Computational Biophysiscs Laboratory (GRIB-IMIM), Universitat Pompeu Fabra, Barcelona Biomedical Research Park (PRBB), Doctor Aiguader 88, 08003 Barcelona, Spain.
Computational Biophysiscs Laboratory (GRIB-IMIM), Universitat Pompeu Fabra, Barcelona Biomedical Research Park (PRBB), Doctor Aiguader 88, 08003 Barcelona, Spain; Institució Catalana de Recerca i Estudis Avançats (ICREA), Passeig Lluis Companys 23, Barcelona 08010, Spain.
Curr Opin Struct Biol. 2018 Apr;49:139-144. doi: 10.1016/j.sbi.2018.02.004. Epub 2018 Feb 21.
Classical molecular dynamics (MD) simulations will be able to reach sampling in the second timescale within five years, producing petabytes of simulation data at current force field accuracy. Notwithstanding this, MD will still be in the regime of low-throughput, high-latency predictions with average accuracy. We envisage that machine learning (ML) will be able to solve both the accuracy and time-to-prediction problem by learning predictive models using expensive simulation data. The synergies between classical, quantum simulations and ML methods, such as artificial neural networks, have the potential to drastically reshape the way we make predictions in computational structural biology and drug discovery.
经典分子动力学（MD）模拟将能够在五年内达到第二个时间尺度的采样，在当前力场精度下产生 PB 级的模拟数据。尽管如此，MD 仍然处于低通量、高延迟预测的平均精度范围内。我们预计，机器学习（ML）将能够通过使用昂贵的模拟数据来学习预测模型来解决准确性和预测时间的问题。经典、量子模拟和 ML 方法（如人工神经网络）之间的协同作用有可能彻底改变我们在计算结构生物学和药物发现领域进行预测的方式。
