- 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

Project Activity

See All Activity >

License

GNU General Public License version 3.0 (GPLv3)

Follow PoseidonQ - AI/ML Based QSAR Modeling

PoseidonQ - AI/ML Based QSAR Modeling Web Site

Other Useful Business Software
Resolve Support Tickets 2x Faster​ with ServoDesk Icon
Resolve Support Tickets 2x Faster​ with ServoDesk

Full access to Enterprise features. No credit card required.

What if You Could Automate 90% of Your Repetitive Tasks in Under 30 Days? At ServoDesk, we help businesses like yours automate operations with AI, allowing you to cut service times in half and increase productivity by 25% - without hiring more staff.
Try ServoDesk for free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of PoseidonQ - AI/ML Based QSAR Modeling!

Additional Project Details

Operating Systems

Linux, Windows

Intended Audience

End Users/Desktop, Information Technology, Science/Research

User Interface

Qt

Programming Language

Python

Related Categories

Python Chemistry Software, Python Machine Learning Software

Registered

2024-12-06