Quantum-Inspired Machine Learning for Molecular Docking
This work addresses computational bottlenecks in drug discovery by improving blind docking accuracy, though it appears incremental relative to existing deep learning approaches.
The paper tackles the problem of blind molecular docking for drug design by combining quantum-inspired algorithms with deep learning gradients, achieving a 10% improvement over traditional and deep learning-based docking algorithms and increasing Top-1 success rates from 33% to 35% compared to DiffDock.
Molecular docking is an important tool for structure-based drug design, accelerating the efficiency of drug development. Complex and dynamic binding processes between proteins and small molecules require searching and sampling over a wide spatial range. Traditional docking by searching for possible binding sites and conformations is computationally complex and results poorly under blind docking. Quantum-inspired algorithms combining quantum properties and annealing show great advantages in solving combinatorial optimization problems. Inspired by this, we achieve an improved in blind docking by using quantum-inspired combined with gradients learned by deep learning in the encoded molecular space. Numerical simulation shows that our method outperforms traditional docking algorithms and deep learning-based algorithms over 10\%. Compared to the current state-of-the-art deep learning-based docking algorithm DiffDock, the success rate of Top-1 (RMSD<2) achieves an improvement from 33\% to 35\% in our same setup. In particular, a 6\% improvement is realized in the high-precision region(RMSD<1) on molecules data unseen in DiffDock, which demonstrates the well-generalized of our method.