QSAR-ready workflow

QSAR-ready workflow standardizes chemical structures through automated rules to generate two-dimensional and/or three-dimensional QSAR-ready forms prior to molecular descriptor calculation.

Key Features:

• Automated Structure Standardization: The workflow applies a series of operations including desalting, stripping of stereochemistry for two-dimensional structures, standardization of tautomers and nitro groups, valence correction, and neutralization when possible.
• Identifier Cross-Referencing: The in-memory representation of the read structure is cross-referenced with any existing identifiers for consistency.
• Duplicate Removal: The workflow removes duplicate structures after standardization operations.
• MS-ready Structure Generation: The workflow was modified to generate MS-ready structures to support substance mappings and searches for non-targeted analysis mass spectrometry software applications.
• Multiple Implementation Formats: The workflow is implemented in KNIME, available as standalone versions, and as a Docker container.

Scientific Applications:

• QSAR Modeling: The workflow prepares standardized chemical structures to ensure consistency of molecular descriptors and improve accuracy, repeatability, and reliability of derived QSAR models.
• Collaborative QSAR Projects: The workflow was initially developed to ensure consistency of results from different participants in collaborative modeling projects.
• Non-targeted Analysis Mass Spectrometry: The MS-ready workflow supports generation of substance mappings and searches for software applications related to non-targeted analysis mass spectrometry.

Methodology:

The workflow consists of three high-level steps: reading a structure encoding, cross-referencing the resulting in-memory representation with existing identifiers for consistency, and standardizing the structure using desalting, stereochemistry stripping for two-dimensional structures, tautomer and nitro group standardization, valence correction, neutralization when possible, and removal of duplicates.