Department of Chemistry, Yale University, New Haven 06511, Connecticut, United States.
J Chem Theory Comput. 2024 Jun 11;20(11):4901-4908. doi: 10.1021/acs.jctc.4c00432. Epub 2024 May 25.
Toxicity is a roadblock that prevents an inordinate number of drugs from being used in potentially life-saving applications. Deep learning provides a promising solution to finding ideal drug candidates; however, the vastness of chemical space coupled with the underlying matrix multiplication means these efforts quickly become computationally demanding. To remedy this, we present a hybrid quantum-classical neural network for predicting drug toxicity utilizing a quantum circuit design that mimics classical neural behavior by explicitly calculating matrix products with complexity . Leveraging the Hadamard test for efficient inner product estimation rather than the conventionally used swap test, we reduce the number of qubits by half and remove the need for quantum phase estimation. Directly computing matrix products quantum mechanically allows for learnable weights to be transferred from a quantum to a classical device for further training. We apply our framework to the Tox21 data set and show that it achieves commensurate predictive accuracy to the model's fully classical analogue. Additionally, we demonstrate that the model continues to learn, without disruption, once transferred to a fully classical architecture. We believe that combining the quantum advantage of reduced complexity and the classical advantage of noise-free calculation will pave the way for more scalable machine learning models.
毒性是阻碍大量药物用于潜在救生应用的一个障碍。深度学习为寻找理想的药物候选物提供了一个有前途的解决方案；然而，化学空间的广阔性加上底层的矩阵乘法意味着这些努力很快就变得计算密集。为了解决这个问题，我们提出了一种混合量子经典神经网络，用于预测药物毒性，利用量子电路设计，通过显式计算矩阵乘积来模拟经典神经网络行为，其复杂度为 。利用 Hadamard 测试进行有效的内积估计，而不是传统使用的交换测试，我们将量子比特的数量减少一半，并消除了量子相位估计的需要。直接进行矩阵乘积的量子计算允许可学习的权重从量子设备转移到经典设备进行进一步训练。我们将我们的框架应用于 Tox21 数据集，并表明它达到了与模型完全经典模拟相当的预测准确性。此外，我们还证明了一旦转移到完全经典的架构，该模型仍能继续学习，而不会中断。我们相信，结合减少复杂度的量子优势和无噪声计算的经典优势，将为更具可扩展性的机器学习模型铺平道路。
