparing Data in different ML Models with Metrics (R2/RMSE) or MCC with setting K-Fold split and Low variance threshold
- Contains 22 ML Models and 16 FP from PadelPy, RDkit and CSFP with RDkit Molecular Descriptors
- Choose ML model or Descriptor/FP of choice to build model (Automatic Internal Validation(R2/RMSE & Accuracy, Sensitivity, Specificity and MCC))
- Convert QSAR model to WebApp (Automatic External Validation)
- Upload the App Folder Files in GitHub Repository , and link to Streamlit to launch your own QSAR app
- Sequential Feature Selection (Forward Direction)
Project Samples
License
GNU General Public License version 3.0 (GPLv3)Follow PoseidonQ - AI/ML Based QSAR Modeling
Other Useful Business Software
MongoDB Atlas runs apps anywhere
MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of PoseidonQ - AI/ML Based QSAR Modeling!