PAULYToolbox Analytical Chemistry
Generate highly accurate retention time and ion mobility data to eliminate false positives in your suspect screening workflows. Our predictive models streamline your method development before you even step into the lab.
Empowering Your Analytical Workflows
Our package provides the critical predictive data needed to interpret complex analytical results and optimize laboratory processes.
- Confident Suspect Screening: Accelerate non-target and suspect screening workflows. Rapidly rule out false positives by comparing your experimental data with highly accurate predicted retention times and collision cross sections (CCS).
- Accelerated Method Development: Reduce trial-and-error in the lab. Use predictive insights to guide your separation strategies and solve complex LC and GC separation problems computationally.
- Intuitive SMILES Input: No need for complex molecular descriptors or pre-formatted CSVs. Simply input your SMILES strings or run large batches to get immediate results.
- Future-Proof Workflow: While currently focused on cutting-edge chromatography and ion mobility predictions, our roadmap includes upcoming models dedicated to optimizing your sample preparation protocols.
Advanced Modeling for Analytical Chemistry
We employ a sophisticated hybrid modeling approach to capture complex molecular interactions and predict critical analytical parameters, including Liquid Chromatography (LC) retention times, Gas Chromatography (GC) retention times, and Ion Mobility Collision Cross Sections (CCS). You can generate your data using the following methodologies:
- Graph Neural Networks (GNNs): State-of-the-art deep learning architectures that directly learn from molecular topology to provide highly accurate, end-to-end predictions for multidimensional separation behavior.
- Linear Solvation Energy Relationship (LSER) Models: Established, physically interpretable models enhanced by AI. We utilize GNNs to highly accurately predict the required underlying substance descriptors, combining mechanistic transparency with the power of machine learning.
Peer-Review Validated
We don’t just calculate; we validate. Our predictive GNN models have been benchmarked against large experimental datasets and published in peer-reviewed scientific journals.
Publications
- "Prediction of solute descriptors for linear solvation energy relationships using k-nearest neighbours, group contributions, and graph-convolutional neural networks", ACS Environ. Au, 2026. https://doi.org/10.1021/acsenvironau.6c00063
- "Linear solvation energy relationships as classifiers in non-target analysis - a capillary liquid chromatography approach",J. Chromatogr. A, 2011. https://doi.org/10.1016/j.chroma.2011.09.031
- "Prediction of gas chromatographic retention indices as classifier in non-target analysis of environmental samples",J. Chromatogr. A, 2013. https://doi.org/10.1016/j.chroma.2013.02.037