Structure-based virtual screenings (SBVSs) play an important role in drug discovery projects. However, it is still a challenge to accurately predict the binding affinity of an arbitrary molecule binds to a drug target and prioritize top ligands from an SBVS. In this study, we developed a novel method, using ligand-residue interaction profiles (IPs) to construct machine learning (ML)-based prediction models, to significantly improve the screening performance in SBVSs. Such a kind of the prediction model is called an IP scoring function (IP-SF). We systematically investigated how to improve the performance of IP-SFs from many perspectives, including the sampling methods before interaction energy calculation and different ML algorithms. Using six drug targets with each having hundreds of known ligands, we conducted a critical evaluation on the developed IP-SFs. The IP-SFs employing a gradient boosting decision tree (GBDT) algorithm in conjunction with the MIN + GB simulation protocol achieved the best overall performance. Its scoring power, ranking power and screening power significantly outperformed the Glide SF. First, compared with Glide, the average values of mean absolute error and root mean square error of GBDT/MIN + GB decreased about 38 and 36%, respectively. Second, the mean values of squared correlation coefficient and predictive index increased about 225 and 73%, respectively. Third, more encouragingly, the average value of the areas under the curve of receiver operating characteristic for six targets by GBDT, 0.87, is significantly better than that by Glide, which is only 0.71. Thus, we expected IP-SFs to have broad and promising applications in SBVSs.

Imaging the activities of hydrolases using molecular imaging probes can reveal underlying molecular mechanisms in the context of cells to organisms and their correlation with different pathological conditions can be used in diagnosis. Due to the nature of hydrolases, substrate-based probes can take advantage of their catalytic cycles to free reporter moieties that can generate amplified signal. This is less ideal in the context of cell- or organism-based detection, as the reporter moiety can easily diffuse away from the target site upon activation. Therefore, spatial resolution is a key factor for probe sensitivity. One strategy to improve the spatial resolution is to form a covalent linkage between the reporter moiety and intracellular proteins upon probe activation by the enzyme via a reactive intermediate. In this work, we tuned the reactivity of the quinone methide intermediate by synthesizing fluorescent probes containing different modifications to the phenol linker for β-galactosidase activation. The labeling efficacy of these probes was evaluated using fluorescence gel electrophoresis, flow cytometry, and fluorescence cell imaging. This study provides insights into the further development of hydrolase-targeting probes for cell- or organism-based imaging with enhanced efficiency via in situ labeling.