The impact of compound library size on the performance of scoring functions for structure-based virtual screening

Larger training datasets have been shown to improve the accuracy of machine learning (ML)-based scoring functions (SFs) for structure-based virtual screening (SBVS). In addition, massive test sets for SBVS, known as ultra-large compound libraries, have been demonstrated to enable the fast discovery of selective drug leads with low-nanomolar potency. This proof-of-concept was carried out on two targets using a single docking tool along with its SF. It is thus unclear whether this high level of performance would generalise to other targets, docking tools and SFs. We found that screening a larger compound library results in more potent actives being identified in all six additional targets using a different docking tool along with its classical SF. Furthermore, we established that a way to improve the potency of the retrieved molecules further is to rank them with more accurate ML-based SFs (we found this to be true in four of the six targets; the difference was not significant in the remaining two targets). A 3-fold increase in average hit rate across targets was also achieved by the ML-based SFs. Lastly, we observed that classical and ML-based SFs often find different actives, which supports using both types of SFs on those targets.

Automated summary

Increasing the size of training datasets improves the accuracy of machine learning-based scoring functions in structure-based virtual screening, and using massive test sets can lead to fast discovery of drug leads with low-nanomolar potency. Screening larger compound libraries results in the identification of more potent actives, and ranking molecules with more accurate machine learning-based scoring functions can further enhance their potency. Additionally, classical and machine learning-based scoring functions often find different actives, suggesting the benefit of using both types of scoring functions on multiple targets.