The accelerating growth of make-on-demand chemical libraries provides novel opportunities to identify starting points for drug discovery with virtual screening. However, the recently released multi-billion-scale libraries are too challenging to screen even for the fastest structure-based docking methods. Here, we introduce a strategy that combines machine learning and molecular docking to enable rapid virtual screening of databases containing billions of compounds. In our workflow, a classification algorithm is first trained to identify top-scoring compounds based on molecular docking of one million compounds to the target protein. The conformal prediction framework is then used to make selections from the multi-billion-scale library, drastically reducing the number of compounds to be scored by the docking algorithm. The performance of the approach was benchmarked on a set of eight different target proteins, and classifiers based on gradient boosting, deep neural network, and transformer architectures were evaluated. The CatBoost classifier exhibited the optimal balance between speed and accuracy and was used to adapt the workflow for screens of ultralarge libraries. The optimized workflow was demonstrated to identify >90% of the very top-scoring molecules in a library with 0.2 billion compounds, which only required docking of 3-5% of this set. Application to a library with >3.5 billion compounds showed that molecules with substantially improved docking scores can be identified by machine learning, enabling efficient virtual screening of the largest commercial chemical libraries available. The accelerated virtual screening workflow has been made publicly available to facilitate exploration of vast chemical libraries for drug discovery.