High-precision Atomic Charge Prediction for Protein Systems Using Fragment Molecular Orbital Calculation and Machine Learning.

Here, we have constructed neural network-based models that predict atomic partial charges with high accuracy at low computational cost. The models were trained by high-quality data acquired by quantum mechanics calculations using the fragment molecular orbital method. We have succeeded in obtaining highly accurate atomic partial charges for three representative molecular systems of proteins, including one large biomolecule (approx. 2000 atoms). The novelty of our approach is the ability to take into account the electronic polarization in the system which is system-depended phenomenon, being important in the field of drug design. Our high-precision models for the prediction of atomic partial charge are useful and expected to be widely applicable to structure based drug design such as structural optimization, high-speed and high-precision docking and molecular dynamics calculations.