QSAR-Co
QSAR-Co implements multitasking and multitarget classification-based QSAR modeling to relate chemical structure to biological or toxicological activity across varied experimental and theoretical conditions.
Key Features:
- Multitasking and Multitarget Classification: Supports construction of classification models that address multiple tasks or multiple biological targets simultaneously.
- Classification-based QSAR Modeling: Focuses on classification rather than regression to predict categorical biological or toxicological outcomes.
- Analytical Methods: Employs linear discriminant analysis and random forest techniques for model development.
- Response-condition Integration: Handles response data arising from varied experimental or theoretical conditions to enhance model applicability.
- Validation Protocols: Incorporates validation procedures aligned with Organisation for Economic Co-operation and Development (OECD) principles.
Scientific Applications:
- Drug Design: Enables creation of multitarget classification models to identify compounds with desired biological activities.
- Toxicity Prediction: Supports development of models to predict compound toxicity under different conditions.
- Nanomaterials Research: Facilitates exploration of structure-activity relationships in nanomaterials for property prediction.
Methodology:
Implements multitasking and multitarget classification-based QSAR modeling using linear discriminant analysis and random forest, with validation aligned to OECD principles and support for varied response conditions.
Topics
Details
- License:
- GPL-3.0
- Maturity:
- Mature
- Cost:
- Free of charge
- Tool Type:
- desktop application
- Operating Systems:
- Linux, Windows, Mac
- Programming Languages:
- Java
- Added:
- 8/9/2019
- Last Updated:
- 6/16/2020
Operations
Publications
Ambure P, Halder AK, González Díaz H, Cordeiro MNDS. QSAR-Co: An Open Source Software for Developing Robust Multitasking or Multitarget Classification-Based QSAR Models. Journal of Chemical Information and Modeling. 2019;59(6):2538-2544. doi:10.1021/acs.jcim.9b00295. PMID:31083984.