Prediction of Ligand-receptor Selectivity and Estimating of Target Potency Using a Multi-Function Machine Learning Model
Introduction
Identifying target-specific ligands is a difficult task, especially in cases where receptors display high structural similarity. Such is the case for metabotropic glutamate receptor subtype 2 (mGlu2) and metabotropic glutamate receptor subtype 3 (mGlu3), which are prime targets for various neurological treatments. However, signal transduction through these two receptors often yields opposing physiological function and differentially affect pathologies. Understanding the need to differentiate ligands based on their binding to mGlu2 and mGlu3, we employed a machine learning approach.
Methods
Using patent-derived datasets, data was preprocessed into an eight-dimension vector space. A Multiple Input and Output (MIO) Model was designed to receive the incoming vectors. A classification arm was designated as an output, differentiating input structures as mGlu2 or mGlu3 ligands. The regression arm was used to estimate ligand efficacy values.
Results
The model yielded greater than 96% accuracy in the classification task, while correctly identifying high-affinity mGlu2 compounds with 81% accuracy and identifying high-affinity mGlu3 compounds with 62% accuracy. We then used docking studies and the trained model to screen an available ZINC database, selecting the top 39 compounds out of 9,270 ligands.
Conclusion
This approach can pave the way for computer-aided searches which screen for high-efficacy ligands belonging to a certain class of interest. This model can be used in combination with other established structure-based methodology like molecular docking, allowing for screening of even more drug candidates for further study and validation. As it pertains to neurosurgery, models such as this one could allow practitioners to develop novel drugs, or repurpose current pharmacotherapies, to better treat their patients. While neurosurgery is highly operative, there do exist neurological pathologies that the scalpel cannot reach. Machine learning models have the potential to become indispensable tools for neurosurgeons, accelerating the translation of novel therapies from bench to bedside.