Explore the vast range of titles available.

“Virtual Screening” is a common step of in silico drug design, where researchers screen a large library of small molecules (ligands) for interesting hits, in a process known as “Docking”. However, docking is a computationally intensive and time-consuming process, usually restricted to small size binding sites (pockets) and small number of interacting residues. When the target site is not known (blind docking), researchers split the docking box into multiple boxes, or repeat the search several times using different seeds, and then merge the results manually. Otherwise, the search time becomes impractically long. In this research, we studied the relation between the search progression and Average Sum of Proximity relative Frequencies (ASoF) of searching threads, which is closely related to the search speed and accuracy. A new inter-process spatio-temporal integration method is employed in Quick Vina 2, resulting in a new docking tool, QuickVina-W, a suitable tool for “blind docking”, (not limited in search space size or number of residues). QuickVina-W is faster than Quick Vina 2, yet better than AutoDock Vina. It should allow researchers to screen huge ligand libraries virtually, in practically short time and with high accuracy without the need to define a target pocket beforehand.

Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery. Multi-scale learning still struggles with imbalanced information and greedy characteristics. Here the authors present MUSE, an Expectation-Maximization-based multi-scale framework, improving predictions across molecular interactions and atomic interfaces.